Upload folder using huggingface_hub

README.md

@@ -1,3 +1,60 @@
----
-license: apache-2.0
----
+---
+library_name: transformers
+license: other
+base_model: deepseek-ai/deepseek-coder-1.3b-instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: one_merge_yhhhhhhh_deepseek-coder-1.3b-instruct
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# one_merge_yhhhhhhh_deepseek-coder-1.3b-instruct
+
+This model is a fine-tuned version of [deepseek-ai/deepseek-coder-1.3b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-instruct) on the output dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1964
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 8
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 4.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.5.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.9975624619134673,
+    "eval_loss": 0.19639351963996887,
+    "eval_runtime": 0.8898,
+    "eval_samples_per_second": 1.124,
+    "eval_steps_per_second": 1.124,
+    "total_flos": 3.38221904554623e+17,
+    "train_loss": 0.21007875238613385,
+    "train_runtime": 5418.5603,
+    "train_samples_per_second": 9.688,
+    "train_steps_per_second": 0.605
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "deepseek-ai/deepseek-coder-1.3b-instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 32013,
+  "eos_token_id": 32021,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "max_position_embeddings": 16384,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "rope_type": "linear",
+    "type": "linear"
+  },
+  "rope_theta": 100000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 32256
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.9975624619134673,
+    "eval_loss": 0.19639351963996887,
+    "eval_runtime": 0.8898,
+    "eval_samples_per_second": 1.124,
+    "eval_steps_per_second": 1.124
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 32013,
+  "eos_token_id": 32021,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dd16e90002e6b75461307550d37ec85c3dc77a3f3e9c50cc243dfa9e96e3f70
+size 4986380064

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1156d11f6546b835964645fb59bb1487240ca066aaa18c0666b5f19a92038798
+size 399532808

model.safetensors.index.json

@@ -0,0 +1,226 @@
+{
+  "metadata": {
+    "total_size": 5385887744
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

runs/Nov09_10-04-36_5937a45575d7/events.out.tfevents.1731146687.5937a45575d7.28655.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8df825f766be98d142e8b2ca2e748363e70d1c4aa7319112e7b871ada273bb1d
+size 74854

runs/Nov09_10-04-36_5937a45575d7/events.out.tfevents.1731152130.5937a45575d7.28655.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adc40ffb0c8c69e275b40399ee8c4ab1f87a6d69d649a20688ad93c88f7e11e7
+size 359

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Please continue to complete the function. You are not allowed to modify the given code and do the completion only. Please return all completed function in a codeblock. Here is the given code to do completion:\n```python\n' + content + '\n' }}{% elif message['role'] == 'assistant' %}{{ '\n' + content + '\n```<|EOT|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|EOT|>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.9975624619134673,
+    "total_flos": 3.38221904554623e+17,
+    "train_loss": 0.21007875238613385,
+    "train_runtime": 5418.5603,
+    "train_samples_per_second": 9.688,
+    "train_steps_per_second": 0.605
+}

trainer_log.jsonl

@@ -0,0 +1,329 @@
+{"current_steps": 10, "total_steps": 3280, "loss": 0.7319, "learning_rate": 5.05050505050505e-07, "epoch": 0.01218769043266301, "percentage": 0.3, "elapsed_time": "0:00:29", "remaining_time": "2:38:38"}
+{"current_steps": 20, "total_steps": 3280, "loss": 0.6746, "learning_rate": 1.01010101010101e-06, "epoch": 0.02437538086532602, "percentage": 0.61, "elapsed_time": "0:00:55", "remaining_time": "2:29:37"}
+{"current_steps": 30, "total_steps": 3280, "loss": 0.722, "learning_rate": 1.5151515151515152e-06, "epoch": 0.03656307129798903, "percentage": 0.91, "elapsed_time": "0:01:21", "remaining_time": "2:26:58"}
+{"current_steps": 40, "total_steps": 3280, "loss": 0.6053, "learning_rate": 2.02020202020202e-06, "epoch": 0.04875076173065204, "percentage": 1.22, "elapsed_time": "0:01:45", "remaining_time": "2:22:44"}
+{"current_steps": 50, "total_steps": 3280, "loss": 0.467, "learning_rate": 2.5252525252525258e-06, "epoch": 0.06093845216331505, "percentage": 1.52, "elapsed_time": "0:02:08", "remaining_time": "2:17:49"}
+{"current_steps": 60, "total_steps": 3280, "loss": 0.4346, "learning_rate": 3.0303030303030305e-06, "epoch": 0.07312614259597806, "percentage": 1.83, "elapsed_time": "0:02:28", "remaining_time": "2:12:58"}
+{"current_steps": 70, "total_steps": 3280, "loss": 0.4145, "learning_rate": 3.5353535353535356e-06, "epoch": 0.08531383302864107, "percentage": 2.13, "elapsed_time": "0:02:47", "remaining_time": "2:08:22"}
+{"current_steps": 80, "total_steps": 3280, "loss": 0.4062, "learning_rate": 4.04040404040404e-06, "epoch": 0.09750152346130408, "percentage": 2.44, "elapsed_time": "0:03:05", "remaining_time": "2:03:38"}
+{"current_steps": 90, "total_steps": 3280, "loss": 0.3627, "learning_rate": 4.5454545454545455e-06, "epoch": 0.10968921389396709, "percentage": 2.74, "elapsed_time": "0:03:23", "remaining_time": "2:00:08"}
+{"current_steps": 100, "total_steps": 3280, "loss": 0.3336, "learning_rate": 4.99999878077914e-06, "epoch": 0.1218769043266301, "percentage": 3.05, "elapsed_time": "0:03:42", "remaining_time": "1:58:01"}
+{"current_steps": 110, "total_steps": 3280, "loss": 0.3489, "learning_rate": 4.9998524757147466e-06, "epoch": 0.1340645947592931, "percentage": 3.35, "elapsed_time": "0:04:02", "remaining_time": "1:56:15"}
+{"current_steps": 120, "total_steps": 3280, "loss": 0.3617, "learning_rate": 4.999462342829388e-06, "epoch": 0.14625228519195613, "percentage": 3.66, "elapsed_time": "0:04:18", "remaining_time": "1:53:33"}
+{"current_steps": 130, "total_steps": 3280, "loss": 0.3894, "learning_rate": 4.9988284201754075e-06, "epoch": 0.15843997562461914, "percentage": 3.96, "elapsed_time": "0:04:36", "remaining_time": "1:51:34"}
+{"current_steps": 140, "total_steps": 3280, "loss": 0.3448, "learning_rate": 4.99795076958365e-06, "epoch": 0.17062766605728213, "percentage": 4.27, "elapsed_time": "0:04:54", "remaining_time": "1:49:55"}
+{"current_steps": 150, "total_steps": 3280, "loss": 0.3187, "learning_rate": 4.996829476657414e-06, "epoch": 0.18281535648994515, "percentage": 4.57, "elapsed_time": "0:05:10", "remaining_time": "1:47:55"}
+{"current_steps": 160, "total_steps": 3280, "loss": 0.3343, "learning_rate": 4.995464650764122e-06, "epoch": 0.19500304692260817, "percentage": 4.88, "elapsed_time": "0:05:28", "remaining_time": "1:46:50"}
+{"current_steps": 170, "total_steps": 3280, "loss": 0.3143, "learning_rate": 4.993856425024637e-06, "epoch": 0.2071907373552712, "percentage": 5.18, "elapsed_time": "0:05:44", "remaining_time": "1:44:55"}
+{"current_steps": 180, "total_steps": 3280, "loss": 0.3301, "learning_rate": 4.992004956300287e-06, "epoch": 0.21937842778793418, "percentage": 5.49, "elapsed_time": "0:06:01", "remaining_time": "1:43:50"}
+{"current_steps": 190, "total_steps": 3280, "loss": 0.3501, "learning_rate": 4.989910425177561e-06, "epoch": 0.2315661182205972, "percentage": 5.79, "elapsed_time": "0:06:19", "remaining_time": "1:42:55"}
+{"current_steps": 200, "total_steps": 3280, "loss": 0.283, "learning_rate": 4.987573035950499e-06, "epoch": 0.2437538086532602, "percentage": 6.1, "elapsed_time": "0:06:35", "remaining_time": "1:41:29"}
+{"current_steps": 210, "total_steps": 3280, "loss": 0.3144, "learning_rate": 4.984993016600763e-06, "epoch": 0.25594149908592323, "percentage": 6.4, "elapsed_time": "0:06:49", "remaining_time": "1:39:52"}
+{"current_steps": 220, "total_steps": 3280, "loss": 0.3221, "learning_rate": 4.982170618775401e-06, "epoch": 0.2681291895185862, "percentage": 6.71, "elapsed_time": "0:07:05", "remaining_time": "1:38:34"}
+{"current_steps": 230, "total_steps": 3280, "loss": 0.3244, "learning_rate": 4.979106117762303e-06, "epoch": 0.28031687995124926, "percentage": 7.01, "elapsed_time": "0:07:24", "remaining_time": "1:38:08"}
+{"current_steps": 240, "total_steps": 3280, "loss": 0.3112, "learning_rate": 4.975799812463348e-06, "epoch": 0.29250457038391225, "percentage": 7.32, "elapsed_time": "0:07:40", "remaining_time": "1:37:14"}
+{"current_steps": 250, "total_steps": 3280, "loss": 0.3321, "learning_rate": 4.972252025365251e-06, "epoch": 0.30469226081657524, "percentage": 7.62, "elapsed_time": "0:07:55", "remaining_time": "1:36:04"}
+{"current_steps": 260, "total_steps": 3280, "loss": 0.3337, "learning_rate": 4.968463102508114e-06, "epoch": 0.3168799512492383, "percentage": 7.93, "elapsed_time": "0:08:14", "remaining_time": "1:35:39"}
+{"current_steps": 270, "total_steps": 3280, "loss": 0.3029, "learning_rate": 4.9644334134516645e-06, "epoch": 0.3290676416819013, "percentage": 8.23, "elapsed_time": "0:08:28", "remaining_time": "1:34:32"}
+{"current_steps": 280, "total_steps": 3280, "loss": 0.3411, "learning_rate": 4.960163351239216e-06, "epoch": 0.34125533211456427, "percentage": 8.54, "elapsed_time": "0:08:43", "remaining_time": "1:33:31"}
+{"current_steps": 290, "total_steps": 3280, "loss": 0.3192, "learning_rate": 4.955653332359331e-06, "epoch": 0.3534430225472273, "percentage": 8.84, "elapsed_time": "0:08:58", "remaining_time": "1:32:36"}
+{"current_steps": 300, "total_steps": 3280, "loss": 0.3113, "learning_rate": 4.950903796705201e-06, "epoch": 0.3656307129798903, "percentage": 9.15, "elapsed_time": "0:09:16", "remaining_time": "1:32:11"}
+{"current_steps": 310, "total_steps": 3280, "loss": 0.3191, "learning_rate": 4.94591520753173e-06, "epoch": 0.3778184034125533, "percentage": 9.45, "elapsed_time": "0:09:33", "remaining_time": "1:31:37"}
+{"current_steps": 320, "total_steps": 3280, "loss": 0.3092, "learning_rate": 4.940688051410364e-06, "epoch": 0.39000609384521634, "percentage": 9.76, "elapsed_time": "0:09:48", "remaining_time": "1:30:40"}
+{"current_steps": 330, "total_steps": 3280, "loss": 0.3343, "learning_rate": 4.935222838181623e-06, "epoch": 0.40219378427787933, "percentage": 10.06, "elapsed_time": "0:10:00", "remaining_time": "1:29:28"}
+{"current_steps": 340, "total_steps": 3280, "loss": 0.3115, "learning_rate": 4.929520100905375e-06, "epoch": 0.4143814747105424, "percentage": 10.37, "elapsed_time": "0:10:17", "remaining_time": "1:29:03"}
+{"current_steps": 350, "total_steps": 3280, "loss": 0.2922, "learning_rate": 4.923580395808846e-06, "epoch": 0.42656916514320536, "percentage": 10.67, "elapsed_time": "0:10:33", "remaining_time": "1:28:21"}
+{"current_steps": 360, "total_steps": 3280, "loss": 0.3211, "learning_rate": 4.917404302232362e-06, "epoch": 0.43875685557586835, "percentage": 10.98, "elapsed_time": "0:10:49", "remaining_time": "1:27:48"}
+{"current_steps": 370, "total_steps": 3280, "loss": 0.3205, "learning_rate": 4.910992422572845e-06, "epoch": 0.4509445460085314, "percentage": 11.28, "elapsed_time": "0:11:04", "remaining_time": "1:27:02"}
+{"current_steps": 380, "total_steps": 3280, "loss": 0.331, "learning_rate": 4.904345382225058e-06, "epoch": 0.4631322364411944, "percentage": 11.59, "elapsed_time": "0:11:19", "remaining_time": "1:26:25"}
+{"current_steps": 390, "total_steps": 3280, "loss": 0.3224, "learning_rate": 4.897463829520604e-06, "epoch": 0.4753199268738574, "percentage": 11.89, "elapsed_time": "0:11:35", "remaining_time": "1:25:52"}
+{"current_steps": 400, "total_steps": 3280, "loss": 0.3054, "learning_rate": 4.890348435664694e-06, "epoch": 0.4875076173065204, "percentage": 12.2, "elapsed_time": "0:11:51", "remaining_time": "1:25:19"}
+{"current_steps": 410, "total_steps": 3280, "loss": 0.2973, "learning_rate": 4.882999894670669e-06, "epoch": 0.4996953077391834, "percentage": 12.5, "elapsed_time": "0:12:05", "remaining_time": "1:24:41"}
+{"current_steps": 420, "total_steps": 3280, "loss": 0.295, "learning_rate": 4.875418923292322e-06, "epoch": 0.5118829981718465, "percentage": 12.8, "elapsed_time": "0:12:20", "remaining_time": "1:24:02"}
+{"current_steps": 430, "total_steps": 3280, "loss": 0.3027, "learning_rate": 4.867606260953979e-06, "epoch": 0.5240706886045094, "percentage": 13.11, "elapsed_time": "0:12:35", "remaining_time": "1:23:30"}
+{"current_steps": 440, "total_steps": 3280, "loss": 0.3007, "learning_rate": 4.85956266967838e-06, "epoch": 0.5362583790371724, "percentage": 13.41, "elapsed_time": "0:12:51", "remaining_time": "1:22:58"}
+{"current_steps": 450, "total_steps": 3280, "loss": 0.3168, "learning_rate": 4.8512889340123535e-06, "epoch": 0.5484460694698354, "percentage": 13.72, "elapsed_time": "0:13:07", "remaining_time": "1:22:35"}
+{"current_steps": 460, "total_steps": 3280, "loss": 0.3137, "learning_rate": 4.842785860950296e-06, "epoch": 0.5606337599024985, "percentage": 14.02, "elapsed_time": "0:13:23", "remaining_time": "1:22:08"}
+{"current_steps": 470, "total_steps": 3280, "loss": 0.3118, "learning_rate": 4.834054279855459e-06, "epoch": 0.5728214503351615, "percentage": 14.33, "elapsed_time": "0:13:40", "remaining_time": "1:21:45"}
+{"current_steps": 480, "total_steps": 3280, "loss": 0.289, "learning_rate": 4.825095042379054e-06, "epoch": 0.5850091407678245, "percentage": 14.63, "elapsed_time": "0:13:56", "remaining_time": "1:21:20"}
+{"current_steps": 490, "total_steps": 3280, "loss": 0.2937, "learning_rate": 4.815909022377189e-06, "epoch": 0.5971968312004875, "percentage": 14.94, "elapsed_time": "0:14:12", "remaining_time": "1:20:52"}
+{"current_steps": 500, "total_steps": 3280, "loss": 0.3063, "learning_rate": 4.806497115825629e-06, "epoch": 0.6093845216331505, "percentage": 15.24, "elapsed_time": "0:14:29", "remaining_time": "1:20:33"}
+{"current_steps": 510, "total_steps": 3280, "loss": 0.316, "learning_rate": 4.796860240732414e-06, "epoch": 0.6215722120658135, "percentage": 15.55, "elapsed_time": "0:15:38", "remaining_time": "1:24:55"}
+{"current_steps": 520, "total_steps": 3280, "loss": 0.3127, "learning_rate": 4.786999337048311e-06, "epoch": 0.6337599024984766, "percentage": 15.85, "elapsed_time": "0:15:54", "remaining_time": "1:24:27"}
+{"current_steps": 530, "total_steps": 3280, "loss": 0.3057, "learning_rate": 4.77691536657514e-06, "epoch": 0.6459475929311396, "percentage": 16.16, "elapsed_time": "0:16:09", "remaining_time": "1:23:49"}
+{"current_steps": 540, "total_steps": 3280, "loss": 0.3006, "learning_rate": 4.766609312871958e-06, "epoch": 0.6581352833638026, "percentage": 16.46, "elapsed_time": "0:16:27", "remaining_time": "1:23:29"}
+{"current_steps": 550, "total_steps": 3280, "loss": 0.3131, "learning_rate": 4.756082181159131e-06, "epoch": 0.6703229737964655, "percentage": 16.77, "elapsed_time": "0:16:41", "remaining_time": "1:22:49"}
+{"current_steps": 560, "total_steps": 3280, "loss": 0.3079, "learning_rate": 4.745334998220282e-06, "epoch": 0.6825106642291285, "percentage": 17.07, "elapsed_time": "0:16:54", "remaining_time": "1:22:09"}
+{"current_steps": 570, "total_steps": 3280, "loss": 0.3257, "learning_rate": 4.734368812302148e-06, "epoch": 0.6946983546617916, "percentage": 17.38, "elapsed_time": "0:17:08", "remaining_time": "1:21:31"}
+{"current_steps": 580, "total_steps": 3280, "loss": 0.2991, "learning_rate": 4.723184693012334e-06, "epoch": 0.7068860450944546, "percentage": 17.68, "elapsed_time": "0:17:22", "remaining_time": "1:20:52"}
+{"current_steps": 590, "total_steps": 3280, "loss": 0.3093, "learning_rate": 4.711783731214984e-06, "epoch": 0.7190737355271176, "percentage": 17.99, "elapsed_time": "0:17:40", "remaining_time": "1:20:35"}
+{"current_steps": 600, "total_steps": 3280, "loss": 0.2807, "learning_rate": 4.700167038924386e-06, "epoch": 0.7312614259597806, "percentage": 18.29, "elapsed_time": "0:17:55", "remaining_time": "1:20:02"}
+{"current_steps": 610, "total_steps": 3280, "loss": 0.3026, "learning_rate": 4.688335749196511e-06, "epoch": 0.7434491163924436, "percentage": 18.6, "elapsed_time": "0:18:11", "remaining_time": "1:19:36"}
+{"current_steps": 620, "total_steps": 3280, "loss": 0.2992, "learning_rate": 4.676291016018491e-06, "epoch": 0.7556368068251066, "percentage": 18.9, "elapsed_time": "0:18:26", "remaining_time": "1:19:05"}
+{"current_steps": 630, "total_steps": 3280, "loss": 0.3223, "learning_rate": 4.664034014196069e-06, "epoch": 0.7678244972577697, "percentage": 19.21, "elapsed_time": "0:18:40", "remaining_time": "1:18:32"}
+{"current_steps": 640, "total_steps": 3280, "loss": 0.3069, "learning_rate": 4.651565939239011e-06, "epoch": 0.7800121876904327, "percentage": 19.51, "elapsed_time": "0:18:54", "remaining_time": "1:17:59"}
+{"current_steps": 650, "total_steps": 3280, "loss": 0.3112, "learning_rate": 4.638888007244498e-06, "epoch": 0.7921998781230957, "percentage": 19.82, "elapsed_time": "0:19:07", "remaining_time": "1:17:22"}
+{"current_steps": 660, "total_steps": 3280, "loss": 0.2949, "learning_rate": 4.626001454778511e-06, "epoch": 0.8043875685557587, "percentage": 20.12, "elapsed_time": "0:19:25", "remaining_time": "1:17:05"}
+{"current_steps": 670, "total_steps": 3280, "loss": 0.3128, "learning_rate": 4.612907538755224e-06, "epoch": 0.8165752589884216, "percentage": 20.43, "elapsed_time": "0:19:42", "remaining_time": "1:16:47"}
+{"current_steps": 680, "total_steps": 3280, "loss": 0.3115, "learning_rate": 4.599607536314406e-06, "epoch": 0.8287629494210847, "percentage": 20.73, "elapsed_time": "0:19:58", "remaining_time": "1:16:21"}
+{"current_steps": 690, "total_steps": 3280, "loss": 0.3189, "learning_rate": 4.586102744696851e-06, "epoch": 0.8409506398537477, "percentage": 21.04, "elapsed_time": "0:20:12", "remaining_time": "1:15:52"}
+{"current_steps": 700, "total_steps": 3280, "loss": 0.2756, "learning_rate": 4.572394481117855e-06, "epoch": 0.8531383302864107, "percentage": 21.34, "elapsed_time": "0:20:27", "remaining_time": "1:15:24"}
+{"current_steps": 710, "total_steps": 3280, "loss": 0.3078, "learning_rate": 4.558484082638729e-06, "epoch": 0.8653260207190737, "percentage": 21.65, "elapsed_time": "0:20:44", "remaining_time": "1:15:05"}
+{"current_steps": 720, "total_steps": 3280, "loss": 0.3017, "learning_rate": 4.544372906036399e-06, "epoch": 0.8775137111517367, "percentage": 21.95, "elapsed_time": "0:21:00", "remaining_time": "1:14:42"}
+{"current_steps": 730, "total_steps": 3280, "loss": 0.3277, "learning_rate": 4.5300623276710604e-06, "epoch": 0.8897014015843998, "percentage": 22.26, "elapsed_time": "0:21:17", "remaining_time": "1:14:21"}
+{"current_steps": 740, "total_steps": 3280, "loss": 0.2817, "learning_rate": 4.515553743351934e-06, "epoch": 0.9018890920170628, "percentage": 22.56, "elapsed_time": "0:21:31", "remaining_time": "1:13:52"}
+{"current_steps": 750, "total_steps": 3280, "loss": 0.2845, "learning_rate": 4.5008485682011265e-06, "epoch": 0.9140767824497258, "percentage": 22.87, "elapsed_time": "0:21:45", "remaining_time": "1:13:25"}
+{"current_steps": 760, "total_steps": 3280, "loss": 0.3032, "learning_rate": 4.4859482365156e-06, "epoch": 0.9262644728823888, "percentage": 23.17, "elapsed_time": "0:21:58", "remaining_time": "1:12:52"}
+{"current_steps": 770, "total_steps": 3280, "loss": 0.3154, "learning_rate": 4.470854201627278e-06, "epoch": 0.9384521633150518, "percentage": 23.48, "elapsed_time": "0:22:13", "remaining_time": "1:12:26"}
+{"current_steps": 780, "total_steps": 3280, "loss": 0.3276, "learning_rate": 4.4555679357612925e-06, "epoch": 0.9506398537477148, "percentage": 23.78, "elapsed_time": "0:22:30", "remaining_time": "1:12:08"}
+{"current_steps": 790, "total_steps": 3280, "loss": 0.2941, "learning_rate": 4.440090929892382e-06, "epoch": 0.9628275441803779, "percentage": 24.09, "elapsed_time": "0:22:45", "remaining_time": "1:11:42"}
+{"current_steps": 800, "total_steps": 3280, "loss": 0.2795, "learning_rate": 4.424424693599474e-06, "epoch": 0.9750152346130408, "percentage": 24.39, "elapsed_time": "0:23:00", "remaining_time": "1:11:20"}
+{"current_steps": 810, "total_steps": 3280, "loss": 0.2968, "learning_rate": 4.4085707549184395e-06, "epoch": 0.9872029250457038, "percentage": 24.7, "elapsed_time": "0:23:16", "remaining_time": "1:10:57"}
+{"current_steps": 820, "total_steps": 3280, "loss": 0.289, "learning_rate": 4.392530660193058e-06, "epoch": 0.9993906154783668, "percentage": 25.0, "elapsed_time": "0:23:31", "remaining_time": "1:10:33"}
+{"current_steps": 830, "total_steps": 3280, "loss": 0.2459, "learning_rate": 4.376305973924188e-06, "epoch": 1.01157830591103, "percentage": 25.3, "elapsed_time": "0:23:45", "remaining_time": "1:10:07"}
+{"current_steps": 840, "total_steps": 3280, "loss": 0.2095, "learning_rate": 4.359898278617171e-06, "epoch": 1.023765996343693, "percentage": 25.61, "elapsed_time": "0:24:00", "remaining_time": "1:09:44"}
+{"current_steps": 850, "total_steps": 3280, "loss": 0.2504, "learning_rate": 4.343309174627484e-06, "epoch": 1.035953686776356, "percentage": 25.91, "elapsed_time": "0:24:15", "remaining_time": "1:09:21"}
+{"current_steps": 860, "total_steps": 3280, "loss": 0.2335, "learning_rate": 4.326540280004634e-06, "epoch": 1.048141377209019, "percentage": 26.22, "elapsed_time": "0:24:32", "remaining_time": "1:09:03"}
+{"current_steps": 870, "total_steps": 3280, "loss": 0.2312, "learning_rate": 4.309593230334355e-06, "epoch": 1.0603290676416819, "percentage": 26.52, "elapsed_time": "0:24:46", "remaining_time": "1:08:38"}
+{"current_steps": 880, "total_steps": 3280, "loss": 0.2367, "learning_rate": 4.292469678579063e-06, "epoch": 1.0725167580743449, "percentage": 26.83, "elapsed_time": "0:25:00", "remaining_time": "1:08:13"}
+{"current_steps": 890, "total_steps": 3280, "loss": 0.2445, "learning_rate": 4.275171294916641e-06, "epoch": 1.0847044485070079, "percentage": 27.13, "elapsed_time": "0:25:16", "remaining_time": "1:07:52"}
+{"current_steps": 900, "total_steps": 3280, "loss": 0.2329, "learning_rate": 4.2576997665775275e-06, "epoch": 1.0968921389396709, "percentage": 27.44, "elapsed_time": "0:25:31", "remaining_time": "1:07:30"}
+{"current_steps": 910, "total_steps": 3280, "loss": 0.2174, "learning_rate": 4.2400567976801575e-06, "epoch": 1.1090798293723338, "percentage": 27.74, "elapsed_time": "0:25:45", "remaining_time": "1:07:04"}
+{"current_steps": 920, "total_steps": 3280, "loss": 0.2304, "learning_rate": 4.22224410906474e-06, "epoch": 1.1212675198049968, "percentage": 28.05, "elapsed_time": "0:25:59", "remaining_time": "1:06:41"}
+{"current_steps": 930, "total_steps": 3280, "loss": 0.2206, "learning_rate": 4.204263438125421e-06, "epoch": 1.13345521023766, "percentage": 28.35, "elapsed_time": "0:26:14", "remaining_time": "1:06:19"}
+{"current_steps": 940, "total_steps": 3280, "loss": 0.2348, "learning_rate": 4.186116538640814e-06, "epoch": 1.145642900670323, "percentage": 28.66, "elapsed_time": "0:26:28", "remaining_time": "1:05:54"}
+{"current_steps": 950, "total_steps": 3280, "loss": 0.2071, "learning_rate": 4.167805180602951e-06, "epoch": 1.157830591102986, "percentage": 28.96, "elapsed_time": "0:26:45", "remaining_time": "1:05:38"}
+{"current_steps": 960, "total_steps": 3280, "loss": 0.2053, "learning_rate": 4.149331150044635e-06, "epoch": 1.170018281535649, "percentage": 29.27, "elapsed_time": "0:27:03", "remaining_time": "1:05:22"}
+{"current_steps": 970, "total_steps": 3280, "loss": 0.2068, "learning_rate": 4.130696248865244e-06, "epoch": 1.182205971968312, "percentage": 29.57, "elapsed_time": "0:27:16", "remaining_time": "1:04:56"}
+{"current_steps": 980, "total_steps": 3280, "loss": 0.2468, "learning_rate": 4.111902294654971e-06, "epoch": 1.194393662400975, "percentage": 29.88, "elapsed_time": "0:27:32", "remaining_time": "1:04:38"}
+{"current_steps": 990, "total_steps": 3280, "loss": 0.2254, "learning_rate": 4.09295112051755e-06, "epoch": 1.206581352833638, "percentage": 30.18, "elapsed_time": "0:27:46", "remaining_time": "1:04:15"}
+{"current_steps": 1000, "total_steps": 3280, "loss": 0.2306, "learning_rate": 4.073844574891452e-06, "epoch": 1.218769043266301, "percentage": 30.49, "elapsed_time": "0:27:59", "remaining_time": "1:03:49"}
+{"current_steps": 1010, "total_steps": 3280, "loss": 0.2294, "learning_rate": 4.054584521369603e-06, "epoch": 1.230956733698964, "percentage": 30.79, "elapsed_time": "0:29:09", "remaining_time": "1:05:31"}
+{"current_steps": 1020, "total_steps": 3280, "loss": 0.2222, "learning_rate": 4.03517283851761e-06, "epoch": 1.2431444241316272, "percentage": 31.1, "elapsed_time": "0:29:24", "remaining_time": "1:05:08"}
+{"current_steps": 1030, "total_steps": 3280, "loss": 0.2636, "learning_rate": 4.01561141969053e-06, "epoch": 1.2553321145642902, "percentage": 31.4, "elapsed_time": "0:29:40", "remaining_time": "1:04:49"}
+{"current_steps": 1040, "total_steps": 3280, "loss": 0.2509, "learning_rate": 3.995902172848205e-06, "epoch": 1.2675198049969532, "percentage": 31.71, "elapsed_time": "0:29:55", "remaining_time": "1:04:26"}
+{"current_steps": 1050, "total_steps": 3280, "loss": 0.2165, "learning_rate": 3.976047020369155e-06, "epoch": 1.2797074954296161, "percentage": 32.01, "elapsed_time": "0:30:07", "remaining_time": "1:03:59"}
+{"current_steps": 1060, "total_steps": 3280, "loss": 0.22, "learning_rate": 3.9560478988630866e-06, "epoch": 1.2918951858622791, "percentage": 32.32, "elapsed_time": "0:30:22", "remaining_time": "1:03:36"}
+{"current_steps": 1070, "total_steps": 3280, "loss": 0.2258, "learning_rate": 3.935906758981993e-06, "epoch": 1.3040828762949421, "percentage": 32.62, "elapsed_time": "0:30:35", "remaining_time": "1:03:10"}
+{"current_steps": 1080, "total_steps": 3280, "loss": 0.2378, "learning_rate": 3.9156255652299005e-06, "epoch": 1.3162705667276051, "percentage": 32.93, "elapsed_time": "0:30:49", "remaining_time": "1:02:46"}
+{"current_steps": 1090, "total_steps": 3280, "loss": 0.2477, "learning_rate": 3.89520629577125e-06, "epoch": 1.328458257160268, "percentage": 33.23, "elapsed_time": "0:31:04", "remaining_time": "1:02:26"}
+{"current_steps": 1100, "total_steps": 3280, "loss": 0.2073, "learning_rate": 3.8746509422379575e-06, "epoch": 1.340645947592931, "percentage": 33.54, "elapsed_time": "0:31:19", "remaining_time": "1:02:04"}
+{"current_steps": 1110, "total_steps": 3280, "loss": 0.2199, "learning_rate": 3.853961509535159e-06, "epoch": 1.352833638025594, "percentage": 33.84, "elapsed_time": "0:31:34", "remaining_time": "1:01:43"}
+{"current_steps": 1120, "total_steps": 3280, "loss": 0.2284, "learning_rate": 3.83314001564565e-06, "epoch": 1.365021328458257, "percentage": 34.15, "elapsed_time": "0:31:48", "remaining_time": "1:01:19"}
+{"current_steps": 1130, "total_steps": 3280, "loss": 0.2372, "learning_rate": 3.8121884914330663e-06, "epoch": 1.37720901889092, "percentage": 34.45, "elapsed_time": "0:32:02", "remaining_time": "1:00:57"}
+{"current_steps": 1140, "total_steps": 3280, "loss": 0.2565, "learning_rate": 3.791108980443794e-06, "epoch": 1.389396709323583, "percentage": 34.76, "elapsed_time": "0:32:16", "remaining_time": "1:00:34"}
+{"current_steps": 1150, "total_steps": 3280, "loss": 0.2066, "learning_rate": 3.769903538707652e-06, "epoch": 1.4015843997562463, "percentage": 35.06, "elapsed_time": "0:32:30", "remaining_time": "1:00:12"}
+{"current_steps": 1160, "total_steps": 3280, "loss": 0.2217, "learning_rate": 3.7485742345373517e-06, "epoch": 1.4137720901889093, "percentage": 35.37, "elapsed_time": "0:32:45", "remaining_time": "0:59:52"}
+{"current_steps": 1170, "total_steps": 3280, "loss": 0.2218, "learning_rate": 3.727123148326758e-06, "epoch": 1.4259597806215722, "percentage": 35.67, "elapsed_time": "0:33:00", "remaining_time": "0:59:32"}
+{"current_steps": 1180, "total_steps": 3280, "loss": 0.225, "learning_rate": 3.705552372347981e-06, "epoch": 1.4381474710542352, "percentage": 35.98, "elapsed_time": "0:33:13", "remaining_time": "0:59:08"}
+{"current_steps": 1190, "total_steps": 3280, "loss": 0.2346, "learning_rate": 3.683864010547294e-06, "epoch": 1.4503351614868982, "percentage": 36.28, "elapsed_time": "0:33:29", "remaining_time": "0:58:49"}
+{"current_steps": 1200, "total_steps": 3280, "loss": 0.2393, "learning_rate": 3.662060178339927e-06, "epoch": 1.4625228519195612, "percentage": 36.59, "elapsed_time": "0:33:44", "remaining_time": "0:58:29"}
+{"current_steps": 1210, "total_steps": 3280, "loss": 0.2361, "learning_rate": 3.6401430024037315e-06, "epoch": 1.4747105423522242, "percentage": 36.89, "elapsed_time": "0:33:58", "remaining_time": "0:58:07"}
+{"current_steps": 1220, "total_steps": 3280, "loss": 0.2198, "learning_rate": 3.618114620471756e-06, "epoch": 1.4868982327848872, "percentage": 37.2, "elapsed_time": "0:34:13", "remaining_time": "0:57:47"}
+{"current_steps": 1230, "total_steps": 3280, "loss": 0.2396, "learning_rate": 3.5959771811237342e-06, "epoch": 1.4990859232175504, "percentage": 37.5, "elapsed_time": "0:34:30", "remaining_time": "0:57:30"}
+{"current_steps": 1240, "total_steps": 3280, "loss": 0.2308, "learning_rate": 3.573732843576519e-06, "epoch": 1.5112736136502134, "percentage": 37.8, "elapsed_time": "0:34:45", "remaining_time": "0:57:10"}
+{"current_steps": 1250, "total_steps": 3280, "loss": 0.2051, "learning_rate": 3.5513837774734816e-06, "epoch": 1.5234613040828764, "percentage": 38.11, "elapsed_time": "0:35:02", "remaining_time": "0:56:55"}
+{"current_steps": 1260, "total_steps": 3280, "loss": 0.2526, "learning_rate": 3.5289321626728912e-06, "epoch": 1.5356489945155394, "percentage": 38.41, "elapsed_time": "0:35:18", "remaining_time": "0:56:36"}
+{"current_steps": 1270, "total_steps": 3280, "loss": 0.2112, "learning_rate": 3.5063801890352955e-06, "epoch": 1.5478366849482024, "percentage": 38.72, "elapsed_time": "0:35:32", "remaining_time": "0:56:14"}
+{"current_steps": 1280, "total_steps": 3280, "loss": 0.2199, "learning_rate": 3.4837300562099324e-06, "epoch": 1.5600243753808654, "percentage": 39.02, "elapsed_time": "0:35:48", "remaining_time": "0:55:57"}
+{"current_steps": 1290, "total_steps": 3280, "loss": 0.249, "learning_rate": 3.4609839734201793e-06, "epoch": 1.5722120658135283, "percentage": 39.33, "elapsed_time": "0:36:02", "remaining_time": "0:55:35"}
+{"current_steps": 1300, "total_steps": 3280, "loss": 0.2634, "learning_rate": 3.4381441592480756e-06, "epoch": 1.5843997562461913, "percentage": 39.63, "elapsed_time": "0:36:20", "remaining_time": "0:55:21"}
+{"current_steps": 1310, "total_steps": 3280, "loss": 0.2243, "learning_rate": 3.4152128414179263e-06, "epoch": 1.5965874466788543, "percentage": 39.94, "elapsed_time": "0:36:33", "remaining_time": "0:54:59"}
+{"current_steps": 1320, "total_steps": 3280, "loss": 0.2478, "learning_rate": 3.3921922565790188e-06, "epoch": 1.6087751371115173, "percentage": 40.24, "elapsed_time": "0:36:48", "remaining_time": "0:54:40"}
+{"current_steps": 1330, "total_steps": 3280, "loss": 0.2005, "learning_rate": 3.3690846500874664e-06, "epoch": 1.6209628275441803, "percentage": 40.55, "elapsed_time": "0:37:04", "remaining_time": "0:54:21"}
+{"current_steps": 1340, "total_steps": 3280, "loss": 0.2517, "learning_rate": 3.345892275787204e-06, "epoch": 1.6331505179768433, "percentage": 40.85, "elapsed_time": "0:37:19", "remaining_time": "0:54:02"}
+{"current_steps": 1350, "total_steps": 3280, "loss": 0.2361, "learning_rate": 3.3226173957901533e-06, "epoch": 1.6453382084095063, "percentage": 41.16, "elapsed_time": "0:37:34", "remaining_time": "0:53:42"}
+{"current_steps": 1360, "total_steps": 3280, "loss": 0.2228, "learning_rate": 3.2992622802555844e-06, "epoch": 1.6575258988421693, "percentage": 41.46, "elapsed_time": "0:37:48", "remaining_time": "0:53:22"}
+{"current_steps": 1370, "total_steps": 3280, "loss": 0.2347, "learning_rate": 3.2758292071686928e-06, "epoch": 1.6697135892748323, "percentage": 41.77, "elapsed_time": "0:38:03", "remaining_time": "0:53:03"}
+{"current_steps": 1380, "total_steps": 3280, "loss": 0.2326, "learning_rate": 3.2523204621184094e-06, "epoch": 1.6819012797074955, "percentage": 42.07, "elapsed_time": "0:38:19", "remaining_time": "0:52:46"}
+{"current_steps": 1390, "total_steps": 3280, "loss": 0.2281, "learning_rate": 3.2287383380744746e-06, "epoch": 1.6940889701401585, "percentage": 42.38, "elapsed_time": "0:38:33", "remaining_time": "0:52:25"}
+{"current_steps": 1400, "total_steps": 3280, "loss": 0.2109, "learning_rate": 3.2050851351637853e-06, "epoch": 1.7062766605728215, "percentage": 42.68, "elapsed_time": "0:38:46", "remaining_time": "0:52:03"}
+{"current_steps": 1410, "total_steps": 3280, "loss": 0.2387, "learning_rate": 3.1813631604460504e-06, "epoch": 1.7184643510054844, "percentage": 42.99, "elapsed_time": "0:39:01", "remaining_time": "0:51:46"}
+{"current_steps": 1420, "total_steps": 3280, "loss": 0.2348, "learning_rate": 3.1575747276887657e-06, "epoch": 1.7306520414381474, "percentage": 43.29, "elapsed_time": "0:39:16", "remaining_time": "0:51:26"}
+{"current_steps": 1430, "total_steps": 3280, "loss": 0.2323, "learning_rate": 3.1337221571415388e-06, "epoch": 1.7428397318708104, "percentage": 43.6, "elapsed_time": "0:39:30", "remaining_time": "0:51:06"}
+{"current_steps": 1440, "total_steps": 3280, "loss": 0.238, "learning_rate": 3.1098077753097763e-06, "epoch": 1.7550274223034736, "percentage": 43.9, "elapsed_time": "0:39:48", "remaining_time": "0:50:51"}
+{"current_steps": 1450, "total_steps": 3280, "loss": 0.2223, "learning_rate": 3.085833914727765e-06, "epoch": 1.7672151127361366, "percentage": 44.21, "elapsed_time": "0:40:03", "remaining_time": "0:50:33"}
+{"current_steps": 1460, "total_steps": 3280, "loss": 0.2271, "learning_rate": 3.0618029137311634e-06, "epoch": 1.7794028031687996, "percentage": 44.51, "elapsed_time": "0:40:18", "remaining_time": "0:50:15"}
+{"current_steps": 1470, "total_steps": 3280, "loss": 0.2372, "learning_rate": 3.037717116228929e-06, "epoch": 1.7915904936014626, "percentage": 44.82, "elapsed_time": "0:40:35", "remaining_time": "0:49:58"}
+{"current_steps": 1480, "total_steps": 3280, "loss": 0.2397, "learning_rate": 3.013578871474699e-06, "epoch": 1.8037781840341256, "percentage": 45.12, "elapsed_time": "0:40:49", "remaining_time": "0:49:38"}
+{"current_steps": 1490, "total_steps": 3280, "loss": 0.2237, "learning_rate": 2.9893905338376503e-06, "epoch": 1.8159658744667886, "percentage": 45.43, "elapsed_time": "0:41:06", "remaining_time": "0:49:22"}
+{"current_steps": 1500, "total_steps": 3280, "loss": 0.2099, "learning_rate": 2.965154462572869e-06, "epoch": 1.8281535648994516, "percentage": 45.73, "elapsed_time": "0:41:19", "remaining_time": "0:49:02"}
+{"current_steps": 1510, "total_steps": 3280, "loss": 0.2205, "learning_rate": 2.9408730215912247e-06, "epoch": 1.8403412553321146, "percentage": 46.04, "elapsed_time": "0:42:27", "remaining_time": "0:49:45"}
+{"current_steps": 1520, "total_steps": 3280, "loss": 0.2149, "learning_rate": 2.91654857922881e-06, "epoch": 1.8525289457647776, "percentage": 46.34, "elapsed_time": "0:42:43", "remaining_time": "0:49:28"}
+{"current_steps": 1530, "total_steps": 3280, "loss": 0.2309, "learning_rate": 2.892183508015939e-06, "epoch": 1.8647166361974405, "percentage": 46.65, "elapsed_time": "0:42:58", "remaining_time": "0:49:09"}
+{"current_steps": 1540, "total_steps": 3280, "loss": 0.2254, "learning_rate": 2.867780184445735e-06, "epoch": 1.8769043266301035, "percentage": 46.95, "elapsed_time": "0:43:14", "remaining_time": "0:48:51"}
+{"current_steps": 1550, "total_steps": 3280, "loss": 0.2251, "learning_rate": 2.8433409887423397e-06, "epoch": 1.8890920170627665, "percentage": 47.26, "elapsed_time": "0:43:28", "remaining_time": "0:48:31"}
+{"current_steps": 1560, "total_steps": 3280, "loss": 0.2375, "learning_rate": 2.8188683046287496e-06, "epoch": 1.9012797074954295, "percentage": 47.56, "elapsed_time": "0:43:44", "remaining_time": "0:48:13"}
+{"current_steps": 1570, "total_steps": 3280, "loss": 0.2195, "learning_rate": 2.794364519094317e-06, "epoch": 1.9134673979280925, "percentage": 47.87, "elapsed_time": "0:44:00", "remaining_time": "0:47:56"}
+{"current_steps": 1580, "total_steps": 3280, "loss": 0.1939, "learning_rate": 2.7698320221619278e-06, "epoch": 1.9256550883607555, "percentage": 48.17, "elapsed_time": "0:44:12", "remaining_time": "0:47:34"}
+{"current_steps": 1590, "total_steps": 3280, "loss": 0.2419, "learning_rate": 2.7452732066548914e-06, "epoch": 1.9378427787934185, "percentage": 48.48, "elapsed_time": "0:44:27", "remaining_time": "0:47:15"}
+{"current_steps": 1600, "total_steps": 3280, "loss": 0.1974, "learning_rate": 2.7206904679635465e-06, "epoch": 1.9500304692260817, "percentage": 48.78, "elapsed_time": "0:44:43", "remaining_time": "0:46:57"}
+{"current_steps": 1610, "total_steps": 3280, "loss": 0.251, "learning_rate": 2.6960862038116265e-06, "epoch": 1.9622181596587447, "percentage": 49.09, "elapsed_time": "0:44:58", "remaining_time": "0:46:38"}
+{"current_steps": 1620, "total_steps": 3280, "loss": 0.2148, "learning_rate": 2.6714628140223885e-06, "epoch": 1.9744058500914077, "percentage": 49.39, "elapsed_time": "0:45:12", "remaining_time": "0:46:19"}
+{"current_steps": 1630, "total_steps": 3280, "loss": 0.2322, "learning_rate": 2.6468227002845476e-06, "epoch": 1.9865935405240707, "percentage": 49.7, "elapsed_time": "0:45:29", "remaining_time": "0:46:03"}
+{"current_steps": 1640, "total_steps": 3280, "loss": 0.2059, "learning_rate": 2.6221682659180186e-06, "epoch": 1.9987812309567337, "percentage": 50.0, "elapsed_time": "0:45:44", "remaining_time": "0:45:44"}
+{"current_steps": 1650, "total_steps": 3280, "loss": 0.1819, "learning_rate": 2.597501915639507e-06, "epoch": 2.010968921389397, "percentage": 50.3, "elapsed_time": "0:45:59", "remaining_time": "0:45:25"}
+{"current_steps": 1660, "total_steps": 3280, "loss": 0.1463, "learning_rate": 2.5728260553279592e-06, "epoch": 2.02315661182206, "percentage": 50.61, "elapsed_time": "0:46:14", "remaining_time": "0:45:07"}
+{"current_steps": 1670, "total_steps": 3280, "loss": 0.1563, "learning_rate": 2.5481430917899e-06, "epoch": 2.035344302254723, "percentage": 50.91, "elapsed_time": "0:46:29", "remaining_time": "0:44:49"}
+{"current_steps": 1680, "total_steps": 3280, "loss": 0.1488, "learning_rate": 2.523455432524681e-06, "epoch": 2.047531992687386, "percentage": 51.22, "elapsed_time": "0:46:43", "remaining_time": "0:44:29"}
+{"current_steps": 1690, "total_steps": 3280, "loss": 0.1599, "learning_rate": 2.4987654854896606e-06, "epoch": 2.059719683120049, "percentage": 51.52, "elapsed_time": "0:46:58", "remaining_time": "0:44:11"}
+{"current_steps": 1700, "total_steps": 3280, "loss": 0.1493, "learning_rate": 2.4740756588653388e-06, "epoch": 2.071907373552712, "percentage": 51.83, "elapsed_time": "0:47:11", "remaining_time": "0:43:51"}
+{"current_steps": 1710, "total_steps": 3280, "loss": 0.161, "learning_rate": 2.4493883608204703e-06, "epoch": 2.084095063985375, "percentage": 52.13, "elapsed_time": "0:47:27", "remaining_time": "0:43:34"}
+{"current_steps": 1720, "total_steps": 3280, "loss": 0.1705, "learning_rate": 2.4247059992771836e-06, "epoch": 2.096282754418038, "percentage": 52.44, "elapsed_time": "0:47:42", "remaining_time": "0:43:16"}
+{"current_steps": 1730, "total_steps": 3280, "loss": 0.15, "learning_rate": 2.4000309816761105e-06, "epoch": 2.108470444850701, "percentage": 52.74, "elapsed_time": "0:47:57", "remaining_time": "0:42:57"}
+{"current_steps": 1740, "total_steps": 3280, "loss": 0.1556, "learning_rate": 2.375365714741584e-06, "epoch": 2.1206581352833638, "percentage": 53.05, "elapsed_time": "0:48:13", "remaining_time": "0:42:40"}
+{"current_steps": 1750, "total_steps": 3280, "loss": 0.1846, "learning_rate": 2.3507126042468807e-06, "epoch": 2.1328458257160268, "percentage": 53.35, "elapsed_time": "0:48:27", "remaining_time": "0:42:22"}
+{"current_steps": 1760, "total_steps": 3280, "loss": 0.1691, "learning_rate": 2.3260740547795818e-06, "epoch": 2.1450335161486898, "percentage": 53.66, "elapsed_time": "0:48:42", "remaining_time": "0:42:03"}
+{"current_steps": 1770, "total_steps": 3280, "loss": 0.1617, "learning_rate": 2.3014524695070277e-06, "epoch": 2.1572212065813527, "percentage": 53.96, "elapsed_time": "0:48:56", "remaining_time": "0:41:45"}
+{"current_steps": 1780, "total_steps": 3280, "loss": 0.1547, "learning_rate": 2.276850249941927e-06, "epoch": 2.1694088970140157, "percentage": 54.27, "elapsed_time": "0:49:11", "remaining_time": "0:41:26"}
+{"current_steps": 1790, "total_steps": 3280, "loss": 0.149, "learning_rate": 2.2522697957081134e-06, "epoch": 2.1815965874466787, "percentage": 54.57, "elapsed_time": "0:49:25", "remaining_time": "0:41:08"}
+{"current_steps": 1800, "total_steps": 3280, "loss": 0.1484, "learning_rate": 2.2277135043065024e-06, "epoch": 2.1937842778793417, "percentage": 54.88, "elapsed_time": "0:49:42", "remaining_time": "0:40:52"}
+{"current_steps": 1810, "total_steps": 3280, "loss": 0.1681, "learning_rate": 2.203183770881239e-06, "epoch": 2.2059719683120047, "percentage": 55.18, "elapsed_time": "0:49:58", "remaining_time": "0:40:35"}
+{"current_steps": 1820, "total_steps": 3280, "loss": 0.1605, "learning_rate": 2.178682987986088e-06, "epoch": 2.2181596587446677, "percentage": 55.49, "elapsed_time": "0:50:14", "remaining_time": "0:40:18"}
+{"current_steps": 1830, "total_steps": 3280, "loss": 0.1645, "learning_rate": 2.154213545351067e-06, "epoch": 2.2303473491773307, "percentage": 55.79, "elapsed_time": "0:50:27", "remaining_time": "0:39:59"}
+{"current_steps": 1840, "total_steps": 3280, "loss": 0.1544, "learning_rate": 2.129777829649367e-06, "epoch": 2.2425350396099937, "percentage": 56.1, "elapsed_time": "0:50:43", "remaining_time": "0:39:41"}
+{"current_steps": 1850, "total_steps": 3280, "loss": 0.1518, "learning_rate": 2.1053782242645534e-06, "epoch": 2.254722730042657, "percentage": 56.4, "elapsed_time": "0:50:58", "remaining_time": "0:39:23"}
+{"current_steps": 1860, "total_steps": 3280, "loss": 0.1896, "learning_rate": 2.081017109058108e-06, "epoch": 2.26691042047532, "percentage": 56.71, "elapsed_time": "0:51:16", "remaining_time": "0:39:08"}
+{"current_steps": 1870, "total_steps": 3280, "loss": 0.1319, "learning_rate": 2.056696860137298e-06, "epoch": 2.279098110907983, "percentage": 57.01, "elapsed_time": "0:51:29", "remaining_time": "0:38:49"}
+{"current_steps": 1880, "total_steps": 3280, "loss": 0.1425, "learning_rate": 2.0324198496234227e-06, "epoch": 2.291285801340646, "percentage": 57.32, "elapsed_time": "0:51:42", "remaining_time": "0:38:30"}
+{"current_steps": 1890, "total_steps": 3280, "loss": 0.1517, "learning_rate": 2.0081884454204396e-06, "epoch": 2.303473491773309, "percentage": 57.62, "elapsed_time": "0:51:57", "remaining_time": "0:38:12"}
+{"current_steps": 1900, "total_steps": 3280, "loss": 0.146, "learning_rate": 1.984005010984011e-06, "epoch": 2.315661182205972, "percentage": 57.93, "elapsed_time": "0:52:10", "remaining_time": "0:37:53"}
+{"current_steps": 1910, "total_steps": 3280, "loss": 0.1529, "learning_rate": 1.9598719050909753e-06, "epoch": 2.327848872638635, "percentage": 58.23, "elapsed_time": "0:52:25", "remaining_time": "0:37:36"}
+{"current_steps": 1920, "total_steps": 3280, "loss": 0.1791, "learning_rate": 1.935791481609283e-06, "epoch": 2.340036563071298, "percentage": 58.54, "elapsed_time": "0:52:42", "remaining_time": "0:37:19"}
+{"current_steps": 1930, "total_steps": 3280, "loss": 0.1528, "learning_rate": 1.9117660892684067e-06, "epoch": 2.352224253503961, "percentage": 58.84, "elapsed_time": "0:52:59", "remaining_time": "0:37:04"}
+{"current_steps": 1940, "total_steps": 3280, "loss": 0.139, "learning_rate": 1.8877980714302532e-06, "epoch": 2.364411943936624, "percentage": 59.15, "elapsed_time": "0:53:13", "remaining_time": "0:36:45"}
+{"current_steps": 1950, "total_steps": 3280, "loss": 0.1495, "learning_rate": 1.8638897658605962e-06, "epoch": 2.376599634369287, "percentage": 59.45, "elapsed_time": "0:53:28", "remaining_time": "0:36:28"}
+{"current_steps": 1960, "total_steps": 3280, "loss": 0.1412, "learning_rate": 1.840043504501065e-06, "epoch": 2.38878732480195, "percentage": 59.76, "elapsed_time": "0:53:42", "remaining_time": "0:36:10"}
+{"current_steps": 1970, "total_steps": 3280, "loss": 0.1507, "learning_rate": 1.816261613241686e-06, "epoch": 2.400975015234613, "percentage": 60.06, "elapsed_time": "0:53:55", "remaining_time": "0:35:51"}
+{"current_steps": 1980, "total_steps": 3280, "loss": 0.1725, "learning_rate": 1.7925464116940299e-06, "epoch": 2.413162705667276, "percentage": 60.37, "elapsed_time": "0:54:11", "remaining_time": "0:35:34"}
+{"current_steps": 1990, "total_steps": 3280, "loss": 0.1605, "learning_rate": 1.7689002129649584e-06, "epoch": 2.425350396099939, "percentage": 60.67, "elapsed_time": "0:54:26", "remaining_time": "0:35:17"}
+{"current_steps": 2000, "total_steps": 3280, "loss": 0.1599, "learning_rate": 1.7453253234310164e-06, "epoch": 2.437538086532602, "percentage": 60.98, "elapsed_time": "0:54:41", "remaining_time": "0:35:00"}
+{"current_steps": 2010, "total_steps": 3280, "loss": 0.1312, "learning_rate": 1.7218240425134669e-06, "epoch": 2.449725776965265, "percentage": 61.28, "elapsed_time": "0:55:50", "remaining_time": "0:35:17"}
+{"current_steps": 2020, "total_steps": 3280, "loss": 0.1627, "learning_rate": 1.6983986624540227e-06, "epoch": 2.461913467397928, "percentage": 61.59, "elapsed_time": "0:56:06", "remaining_time": "0:34:59"}
+{"current_steps": 2030, "total_steps": 3280, "loss": 0.1685, "learning_rate": 1.6750514680912606e-06, "epoch": 2.474101157830591, "percentage": 61.89, "elapsed_time": "0:56:20", "remaining_time": "0:34:41"}
+{"current_steps": 2040, "total_steps": 3280, "loss": 0.1704, "learning_rate": 1.6517847366377693e-06, "epoch": 2.4862888482632544, "percentage": 62.2, "elapsed_time": "0:56:35", "remaining_time": "0:34:23"}
+{"current_steps": 2050, "total_steps": 3280, "loss": 0.1598, "learning_rate": 1.628600737458037e-06, "epoch": 2.4984765386959173, "percentage": 62.5, "elapsed_time": "0:56:50", "remaining_time": "0:34:06"}
+{"current_steps": 2060, "total_steps": 3280, "loss": 0.169, "learning_rate": 1.605501731847101e-06, "epoch": 2.5106642291285803, "percentage": 62.8, "elapsed_time": "0:57:08", "remaining_time": "0:33:50"}
+{"current_steps": 2070, "total_steps": 3280, "loss": 0.1509, "learning_rate": 1.5824899728099934e-06, "epoch": 2.5228519195612433, "percentage": 63.11, "elapsed_time": "0:57:22", "remaining_time": "0:33:32"}
+{"current_steps": 2080, "total_steps": 3280, "loss": 0.153, "learning_rate": 1.5595677048419855e-06, "epoch": 2.5350396099939063, "percentage": 63.41, "elapsed_time": "0:57:34", "remaining_time": "0:33:12"}
+{"current_steps": 2090, "total_steps": 3280, "loss": 0.165, "learning_rate": 1.5367371637096705e-06, "epoch": 2.5472273004265693, "percentage": 63.72, "elapsed_time": "0:57:50", "remaining_time": "0:32:55"}
+{"current_steps": 2100, "total_steps": 3280, "loss": 0.1773, "learning_rate": 1.5140005762328892e-06, "epoch": 2.5594149908592323, "percentage": 64.02, "elapsed_time": "0:58:06", "remaining_time": "0:32:38"}
+{"current_steps": 2110, "total_steps": 3280, "loss": 0.1439, "learning_rate": 1.4913601600675387e-06, "epoch": 2.5716026812918953, "percentage": 64.33, "elapsed_time": "0:58:20", "remaining_time": "0:32:21"}
+{"current_steps": 2120, "total_steps": 3280, "loss": 0.1378, "learning_rate": 1.468818123489263e-06, "epoch": 2.5837903717245583, "percentage": 64.63, "elapsed_time": "0:58:35", "remaining_time": "0:32:03"}
+{"current_steps": 2130, "total_steps": 3280, "loss": 0.1614, "learning_rate": 1.4463766651780698e-06, "epoch": 2.5959780621572213, "percentage": 64.94, "elapsed_time": "0:58:51", "remaining_time": "0:31:46"}
+{"current_steps": 2140, "total_steps": 3280, "loss": 0.1639, "learning_rate": 1.4240379740038758e-06, "epoch": 2.6081657525898843, "percentage": 65.24, "elapsed_time": "0:59:05", "remaining_time": "0:31:28"}
+{"current_steps": 2150, "total_steps": 3280, "loss": 0.154, "learning_rate": 1.4018042288130101e-06, "epoch": 2.6203534430225472, "percentage": 65.55, "elapsed_time": "0:59:19", "remaining_time": "0:31:10"}
+{"current_steps": 2160, "total_steps": 3280, "loss": 0.1558, "learning_rate": 1.3796775982156984e-06, "epoch": 2.6325411334552102, "percentage": 65.85, "elapsed_time": "0:59:32", "remaining_time": "0:30:52"}
+{"current_steps": 2170, "total_steps": 3280, "loss": 0.1618, "learning_rate": 1.3576602403745456e-06, "epoch": 2.6447288238878732, "percentage": 66.16, "elapsed_time": "0:59:48", "remaining_time": "0:30:35"}
+{"current_steps": 2180, "total_steps": 3280, "loss": 0.1502, "learning_rate": 1.3357543027940254e-06, "epoch": 2.656916514320536, "percentage": 66.46, "elapsed_time": "1:00:04", "remaining_time": "0:30:18"}
+{"current_steps": 2190, "total_steps": 3280, "loss": 0.161, "learning_rate": 1.3139619221110348e-06, "epoch": 2.669104204753199, "percentage": 66.77, "elapsed_time": "1:00:18", "remaining_time": "0:30:00"}
+{"current_steps": 2200, "total_steps": 3280, "loss": 0.169, "learning_rate": 1.2922852238864767e-06, "epoch": 2.681291895185862, "percentage": 67.07, "elapsed_time": "1:00:33", "remaining_time": "0:29:43"}
+{"current_steps": 2210, "total_steps": 3280, "loss": 0.1466, "learning_rate": 1.2707263223979544e-06, "epoch": 2.693479585618525, "percentage": 67.38, "elapsed_time": "1:00:48", "remaining_time": "0:29:26"}
+{"current_steps": 2220, "total_steps": 3280, "loss": 0.1594, "learning_rate": 1.2492873204335415e-06, "epoch": 2.705667276051188, "percentage": 67.68, "elapsed_time": "1:01:03", "remaining_time": "0:29:09"}
+{"current_steps": 2230, "total_steps": 3280, "loss": 0.1431, "learning_rate": 1.227970309086685e-06, "epoch": 2.717854966483851, "percentage": 67.99, "elapsed_time": "1:01:18", "remaining_time": "0:28:52"}
+{"current_steps": 2240, "total_steps": 3280, "loss": 0.162, "learning_rate": 1.2067773675522487e-06, "epoch": 2.730042656916514, "percentage": 68.29, "elapsed_time": "1:01:34", "remaining_time": "0:28:35"}
+{"current_steps": 2250, "total_steps": 3280, "loss": 0.1597, "learning_rate": 1.1857105629237126e-06, "epoch": 2.742230347349177, "percentage": 68.6, "elapsed_time": "1:01:48", "remaining_time": "0:28:17"}
+{"current_steps": 2260, "total_steps": 3280, "loss": 0.14, "learning_rate": 1.164771949991556e-06, "epoch": 2.75441803778184, "percentage": 68.9, "elapsed_time": "1:02:01", "remaining_time": "0:27:59"}
+{"current_steps": 2270, "total_steps": 3280, "loss": 0.1363, "learning_rate": 1.1439635710428405e-06, "epoch": 2.766605728214503, "percentage": 69.21, "elapsed_time": "1:02:18", "remaining_time": "0:27:43"}
+{"current_steps": 2280, "total_steps": 3280, "loss": 0.1849, "learning_rate": 1.1232874556620086e-06, "epoch": 2.778793418647166, "percentage": 69.51, "elapsed_time": "1:02:36", "remaining_time": "0:27:27"}
+{"current_steps": 2290, "total_steps": 3280, "loss": 0.1435, "learning_rate": 1.1027456205329306e-06, "epoch": 2.790981109079829, "percentage": 69.82, "elapsed_time": "1:02:49", "remaining_time": "0:27:09"}
+{"current_steps": 2300, "total_steps": 3280, "loss": 0.172, "learning_rate": 1.0823400692421938e-06, "epoch": 2.8031687995124925, "percentage": 70.12, "elapsed_time": "1:03:03", "remaining_time": "0:26:52"}
+{"current_steps": 2310, "total_steps": 3280, "loss": 0.1562, "learning_rate": 1.0620727920836906e-06, "epoch": 2.8153564899451555, "percentage": 70.43, "elapsed_time": "1:03:18", "remaining_time": "0:26:34"}
+{"current_steps": 2320, "total_steps": 3280, "loss": 0.1685, "learning_rate": 1.04194576586448e-06, "epoch": 2.8275441803778185, "percentage": 70.73, "elapsed_time": "1:03:32", "remaining_time": "0:26:17"}
+{"current_steps": 2330, "total_steps": 3280, "loss": 0.1762, "learning_rate": 1.0219609537119838e-06, "epoch": 2.8397318708104815, "percentage": 71.04, "elapsed_time": "1:03:49", "remaining_time": "0:26:01"}
+{"current_steps": 2340, "total_steps": 3280, "loss": 0.1601, "learning_rate": 1.0021203048825095e-06, "epoch": 2.8519195612431445, "percentage": 71.34, "elapsed_time": "1:04:04", "remaining_time": "0:25:44"}
+{"current_steps": 2350, "total_steps": 3280, "loss": 0.1451, "learning_rate": 9.824257545711172e-07, "epoch": 2.8641072516758075, "percentage": 71.65, "elapsed_time": "1:04:20", "remaining_time": "0:25:27"}
+{"current_steps": 2360, "total_steps": 3280, "loss": 0.1703, "learning_rate": 9.628792237228787e-07, "epoch": 2.8762949421084705, "percentage": 71.95, "elapsed_time": "1:04:35", "remaining_time": "0:25:10"}
+{"current_steps": 2370, "total_steps": 3280, "loss": 0.1607, "learning_rate": 9.434826188455056e-07, "epoch": 2.8884826325411335, "percentage": 72.26, "elapsed_time": "1:04:52", "remaining_time": "0:24:54"}
+{"current_steps": 2380, "total_steps": 3280, "loss": 0.1771, "learning_rate": 9.242378318233978e-07, "epoch": 2.9006703229737965, "percentage": 72.56, "elapsed_time": "1:05:09", "remaining_time": "0:24:38"}
+{"current_steps": 2390, "total_steps": 3280, "loss": 0.1738, "learning_rate": 9.051467397331148e-07, "epoch": 2.9128580134064594, "percentage": 72.87, "elapsed_time": "1:05:23", "remaining_time": "0:24:21"}
+{"current_steps": 2400, "total_steps": 3280, "loss": 0.167, "learning_rate": 8.862112046602917e-07, "epoch": 2.9250457038391224, "percentage": 73.17, "elapsed_time": "1:05:38", "remaining_time": "0:24:03"}
+{"current_steps": 2410, "total_steps": 3280, "loss": 0.1561, "learning_rate": 8.674330735180164e-07, "epoch": 2.9372333942717854, "percentage": 73.48, "elapsed_time": "1:05:53", "remaining_time": "0:23:47"}
+{"current_steps": 2420, "total_steps": 3280, "loss": 0.1586, "learning_rate": 8.488141778666878e-07, "epoch": 2.9494210847044484, "percentage": 73.78, "elapsed_time": "1:06:07", "remaining_time": "0:23:29"}
+{"current_steps": 2430, "total_steps": 3280, "loss": 0.1435, "learning_rate": 8.303563337353713e-07, "epoch": 2.9616087751371114, "percentage": 74.09, "elapsed_time": "1:06:23", "remaining_time": "0:23:13"}
+{"current_steps": 2440, "total_steps": 3280, "loss": 0.1395, "learning_rate": 8.120613414446707e-07, "epoch": 2.9737964655697744, "percentage": 74.39, "elapsed_time": "1:06:37", "remaining_time": "0:22:56"}
+{"current_steps": 2450, "total_steps": 3280, "loss": 0.1637, "learning_rate": 7.939309854311242e-07, "epoch": 2.9859841560024374, "percentage": 74.7, "elapsed_time": "1:06:51", "remaining_time": "0:22:38"}
+{"current_steps": 2460, "total_steps": 3280, "loss": 0.1819, "learning_rate": 7.759670340731662e-07, "epoch": 2.998171846435101, "percentage": 75.0, "elapsed_time": "1:07:05", "remaining_time": "0:22:21"}
+{"current_steps": 2470, "total_steps": 3280, "loss": 0.1143, "learning_rate": 7.581712395186341e-07, "epoch": 3.0103595368677634, "percentage": 75.3, "elapsed_time": "1:07:20", "remaining_time": "0:22:04"}
+{"current_steps": 2480, "total_steps": 3280, "loss": 0.1116, "learning_rate": 7.405453375138794e-07, "epoch": 3.0225472273004264, "percentage": 75.61, "elapsed_time": "1:07:36", "remaining_time": "0:21:48"}
+{"current_steps": 2490, "total_steps": 3280, "loss": 0.1226, "learning_rate": 7.230910472344601e-07, "epoch": 3.03473491773309, "percentage": 75.91, "elapsed_time": "1:07:52", "remaining_time": "0:21:31"}
+{"current_steps": 2500, "total_steps": 3280, "loss": 0.1304, "learning_rate": 7.058100711174637e-07, "epoch": 3.0469226081657528, "percentage": 76.22, "elapsed_time": "1:08:06", "remaining_time": "0:21:15"}
+{"current_steps": 2510, "total_steps": 3280, "loss": 0.1221, "learning_rate": 6.887040946954524e-07, "epoch": 3.0591102985984158, "percentage": 76.52, "elapsed_time": "1:09:13", "remaining_time": "0:21:14"}
+{"current_steps": 2520, "total_steps": 3280, "loss": 0.1154, "learning_rate": 6.717747864320648e-07, "epoch": 3.0712979890310788, "percentage": 76.83, "elapsed_time": "1:09:28", "remaining_time": "0:20:57"}
+{"current_steps": 2530, "total_steps": 3280, "loss": 0.1084, "learning_rate": 6.550237975592774e-07, "epoch": 3.0834856794637417, "percentage": 77.13, "elapsed_time": "1:09:41", "remaining_time": "0:20:39"}
+{"current_steps": 2540, "total_steps": 3280, "loss": 0.1272, "learning_rate": 6.384527619163486e-07, "epoch": 3.0956733698964047, "percentage": 77.44, "elapsed_time": "1:09:57", "remaining_time": "0:20:22"}
+{"current_steps": 2550, "total_steps": 3280, "loss": 0.1126, "learning_rate": 6.220632957904593e-07, "epoch": 3.1078610603290677, "percentage": 77.74, "elapsed_time": "1:10:13", "remaining_time": "0:20:06"}
+{"current_steps": 2560, "total_steps": 3280, "loss": 0.1334, "learning_rate": 6.058569977590683e-07, "epoch": 3.1200487507617307, "percentage": 78.05, "elapsed_time": "1:10:31", "remaining_time": "0:19:50"}
+{"current_steps": 2570, "total_steps": 3280, "loss": 0.098, "learning_rate": 5.898354485339839e-07, "epoch": 3.1322364411943937, "percentage": 78.35, "elapsed_time": "1:10:48", "remaining_time": "0:19:33"}
+{"current_steps": 2580, "total_steps": 3280, "loss": 0.1242, "learning_rate": 5.740002108071974e-07, "epoch": 3.1444241316270567, "percentage": 78.66, "elapsed_time": "1:11:04", "remaining_time": "0:19:16"}
+{"current_steps": 2590, "total_steps": 3280, "loss": 0.1071, "learning_rate": 5.583528290984516e-07, "epoch": 3.1566118220597197, "percentage": 78.96, "elapsed_time": "1:11:18", "remaining_time": "0:18:59"}
+{"current_steps": 2600, "total_steps": 3280, "loss": 0.114, "learning_rate": 5.42894829604603e-07, "epoch": 3.1687995124923827, "percentage": 79.27, "elapsed_time": "1:11:34", "remaining_time": "0:18:43"}
+{"current_steps": 2610, "total_steps": 3280, "loss": 0.1066, "learning_rate": 5.276277200507549e-07, "epoch": 3.1809872029250457, "percentage": 79.57, "elapsed_time": "1:11:50", "remaining_time": "0:18:26"}
+{"current_steps": 2620, "total_steps": 3280, "loss": 0.1237, "learning_rate": 5.125529895432008e-07, "epoch": 3.1931748933577087, "percentage": 79.88, "elapsed_time": "1:12:07", "remaining_time": "0:18:10"}
+{"current_steps": 2630, "total_steps": 3280, "loss": 0.1302, "learning_rate": 4.976721084241818e-07, "epoch": 3.2053625837903716, "percentage": 80.18, "elapsed_time": "1:12:21", "remaining_time": "0:17:53"}
+{"current_steps": 2640, "total_steps": 3280, "loss": 0.1101, "learning_rate": 4.829865281284734e-07, "epoch": 3.2175502742230346, "percentage": 80.49, "elapsed_time": "1:12:36", "remaining_time": "0:17:36"}
+{"current_steps": 2650, "total_steps": 3280, "loss": 0.1057, "learning_rate": 4.684976810418179e-07, "epoch": 3.2297379646556976, "percentage": 80.79, "elapsed_time": "1:12:49", "remaining_time": "0:17:18"}
+{"current_steps": 2660, "total_steps": 3280, "loss": 0.113, "learning_rate": 4.5420698036121285e-07, "epoch": 3.2419256550883606, "percentage": 81.1, "elapsed_time": "1:13:04", "remaining_time": "0:17:01"}
+{"current_steps": 2670, "total_steps": 3280, "loss": 0.1094, "learning_rate": 4.4011581995707267e-07, "epoch": 3.2541133455210236, "percentage": 81.4, "elapsed_time": "1:13:19", "remaining_time": "0:16:45"}
+{"current_steps": 2680, "total_steps": 3280, "loss": 0.1224, "learning_rate": 4.262255742372759e-07, "epoch": 3.2663010359536866, "percentage": 81.71, "elapsed_time": "1:13:34", "remaining_time": "0:16:28"}
+{"current_steps": 2690, "total_steps": 3280, "loss": 0.1038, "learning_rate": 4.1253759801310745e-07, "epoch": 3.2784887263863496, "percentage": 82.01, "elapsed_time": "1:13:50", "remaining_time": "0:16:11"}
+{"current_steps": 2700, "total_steps": 3280, "loss": 0.115, "learning_rate": 3.9905322636711654e-07, "epoch": 3.2906764168190126, "percentage": 82.32, "elapsed_time": "1:14:04", "remaining_time": "0:15:54"}
+{"current_steps": 2710, "total_steps": 3280, "loss": 0.1281, "learning_rate": 3.8577377452289787e-07, "epoch": 3.3028641072516756, "percentage": 82.62, "elapsed_time": "1:14:18", "remaining_time": "0:15:37"}
+{"current_steps": 2720, "total_steps": 3280, "loss": 0.1246, "learning_rate": 3.727005377168036e-07, "epoch": 3.315051797684339, "percentage": 82.93, "elapsed_time": "1:14:35", "remaining_time": "0:15:21"}
+{"current_steps": 2730, "total_steps": 3280, "loss": 0.1173, "learning_rate": 3.5983479107161793e-07, "epoch": 3.327239488117002, "percentage": 83.23, "elapsed_time": "1:14:49", "remaining_time": "0:15:04"}
+{"current_steps": 2740, "total_steps": 3280, "loss": 0.1051, "learning_rate": 3.471777894721767e-07, "epoch": 3.339427178549665, "percentage": 83.54, "elapsed_time": "1:15:02", "remaining_time": "0:14:47"}
+{"current_steps": 2750, "total_steps": 3280, "loss": 0.126, "learning_rate": 3.347307674429784e-07, "epoch": 3.351614868982328, "percentage": 83.84, "elapsed_time": "1:15:15", "remaining_time": "0:14:30"}
+{"current_steps": 2760, "total_steps": 3280, "loss": 0.0962, "learning_rate": 3.224949390277668e-07, "epoch": 3.363802559414991, "percentage": 84.15, "elapsed_time": "1:15:30", "remaining_time": "0:14:13"}
+{"current_steps": 2770, "total_steps": 3280, "loss": 0.096, "learning_rate": 3.1047149767111874e-07, "epoch": 3.375990249847654, "percentage": 84.45, "elapsed_time": "1:15:44", "remaining_time": "0:13:56"}
+{"current_steps": 2780, "total_steps": 3280, "loss": 0.0954, "learning_rate": 2.9866161610203866e-07, "epoch": 3.388177940280317, "percentage": 84.76, "elapsed_time": "1:15:59", "remaining_time": "0:13:39"}
+{"current_steps": 2790, "total_steps": 3280, "loss": 0.1221, "learning_rate": 2.8706644621957605e-07, "epoch": 3.40036563071298, "percentage": 85.06, "elapsed_time": "1:16:16", "remaining_time": "0:13:23"}
+{"current_steps": 2800, "total_steps": 3280, "loss": 0.1054, "learning_rate": 2.756871189804705e-07, "epoch": 3.412553321145643, "percentage": 85.37, "elapsed_time": "1:16:30", "remaining_time": "0:13:06"}
+{"current_steps": 2810, "total_steps": 3280, "loss": 0.1255, "learning_rate": 2.6452474428884294e-07, "epoch": 3.424741011578306, "percentage": 85.67, "elapsed_time": "1:16:45", "remaining_time": "0:12:50"}
+{"current_steps": 2820, "total_steps": 3280, "loss": 0.1157, "learning_rate": 2.5358041088793863e-07, "epoch": 3.436928702010969, "percentage": 85.98, "elapsed_time": "1:17:00", "remaining_time": "0:12:33"}
+{"current_steps": 2830, "total_steps": 3280, "loss": 0.1246, "learning_rate": 2.428551862539366e-07, "epoch": 3.449116392443632, "percentage": 86.28, "elapsed_time": "1:17:16", "remaining_time": "0:12:17"}
+{"current_steps": 2840, "total_steps": 3280, "loss": 0.0985, "learning_rate": 2.323501164918257e-07, "epoch": 3.461304082876295, "percentage": 86.59, "elapsed_time": "1:17:29", "remaining_time": "0:12:00"}
+{"current_steps": 2850, "total_steps": 3280, "loss": 0.1228, "learning_rate": 2.2206622623337864e-07, "epoch": 3.473491773308958, "percentage": 86.89, "elapsed_time": "1:17:44", "remaining_time": "0:11:43"}
+{"current_steps": 2860, "total_steps": 3280, "loss": 0.1148, "learning_rate": 2.1200451853720605e-07, "epoch": 3.485679463741621, "percentage": 87.2, "elapsed_time": "1:18:00", "remaining_time": "0:11:27"}
+{"current_steps": 2870, "total_steps": 3280, "loss": 0.1408, "learning_rate": 2.0216597479092437e-07, "epoch": 3.497867154174284, "percentage": 87.5, "elapsed_time": "1:18:15", "remaining_time": "0:11:10"}
+{"current_steps": 2880, "total_steps": 3280, "loss": 0.1124, "learning_rate": 1.9255155461543385e-07, "epoch": 3.510054844606947, "percentage": 87.8, "elapsed_time": "1:18:30", "remaining_time": "0:10:54"}
+{"current_steps": 2890, "total_steps": 3280, "loss": 0.1217, "learning_rate": 1.8316219577132033e-07, "epoch": 3.5222425350396103, "percentage": 88.11, "elapsed_time": "1:18:44", "remaining_time": "0:10:37"}
+{"current_steps": 2900, "total_steps": 3280, "loss": 0.1087, "learning_rate": 1.7399881406738762e-07, "epoch": 3.5344302254722733, "percentage": 88.41, "elapsed_time": "1:19:00", "remaining_time": "0:10:21"}
+{"current_steps": 2910, "total_steps": 3280, "loss": 0.1047, "learning_rate": 1.650623032713347e-07, "epoch": 3.5466179159049362, "percentage": 88.72, "elapsed_time": "1:19:14", "remaining_time": "0:10:04"}
+{"current_steps": 2920, "total_steps": 3280, "loss": 0.1356, "learning_rate": 1.5635353502257812e-07, "epoch": 3.5588056063375992, "percentage": 89.02, "elapsed_time": "1:19:28", "remaining_time": "0:09:47"}
+{"current_steps": 2930, "total_steps": 3280, "loss": 0.1148, "learning_rate": 1.4787335874723724e-07, "epoch": 3.5709932967702622, "percentage": 89.33, "elapsed_time": "1:19:41", "remaining_time": "0:09:31"}
+{"current_steps": 2940, "total_steps": 3280, "loss": 0.1197, "learning_rate": 1.3962260157528052e-07, "epoch": 3.583180987202925, "percentage": 89.63, "elapsed_time": "1:19:56", "remaining_time": "0:09:14"}
+{"current_steps": 2950, "total_steps": 3280, "loss": 0.1037, "learning_rate": 1.3160206825985457e-07, "epoch": 3.595368677635588, "percentage": 89.94, "elapsed_time": "1:20:07", "remaining_time": "0:08:57"}
+{"current_steps": 2960, "total_steps": 3280, "loss": 0.1106, "learning_rate": 1.2381254109878644e-07, "epoch": 3.607556368068251, "percentage": 90.24, "elapsed_time": "1:20:21", "remaining_time": "0:08:41"}
+{"current_steps": 2970, "total_steps": 3280, "loss": 0.1358, "learning_rate": 1.1625477985828276e-07, "epoch": 3.619744058500914, "percentage": 90.55, "elapsed_time": "1:20:37", "remaining_time": "0:08:24"}
+{"current_steps": 2980, "total_steps": 3280, "loss": 0.1119, "learning_rate": 1.089295216988262e-07, "epoch": 3.631931748933577, "percentage": 90.85, "elapsed_time": "1:20:51", "remaining_time": "0:08:08"}
+{"current_steps": 2990, "total_steps": 3280, "loss": 0.1245, "learning_rate": 1.0183748110327102e-07, "epoch": 3.64411943936624, "percentage": 91.16, "elapsed_time": "1:21:05", "remaining_time": "0:07:51"}
+{"current_steps": 3000, "total_steps": 3280, "loss": 0.1097, "learning_rate": 9.497934980715939e-08, "epoch": 3.656307129798903, "percentage": 91.46, "elapsed_time": "1:21:22", "remaining_time": "0:07:35"}
+{"current_steps": 3010, "total_steps": 3280, "loss": 0.1009, "learning_rate": 8.835579673124677e-08, "epoch": 3.668494820231566, "percentage": 91.77, "elapsed_time": "1:22:28", "remaining_time": "0:07:23"}
+{"current_steps": 3020, "total_steps": 3280, "loss": 0.1167, "learning_rate": 8.196746791626243e-08, "epoch": 3.680682510664229, "percentage": 92.07, "elapsed_time": "1:22:44", "remaining_time": "0:07:07"}
+{"current_steps": 3030, "total_steps": 3280, "loss": 0.1186, "learning_rate": 7.581498645989255e-08, "epoch": 3.692870201096892, "percentage": 92.38, "elapsed_time": "1:23:00", "remaining_time": "0:06:50"}
+{"current_steps": 3040, "total_steps": 3280, "loss": 0.1264, "learning_rate": 6.989895245600702e-08, "epoch": 3.705057891529555, "percentage": 92.68, "elapsed_time": "1:23:16", "remaining_time": "0:06:34"}
+{"current_steps": 3050, "total_steps": 3280, "loss": 0.1304, "learning_rate": 6.421994293612871e-08, "epoch": 3.717245581962218, "percentage": 92.99, "elapsed_time": "1:23:31", "remaining_time": "0:06:17"}
+{"current_steps": 3060, "total_steps": 3280, "loss": 0.1158, "learning_rate": 5.8778511813150365e-08, "epoch": 3.729433272394881, "percentage": 93.29, "elapsed_time": "1:23:45", "remaining_time": "0:06:01"}
+{"current_steps": 3070, "total_steps": 3280, "loss": 0.1045, "learning_rate": 5.357518982730792e-08, "epoch": 3.741620962827544, "percentage": 93.6, "elapsed_time": "1:23:59", "remaining_time": "0:05:44"}
+{"current_steps": 3080, "total_steps": 3280, "loss": 0.1203, "learning_rate": 4.861048449441491e-08, "epoch": 3.753808653260207, "percentage": 93.9, "elapsed_time": "1:24:15", "remaining_time": "0:05:28"}
+{"current_steps": 3090, "total_steps": 3280, "loss": 0.1174, "learning_rate": 4.3884880056359045e-08, "epoch": 3.76599634369287, "percentage": 94.21, "elapsed_time": "1:24:31", "remaining_time": "0:05:11"}
+{"current_steps": 3100, "total_steps": 3280, "loss": 0.103, "learning_rate": 3.939883743387302e-08, "epoch": 3.778184034125533, "percentage": 94.51, "elapsed_time": "1:24:45", "remaining_time": "0:04:55"}
+{"current_steps": 3110, "total_steps": 3280, "loss": 0.1146, "learning_rate": 3.515279418157463e-08, "epoch": 3.790371724558196, "percentage": 94.82, "elapsed_time": "1:25:00", "remaining_time": "0:04:38"}
+{"current_steps": 3120, "total_steps": 3280, "loss": 0.1162, "learning_rate": 3.1147164445292923e-08, "epoch": 3.802559414990859, "percentage": 95.12, "elapsed_time": "1:25:16", "remaining_time": "0:04:22"}
+{"current_steps": 3130, "total_steps": 3280, "loss": 0.1166, "learning_rate": 2.7382338921670693e-08, "epoch": 3.814747105423522, "percentage": 95.43, "elapsed_time": "1:25:29", "remaining_time": "0:04:05"}
+{"current_steps": 3140, "total_steps": 3280, "loss": 0.1123, "learning_rate": 2.3858684820058376e-08, "epoch": 3.826934795856185, "percentage": 95.73, "elapsed_time": "1:25:44", "remaining_time": "0:03:49"}
+{"current_steps": 3150, "total_steps": 3280, "loss": 0.1151, "learning_rate": 2.057654582669738e-08, "epoch": 3.839122486288848, "percentage": 96.04, "elapsed_time": "1:25:58", "remaining_time": "0:03:32"}
+{"current_steps": 3160, "total_steps": 3280, "loss": 0.112, "learning_rate": 1.753624207119775e-08, "epoch": 3.8513101767215114, "percentage": 96.34, "elapsed_time": "1:26:14", "remaining_time": "0:03:16"}
+{"current_steps": 3170, "total_steps": 3280, "loss": 0.1101, "learning_rate": 1.4738070095314527e-08, "epoch": 3.8634978671541744, "percentage": 96.65, "elapsed_time": "1:26:27", "remaining_time": "0:03:00"}
+{"current_steps": 3180, "total_steps": 3280, "loss": 0.1212, "learning_rate": 1.2182302824023107e-08, "epoch": 3.8756855575868374, "percentage": 96.95, "elapsed_time": "1:26:42", "remaining_time": "0:02:43"}
+{"current_steps": 3190, "total_steps": 3280, "loss": 0.1042, "learning_rate": 9.869189538899149e-09, "epoch": 3.8878732480195004, "percentage": 97.26, "elapsed_time": "1:26:56", "remaining_time": "0:02:27"}
+{"current_steps": 3200, "total_steps": 3280, "loss": 0.1231, "learning_rate": 7.798955853805245e-09, "epoch": 3.9000609384521634, "percentage": 97.56, "elapsed_time": "1:27:11", "remaining_time": "0:02:10"}
+{"current_steps": 3210, "total_steps": 3280, "loss": 0.1181, "learning_rate": 5.971803692883804e-09, "epoch": 3.9122486288848264, "percentage": 97.87, "elapsed_time": "1:27:26", "remaining_time": "0:01:54"}
+{"current_steps": 3220, "total_steps": 3280, "loss": 0.1309, "learning_rate": 4.387911270863632e-09, "epoch": 3.9244363193174894, "percentage": 98.17, "elapsed_time": "1:27:42", "remaining_time": "0:01:38"}
+{"current_steps": 3230, "total_steps": 3280, "loss": 0.1027, "learning_rate": 3.0474330756757874e-09, "epoch": 3.9366240097501524, "percentage": 98.48, "elapsed_time": "1:27:56", "remaining_time": "0:01:21"}
+{"current_steps": 3240, "total_steps": 3280, "loss": 0.1265, "learning_rate": 1.9504998533870223e-09, "epoch": 3.9488117001828154, "percentage": 98.78, "elapsed_time": "1:28:12", "remaining_time": "0:01:05"}
+{"current_steps": 3250, "total_steps": 3280, "loss": 0.1099, "learning_rate": 1.0972185954452596e-09, "epoch": 3.9609993906154783, "percentage": 99.09, "elapsed_time": "1:28:27", "remaining_time": "0:00:48"}
+{"current_steps": 3260, "total_steps": 3280, "loss": 0.1164, "learning_rate": 4.876725282457195e-10, "epoch": 3.9731870810481413, "percentage": 99.39, "elapsed_time": "1:28:41", "remaining_time": "0:00:32"}
+{"current_steps": 3270, "total_steps": 3280, "loss": 0.139, "learning_rate": 1.2192110501269005e-10, "epoch": 3.9853747714808043, "percentage": 99.7, "elapsed_time": "1:28:57", "remaining_time": "0:00:16"}
+{"current_steps": 3280, "total_steps": 3280, "loss": 0.1073, "learning_rate": 0.0, "epoch": 3.9975624619134673, "percentage": 100.0, "elapsed_time": "1:29:12", "remaining_time": "0:00:00"}
+{"current_steps": 3280, "total_steps": 3280, "epoch": 3.9975624619134673, "percentage": 100.0, "elapsed_time": "1:30:12", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2338 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.9975624619134673,
+  "eval_steps": 50000,
+  "global_step": 3280,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01218769043266301,
+      "grad_norm": 3.578172206878662,
+      "learning_rate": 5.05050505050505e-07,
+      "loss": 0.7319,
+      "step": 10
+    },
+    {
+      "epoch": 0.02437538086532602,
+      "grad_norm": 4.391892433166504,
+      "learning_rate": 1.01010101010101e-06,
+      "loss": 0.6746,
+      "step": 20
+    },
+    {
+      "epoch": 0.03656307129798903,
+      "grad_norm": 4.259323596954346,
+      "learning_rate": 1.5151515151515152e-06,
+      "loss": 0.722,
+      "step": 30
+    },
+    {
+      "epoch": 0.04875076173065204,
+      "grad_norm": 2.5641062259674072,
+      "learning_rate": 2.02020202020202e-06,
+      "loss": 0.6053,
+      "step": 40
+    },
+    {
+      "epoch": 0.06093845216331505,
+      "grad_norm": 2.138474225997925,
+      "learning_rate": 2.5252525252525258e-06,
+      "loss": 0.467,
+      "step": 50
+    },
+    {
+      "epoch": 0.07312614259597806,
+      "grad_norm": 3.2234861850738525,
+      "learning_rate": 3.0303030303030305e-06,
+      "loss": 0.4346,
+      "step": 60
+    },
+    {
+      "epoch": 0.08531383302864107,
+      "grad_norm": 1.6952118873596191,
+      "learning_rate": 3.5353535353535356e-06,
+      "loss": 0.4145,
+      "step": 70
+    },
+    {
+      "epoch": 0.09750152346130408,
+      "grad_norm": 1.6948118209838867,
+      "learning_rate": 4.04040404040404e-06,
+      "loss": 0.4062,
+      "step": 80
+    },
+    {
+      "epoch": 0.10968921389396709,
+      "grad_norm": 1.8601840734481812,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 0.3627,
+      "step": 90
+    },
+    {
+      "epoch": 0.1218769043266301,
+      "grad_norm": 1.8506708145141602,
+      "learning_rate": 4.99999878077914e-06,
+      "loss": 0.3336,
+      "step": 100
+    },
+    {
+      "epoch": 0.1340645947592931,
+      "grad_norm": 1.8687206506729126,
+      "learning_rate": 4.9998524757147466e-06,
+      "loss": 0.3489,
+      "step": 110
+    },
+    {
+      "epoch": 0.14625228519195613,
+      "grad_norm": 2.1408703327178955,
+      "learning_rate": 4.999462342829388e-06,
+      "loss": 0.3617,
+      "step": 120
+    },
+    {
+      "epoch": 0.15843997562461914,
+      "grad_norm": 1.6488077640533447,
+      "learning_rate": 4.9988284201754075e-06,
+      "loss": 0.3894,
+      "step": 130
+    },
+    {
+      "epoch": 0.17062766605728213,
+      "grad_norm": 1.5750221014022827,
+      "learning_rate": 4.99795076958365e-06,
+      "loss": 0.3448,
+      "step": 140
+    },
+    {
+      "epoch": 0.18281535648994515,
+      "grad_norm": 1.7642357349395752,
+      "learning_rate": 4.996829476657414e-06,
+      "loss": 0.3187,
+      "step": 150
+    },
+    {
+      "epoch": 0.19500304692260817,
+      "grad_norm": 1.404475212097168,
+      "learning_rate": 4.995464650764122e-06,
+      "loss": 0.3343,
+      "step": 160
+    },
+    {
+      "epoch": 0.2071907373552712,
+      "grad_norm": 1.5260435342788696,
+      "learning_rate": 4.993856425024637e-06,
+      "loss": 0.3143,
+      "step": 170
+    },
+    {
+      "epoch": 0.21937842778793418,
+      "grad_norm": 1.5985782146453857,
+      "learning_rate": 4.992004956300287e-06,
+      "loss": 0.3301,
+      "step": 180
+    },
+    {
+      "epoch": 0.2315661182205972,
+      "grad_norm": 1.6050117015838623,
+      "learning_rate": 4.989910425177561e-06,
+      "loss": 0.3501,
+      "step": 190
+    },
+    {
+      "epoch": 0.2437538086532602,
+      "grad_norm": 1.5097649097442627,
+      "learning_rate": 4.987573035950499e-06,
+      "loss": 0.283,
+      "step": 200
+    },
+    {
+      "epoch": 0.25594149908592323,
+      "grad_norm": 1.6257539987564087,
+      "learning_rate": 4.984993016600763e-06,
+      "loss": 0.3144,
+      "step": 210
+    },
+    {
+      "epoch": 0.2681291895185862,
+      "grad_norm": 1.656672477722168,
+      "learning_rate": 4.982170618775401e-06,
+      "loss": 0.3221,
+      "step": 220
+    },
+    {
+      "epoch": 0.28031687995124926,
+      "grad_norm": 1.3519649505615234,
+      "learning_rate": 4.979106117762303e-06,
+      "loss": 0.3244,
+      "step": 230
+    },
+    {
+      "epoch": 0.29250457038391225,
+      "grad_norm": 1.7282569408416748,
+      "learning_rate": 4.975799812463348e-06,
+      "loss": 0.3112,
+      "step": 240
+    },
+    {
+      "epoch": 0.30469226081657524,
+      "grad_norm": 1.7917057275772095,
+      "learning_rate": 4.972252025365251e-06,
+      "loss": 0.3321,
+      "step": 250
+    },
+    {
+      "epoch": 0.3168799512492383,
+      "grad_norm": 1.2842172384262085,
+      "learning_rate": 4.968463102508114e-06,
+      "loss": 0.3337,
+      "step": 260
+    },
+    {
+      "epoch": 0.3290676416819013,
+      "grad_norm": 1.4093726873397827,
+      "learning_rate": 4.9644334134516645e-06,
+      "loss": 0.3029,
+      "step": 270
+    },
+    {
+      "epoch": 0.34125533211456427,
+      "grad_norm": 1.5072354078292847,
+      "learning_rate": 4.960163351239216e-06,
+      "loss": 0.3411,
+      "step": 280
+    },
+    {
+      "epoch": 0.3534430225472273,
+      "grad_norm": 1.494828224182129,
+      "learning_rate": 4.955653332359331e-06,
+      "loss": 0.3192,
+      "step": 290
+    },
+    {
+      "epoch": 0.3656307129798903,
+      "grad_norm": 1.6439958810806274,
+      "learning_rate": 4.950903796705201e-06,
+      "loss": 0.3113,
+      "step": 300
+    },
+    {
+      "epoch": 0.3778184034125533,
+      "grad_norm": 1.5399495363235474,
+      "learning_rate": 4.94591520753173e-06,
+      "loss": 0.3191,
+      "step": 310
+    },
+    {
+      "epoch": 0.39000609384521634,
+      "grad_norm": 1.697625756263733,
+      "learning_rate": 4.940688051410364e-06,
+      "loss": 0.3092,
+      "step": 320
+    },
+    {
+      "epoch": 0.40219378427787933,
+      "grad_norm": 1.5218887329101562,
+      "learning_rate": 4.935222838181623e-06,
+      "loss": 0.3343,
+      "step": 330
+    },
+    {
+      "epoch": 0.4143814747105424,
+      "grad_norm": 1.6118853092193604,
+      "learning_rate": 4.929520100905375e-06,
+      "loss": 0.3115,
+      "step": 340
+    },
+    {
+      "epoch": 0.42656916514320536,
+      "grad_norm": 1.3823405504226685,
+      "learning_rate": 4.923580395808846e-06,
+      "loss": 0.2922,
+      "step": 350
+    },
+    {
+      "epoch": 0.43875685557586835,
+      "grad_norm": 1.289500117301941,
+      "learning_rate": 4.917404302232362e-06,
+      "loss": 0.3211,
+      "step": 360
+    },
+    {
+      "epoch": 0.4509445460085314,
+      "grad_norm": 1.5171111822128296,
+      "learning_rate": 4.910992422572845e-06,
+      "loss": 0.3205,
+      "step": 370
+    },
+    {
+      "epoch": 0.4631322364411944,
+      "grad_norm": 1.4650630950927734,
+      "learning_rate": 4.904345382225058e-06,
+      "loss": 0.331,
+      "step": 380
+    },
+    {
+      "epoch": 0.4753199268738574,
+      "grad_norm": 1.4301706552505493,
+      "learning_rate": 4.897463829520604e-06,
+      "loss": 0.3224,
+      "step": 390
+    },
+    {
+      "epoch": 0.4875076173065204,
+      "grad_norm": 1.3901742696762085,
+      "learning_rate": 4.890348435664694e-06,
+      "loss": 0.3054,
+      "step": 400
+    },
+    {
+      "epoch": 0.4996953077391834,
+      "grad_norm": 1.703951358795166,
+      "learning_rate": 4.882999894670669e-06,
+      "loss": 0.2973,
+      "step": 410
+    },
+    {
+      "epoch": 0.5118829981718465,
+      "grad_norm": 1.3318638801574707,
+      "learning_rate": 4.875418923292322e-06,
+      "loss": 0.295,
+      "step": 420
+    },
+    {
+      "epoch": 0.5240706886045094,
+      "grad_norm": 1.420301914215088,
+      "learning_rate": 4.867606260953979e-06,
+      "loss": 0.3027,
+      "step": 430
+    },
+    {
+      "epoch": 0.5362583790371724,
+      "grad_norm": 1.350051999092102,
+      "learning_rate": 4.85956266967838e-06,
+      "loss": 0.3007,
+      "step": 440
+    },
+    {
+      "epoch": 0.5484460694698354,
+      "grad_norm": 1.2033629417419434,
+      "learning_rate": 4.8512889340123535e-06,
+      "loss": 0.3168,
+      "step": 450
+    },
+    {
+      "epoch": 0.5606337599024985,
+      "grad_norm": 1.508357286453247,
+      "learning_rate": 4.842785860950296e-06,
+      "loss": 0.3137,
+      "step": 460
+    },
+    {
+      "epoch": 0.5728214503351615,
+      "grad_norm": 1.8802692890167236,
+      "learning_rate": 4.834054279855459e-06,
+      "loss": 0.3118,
+      "step": 470
+    },
+    {
+      "epoch": 0.5850091407678245,
+      "grad_norm": 1.3695592880249023,
+      "learning_rate": 4.825095042379054e-06,
+      "loss": 0.289,
+      "step": 480
+    },
+    {
+      "epoch": 0.5971968312004875,
+      "grad_norm": 1.6230717897415161,
+      "learning_rate": 4.815909022377189e-06,
+      "loss": 0.2937,
+      "step": 490
+    },
+    {
+      "epoch": 0.6093845216331505,
+      "grad_norm": 1.2749711275100708,
+      "learning_rate": 4.806497115825629e-06,
+      "loss": 0.3063,
+      "step": 500
+    },
+    {
+      "epoch": 0.6215722120658135,
+      "grad_norm": 1.3291198015213013,
+      "learning_rate": 4.796860240732414e-06,
+      "loss": 0.316,
+      "step": 510
+    },
+    {
+      "epoch": 0.6337599024984766,
+      "grad_norm": 1.5014513731002808,
+      "learning_rate": 4.786999337048311e-06,
+      "loss": 0.3127,
+      "step": 520
+    },
+    {
+      "epoch": 0.6459475929311396,
+      "grad_norm": 1.442225456237793,
+      "learning_rate": 4.77691536657514e-06,
+      "loss": 0.3057,
+      "step": 530
+    },
+    {
+      "epoch": 0.6581352833638026,
+      "grad_norm": 1.5001622438430786,
+      "learning_rate": 4.766609312871958e-06,
+      "loss": 0.3006,
+      "step": 540
+    },
+    {
+      "epoch": 0.6703229737964655,
+      "grad_norm": 1.5903184413909912,
+      "learning_rate": 4.756082181159131e-06,
+      "loss": 0.3131,
+      "step": 550
+    },
+    {
+      "epoch": 0.6825106642291285,
+      "grad_norm": 1.5622376203536987,
+      "learning_rate": 4.745334998220282e-06,
+      "loss": 0.3079,
+      "step": 560
+    },
+    {
+      "epoch": 0.6946983546617916,
+      "grad_norm": 1.5198042392730713,
+      "learning_rate": 4.734368812302148e-06,
+      "loss": 0.3257,
+      "step": 570
+    },
+    {
+      "epoch": 0.7068860450944546,
+      "grad_norm": 1.7607523202896118,
+      "learning_rate": 4.723184693012334e-06,
+      "loss": 0.2991,
+      "step": 580
+    },
+    {
+      "epoch": 0.7190737355271176,
+      "grad_norm": 1.416548252105713,
+      "learning_rate": 4.711783731214984e-06,
+      "loss": 0.3093,
+      "step": 590
+    },
+    {
+      "epoch": 0.7312614259597806,
+      "grad_norm": 1.419439435005188,
+      "learning_rate": 4.700167038924386e-06,
+      "loss": 0.2807,
+      "step": 600
+    },
+    {
+      "epoch": 0.7434491163924436,
+      "grad_norm": 1.4541571140289307,
+      "learning_rate": 4.688335749196511e-06,
+      "loss": 0.3026,
+      "step": 610
+    },
+    {
+      "epoch": 0.7556368068251066,
+      "grad_norm": 1.3236526250839233,
+      "learning_rate": 4.676291016018491e-06,
+      "loss": 0.2992,
+      "step": 620
+    },
+    {
+      "epoch": 0.7678244972577697,
+      "grad_norm": 1.555803656578064,
+      "learning_rate": 4.664034014196069e-06,
+      "loss": 0.3223,
+      "step": 630
+    },
+    {
+      "epoch": 0.7800121876904327,
+      "grad_norm": 1.5638824701309204,
+      "learning_rate": 4.651565939239011e-06,
+      "loss": 0.3069,
+      "step": 640
+    },
+    {
+      "epoch": 0.7921998781230957,
+      "grad_norm": 1.5447410345077515,
+      "learning_rate": 4.638888007244498e-06,
+      "loss": 0.3112,
+      "step": 650
+    },
+    {
+      "epoch": 0.8043875685557587,
+      "grad_norm": 1.562729835510254,
+      "learning_rate": 4.626001454778511e-06,
+      "loss": 0.2949,
+      "step": 660
+    },
+    {
+      "epoch": 0.8165752589884216,
+      "grad_norm": 1.2367265224456787,
+      "learning_rate": 4.612907538755224e-06,
+      "loss": 0.3128,
+      "step": 670
+    },
+    {
+      "epoch": 0.8287629494210847,
+      "grad_norm": 1.6397625207901,
+      "learning_rate": 4.599607536314406e-06,
+      "loss": 0.3115,
+      "step": 680
+    },
+    {
+      "epoch": 0.8409506398537477,
+      "grad_norm": 1.392140507698059,
+      "learning_rate": 4.586102744696851e-06,
+      "loss": 0.3189,
+      "step": 690
+    },
+    {
+      "epoch": 0.8531383302864107,
+      "grad_norm": 1.19057035446167,
+      "learning_rate": 4.572394481117855e-06,
+      "loss": 0.2756,
+      "step": 700
+    },
+    {
+      "epoch": 0.8653260207190737,
+      "grad_norm": 1.3636456727981567,
+      "learning_rate": 4.558484082638729e-06,
+      "loss": 0.3078,
+      "step": 710
+    },
+    {
+      "epoch": 0.8775137111517367,
+      "grad_norm": 1.2579822540283203,
+      "learning_rate": 4.544372906036399e-06,
+      "loss": 0.3017,
+      "step": 720
+    },
+    {
+      "epoch": 0.8897014015843998,
+      "grad_norm": 1.3275364637374878,
+      "learning_rate": 4.5300623276710604e-06,
+      "loss": 0.3277,
+      "step": 730
+    },
+    {
+      "epoch": 0.9018890920170628,
+      "grad_norm": 1.1951191425323486,
+      "learning_rate": 4.515553743351934e-06,
+      "loss": 0.2817,
+      "step": 740
+    },
+    {
+      "epoch": 0.9140767824497258,
+      "grad_norm": 1.5521240234375,
+      "learning_rate": 4.5008485682011265e-06,
+      "loss": 0.2845,
+      "step": 750
+    },
+    {
+      "epoch": 0.9262644728823888,
+      "grad_norm": 1.7351168394088745,
+      "learning_rate": 4.4859482365156e-06,
+      "loss": 0.3032,
+      "step": 760
+    },
+    {
+      "epoch": 0.9384521633150518,
+      "grad_norm": 1.2030630111694336,
+      "learning_rate": 4.470854201627278e-06,
+      "loss": 0.3154,
+      "step": 770
+    },
+    {
+      "epoch": 0.9506398537477148,
+      "grad_norm": 1.4315277338027954,
+      "learning_rate": 4.4555679357612925e-06,
+      "loss": 0.3276,
+      "step": 780
+    },
+    {
+      "epoch": 0.9628275441803779,
+      "grad_norm": 1.5054643154144287,
+      "learning_rate": 4.440090929892382e-06,
+      "loss": 0.2941,
+      "step": 790
+    },
+    {
+      "epoch": 0.9750152346130408,
+      "grad_norm": 1.1270413398742676,
+      "learning_rate": 4.424424693599474e-06,
+      "loss": 0.2795,
+      "step": 800
+    },
+    {
+      "epoch": 0.9872029250457038,
+      "grad_norm": 1.823027491569519,
+      "learning_rate": 4.4085707549184395e-06,
+      "loss": 0.2968,
+      "step": 810
+    },
+    {
+      "epoch": 0.9993906154783668,
+      "grad_norm": 1.2933018207550049,
+      "learning_rate": 4.392530660193058e-06,
+      "loss": 0.289,
+      "step": 820
+    },
+    {
+      "epoch": 1.01157830591103,
+      "grad_norm": 1.5592014789581299,
+      "learning_rate": 4.376305973924188e-06,
+      "loss": 0.2459,
+      "step": 830
+    },
+    {
+      "epoch": 1.023765996343693,
+      "grad_norm": 1.4350308179855347,
+      "learning_rate": 4.359898278617171e-06,
+      "loss": 0.2095,
+      "step": 840
+    },
+    {
+      "epoch": 1.035953686776356,
+      "grad_norm": 1.4992603063583374,
+      "learning_rate": 4.343309174627484e-06,
+      "loss": 0.2504,
+      "step": 850
+    },
+    {
+      "epoch": 1.048141377209019,
+      "grad_norm": 1.5574085712432861,
+      "learning_rate": 4.326540280004634e-06,
+      "loss": 0.2335,
+      "step": 860
+    },
+    {
+      "epoch": 1.0603290676416819,
+      "grad_norm": 1.4838849306106567,
+      "learning_rate": 4.309593230334355e-06,
+      "loss": 0.2312,
+      "step": 870
+    },
+    {
+      "epoch": 1.0725167580743449,
+      "grad_norm": 1.5157781839370728,
+      "learning_rate": 4.292469678579063e-06,
+      "loss": 0.2367,
+      "step": 880
+    },
+    {
+      "epoch": 1.0847044485070079,
+      "grad_norm": 1.3213136196136475,
+      "learning_rate": 4.275171294916641e-06,
+      "loss": 0.2445,
+      "step": 890
+    },
+    {
+      "epoch": 1.0968921389396709,
+      "grad_norm": 1.2431010007858276,
+      "learning_rate": 4.2576997665775275e-06,
+      "loss": 0.2329,
+      "step": 900
+    },
+    {
+      "epoch": 1.1090798293723338,
+      "grad_norm": 1.3120806217193604,
+      "learning_rate": 4.2400567976801575e-06,
+      "loss": 0.2174,
+      "step": 910
+    },
+    {
+      "epoch": 1.1212675198049968,
+      "grad_norm": 1.7084835767745972,
+      "learning_rate": 4.22224410906474e-06,
+      "loss": 0.2304,
+      "step": 920
+    },
+    {
+      "epoch": 1.13345521023766,
+      "grad_norm": 1.3486850261688232,
+      "learning_rate": 4.204263438125421e-06,
+      "loss": 0.2206,
+      "step": 930
+    },
+    {
+      "epoch": 1.145642900670323,
+      "grad_norm": 1.3106797933578491,
+      "learning_rate": 4.186116538640814e-06,
+      "loss": 0.2348,
+      "step": 940
+    },
+    {
+      "epoch": 1.157830591102986,
+      "grad_norm": 1.3655650615692139,
+      "learning_rate": 4.167805180602951e-06,
+      "loss": 0.2071,
+      "step": 950
+    },
+    {
+      "epoch": 1.170018281535649,
+      "grad_norm": 1.3001152276992798,
+      "learning_rate": 4.149331150044635e-06,
+      "loss": 0.2053,
+      "step": 960
+    },
+    {
+      "epoch": 1.182205971968312,
+      "grad_norm": 1.604116678237915,
+      "learning_rate": 4.130696248865244e-06,
+      "loss": 0.2068,
+      "step": 970
+    },
+    {
+      "epoch": 1.194393662400975,
+      "grad_norm": 1.3530467748641968,
+      "learning_rate": 4.111902294654971e-06,
+      "loss": 0.2468,
+      "step": 980
+    },
+    {
+      "epoch": 1.206581352833638,
+      "grad_norm": 1.5899338722229004,
+      "learning_rate": 4.09295112051755e-06,
+      "loss": 0.2254,
+      "step": 990
+    },
+    {
+      "epoch": 1.218769043266301,
+      "grad_norm": 1.774383306503296,
+      "learning_rate": 4.073844574891452e-06,
+      "loss": 0.2306,
+      "step": 1000
+    },
+    {
+      "epoch": 1.230956733698964,
+      "grad_norm": 1.1993497610092163,
+      "learning_rate": 4.054584521369603e-06,
+      "loss": 0.2294,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2431444241316272,
+      "grad_norm": 1.2832852602005005,
+      "learning_rate": 4.03517283851761e-06,
+      "loss": 0.2222,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2553321145642902,
+      "grad_norm": 1.370401382446289,
+      "learning_rate": 4.01561141969053e-06,
+      "loss": 0.2636,
+      "step": 1030
+    },
+    {
+      "epoch": 1.2675198049969532,
+      "grad_norm": 1.5473796129226685,
+      "learning_rate": 3.995902172848205e-06,
+      "loss": 0.2509,
+      "step": 1040
+    },
+    {
+      "epoch": 1.2797074954296161,
+      "grad_norm": 1.3431543111801147,
+      "learning_rate": 3.976047020369155e-06,
+      "loss": 0.2165,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2918951858622791,
+      "grad_norm": 1.580149531364441,
+      "learning_rate": 3.9560478988630866e-06,
+      "loss": 0.22,
+      "step": 1060
+    },
+    {
+      "epoch": 1.3040828762949421,
+      "grad_norm": 1.5631303787231445,
+      "learning_rate": 3.935906758981993e-06,
+      "loss": 0.2258,
+      "step": 1070
+    },
+    {
+      "epoch": 1.3162705667276051,
+      "grad_norm": 1.7426769733428955,
+      "learning_rate": 3.9156255652299005e-06,
+      "loss": 0.2378,
+      "step": 1080
+    },
+    {
+      "epoch": 1.328458257160268,
+      "grad_norm": 1.5809776782989502,
+      "learning_rate": 3.89520629577125e-06,
+      "loss": 0.2477,
+      "step": 1090
+    },
+    {
+      "epoch": 1.340645947592931,
+      "grad_norm": 1.4274479150772095,
+      "learning_rate": 3.8746509422379575e-06,
+      "loss": 0.2073,
+      "step": 1100
+    },
+    {
+      "epoch": 1.352833638025594,
+      "grad_norm": 1.4454461336135864,
+      "learning_rate": 3.853961509535159e-06,
+      "loss": 0.2199,
+      "step": 1110
+    },
+    {
+      "epoch": 1.365021328458257,
+      "grad_norm": 1.6029589176177979,
+      "learning_rate": 3.83314001564565e-06,
+      "loss": 0.2284,
+      "step": 1120
+    },
+    {
+      "epoch": 1.37720901889092,
+      "grad_norm": 1.6308578252792358,
+      "learning_rate": 3.8121884914330663e-06,
+      "loss": 0.2372,
+      "step": 1130
+    },
+    {
+      "epoch": 1.389396709323583,
+      "grad_norm": 1.8481136560440063,
+      "learning_rate": 3.791108980443794e-06,
+      "loss": 0.2565,
+      "step": 1140
+    },
+    {
+      "epoch": 1.4015843997562463,
+      "grad_norm": 1.325615644454956,
+      "learning_rate": 3.769903538707652e-06,
+      "loss": 0.2066,
+      "step": 1150
+    },
+    {
+      "epoch": 1.4137720901889093,
+      "grad_norm": 2.084979295730591,
+      "learning_rate": 3.7485742345373517e-06,
+      "loss": 0.2217,
+      "step": 1160
+    },
+    {
+      "epoch": 1.4259597806215722,
+      "grad_norm": 1.0964964628219604,
+      "learning_rate": 3.727123148326758e-06,
+      "loss": 0.2218,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4381474710542352,
+      "grad_norm": 1.4757567644119263,
+      "learning_rate": 3.705552372347981e-06,
+      "loss": 0.225,
+      "step": 1180
+    },
+    {
+      "epoch": 1.4503351614868982,
+      "grad_norm": 1.6368629932403564,
+      "learning_rate": 3.683864010547294e-06,
+      "loss": 0.2346,
+      "step": 1190
+    },
+    {
+      "epoch": 1.4625228519195612,
+      "grad_norm": 1.3107318878173828,
+      "learning_rate": 3.662060178339927e-06,
+      "loss": 0.2393,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4747105423522242,
+      "grad_norm": 1.5922001600265503,
+      "learning_rate": 3.6401430024037315e-06,
+      "loss": 0.2361,
+      "step": 1210
+    },
+    {
+      "epoch": 1.4868982327848872,
+      "grad_norm": 1.651711344718933,
+      "learning_rate": 3.618114620471756e-06,
+      "loss": 0.2198,
+      "step": 1220
+    },
+    {
+      "epoch": 1.4990859232175504,
+      "grad_norm": 1.4375849962234497,
+      "learning_rate": 3.5959771811237342e-06,
+      "loss": 0.2396,
+      "step": 1230
+    },
+    {
+      "epoch": 1.5112736136502134,
+      "grad_norm": 1.561681866645813,
+      "learning_rate": 3.573732843576519e-06,
+      "loss": 0.2308,
+      "step": 1240
+    },
+    {
+      "epoch": 1.5234613040828764,
+      "grad_norm": 1.8882336616516113,
+      "learning_rate": 3.5513837774734816e-06,
+      "loss": 0.2051,
+      "step": 1250
+    },
+    {
+      "epoch": 1.5356489945155394,
+      "grad_norm": 1.4128990173339844,
+      "learning_rate": 3.5289321626728912e-06,
+      "loss": 0.2526,
+      "step": 1260
+    },
+    {
+      "epoch": 1.5478366849482024,
+      "grad_norm": 1.9354671239852905,
+      "learning_rate": 3.5063801890352955e-06,
+      "loss": 0.2112,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5600243753808654,
+      "grad_norm": 1.6497639417648315,
+      "learning_rate": 3.4837300562099324e-06,
+      "loss": 0.2199,
+      "step": 1280
+    },
+    {
+      "epoch": 1.5722120658135283,
+      "grad_norm": 1.467066764831543,
+      "learning_rate": 3.4609839734201793e-06,
+      "loss": 0.249,
+      "step": 1290
+    },
+    {
+      "epoch": 1.5843997562461913,
+      "grad_norm": 1.3116928339004517,
+      "learning_rate": 3.4381441592480756e-06,
+      "loss": 0.2634,
+      "step": 1300
+    },
+    {
+      "epoch": 1.5965874466788543,
+      "grad_norm": 1.9211691617965698,
+      "learning_rate": 3.4152128414179263e-06,
+      "loss": 0.2243,
+      "step": 1310
+    },
+    {
+      "epoch": 1.6087751371115173,
+      "grad_norm": 1.396285057067871,
+      "learning_rate": 3.3921922565790188e-06,
+      "loss": 0.2478,
+      "step": 1320
+    },
+    {
+      "epoch": 1.6209628275441803,
+      "grad_norm": 1.3925182819366455,
+      "learning_rate": 3.3690846500874664e-06,
+      "loss": 0.2005,
+      "step": 1330
+    },
+    {
+      "epoch": 1.6331505179768433,
+      "grad_norm": 1.3843952417373657,
+      "learning_rate": 3.345892275787204e-06,
+      "loss": 0.2517,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6453382084095063,
+      "grad_norm": 1.3334903717041016,
+      "learning_rate": 3.3226173957901533e-06,
+      "loss": 0.2361,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6575258988421693,
+      "grad_norm": 1.5368155241012573,
+      "learning_rate": 3.2992622802555844e-06,
+      "loss": 0.2228,
+      "step": 1360
+    },
+    {
+      "epoch": 1.6697135892748323,
+      "grad_norm": 1.563447117805481,
+      "learning_rate": 3.2758292071686928e-06,
+      "loss": 0.2347,
+      "step": 1370
+    },
+    {
+      "epoch": 1.6819012797074955,
+      "grad_norm": 1.3434542417526245,
+      "learning_rate": 3.2523204621184094e-06,
+      "loss": 0.2326,
+      "step": 1380
+    },
+    {
+      "epoch": 1.6940889701401585,
+      "grad_norm": 1.6988780498504639,
+      "learning_rate": 3.2287383380744746e-06,
+      "loss": 0.2281,
+      "step": 1390
+    },
+    {
+      "epoch": 1.7062766605728215,
+      "grad_norm": 1.9776115417480469,
+      "learning_rate": 3.2050851351637853e-06,
+      "loss": 0.2109,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7184643510054844,
+      "grad_norm": 1.5286093950271606,
+      "learning_rate": 3.1813631604460504e-06,
+      "loss": 0.2387,
+      "step": 1410
+    },
+    {
+      "epoch": 1.7306520414381474,
+      "grad_norm": 1.8186579942703247,
+      "learning_rate": 3.1575747276887657e-06,
+      "loss": 0.2348,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7428397318708104,
+      "grad_norm": 1.8635733127593994,
+      "learning_rate": 3.1337221571415388e-06,
+      "loss": 0.2323,
+      "step": 1430
+    },
+    {
+      "epoch": 1.7550274223034736,
+      "grad_norm": 1.9394007921218872,
+      "learning_rate": 3.1098077753097763e-06,
+      "loss": 0.238,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7672151127361366,
+      "grad_norm": 1.6605966091156006,
+      "learning_rate": 3.085833914727765e-06,
+      "loss": 0.2223,
+      "step": 1450
+    },
+    {
+      "epoch": 1.7794028031687996,
+      "grad_norm": 1.7482880353927612,
+      "learning_rate": 3.0618029137311634e-06,
+      "loss": 0.2271,
+      "step": 1460
+    },
+    {
+      "epoch": 1.7915904936014626,
+      "grad_norm": 1.3232003450393677,
+      "learning_rate": 3.037717116228929e-06,
+      "loss": 0.2372,
+      "step": 1470
+    },
+    {
+      "epoch": 1.8037781840341256,
+      "grad_norm": 1.541633129119873,
+      "learning_rate": 3.013578871474699e-06,
+      "loss": 0.2397,
+      "step": 1480
+    },
+    {
+      "epoch": 1.8159658744667886,
+      "grad_norm": 1.5761010646820068,
+      "learning_rate": 2.9893905338376503e-06,
+      "loss": 0.2237,
+      "step": 1490
+    },
+    {
+      "epoch": 1.8281535648994516,
+      "grad_norm": 1.5969911813735962,
+      "learning_rate": 2.965154462572869e-06,
+      "loss": 0.2099,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8403412553321146,
+      "grad_norm": 1.5702909231185913,
+      "learning_rate": 2.9408730215912247e-06,
+      "loss": 0.2205,
+      "step": 1510
+    },
+    {
+      "epoch": 1.8525289457647776,
+      "grad_norm": 1.5175156593322754,
+      "learning_rate": 2.91654857922881e-06,
+      "loss": 0.2149,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8647166361974405,
+      "grad_norm": 1.2331769466400146,
+      "learning_rate": 2.892183508015939e-06,
+      "loss": 0.2309,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8769043266301035,
+      "grad_norm": 1.3271231651306152,
+      "learning_rate": 2.867780184445735e-06,
+      "loss": 0.2254,
+      "step": 1540
+    },
+    {
+      "epoch": 1.8890920170627665,
+      "grad_norm": 1.648229956626892,
+      "learning_rate": 2.8433409887423397e-06,
+      "loss": 0.2251,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9012797074954295,
+      "grad_norm": 1.3332548141479492,
+      "learning_rate": 2.8188683046287496e-06,
+      "loss": 0.2375,
+      "step": 1560
+    },
+    {
+      "epoch": 1.9134673979280925,
+      "grad_norm": 1.6312288045883179,
+      "learning_rate": 2.794364519094317e-06,
+      "loss": 0.2195,
+      "step": 1570
+    },
+    {
+      "epoch": 1.9256550883607555,
+      "grad_norm": 1.9400866031646729,
+      "learning_rate": 2.7698320221619278e-06,
+      "loss": 0.1939,
+      "step": 1580
+    },
+    {
+      "epoch": 1.9378427787934185,
+      "grad_norm": 1.6435078382492065,
+      "learning_rate": 2.7452732066548914e-06,
+      "loss": 0.2419,
+      "step": 1590
+    },
+    {
+      "epoch": 1.9500304692260817,
+      "grad_norm": 1.4376393556594849,
+      "learning_rate": 2.7206904679635465e-06,
+      "loss": 0.1974,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9622181596587447,
+      "grad_norm": 1.4124246835708618,
+      "learning_rate": 2.6960862038116265e-06,
+      "loss": 0.251,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9744058500914077,
+      "grad_norm": 1.6351146697998047,
+      "learning_rate": 2.6714628140223885e-06,
+      "loss": 0.2148,
+      "step": 1620
+    },
+    {
+      "epoch": 1.9865935405240707,
+      "grad_norm": 1.588615894317627,
+      "learning_rate": 2.6468227002845476e-06,
+      "loss": 0.2322,
+      "step": 1630
+    },
+    {
+      "epoch": 1.9987812309567337,
+      "grad_norm": 1.5556650161743164,
+      "learning_rate": 2.6221682659180186e-06,
+      "loss": 0.2059,
+      "step": 1640
+    },
+    {
+      "epoch": 2.010968921389397,
+      "grad_norm": 1.7614095211029053,
+      "learning_rate": 2.597501915639507e-06,
+      "loss": 0.1819,
+      "step": 1650
+    },
+    {
+      "epoch": 2.02315661182206,
+      "grad_norm": 1.7154064178466797,
+      "learning_rate": 2.5728260553279592e-06,
+      "loss": 0.1463,
+      "step": 1660
+    },
+    {
+      "epoch": 2.035344302254723,
+      "grad_norm": 1.9462904930114746,
+      "learning_rate": 2.5481430917899e-06,
+      "loss": 0.1563,
+      "step": 1670
+    },
+    {
+      "epoch": 2.047531992687386,
+      "grad_norm": 1.5392667055130005,
+      "learning_rate": 2.523455432524681e-06,
+      "loss": 0.1488,
+      "step": 1680
+    },
+    {
+      "epoch": 2.059719683120049,
+      "grad_norm": 1.2421252727508545,
+      "learning_rate": 2.4987654854896606e-06,
+      "loss": 0.1599,
+      "step": 1690
+    },
+    {
+      "epoch": 2.071907373552712,
+      "grad_norm": 1.9953041076660156,
+      "learning_rate": 2.4740756588653388e-06,
+      "loss": 0.1493,
+      "step": 1700
+    },
+    {
+      "epoch": 2.084095063985375,
+      "grad_norm": 1.3034099340438843,
+      "learning_rate": 2.4493883608204703e-06,
+      "loss": 0.161,
+      "step": 1710
+    },
+    {
+      "epoch": 2.096282754418038,
+      "grad_norm": 2.1974692344665527,
+      "learning_rate": 2.4247059992771836e-06,
+      "loss": 0.1705,
+      "step": 1720
+    },
+    {
+      "epoch": 2.108470444850701,
+      "grad_norm": 1.4389041662216187,
+      "learning_rate": 2.4000309816761105e-06,
+      "loss": 0.15,
+      "step": 1730
+    },
+    {
+      "epoch": 2.1206581352833638,
+      "grad_norm": 1.538169503211975,
+      "learning_rate": 2.375365714741584e-06,
+      "loss": 0.1556,
+      "step": 1740
+    },
+    {
+      "epoch": 2.1328458257160268,
+      "grad_norm": 1.5628312826156616,
+      "learning_rate": 2.3507126042468807e-06,
+      "loss": 0.1846,
+      "step": 1750
+    },
+    {
+      "epoch": 2.1450335161486898,
+      "grad_norm": 1.6945581436157227,
+      "learning_rate": 2.3260740547795818e-06,
+      "loss": 0.1691,
+      "step": 1760
+    },
+    {
+      "epoch": 2.1572212065813527,
+      "grad_norm": 1.927711009979248,
+      "learning_rate": 2.3014524695070277e-06,
+      "loss": 0.1617,
+      "step": 1770
+    },
+    {
+      "epoch": 2.1694088970140157,
+      "grad_norm": 2.3531131744384766,
+      "learning_rate": 2.276850249941927e-06,
+      "loss": 0.1547,
+      "step": 1780
+    },
+    {
+      "epoch": 2.1815965874466787,
+      "grad_norm": 1.3538850545883179,
+      "learning_rate": 2.2522697957081134e-06,
+      "loss": 0.149,
+      "step": 1790
+    },
+    {
+      "epoch": 2.1937842778793417,
+      "grad_norm": 1.6864837408065796,
+      "learning_rate": 2.2277135043065024e-06,
+      "loss": 0.1484,
+      "step": 1800
+    },
+    {
+      "epoch": 2.2059719683120047,
+      "grad_norm": 1.511353611946106,
+      "learning_rate": 2.203183770881239e-06,
+      "loss": 0.1681,
+      "step": 1810
+    },
+    {
+      "epoch": 2.2181596587446677,
+      "grad_norm": 1.9546992778778076,
+      "learning_rate": 2.178682987986088e-06,
+      "loss": 0.1605,
+      "step": 1820
+    },
+    {
+      "epoch": 2.2303473491773307,
+      "grad_norm": 1.924833059310913,
+      "learning_rate": 2.154213545351067e-06,
+      "loss": 0.1645,
+      "step": 1830
+    },
+    {
+      "epoch": 2.2425350396099937,
+      "grad_norm": 1.4835309982299805,
+      "learning_rate": 2.129777829649367e-06,
+      "loss": 0.1544,
+      "step": 1840
+    },
+    {
+      "epoch": 2.254722730042657,
+      "grad_norm": 2.8786847591400146,
+      "learning_rate": 2.1053782242645534e-06,
+      "loss": 0.1518,
+      "step": 1850
+    },
+    {
+      "epoch": 2.26691042047532,
+      "grad_norm": 1.7257006168365479,
+      "learning_rate": 2.081017109058108e-06,
+      "loss": 0.1896,
+      "step": 1860
+    },
+    {
+      "epoch": 2.279098110907983,
+      "grad_norm": 1.3914209604263306,
+      "learning_rate": 2.056696860137298e-06,
+      "loss": 0.1319,
+      "step": 1870
+    },
+    {
+      "epoch": 2.291285801340646,
+      "grad_norm": 1.4881747961044312,
+      "learning_rate": 2.0324198496234227e-06,
+      "loss": 0.1425,
+      "step": 1880
+    },
+    {
+      "epoch": 2.303473491773309,
+      "grad_norm": 1.2742137908935547,
+      "learning_rate": 2.0081884454204396e-06,
+      "loss": 0.1517,
+      "step": 1890
+    },
+    {
+      "epoch": 2.315661182205972,
+      "grad_norm": 2.283926486968994,
+      "learning_rate": 1.984005010984011e-06,
+      "loss": 0.146,
+      "step": 1900
+    },
+    {
+      "epoch": 2.327848872638635,
+      "grad_norm": 1.780540943145752,
+      "learning_rate": 1.9598719050909753e-06,
+      "loss": 0.1529,
+      "step": 1910
+    },
+    {
+      "epoch": 2.340036563071298,
+      "grad_norm": 1.6674730777740479,
+      "learning_rate": 1.935791481609283e-06,
+      "loss": 0.1791,
+      "step": 1920
+    },
+    {
+      "epoch": 2.352224253503961,
+      "grad_norm": 1.363561987876892,
+      "learning_rate": 1.9117660892684067e-06,
+      "loss": 0.1528,
+      "step": 1930
+    },
+    {
+      "epoch": 2.364411943936624,
+      "grad_norm": 1.843386173248291,
+      "learning_rate": 1.8877980714302532e-06,
+      "loss": 0.139,
+      "step": 1940
+    },
+    {
+      "epoch": 2.376599634369287,
+      "grad_norm": 2.3764960765838623,
+      "learning_rate": 1.8638897658605962e-06,
+      "loss": 0.1495,
+      "step": 1950
+    },
+    {
+      "epoch": 2.38878732480195,
+      "grad_norm": 1.8273096084594727,
+      "learning_rate": 1.840043504501065e-06,
+      "loss": 0.1412,
+      "step": 1960
+    },
+    {
+      "epoch": 2.400975015234613,
+      "grad_norm": 1.5394623279571533,
+      "learning_rate": 1.816261613241686e-06,
+      "loss": 0.1507,
+      "step": 1970
+    },
+    {
+      "epoch": 2.413162705667276,
+      "grad_norm": 1.75933837890625,
+      "learning_rate": 1.7925464116940299e-06,
+      "loss": 0.1725,
+      "step": 1980
+    },
+    {
+      "epoch": 2.425350396099939,
+      "grad_norm": 2.1179471015930176,
+      "learning_rate": 1.7689002129649584e-06,
+      "loss": 0.1605,
+      "step": 1990
+    },
+    {
+      "epoch": 2.437538086532602,
+      "grad_norm": 1.8330628871917725,
+      "learning_rate": 1.7453253234310164e-06,
+      "loss": 0.1599,
+      "step": 2000
+    },
+    {
+      "epoch": 2.449725776965265,
+      "grad_norm": 1.8222659826278687,
+      "learning_rate": 1.7218240425134669e-06,
+      "loss": 0.1312,
+      "step": 2010
+    },
+    {
+      "epoch": 2.461913467397928,
+      "grad_norm": 2.930623769760132,
+      "learning_rate": 1.6983986624540227e-06,
+      "loss": 0.1627,
+      "step": 2020
+    },
+    {
+      "epoch": 2.474101157830591,
+      "grad_norm": 2.1240384578704834,
+      "learning_rate": 1.6750514680912606e-06,
+      "loss": 0.1685,
+      "step": 2030
+    },
+    {
+      "epoch": 2.4862888482632544,
+      "grad_norm": 1.4878756999969482,
+      "learning_rate": 1.6517847366377693e-06,
+      "loss": 0.1704,
+      "step": 2040
+    },
+    {
+      "epoch": 2.4984765386959173,
+      "grad_norm": 1.8569579124450684,
+      "learning_rate": 1.628600737458037e-06,
+      "loss": 0.1598,
+      "step": 2050
+    },
+    {
+      "epoch": 2.5106642291285803,
+      "grad_norm": 1.5510886907577515,
+      "learning_rate": 1.605501731847101e-06,
+      "loss": 0.169,
+      "step": 2060
+    },
+    {
+      "epoch": 2.5228519195612433,
+      "grad_norm": 2.6488049030303955,
+      "learning_rate": 1.5824899728099934e-06,
+      "loss": 0.1509,
+      "step": 2070
+    },
+    {
+      "epoch": 2.5350396099939063,
+      "grad_norm": 2.071225166320801,
+      "learning_rate": 1.5595677048419855e-06,
+      "loss": 0.153,
+      "step": 2080
+    },
+    {
+      "epoch": 2.5472273004265693,
+      "grad_norm": 2.2100391387939453,
+      "learning_rate": 1.5367371637096705e-06,
+      "loss": 0.165,
+      "step": 2090
+    },
+    {
+      "epoch": 2.5594149908592323,
+      "grad_norm": 1.6370184421539307,
+      "learning_rate": 1.5140005762328892e-06,
+      "loss": 0.1773,
+      "step": 2100
+    },
+    {
+      "epoch": 2.5716026812918953,
+      "grad_norm": 1.585856318473816,
+      "learning_rate": 1.4913601600675387e-06,
+      "loss": 0.1439,
+      "step": 2110
+    },
+    {
+      "epoch": 2.5837903717245583,
+      "grad_norm": 1.8817006349563599,
+      "learning_rate": 1.468818123489263e-06,
+      "loss": 0.1378,
+      "step": 2120
+    },
+    {
+      "epoch": 2.5959780621572213,
+      "grad_norm": 1.554551124572754,
+      "learning_rate": 1.4463766651780698e-06,
+      "loss": 0.1614,
+      "step": 2130
+    },
+    {
+      "epoch": 2.6081657525898843,
+      "grad_norm": 2.056910753250122,
+      "learning_rate": 1.4240379740038758e-06,
+      "loss": 0.1639,
+      "step": 2140
+    },
+    {
+      "epoch": 2.6203534430225472,
+      "grad_norm": 1.518649935722351,
+      "learning_rate": 1.4018042288130101e-06,
+      "loss": 0.154,
+      "step": 2150
+    },
+    {
+      "epoch": 2.6325411334552102,
+      "grad_norm": 1.8066517114639282,
+      "learning_rate": 1.3796775982156984e-06,
+      "loss": 0.1558,
+      "step": 2160
+    },
+    {
+      "epoch": 2.6447288238878732,
+      "grad_norm": 1.8393446207046509,
+      "learning_rate": 1.3576602403745456e-06,
+      "loss": 0.1618,
+      "step": 2170
+    },
+    {
+      "epoch": 2.656916514320536,
+      "grad_norm": 1.4357062578201294,
+      "learning_rate": 1.3357543027940254e-06,
+      "loss": 0.1502,
+      "step": 2180
+    },
+    {
+      "epoch": 2.669104204753199,
+      "grad_norm": 1.953147053718567,
+      "learning_rate": 1.3139619221110348e-06,
+      "loss": 0.161,
+      "step": 2190
+    },
+    {
+      "epoch": 2.681291895185862,
+      "grad_norm": 1.988788366317749,
+      "learning_rate": 1.2922852238864767e-06,
+      "loss": 0.169,
+      "step": 2200
+    },
+    {
+      "epoch": 2.693479585618525,
+      "grad_norm": 1.5082643032073975,
+      "learning_rate": 1.2707263223979544e-06,
+      "loss": 0.1466,
+      "step": 2210
+    },
+    {
+      "epoch": 2.705667276051188,
+      "grad_norm": 1.587957501411438,
+      "learning_rate": 1.2492873204335415e-06,
+      "loss": 0.1594,
+      "step": 2220
+    },
+    {
+      "epoch": 2.717854966483851,
+      "grad_norm": 4.279134750366211,
+      "learning_rate": 1.227970309086685e-06,
+      "loss": 0.1431,
+      "step": 2230
+    },
+    {
+      "epoch": 2.730042656916514,
+      "grad_norm": 2.2551496028900146,
+      "learning_rate": 1.2067773675522487e-06,
+      "loss": 0.162,
+      "step": 2240
+    },
+    {
+      "epoch": 2.742230347349177,
+      "grad_norm": 1.6612194776535034,
+      "learning_rate": 1.1857105629237126e-06,
+      "loss": 0.1597,
+      "step": 2250
+    },
+    {
+      "epoch": 2.75441803778184,
+      "grad_norm": 1.6561633348464966,
+      "learning_rate": 1.164771949991556e-06,
+      "loss": 0.14,
+      "step": 2260
+    },
+    {
+      "epoch": 2.766605728214503,
+      "grad_norm": 2.2157464027404785,
+      "learning_rate": 1.1439635710428405e-06,
+      "loss": 0.1363,
+      "step": 2270
+    },
+    {
+      "epoch": 2.778793418647166,
+      "grad_norm": 1.709621548652649,
+      "learning_rate": 1.1232874556620086e-06,
+      "loss": 0.1849,
+      "step": 2280
+    },
+    {
+      "epoch": 2.790981109079829,
+      "grad_norm": 1.89210045337677,
+      "learning_rate": 1.1027456205329306e-06,
+      "loss": 0.1435,
+      "step": 2290
+    },
+    {
+      "epoch": 2.8031687995124925,
+      "grad_norm": 1.8157742023468018,
+      "learning_rate": 1.0823400692421938e-06,
+      "loss": 0.172,
+      "step": 2300
+    },
+    {
+      "epoch": 2.8153564899451555,
+      "grad_norm": 1.8622268438339233,
+      "learning_rate": 1.0620727920836906e-06,
+      "loss": 0.1562,
+      "step": 2310
+    },
+    {
+      "epoch": 2.8275441803778185,
+      "grad_norm": 1.6750710010528564,
+      "learning_rate": 1.04194576586448e-06,
+      "loss": 0.1685,
+      "step": 2320
+    },
+    {
+      "epoch": 2.8397318708104815,
+      "grad_norm": 1.5609955787658691,
+      "learning_rate": 1.0219609537119838e-06,
+      "loss": 0.1762,
+      "step": 2330
+    },
+    {
+      "epoch": 2.8519195612431445,
+      "grad_norm": 1.5106117725372314,
+      "learning_rate": 1.0021203048825095e-06,
+      "loss": 0.1601,
+      "step": 2340
+    },
+    {
+      "epoch": 2.8641072516758075,
+      "grad_norm": 1.2436853647232056,
+      "learning_rate": 9.824257545711172e-07,
+      "loss": 0.1451,
+      "step": 2350
+    },
+    {
+      "epoch": 2.8762949421084705,
+      "grad_norm": 2.1535840034484863,
+      "learning_rate": 9.628792237228787e-07,
+      "loss": 0.1703,
+      "step": 2360
+    },
+    {
+      "epoch": 2.8884826325411335,
+      "grad_norm": 1.6186459064483643,
+      "learning_rate": 9.434826188455056e-07,
+      "loss": 0.1607,
+      "step": 2370
+    },
+    {
+      "epoch": 2.9006703229737965,
+      "grad_norm": 2.03439998626709,
+      "learning_rate": 9.242378318233978e-07,
+      "loss": 0.1771,
+      "step": 2380
+    },
+    {
+      "epoch": 2.9128580134064594,
+      "grad_norm": 1.5456159114837646,
+      "learning_rate": 9.051467397331148e-07,
+      "loss": 0.1738,
+      "step": 2390
+    },
+    {
+      "epoch": 2.9250457038391224,
+      "grad_norm": 1.4887679815292358,
+      "learning_rate": 8.862112046602917e-07,
+      "loss": 0.167,
+      "step": 2400
+    },
+    {
+      "epoch": 2.9372333942717854,
+      "grad_norm": 2.0322256088256836,
+      "learning_rate": 8.674330735180164e-07,
+      "loss": 0.1561,
+      "step": 2410
+    },
+    {
+      "epoch": 2.9494210847044484,
+      "grad_norm": 1.4082711935043335,
+      "learning_rate": 8.488141778666878e-07,
+      "loss": 0.1586,
+      "step": 2420
+    },
+    {
+      "epoch": 2.9616087751371114,
+      "grad_norm": 1.7697067260742188,
+      "learning_rate": 8.303563337353713e-07,
+      "loss": 0.1435,
+      "step": 2430
+    },
+    {
+      "epoch": 2.9737964655697744,
+      "grad_norm": 1.3499540090560913,
+      "learning_rate": 8.120613414446707e-07,
+      "loss": 0.1395,
+      "step": 2440
+    },
+    {
+      "epoch": 2.9859841560024374,
+      "grad_norm": 1.8283402919769287,
+      "learning_rate": 7.939309854311242e-07,
+      "loss": 0.1637,
+      "step": 2450
+    },
+    {
+      "epoch": 2.998171846435101,
+      "grad_norm": 1.988641381263733,
+      "learning_rate": 7.759670340731662e-07,
+      "loss": 0.1819,
+      "step": 2460
+    },
+    {
+      "epoch": 3.0103595368677634,
+      "grad_norm": 1.3205652236938477,
+      "learning_rate": 7.581712395186341e-07,
+      "loss": 0.1143,
+      "step": 2470
+    },
+    {
+      "epoch": 3.0225472273004264,
+      "grad_norm": 1.1017987728118896,
+      "learning_rate": 7.405453375138794e-07,
+      "loss": 0.1116,
+      "step": 2480
+    },
+    {
+      "epoch": 3.03473491773309,
+      "grad_norm": 1.5111011266708374,
+      "learning_rate": 7.230910472344601e-07,
+      "loss": 0.1226,
+      "step": 2490
+    },
+    {
+      "epoch": 3.0469226081657528,
+      "grad_norm": 1.614180088043213,
+      "learning_rate": 7.058100711174637e-07,
+      "loss": 0.1304,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0591102985984158,
+      "grad_norm": 1.8207646608352661,
+      "learning_rate": 6.887040946954524e-07,
+      "loss": 0.1221,
+      "step": 2510
+    },
+    {
+      "epoch": 3.0712979890310788,
+      "grad_norm": 1.3963004350662231,
+      "learning_rate": 6.717747864320648e-07,
+      "loss": 0.1154,
+      "step": 2520
+    },
+    {
+      "epoch": 3.0834856794637417,
+      "grad_norm": 1.460038185119629,
+      "learning_rate": 6.550237975592774e-07,
+      "loss": 0.1084,
+      "step": 2530
+    },
+    {
+      "epoch": 3.0956733698964047,
+      "grad_norm": 1.6919264793395996,
+      "learning_rate": 6.384527619163486e-07,
+      "loss": 0.1272,
+      "step": 2540
+    },
+    {
+      "epoch": 3.1078610603290677,
+      "grad_norm": 1.711581826210022,
+      "learning_rate": 6.220632957904593e-07,
+      "loss": 0.1126,
+      "step": 2550
+    },
+    {
+      "epoch": 3.1200487507617307,
+      "grad_norm": 1.6653200387954712,
+      "learning_rate": 6.058569977590683e-07,
+      "loss": 0.1334,
+      "step": 2560
+    },
+    {
+      "epoch": 3.1322364411943937,
+      "grad_norm": 1.6422685384750366,
+      "learning_rate": 5.898354485339839e-07,
+      "loss": 0.098,
+      "step": 2570
+    },
+    {
+      "epoch": 3.1444241316270567,
+      "grad_norm": 1.5357776880264282,
+      "learning_rate": 5.740002108071974e-07,
+      "loss": 0.1242,
+      "step": 2580
+    },
+    {
+      "epoch": 3.1566118220597197,
+      "grad_norm": 1.4460564851760864,
+      "learning_rate": 5.583528290984516e-07,
+      "loss": 0.1071,
+      "step": 2590
+    },
+    {
+      "epoch": 3.1687995124923827,
+      "grad_norm": 1.7668797969818115,
+      "learning_rate": 5.42894829604603e-07,
+      "loss": 0.114,
+      "step": 2600
+    },
+    {
+      "epoch": 3.1809872029250457,
+      "grad_norm": 1.7189100980758667,
+      "learning_rate": 5.276277200507549e-07,
+      "loss": 0.1066,
+      "step": 2610
+    },
+    {
+      "epoch": 3.1931748933577087,
+      "grad_norm": 1.6018712520599365,
+      "learning_rate": 5.125529895432008e-07,
+      "loss": 0.1237,
+      "step": 2620
+    },
+    {
+      "epoch": 3.2053625837903716,
+      "grad_norm": 2.137363910675049,
+      "learning_rate": 4.976721084241818e-07,
+      "loss": 0.1302,
+      "step": 2630
+    },
+    {
+      "epoch": 3.2175502742230346,
+      "grad_norm": 1.3726582527160645,
+      "learning_rate": 4.829865281284734e-07,
+      "loss": 0.1101,
+      "step": 2640
+    },
+    {
+      "epoch": 3.2297379646556976,
+      "grad_norm": 2.303097724914551,
+      "learning_rate": 4.684976810418179e-07,
+      "loss": 0.1057,
+      "step": 2650
+    },
+    {
+      "epoch": 3.2419256550883606,
+      "grad_norm": 2.5125813484191895,
+      "learning_rate": 4.5420698036121285e-07,
+      "loss": 0.113,
+      "step": 2660
+    },
+    {
+      "epoch": 3.2541133455210236,
+      "grad_norm": 1.2105039358139038,
+      "learning_rate": 4.4011581995707267e-07,
+      "loss": 0.1094,
+      "step": 2670
+    },
+    {
+      "epoch": 3.2663010359536866,
+      "grad_norm": 1.7184550762176514,
+      "learning_rate": 4.262255742372759e-07,
+      "loss": 0.1224,
+      "step": 2680
+    },
+    {
+      "epoch": 3.2784887263863496,
+      "grad_norm": 1.8564852476119995,
+      "learning_rate": 4.1253759801310745e-07,
+      "loss": 0.1038,
+      "step": 2690
+    },
+    {
+      "epoch": 3.2906764168190126,
+      "grad_norm": 1.9307692050933838,
+      "learning_rate": 3.9905322636711654e-07,
+      "loss": 0.115,
+      "step": 2700
+    },
+    {
+      "epoch": 3.3028641072516756,
+      "grad_norm": 2.4194962978363037,
+      "learning_rate": 3.8577377452289787e-07,
+      "loss": 0.1281,
+      "step": 2710
+    },
+    {
+      "epoch": 3.315051797684339,
+      "grad_norm": 1.7740304470062256,
+      "learning_rate": 3.727005377168036e-07,
+      "loss": 0.1246,
+      "step": 2720
+    },
+    {
+      "epoch": 3.327239488117002,
+      "grad_norm": 1.6812636852264404,
+      "learning_rate": 3.5983479107161793e-07,
+      "loss": 0.1173,
+      "step": 2730
+    },
+    {
+      "epoch": 3.339427178549665,
+      "grad_norm": 5.8957037925720215,
+      "learning_rate": 3.471777894721767e-07,
+      "loss": 0.1051,
+      "step": 2740
+    },
+    {
+      "epoch": 3.351614868982328,
+      "grad_norm": 2.193671226501465,
+      "learning_rate": 3.347307674429784e-07,
+      "loss": 0.126,
+      "step": 2750
+    },
+    {
+      "epoch": 3.363802559414991,
+      "grad_norm": 1.9564625024795532,
+      "learning_rate": 3.224949390277668e-07,
+      "loss": 0.0962,
+      "step": 2760
+    },
+    {
+      "epoch": 3.375990249847654,
+      "grad_norm": 2.2077689170837402,
+      "learning_rate": 3.1047149767111874e-07,
+      "loss": 0.096,
+      "step": 2770
+    },
+    {
+      "epoch": 3.388177940280317,
+      "grad_norm": 1.5315691232681274,
+      "learning_rate": 2.9866161610203866e-07,
+      "loss": 0.0954,
+      "step": 2780
+    },
+    {
+      "epoch": 3.40036563071298,
+      "grad_norm": 1.900850534439087,
+      "learning_rate": 2.8706644621957605e-07,
+      "loss": 0.1221,
+      "step": 2790
+    },
+    {
+      "epoch": 3.412553321145643,
+      "grad_norm": 1.5665889978408813,
+      "learning_rate": 2.756871189804705e-07,
+      "loss": 0.1054,
+      "step": 2800
+    },
+    {
+      "epoch": 3.424741011578306,
+      "grad_norm": 1.9411475658416748,
+      "learning_rate": 2.6452474428884294e-07,
+      "loss": 0.1255,
+      "step": 2810
+    },
+    {
+      "epoch": 3.436928702010969,
+      "grad_norm": 1.8464025259017944,
+      "learning_rate": 2.5358041088793863e-07,
+      "loss": 0.1157,
+      "step": 2820
+    },
+    {
+      "epoch": 3.449116392443632,
+      "grad_norm": 2.363825559616089,
+      "learning_rate": 2.428551862539366e-07,
+      "loss": 0.1246,
+      "step": 2830
+    },
+    {
+      "epoch": 3.461304082876295,
+      "grad_norm": 1.678460955619812,
+      "learning_rate": 2.323501164918257e-07,
+      "loss": 0.0985,
+      "step": 2840
+    },
+    {
+      "epoch": 3.473491773308958,
+      "grad_norm": 1.818058967590332,
+      "learning_rate": 2.2206622623337864e-07,
+      "loss": 0.1228,
+      "step": 2850
+    },
+    {
+      "epoch": 3.485679463741621,
+      "grad_norm": 1.9547301530838013,
+      "learning_rate": 2.1200451853720605e-07,
+      "loss": 0.1148,
+      "step": 2860
+    },
+    {
+      "epoch": 3.497867154174284,
+      "grad_norm": 2.967578172683716,
+      "learning_rate": 2.0216597479092437e-07,
+      "loss": 0.1408,
+      "step": 2870
+    },
+    {
+      "epoch": 3.510054844606947,
+      "grad_norm": 2.1174635887145996,
+      "learning_rate": 1.9255155461543385e-07,
+      "loss": 0.1124,
+      "step": 2880
+    },
+    {
+      "epoch": 3.5222425350396103,
+      "grad_norm": 1.7792600393295288,
+      "learning_rate": 1.8316219577132033e-07,
+      "loss": 0.1217,
+      "step": 2890
+    },
+    {
+      "epoch": 3.5344302254722733,
+      "grad_norm": 1.700875163078308,
+      "learning_rate": 1.7399881406738762e-07,
+      "loss": 0.1087,
+      "step": 2900
+    },
+    {
+      "epoch": 3.5466179159049362,
+      "grad_norm": 1.9662463665008545,
+      "learning_rate": 1.650623032713347e-07,
+      "loss": 0.1047,
+      "step": 2910
+    },
+    {
+      "epoch": 3.5588056063375992,
+      "grad_norm": 1.718908429145813,
+      "learning_rate": 1.5635353502257812e-07,
+      "loss": 0.1356,
+      "step": 2920
+    },
+    {
+      "epoch": 3.5709932967702622,
+      "grad_norm": 1.5018715858459473,
+      "learning_rate": 1.4787335874723724e-07,
+      "loss": 0.1148,
+      "step": 2930
+    },
+    {
+      "epoch": 3.583180987202925,
+      "grad_norm": 1.5846534967422485,
+      "learning_rate": 1.3962260157528052e-07,
+      "loss": 0.1197,
+      "step": 2940
+    },
+    {
+      "epoch": 3.595368677635588,
+      "grad_norm": 1.947350025177002,
+      "learning_rate": 1.3160206825985457e-07,
+      "loss": 0.1037,
+      "step": 2950
+    },
+    {
+      "epoch": 3.607556368068251,
+      "grad_norm": 1.5652320384979248,
+      "learning_rate": 1.2381254109878644e-07,
+      "loss": 0.1106,
+      "step": 2960
+    },
+    {
+      "epoch": 3.619744058500914,
+      "grad_norm": 2.34379243850708,
+      "learning_rate": 1.1625477985828276e-07,
+      "loss": 0.1358,
+      "step": 2970
+    },
+    {
+      "epoch": 3.631931748933577,
+      "grad_norm": 2.6311395168304443,
+      "learning_rate": 1.089295216988262e-07,
+      "loss": 0.1119,
+      "step": 2980
+    },
+    {
+      "epoch": 3.64411943936624,
+      "grad_norm": 1.8833256959915161,
+      "learning_rate": 1.0183748110327102e-07,
+      "loss": 0.1245,
+      "step": 2990
+    },
+    {
+      "epoch": 3.656307129798903,
+      "grad_norm": 1.1179873943328857,
+      "learning_rate": 9.497934980715939e-08,
+      "loss": 0.1097,
+      "step": 3000
+    },
+    {
+      "epoch": 3.668494820231566,
+      "grad_norm": 2.062716484069824,
+      "learning_rate": 8.835579673124677e-08,
+      "loss": 0.1009,
+      "step": 3010
+    },
+    {
+      "epoch": 3.680682510664229,
+      "grad_norm": 1.951429843902588,
+      "learning_rate": 8.196746791626243e-08,
+      "loss": 0.1167,
+      "step": 3020
+    },
+    {
+      "epoch": 3.692870201096892,
+      "grad_norm": 1.7196236848831177,
+      "learning_rate": 7.581498645989255e-08,
+      "loss": 0.1186,
+      "step": 3030
+    },
+    {
+      "epoch": 3.705057891529555,
+      "grad_norm": 2.037466049194336,
+      "learning_rate": 6.989895245600702e-08,
+      "loss": 0.1264,
+      "step": 3040
+    },
+    {
+      "epoch": 3.717245581962218,
+      "grad_norm": 1.9185491800308228,
+      "learning_rate": 6.421994293612871e-08,
+      "loss": 0.1304,
+      "step": 3050
+    },
+    {
+      "epoch": 3.729433272394881,
+      "grad_norm": 1.453826904296875,
+      "learning_rate": 5.8778511813150365e-08,
+      "loss": 0.1158,
+      "step": 3060
+    },
+    {
+      "epoch": 3.741620962827544,
+      "grad_norm": 1.3658956289291382,
+      "learning_rate": 5.357518982730792e-08,
+      "loss": 0.1045,
+      "step": 3070
+    },
+    {
+      "epoch": 3.753808653260207,
+      "grad_norm": 1.7934198379516602,
+      "learning_rate": 4.861048449441491e-08,
+      "loss": 0.1203,
+      "step": 3080
+    },
+    {
+      "epoch": 3.76599634369287,
+      "grad_norm": 1.9196701049804688,
+      "learning_rate": 4.3884880056359045e-08,
+      "loss": 0.1174,
+      "step": 3090
+    },
+    {
+      "epoch": 3.778184034125533,
+      "grad_norm": 1.391270399093628,
+      "learning_rate": 3.939883743387302e-08,
+      "loss": 0.103,
+      "step": 3100
+    },
+    {
+      "epoch": 3.790371724558196,
+      "grad_norm": 1.528946876525879,
+      "learning_rate": 3.515279418157463e-08,
+      "loss": 0.1146,
+      "step": 3110
+    },
+    {
+      "epoch": 3.802559414990859,
+      "grad_norm": 1.5788449048995972,
+      "learning_rate": 3.1147164445292923e-08,
+      "loss": 0.1162,
+      "step": 3120
+    },
+    {
+      "epoch": 3.814747105423522,
+      "grad_norm": 2.370635747909546,
+      "learning_rate": 2.7382338921670693e-08,
+      "loss": 0.1166,
+      "step": 3130
+    },
+    {
+      "epoch": 3.826934795856185,
+      "grad_norm": 1.730526328086853,
+      "learning_rate": 2.3858684820058376e-08,
+      "loss": 0.1123,
+      "step": 3140
+    },
+    {
+      "epoch": 3.839122486288848,
+      "grad_norm": 1.4985235929489136,
+      "learning_rate": 2.057654582669738e-08,
+      "loss": 0.1151,
+      "step": 3150
+    },
+    {
+      "epoch": 3.8513101767215114,
+      "grad_norm": 1.7269705533981323,
+      "learning_rate": 1.753624207119775e-08,
+      "loss": 0.112,
+      "step": 3160
+    },
+    {
+      "epoch": 3.8634978671541744,
+      "grad_norm": 2.0060977935791016,
+      "learning_rate": 1.4738070095314527e-08,
+      "loss": 0.1101,
+      "step": 3170
+    },
+    {
+      "epoch": 3.8756855575868374,
+      "grad_norm": 2.1134166717529297,
+      "learning_rate": 1.2182302824023107e-08,
+      "loss": 0.1212,
+      "step": 3180
+    },
+    {
+      "epoch": 3.8878732480195004,
+      "grad_norm": 1.5718306303024292,
+      "learning_rate": 9.869189538899149e-09,
+      "loss": 0.1042,
+      "step": 3190
+    },
+    {
+      "epoch": 3.9000609384521634,
+      "grad_norm": 1.7236390113830566,
+      "learning_rate": 7.798955853805245e-09,
+      "loss": 0.1231,
+      "step": 3200
+    },
+    {
+      "epoch": 3.9122486288848264,
+      "grad_norm": 2.0345866680145264,
+      "learning_rate": 5.971803692883804e-09,
+      "loss": 0.1181,
+      "step": 3210
+    },
+    {
+      "epoch": 3.9244363193174894,
+      "grad_norm": 1.8747888803482056,
+      "learning_rate": 4.387911270863632e-09,
+      "loss": 0.1309,
+      "step": 3220
+    },
+    {
+      "epoch": 3.9366240097501524,
+      "grad_norm": 2.027182102203369,
+      "learning_rate": 3.0474330756757874e-09,
+      "loss": 0.1027,
+      "step": 3230
+    },
+    {
+      "epoch": 3.9488117001828154,
+      "grad_norm": 1.62562096118927,
+      "learning_rate": 1.9504998533870223e-09,
+      "loss": 0.1265,
+      "step": 3240
+    },
+    {
+      "epoch": 3.9609993906154783,
+      "grad_norm": 2.0606415271759033,
+      "learning_rate": 1.0972185954452596e-09,
+      "loss": 0.1099,
+      "step": 3250
+    },
+    {
+      "epoch": 3.9731870810481413,
+      "grad_norm": 1.293489933013916,
+      "learning_rate": 4.876725282457195e-10,
+      "loss": 0.1164,
+      "step": 3260
+    },
+    {
+      "epoch": 3.9853747714808043,
+      "grad_norm": 1.6779310703277588,
+      "learning_rate": 1.2192110501269005e-10,
+      "loss": 0.139,
+      "step": 3270
+    },
+    {
+      "epoch": 3.9975624619134673,
+      "grad_norm": 2.0987327098846436,
+      "learning_rate": 0.0,
+      "loss": 0.1073,
+      "step": 3280
+    },
+    {
+      "epoch": 3.9975624619134673,
+      "step": 3280,
+      "total_flos": 3.38221904554623e+17,
+      "train_loss": 0.21007875238613385,
+      "train_runtime": 5418.5603,
+      "train_samples_per_second": 9.688,
+      "train_steps_per_second": 0.605
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3280,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.38221904554623e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dade4871e2101a640babfb7155b7f96d0f2eafc02855dfbbd9f2969d5c53445
+size 5432