upload

README.md

@@ -0,0 +1,59 @@
+---
+license: other
+base_model: google/gemma-2b
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: final_trained
+  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. -->
+
+# final_trained
+
+This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the samvaad-hi-v1 dataset.
+
+## 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-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.39.0.dev0
+- Pytorch 2.0.1+cu118
+- Datasets 2.16.1
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.5383612829627413,
+    "train_runtime": 4681.1872,
+    "train_samples_per_second": 21.666,
+    "train_steps_per_second": 0.338
+}

checkpoint-1000/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "google/gemma-2b",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": false,
+  "vocab_size": 256000
+}

checkpoint-1000/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.39.0.dev0"
+}

checkpoint-1000/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0368dc4194ee2fdbe49909e4846ccc81d0b9fb3d1a1fd9c9d3b26a72c7895653
+size 4911635192

checkpoint-1000/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f92fd384fe15130d9e13c2dc3394517b4fd642d7af96d5e734699919ff39a365
+size 4978830584

checkpoint-1000/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:585b62412105f82990495f02d7c75c28b5e3c5777ce25a5021ffb17ee4c151e5
+size 134242760

checkpoint-1000/model.safetensors.index.json

@@ -0,0 +1,171 @@
+{
+  "metadata": {
+    "total_size": 10024689664
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7015da0998d2376a75ff258403df7cc2e7ccd73d5263d78ab3e8265f255037cc
+size 20049522541

checkpoint-1000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eafe3d5e0585dde8c5033613de99a5d4f23df4284a488f4007b3944580c0b97
+size 17655

checkpoint-1000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e34eb456d2d003a2839f2daa9425e99bdd79ed7e24a1de9fc7d5738476bfb4b
+size 17655

checkpoint-1000/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b374af4a2765d8771cee7a72921d3c2e438b9bee34f0b2d098ce6071afeb65e4
+size 17655

checkpoint-1000/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5df75d8477fcc69c7abb03025313915ebfe3ac18c54a7c57aaa455c0099e13e5
+size 17655

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20cd9ebcbc893aaeed7a3e32a2a0eeb344f999c91a3ede9cd26c28f6dd8957bb
+size 627

checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1000/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,51 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,721 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6310143555765894,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.7190074920654297,
+      "learning_rate": 4.9995083170283816e-05,
+      "loss": 2.9245,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.431870222091675,
+      "learning_rate": 4.998033461515242e-05,
+      "loss": 2.0053,
+      "step": 20
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.3315682411193848,
+      "learning_rate": 4.9955760135896534e-05,
+      "loss": 1.888,
+      "step": 30
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 3.2937276363372803,
+      "learning_rate": 4.992136939879856e-05,
+      "loss": 1.8447,
+      "step": 40
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.7375714778900146,
+      "learning_rate": 4.9877175931330346e-05,
+      "loss": 1.8212,
+      "step": 50
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.15061092376709,
+      "learning_rate": 4.982319711683221e-05,
+      "loss": 1.793,
+      "step": 60
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.0427424907684326,
+      "learning_rate": 4.975945418767529e-05,
+      "loss": 1.756,
+      "step": 70
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.107785224914551,
+      "learning_rate": 4.968597221690986e-05,
+      "loss": 1.7285,
+      "step": 80
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.100552558898926,
+      "learning_rate": 4.96027801084029e-05,
+      "loss": 1.7297,
+      "step": 90
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.2227377891540527,
+      "learning_rate": 4.950991058546893e-05,
+      "loss": 1.7602,
+      "step": 100
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.535144567489624,
+      "learning_rate": 4.940740017799833e-05,
+      "loss": 1.7433,
+      "step": 110
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.6522979736328125,
+      "learning_rate": 4.929528920808854e-05,
+      "loss": 1.7363,
+      "step": 120
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.8091869354248047,
+      "learning_rate": 4.917362177418342e-05,
+      "loss": 1.6872,
+      "step": 130
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.1017510890960693,
+      "learning_rate": 4.904244573372733e-05,
+      "loss": 1.7084,
+      "step": 140
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.6424258947372437,
+      "learning_rate": 4.8901812684340564e-05,
+      "loss": 1.6997,
+      "step": 150
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.4547488689422607,
+      "learning_rate": 4.8751777943523634e-05,
+      "loss": 1.6747,
+      "step": 160
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.6251146793365479,
+      "learning_rate": 4.8592400526898314e-05,
+      "loss": 1.6836,
+      "step": 170
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.098386526107788,
+      "learning_rate": 4.842374312499405e-05,
+      "loss": 1.6552,
+      "step": 180
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.2387640476226807,
+      "learning_rate": 4.824587207858888e-05,
+      "loss": 1.6489,
+      "step": 190
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.7299611568450928,
+      "learning_rate": 4.805885735261454e-05,
+      "loss": 1.6576,
+      "step": 200
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.5701665878295898,
+      "learning_rate": 4.786277250863599e-05,
+      "loss": 1.6533,
+      "step": 210
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.417296886444092,
+      "learning_rate": 4.765769467591625e-05,
+      "loss": 1.6356,
+      "step": 220
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.2636029720306396,
+      "learning_rate": 4.744370452107789e-05,
+      "loss": 1.6389,
+      "step": 230
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.576324224472046,
+      "learning_rate": 4.722088621637309e-05,
+      "loss": 1.6546,
+      "step": 240
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.9720542430877686,
+      "learning_rate": 4.698932740657479e-05,
+      "loss": 1.6354,
+      "step": 250
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.5250279903411865,
+      "learning_rate": 4.6749119174501975e-05,
+      "loss": 1.6342,
+      "step": 260
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 2.4737966060638428,
+      "learning_rate": 4.6500356005192514e-05,
+      "loss": 1.6407,
+      "step": 270
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.2792372703552246,
+      "learning_rate": 4.6243135748737864e-05,
+      "loss": 1.6339,
+      "step": 280
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.5593037605285645,
+      "learning_rate": 4.597755958179406e-05,
+      "loss": 1.6095,
+      "step": 290
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.3141404390335083,
+      "learning_rate": 4.570373196778427e-05,
+      "loss": 1.6036,
+      "step": 300
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.2617065906524658,
+      "learning_rate": 4.5421760615808474e-05,
+      "loss": 1.6244,
+      "step": 310
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.64117431640625,
+      "learning_rate": 4.513175643827647e-05,
+      "loss": 1.6449,
+      "step": 320
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.7132749557495117,
+      "learning_rate": 4.4833833507280884e-05,
+      "loss": 1.5948,
+      "step": 330
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 2.1323654651641846,
+      "learning_rate": 4.4528109009727336e-05,
+      "loss": 1.627,
+      "step": 340
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.253115653991699,
+      "learning_rate": 4.42147032012394e-05,
+      "loss": 1.6151,
+      "step": 350
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.6143097877502441,
+      "learning_rate": 4.389373935885646e-05,
+      "loss": 1.5838,
+      "step": 360
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.3353707790374756,
+      "learning_rate": 4.356534373254316e-05,
+      "loss": 1.5935,
+      "step": 370
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.283742904663086,
+      "learning_rate": 4.322964549552943e-05,
+      "loss": 1.6015,
+      "step": 380
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.437249779701233,
+      "learning_rate": 4.288677669350066e-05,
+      "loss": 1.577,
+      "step": 390
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.5190638303756714,
+      "learning_rate": 4.2536872192658036e-05,
+      "loss": 1.5843,
+      "step": 400
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.1320886611938477,
+      "learning_rate": 4.218006962666934e-05,
+      "loss": 1.6145,
+      "step": 410
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.0696591138839722,
+      "learning_rate": 4.181650934253132e-05,
+      "loss": 1.5601,
+      "step": 420
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.3149545192718506,
+      "learning_rate": 4.144633434536467e-05,
+      "loss": 1.5664,
+      "step": 430
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.3661577701568604,
+      "learning_rate": 4.1069690242163484e-05,
+      "loss": 1.6002,
+      "step": 440
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.6984481811523438,
+      "learning_rate": 4.06867251845213e-05,
+      "loss": 1.576,
+      "step": 450
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.2728784084320068,
+      "learning_rate": 4.0297589810356165e-05,
+      "loss": 1.5448,
+      "step": 460
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.4147616624832153,
+      "learning_rate": 3.9902437184657784e-05,
+      "loss": 1.5595,
+      "step": 470
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.2289011478424072,
+      "learning_rate": 3.9501422739279956e-05,
+      "loss": 1.5628,
+      "step": 480
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.5690233707427979,
+      "learning_rate": 3.909470421180201e-05,
+      "loss": 1.5731,
+      "step": 490
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.4935098886489868,
+      "learning_rate": 3.8682441583483314e-05,
+      "loss": 1.545,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.2939772605895996,
+      "learning_rate": 3.8264797016335205e-05,
+      "loss": 1.5793,
+      "step": 510
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.2150651216506958,
+      "learning_rate": 3.7841934789335164e-05,
+      "loss": 1.5378,
+      "step": 520
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.2153139114379883,
+      "learning_rate": 3.741402123380828e-05,
+      "loss": 1.5345,
+      "step": 530
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.290591835975647,
+      "learning_rate": 3.6981224668001424e-05,
+      "loss": 1.5517,
+      "step": 540
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.1924967765808105,
+      "learning_rate": 3.654371533087586e-05,
+      "loss": 1.5472,
+      "step": 550
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.6345056295394897,
+      "learning_rate": 3.610166531514436e-05,
+      "loss": 1.5564,
+      "step": 560
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.185119867324829,
+      "learning_rate": 3.565524849957921e-05,
+      "loss": 1.5574,
+      "step": 570
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.3646321296691895,
+      "learning_rate": 3.520464048061758e-05,
+      "loss": 1.5584,
+      "step": 580
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.2333228588104248,
+      "learning_rate": 3.47500185032913e-05,
+      "loss": 1.518,
+      "step": 590
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.3945318460464478,
+      "learning_rate": 3.4291561391508185e-05,
+      "loss": 1.5339,
+      "step": 600
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.304306149482727,
+      "learning_rate": 3.3829449477712324e-05,
+      "loss": 1.5339,
+      "step": 610
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.6393932104110718,
+      "learning_rate": 3.336386453195088e-05,
+      "loss": 1.5399,
+      "step": 620
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.2000635862350464,
+      "learning_rate": 3.2894989690375626e-05,
+      "loss": 1.5233,
+      "step": 630
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.1479601860046387,
+      "learning_rate": 3.2423009383206876e-05,
+      "loss": 1.538,
+      "step": 640
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.1483389139175415,
+      "learning_rate": 3.194810926218861e-05,
+      "loss": 1.528,
+      "step": 650
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.2403253316879272,
+      "learning_rate": 3.147047612756302e-05,
+      "loss": 1.5307,
+      "step": 660
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.3997712135314941,
+      "learning_rate": 3.099029785459328e-05,
+      "loss": 1.4915,
+      "step": 670
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.2010352611541748,
+      "learning_rate": 3.0507763319663517e-05,
+      "loss": 1.5268,
+      "step": 680
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.0670932531356812,
+      "learning_rate": 3.002306232598497e-05,
+      "loss": 1.5273,
+      "step": 690
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.2283655405044556,
+      "learning_rate": 2.9536385528937567e-05,
+      "loss": 1.5273,
+      "step": 700
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.1306476593017578,
+      "learning_rate": 2.9047924361076345e-05,
+      "loss": 1.5072,
+      "step": 710
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.1699943542480469,
+      "learning_rate": 2.8557870956832132e-05,
+      "loss": 1.4856,
+      "step": 720
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.2550854682922363,
+      "learning_rate": 2.8066418076936167e-05,
+      "loss": 1.4983,
+      "step": 730
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.0610970258712769,
+      "learning_rate": 2.7573759032598366e-05,
+      "loss": 1.5518,
+      "step": 740
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.1754754781723022,
+      "learning_rate": 2.7080087609469062e-05,
+      "loss": 1.4998,
+      "step": 750
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.1955766677856445,
+      "learning_rate": 2.6585597991414114e-05,
+      "loss": 1.5109,
+      "step": 760
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.0891656875610352,
+      "learning_rate": 2.6090484684133404e-05,
+      "loss": 1.5007,
+      "step": 770
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.0880335569381714,
+      "learning_rate": 2.5594942438652688e-05,
+      "loss": 1.5049,
+      "step": 780
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.345954418182373,
+      "learning_rate": 2.509916617471903e-05,
+      "loss": 1.5154,
+      "step": 790
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.1668224334716797,
+      "learning_rate": 2.46033509041298e-05,
+      "loss": 1.4883,
+      "step": 800
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.055127501487732,
+      "learning_rate": 2.410769165402549e-05,
+      "loss": 1.5053,
+      "step": 810
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.0528500080108643,
+      "learning_rate": 2.3612383390176503e-05,
+      "loss": 1.4871,
+      "step": 820
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.328258991241455,
+      "learning_rate": 2.3117620940294048e-05,
+      "loss": 1.5037,
+      "step": 830
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.0326772928237915,
+      "learning_rate": 2.2623598917395438e-05,
+      "loss": 1.4525,
+      "step": 840
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.057058811187744,
+      "learning_rate": 2.213051164325366e-05,
+      "loss": 1.4898,
+      "step": 850
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.1190940141677856,
+      "learning_rate": 2.1638553071961708e-05,
+      "loss": 1.488,
+      "step": 860
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.1501041650772095,
+      "learning_rate": 2.1147916713641367e-05,
+      "loss": 1.4711,
+      "step": 870
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.090022325515747,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 1.488,
+      "step": 880
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.0642565488815308,
+      "learning_rate": 2.017138200005236e-05,
+      "loss": 1.4791,
+      "step": 890
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.3562296628952026,
+      "learning_rate": 1.9685867761175584e-05,
+      "loss": 1.4956,
+      "step": 900
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.2069261074066162,
+      "learning_rate": 1.9202443816963425e-05,
+      "loss": 1.4918,
+      "step": 910
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.3227437734603882,
+      "learning_rate": 1.872130032047302e-05,
+      "loss": 1.4577,
+      "step": 920
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.0784181356430054,
+      "learning_rate": 1.824262652775568e-05,
+      "loss": 1.4888,
+      "step": 930
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.000135898590088,
+      "learning_rate": 1.7766610723413684e-05,
+      "loss": 1.4673,
+      "step": 940
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.136026382446289,
+      "learning_rate": 1.7293440146539196e-05,
+      "loss": 1.4779,
+      "step": 950
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.123252272605896,
+      "learning_rate": 1.682330091706446e-05,
+      "loss": 1.4583,
+      "step": 960
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.0559343099594116,
+      "learning_rate": 1.6356377962552238e-05,
+      "loss": 1.4471,
+      "step": 970
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.0266658067703247,
+      "learning_rate": 1.589285494545514e-05,
+      "loss": 1.4632,
+      "step": 980
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.1371444463729858,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 1.4732,
+      "step": 990
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.1203784942626953,
+      "learning_rate": 1.4976736614834664e-05,
+      "loss": 1.452,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1584,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "total_flos": 7.003073868034212e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5f270ab83bb6b8b6198abab8938484e33528253ff0e05545853f6357e16e105
+size 4603

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "google/gemma-2b",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": false,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.39.0.dev0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5828c23c231714f0c3a5adfbeaa34e33ca63a3fa9b43cec046bb63f6105b8070
+size 4911635192

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c18d66a22c4354915b02d45a604f4985c6dee807860bf3a62648f1d90989741
+size 4978830584

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24ea177b26459a76af2bc31a814a448e76fa4b497980a84cf3a9e333378a07c0
+size 134242760

model.safetensors.index.json

@@ -0,0 +1,171 @@
+{
+  "metadata": {
+    "total_size": 10024689664
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

runs/Feb22_05-59-21_e8792c30e3aa/events.out.tfevents.1708582264.e8792c30e3aa.257.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8179b2643fcee37e93feebb21bf0d7dfa8569a8cca50d5cf3a4eaeb9a81016e2
+size 38398

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,51 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.5383612829627413,
+    "train_runtime": 4681.1872,
+    "train_samples_per_second": 21.666,
+    "train_steps_per_second": 0.338
+}

trainer_log.jsonl

@@ -0,0 +1,159 @@
+{"current_steps": 10, "total_steps": 1584, "loss": 2.9245, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9995083170283816e-05, "epoch": 0.01, "percentage": 0.63, "elapsed_time": "0:00:31", "remaining_time": "1:22:22"}
+{"current_steps": 20, "total_steps": 1584, "loss": 2.0053, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.998033461515242e-05, "epoch": 0.01, "percentage": 1.26, "elapsed_time": "0:01:00", "remaining_time": "1:18:25"}
+{"current_steps": 30, "total_steps": 1584, "loss": 1.888, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9955760135896534e-05, "epoch": 0.02, "percentage": 1.89, "elapsed_time": "0:01:29", "remaining_time": "1:16:52"}
+{"current_steps": 40, "total_steps": 1584, "loss": 1.8447, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.992136939879856e-05, "epoch": 0.03, "percentage": 2.53, "elapsed_time": "0:01:58", "remaining_time": "1:16:07"}
+{"current_steps": 50, "total_steps": 1584, "loss": 1.8212, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9877175931330346e-05, "epoch": 0.03, "percentage": 3.16, "elapsed_time": "0:02:28", "remaining_time": "1:15:43"}
+{"current_steps": 60, "total_steps": 1584, "loss": 1.793, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.982319711683221e-05, "epoch": 0.04, "percentage": 3.79, "elapsed_time": "0:02:57", "remaining_time": "1:15:10"}
+{"current_steps": 70, "total_steps": 1584, "loss": 1.756, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.975945418767529e-05, "epoch": 0.04, "percentage": 4.42, "elapsed_time": "0:03:27", "remaining_time": "1:14:37"}
+{"current_steps": 80, "total_steps": 1584, "loss": 1.7285, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.968597221690986e-05, "epoch": 0.05, "percentage": 5.05, "elapsed_time": "0:03:56", "remaining_time": "1:14:01"}
+{"current_steps": 90, "total_steps": 1584, "loss": 1.7297, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.96027801084029e-05, "epoch": 0.06, "percentage": 5.68, "elapsed_time": "0:04:25", "remaining_time": "1:13:25"}
+{"current_steps": 100, "total_steps": 1584, "loss": 1.7602, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.950991058546893e-05, "epoch": 0.06, "percentage": 6.31, "elapsed_time": "0:04:55", "remaining_time": "1:12:57"}
+{"current_steps": 110, "total_steps": 1584, "loss": 1.7433, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.940740017799833e-05, "epoch": 0.07, "percentage": 6.94, "elapsed_time": "0:05:24", "remaining_time": "1:12:26"}
+{"current_steps": 120, "total_steps": 1584, "loss": 1.7363, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.929528920808854e-05, "epoch": 0.08, "percentage": 7.58, "elapsed_time": "0:05:53", "remaining_time": "1:11:54"}
+{"current_steps": 130, "total_steps": 1584, "loss": 1.6872, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.917362177418342e-05, "epoch": 0.08, "percentage": 8.21, "elapsed_time": "0:06:22", "remaining_time": "1:11:21"}
+{"current_steps": 140, "total_steps": 1584, "loss": 1.7084, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.904244573372733e-05, "epoch": 0.09, "percentage": 8.84, "elapsed_time": "0:06:52", "remaining_time": "1:10:53"}
+{"current_steps": 150, "total_steps": 1584, "loss": 1.6997, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8901812684340564e-05, "epoch": 0.09, "percentage": 9.47, "elapsed_time": "0:07:21", "remaining_time": "1:10:22"}
+{"current_steps": 160, "total_steps": 1584, "loss": 1.6747, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8751777943523634e-05, "epoch": 0.1, "percentage": 10.1, "elapsed_time": "0:07:50", "remaining_time": "1:09:50"}
+{"current_steps": 170, "total_steps": 1584, "loss": 1.6836, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8592400526898314e-05, "epoch": 0.11, "percentage": 10.73, "elapsed_time": "0:08:20", "remaining_time": "1:09:22"}
+{"current_steps": 180, "total_steps": 1584, "loss": 1.6552, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.842374312499405e-05, "epoch": 0.11, "percentage": 11.36, "elapsed_time": "0:08:49", "remaining_time": "1:08:51"}
+{"current_steps": 190, "total_steps": 1584, "loss": 1.6489, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.824587207858888e-05, "epoch": 0.12, "percentage": 11.99, "elapsed_time": "0:09:18", "remaining_time": "1:08:20"}
+{"current_steps": 200, "total_steps": 1584, "loss": 1.6576, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.805885735261454e-05, "epoch": 0.13, "percentage": 12.63, "elapsed_time": "0:09:48", "remaining_time": "1:07:51"}
+{"current_steps": 210, "total_steps": 1584, "loss": 1.6533, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.786277250863599e-05, "epoch": 0.13, "percentage": 13.26, "elapsed_time": "0:10:17", "remaining_time": "1:07:21"}
+{"current_steps": 220, "total_steps": 1584, "loss": 1.6356, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.765769467591625e-05, "epoch": 0.14, "percentage": 13.89, "elapsed_time": "0:10:46", "remaining_time": "1:06:50"}
+{"current_steps": 230, "total_steps": 1584, "loss": 1.6389, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.744370452107789e-05, "epoch": 0.15, "percentage": 14.52, "elapsed_time": "0:11:16", "remaining_time": "1:06:20"}
+{"current_steps": 240, "total_steps": 1584, "loss": 1.6546, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.722088621637309e-05, "epoch": 0.15, "percentage": 15.15, "elapsed_time": "0:11:45", "remaining_time": "1:05:50"}
+{"current_steps": 250, "total_steps": 1584, "loss": 1.6354, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.698932740657479e-05, "epoch": 0.16, "percentage": 15.78, "elapsed_time": "0:12:14", "remaining_time": "1:05:20"}
+{"current_steps": 260, "total_steps": 1584, "loss": 1.6342, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6749119174501975e-05, "epoch": 0.16, "percentage": 16.41, "elapsed_time": "0:12:43", "remaining_time": "1:04:49"}
+{"current_steps": 270, "total_steps": 1584, "loss": 1.6407, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6500356005192514e-05, "epoch": 0.17, "percentage": 17.05, "elapsed_time": "0:13:13", "remaining_time": "1:04:19"}
+{"current_steps": 280, "total_steps": 1584, "loss": 1.6339, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6243135748737864e-05, "epoch": 0.18, "percentage": 17.68, "elapsed_time": "0:13:42", "remaining_time": "1:03:50"}
+{"current_steps": 290, "total_steps": 1584, "loss": 1.6095, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.597755958179406e-05, "epoch": 0.18, "percentage": 18.31, "elapsed_time": "0:14:11", "remaining_time": "1:03:19"}
+{"current_steps": 300, "total_steps": 1584, "loss": 1.6036, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.570373196778427e-05, "epoch": 0.19, "percentage": 18.94, "elapsed_time": "0:14:40", "remaining_time": "1:02:48"}
+{"current_steps": 310, "total_steps": 1584, "loss": 1.6244, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5421760615808474e-05, "epoch": 0.2, "percentage": 19.57, "elapsed_time": "0:15:09", "remaining_time": "1:02:17"}
+{"current_steps": 320, "total_steps": 1584, "loss": 1.6449, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.513175643827647e-05, "epoch": 0.2, "percentage": 20.2, "elapsed_time": "0:15:38", "remaining_time": "1:01:47"}
+{"current_steps": 330, "total_steps": 1584, "loss": 1.5948, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.4833833507280884e-05, "epoch": 0.21, "percentage": 20.83, "elapsed_time": "0:16:07", "remaining_time": "1:01:18"}
+{"current_steps": 340, "total_steps": 1584, "loss": 1.627, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.4528109009727336e-05, "epoch": 0.21, "percentage": 21.46, "elapsed_time": "0:16:37", "remaining_time": "1:00:48"}
+{"current_steps": 350, "total_steps": 1584, "loss": 1.6151, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.42147032012394e-05, "epoch": 0.22, "percentage": 22.1, "elapsed_time": "0:17:06", "remaining_time": "1:00:20"}
+{"current_steps": 360, "total_steps": 1584, "loss": 1.5838, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.389373935885646e-05, "epoch": 0.23, "percentage": 22.73, "elapsed_time": "0:17:36", "remaining_time": "0:59:51"}
+{"current_steps": 370, "total_steps": 1584, "loss": 1.5935, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.356534373254316e-05, "epoch": 0.23, "percentage": 23.36, "elapsed_time": "0:18:05", "remaining_time": "0:59:20"}
+{"current_steps": 380, "total_steps": 1584, "loss": 1.6015, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.322964549552943e-05, "epoch": 0.24, "percentage": 23.99, "elapsed_time": "0:18:34", "remaining_time": "0:58:52"}
+{"current_steps": 390, "total_steps": 1584, "loss": 1.577, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.288677669350066e-05, "epoch": 0.25, "percentage": 24.62, "elapsed_time": "0:19:04", "remaining_time": "0:58:22"}
+{"current_steps": 400, "total_steps": 1584, "loss": 1.5843, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.2536872192658036e-05, "epoch": 0.25, "percentage": 25.25, "elapsed_time": "0:19:33", "remaining_time": "0:57:53"}
+{"current_steps": 410, "total_steps": 1584, "loss": 1.6145, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.218006962666934e-05, "epoch": 0.26, "percentage": 25.88, "elapsed_time": "0:20:02", "remaining_time": "0:57:23"}
+{"current_steps": 420, "total_steps": 1584, "loss": 1.5601, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.181650934253132e-05, "epoch": 0.27, "percentage": 26.52, "elapsed_time": "0:20:32", "remaining_time": "0:56:54"}
+{"current_steps": 430, "total_steps": 1584, "loss": 1.5664, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.144633434536467e-05, "epoch": 0.27, "percentage": 27.15, "elapsed_time": "0:21:00", "remaining_time": "0:56:24"}
+{"current_steps": 440, "total_steps": 1584, "loss": 1.6002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.1069690242163484e-05, "epoch": 0.28, "percentage": 27.78, "elapsed_time": "0:21:30", "remaining_time": "0:55:54"}
+{"current_steps": 450, "total_steps": 1584, "loss": 1.576, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.06867251845213e-05, "epoch": 0.28, "percentage": 28.41, "elapsed_time": "0:21:59", "remaining_time": "0:55:24"}
+{"current_steps": 460, "total_steps": 1584, "loss": 1.5448, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.0297589810356165e-05, "epoch": 0.29, "percentage": 29.04, "elapsed_time": "0:22:28", "remaining_time": "0:54:55"}
+{"current_steps": 470, "total_steps": 1584, "loss": 1.5595, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.9902437184657784e-05, "epoch": 0.3, "percentage": 29.67, "elapsed_time": "0:22:58", "remaining_time": "0:54:26"}
+{"current_steps": 480, "total_steps": 1584, "loss": 1.5628, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.9501422739279956e-05, "epoch": 0.3, "percentage": 30.3, "elapsed_time": "0:23:27", "remaining_time": "0:53:57"}
+{"current_steps": 490, "total_steps": 1584, "loss": 1.5731, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.909470421180201e-05, "epoch": 0.31, "percentage": 30.93, "elapsed_time": "0:23:57", "remaining_time": "0:53:28"}
+{"current_steps": 500, "total_steps": 1584, "loss": 1.545, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.8682441583483314e-05, "epoch": 0.32, "percentage": 31.57, "elapsed_time": "0:24:26", "remaining_time": "0:52:59"}
+{"current_steps": 510, "total_steps": 1584, "loss": 1.5793, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.8264797016335205e-05, "epoch": 0.32, "percentage": 32.2, "elapsed_time": "0:24:55", "remaining_time": "0:52:30"}
+{"current_steps": 520, "total_steps": 1584, "loss": 1.5378, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.7841934789335164e-05, "epoch": 0.33, "percentage": 32.83, "elapsed_time": "0:25:25", "remaining_time": "0:52:01"}
+{"current_steps": 530, "total_steps": 1584, "loss": 1.5345, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.741402123380828e-05, "epoch": 0.33, "percentage": 33.46, "elapsed_time": "0:25:54", "remaining_time": "0:51:31"}
+{"current_steps": 540, "total_steps": 1584, "loss": 1.5517, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6981224668001424e-05, "epoch": 0.34, "percentage": 34.09, "elapsed_time": "0:26:23", "remaining_time": "0:51:02"}
+{"current_steps": 550, "total_steps": 1584, "loss": 1.5472, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.654371533087586e-05, "epoch": 0.35, "percentage": 34.72, "elapsed_time": "0:26:53", "remaining_time": "0:50:33"}
+{"current_steps": 560, "total_steps": 1584, "loss": 1.5564, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.610166531514436e-05, "epoch": 0.35, "percentage": 35.35, "elapsed_time": "0:27:22", "remaining_time": "0:50:03"}
+{"current_steps": 570, "total_steps": 1584, "loss": 1.5574, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.565524849957921e-05, "epoch": 0.36, "percentage": 35.98, "elapsed_time": "0:27:51", "remaining_time": "0:49:33"}
+{"current_steps": 580, "total_steps": 1584, "loss": 1.5584, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.520464048061758e-05, "epoch": 0.37, "percentage": 36.62, "elapsed_time": "0:28:20", "remaining_time": "0:49:03"}
+{"current_steps": 590, "total_steps": 1584, "loss": 1.518, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.47500185032913e-05, "epoch": 0.37, "percentage": 37.25, "elapsed_time": "0:28:50", "remaining_time": "0:48:35"}
+{"current_steps": 600, "total_steps": 1584, "loss": 1.5339, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.4291561391508185e-05, "epoch": 0.38, "percentage": 37.88, "elapsed_time": "0:29:19", "remaining_time": "0:48:05"}
+{"current_steps": 610, "total_steps": 1584, "loss": 1.5339, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3829449477712324e-05, "epoch": 0.38, "percentage": 38.51, "elapsed_time": "0:29:48", "remaining_time": "0:47:36"}
+{"current_steps": 620, "total_steps": 1584, "loss": 1.5399, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.336386453195088e-05, "epoch": 0.39, "percentage": 39.14, "elapsed_time": "0:30:18", "remaining_time": "0:47:07"}
+{"current_steps": 630, "total_steps": 1584, "loss": 1.5233, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.2894989690375626e-05, "epoch": 0.4, "percentage": 39.77, "elapsed_time": "0:30:47", "remaining_time": "0:46:38"}
+{"current_steps": 640, "total_steps": 1584, "loss": 1.538, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.2423009383206876e-05, "epoch": 0.4, "percentage": 40.4, "elapsed_time": "0:31:17", "remaining_time": "0:46:08"}
+{"current_steps": 650, "total_steps": 1584, "loss": 1.528, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.194810926218861e-05, "epoch": 0.41, "percentage": 41.04, "elapsed_time": "0:31:46", "remaining_time": "0:45:39"}
+{"current_steps": 660, "total_steps": 1584, "loss": 1.5307, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.147047612756302e-05, "epoch": 0.42, "percentage": 41.67, "elapsed_time": "0:32:15", "remaining_time": "0:45:09"}
+{"current_steps": 670, "total_steps": 1584, "loss": 1.4915, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.099029785459328e-05, "epoch": 0.42, "percentage": 42.3, "elapsed_time": "0:32:45", "remaining_time": "0:44:40"}
+{"current_steps": 680, "total_steps": 1584, "loss": 1.5268, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0507763319663517e-05, "epoch": 0.43, "percentage": 42.93, "elapsed_time": "0:33:14", "remaining_time": "0:44:11"}
+{"current_steps": 690, "total_steps": 1584, "loss": 1.5273, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.002306232598497e-05, "epoch": 0.44, "percentage": 43.56, "elapsed_time": "0:33:43", "remaining_time": "0:43:42"}
+{"current_steps": 700, "total_steps": 1584, "loss": 1.5273, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9536385528937567e-05, "epoch": 0.44, "percentage": 44.19, "elapsed_time": "0:34:13", "remaining_time": "0:43:12"}
+{"current_steps": 710, "total_steps": 1584, "loss": 1.5072, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9047924361076345e-05, "epoch": 0.45, "percentage": 44.82, "elapsed_time": "0:34:42", "remaining_time": "0:42:43"}
+{"current_steps": 720, "total_steps": 1584, "loss": 1.4856, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8557870956832132e-05, "epoch": 0.45, "percentage": 45.45, "elapsed_time": "0:35:12", "remaining_time": "0:42:14"}
+{"current_steps": 730, "total_steps": 1584, "loss": 1.4983, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8066418076936167e-05, "epoch": 0.46, "percentage": 46.09, "elapsed_time": "0:35:41", "remaining_time": "0:41:44"}
+{"current_steps": 740, "total_steps": 1584, "loss": 1.5518, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7573759032598366e-05, "epoch": 0.47, "percentage": 46.72, "elapsed_time": "0:36:10", "remaining_time": "0:41:15"}
+{"current_steps": 750, "total_steps": 1584, "loss": 1.4998, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7080087609469062e-05, "epoch": 0.47, "percentage": 47.35, "elapsed_time": "0:36:39", "remaining_time": "0:40:46"}
+{"current_steps": 760, "total_steps": 1584, "loss": 1.5109, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6585597991414114e-05, "epoch": 0.48, "percentage": 47.98, "elapsed_time": "0:37:08", "remaining_time": "0:40:16"}
+{"current_steps": 770, "total_steps": 1584, "loss": 1.5007, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6090484684133404e-05, "epoch": 0.49, "percentage": 48.61, "elapsed_time": "0:37:38", "remaining_time": "0:39:47"}
+{"current_steps": 780, "total_steps": 1584, "loss": 1.5049, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5594942438652688e-05, "epoch": 0.49, "percentage": 49.24, "elapsed_time": "0:38:07", "remaining_time": "0:39:18"}
+{"current_steps": 790, "total_steps": 1584, "loss": 1.5154, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.509916617471903e-05, "epoch": 0.5, "percentage": 49.87, "elapsed_time": "0:38:37", "remaining_time": "0:38:49"}
+{"current_steps": 800, "total_steps": 1584, "loss": 1.4883, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.46033509041298e-05, "epoch": 0.5, "percentage": 50.51, "elapsed_time": "0:39:06", "remaining_time": "0:38:19"}
+{"current_steps": 810, "total_steps": 1584, "loss": 1.5053, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.410769165402549e-05, "epoch": 0.51, "percentage": 51.14, "elapsed_time": "0:39:36", "remaining_time": "0:37:50"}
+{"current_steps": 820, "total_steps": 1584, "loss": 1.4871, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3612383390176503e-05, "epoch": 0.52, "percentage": 51.77, "elapsed_time": "0:40:05", "remaining_time": "0:37:21"}
+{"current_steps": 830, "total_steps": 1584, "loss": 1.5037, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3117620940294048e-05, "epoch": 0.52, "percentage": 52.4, "elapsed_time": "0:40:35", "remaining_time": "0:36:52"}
+{"current_steps": 840, "total_steps": 1584, "loss": 1.4525, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2623598917395438e-05, "epoch": 0.53, "percentage": 53.03, "elapsed_time": "0:41:04", "remaining_time": "0:36:22"}
+{"current_steps": 850, "total_steps": 1584, "loss": 1.4898, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.213051164325366e-05, "epoch": 0.54, "percentage": 53.66, "elapsed_time": "0:41:33", "remaining_time": "0:35:53"}
+{"current_steps": 860, "total_steps": 1584, "loss": 1.488, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1638553071961708e-05, "epoch": 0.54, "percentage": 54.29, "elapsed_time": "0:42:03", "remaining_time": "0:35:24"}
+{"current_steps": 870, "total_steps": 1584, "loss": 1.4711, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1147916713641367e-05, "epoch": 0.55, "percentage": 54.92, "elapsed_time": "0:42:32", "remaining_time": "0:34:54"}
+{"current_steps": 880, "total_steps": 1584, "loss": 1.488, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0658795558326743e-05, "epoch": 0.56, "percentage": 55.56, "elapsed_time": "0:43:01", "remaining_time": "0:34:25"}
+{"current_steps": 890, "total_steps": 1584, "loss": 1.4791, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.017138200005236e-05, "epoch": 0.56, "percentage": 56.19, "elapsed_time": "0:43:31", "remaining_time": "0:33:56"}
+{"current_steps": 900, "total_steps": 1584, "loss": 1.4956, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9685867761175584e-05, "epoch": 0.57, "percentage": 56.82, "elapsed_time": "0:44:00", "remaining_time": "0:33:26"}
+{"current_steps": 910, "total_steps": 1584, "loss": 1.4918, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9202443816963425e-05, "epoch": 0.57, "percentage": 57.45, "elapsed_time": "0:44:29", "remaining_time": "0:32:57"}
+{"current_steps": 920, "total_steps": 1584, "loss": 1.4577, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.872130032047302e-05, "epoch": 0.58, "percentage": 58.08, "elapsed_time": "0:44:59", "remaining_time": "0:32:28"}
+{"current_steps": 930, "total_steps": 1584, "loss": 1.4888, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.824262652775568e-05, "epoch": 0.59, "percentage": 58.71, "elapsed_time": "0:45:28", "remaining_time": "0:31:58"}
+{"current_steps": 940, "total_steps": 1584, "loss": 1.4673, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7766610723413684e-05, "epoch": 0.59, "percentage": 59.34, "elapsed_time": "0:45:57", "remaining_time": "0:31:29"}
+{"current_steps": 950, "total_steps": 1584, "loss": 1.4779, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7293440146539196e-05, "epoch": 0.6, "percentage": 59.97, "elapsed_time": "0:46:26", "remaining_time": "0:30:59"}
+{"current_steps": 960, "total_steps": 1584, "loss": 1.4583, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.682330091706446e-05, "epoch": 0.61, "percentage": 60.61, "elapsed_time": "0:46:55", "remaining_time": "0:30:30"}
+{"current_steps": 970, "total_steps": 1584, "loss": 1.4471, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6356377962552238e-05, "epoch": 0.61, "percentage": 61.24, "elapsed_time": "0:47:25", "remaining_time": "0:30:01"}
+{"current_steps": 980, "total_steps": 1584, "loss": 1.4632, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.589285494545514e-05, "epoch": 0.62, "percentage": 61.87, "elapsed_time": "0:47:54", "remaining_time": "0:29:31"}
+{"current_steps": 990, "total_steps": 1584, "loss": 1.4732, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5432914190872757e-05, "epoch": 0.62, "percentage": 62.5, "elapsed_time": "0:48:23", "remaining_time": "0:29:02"}
+{"current_steps": 1000, "total_steps": 1584, "loss": 1.452, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4976736614834664e-05, "epoch": 0.63, "percentage": 63.13, "elapsed_time": "0:48:52", "remaining_time": "0:28:32"}
+{"current_steps": 1010, "total_steps": 1584, "loss": 1.461, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4524501653137787e-05, "epoch": 0.64, "percentage": 63.76, "elapsed_time": "0:49:49", "remaining_time": "0:28:19"}
+{"current_steps": 1020, "total_steps": 1584, "loss": 1.4538, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4076387190766017e-05, "epoch": 0.64, "percentage": 64.39, "elapsed_time": "0:50:19", "remaining_time": "0:27:49"}
+{"current_steps": 1030, "total_steps": 1584, "loss": 1.4681, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.363256949191972e-05, "epoch": 0.65, "percentage": 65.03, "elapsed_time": "0:50:49", "remaining_time": "0:27:20"}
+{"current_steps": 1040, "total_steps": 1584, "loss": 1.4548, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3193223130682936e-05, "epoch": 0.66, "percentage": 65.66, "elapsed_time": "0:51:19", "remaining_time": "0:26:50"}
+{"current_steps": 1050, "total_steps": 1584, "loss": 1.4535, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2758520922355226e-05, "epoch": 0.66, "percentage": 66.29, "elapsed_time": "0:51:49", "remaining_time": "0:26:21"}
+{"current_steps": 1060, "total_steps": 1584, "loss": 1.4621, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2328633855475429e-05, "epoch": 0.67, "percentage": 66.92, "elapsed_time": "0:52:18", "remaining_time": "0:25:51"}
+{"current_steps": 1070, "total_steps": 1584, "loss": 1.4621, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1903731024563966e-05, "epoch": 0.68, "percentage": 67.55, "elapsed_time": "0:52:47", "remaining_time": "0:25:21"}
+{"current_steps": 1080, "total_steps": 1584, "loss": 1.4636, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.148397956361007e-05, "epoch": 0.68, "percentage": 68.18, "elapsed_time": "0:53:18", "remaining_time": "0:24:52"}
+{"current_steps": 1090, "total_steps": 1584, "loss": 1.4495, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.106954458033026e-05, "epoch": 0.69, "percentage": 68.81, "elapsed_time": "0:53:47", "remaining_time": "0:24:22"}
+{"current_steps": 1100, "total_steps": 1584, "loss": 1.4395, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0660589091223855e-05, "epoch": 0.69, "percentage": 69.44, "elapsed_time": "0:54:17", "remaining_time": "0:23:53"}
+{"current_steps": 1110, "total_steps": 1584, "loss": 1.4583, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.025727395745095e-05, "epoch": 0.7, "percentage": 70.08, "elapsed_time": "0:54:46", "remaining_time": "0:23:23"}
+{"current_steps": 1120, "total_steps": 1584, "loss": 1.4606, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.859757821558337e-06, "epoch": 0.71, "percentage": 70.71, "elapsed_time": "0:55:16", "remaining_time": "0:22:53"}
+{"current_steps": 1130, "total_steps": 1584, "loss": 1.454, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.468197045077976e-06, "epoch": 0.71, "percentage": 71.34, "elapsed_time": "0:55:45", "remaining_time": "0:22:24"}
+{"current_steps": 1140, "total_steps": 1584, "loss": 1.4654, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.082745647022797e-06, "epoch": 0.72, "percentage": 71.97, "elapsed_time": "0:56:14", "remaining_time": "0:21:54"}
+{"current_steps": 1150, "total_steps": 1584, "loss": 1.4526, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.703555243303835e-06, "epoch": 0.73, "percentage": 72.6, "elapsed_time": "0:56:44", "remaining_time": "0:21:24"}
+{"current_steps": 1160, "total_steps": 1584, "loss": 1.448, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.330774987092712e-06, "epoch": 0.73, "percentage": 73.23, "elapsed_time": "0:57:13", "remaining_time": "0:20:54"}
+{"current_steps": 1170, "total_steps": 1584, "loss": 1.4606, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.96455151015272e-06, "epoch": 0.74, "percentage": 73.86, "elapsed_time": "0:57:42", "remaining_time": "0:20:25"}
+{"current_steps": 1180, "total_steps": 1584, "loss": 1.4661, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.605028865161809e-06, "epoch": 0.74, "percentage": 74.49, "elapsed_time": "0:58:11", "remaining_time": "0:19:55"}
+{"current_steps": 1190, "total_steps": 1584, "loss": 1.4567, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.25234846904993e-06, "epoch": 0.75, "percentage": 75.13, "elapsed_time": "0:58:41", "remaining_time": "0:19:25"}
+{"current_steps": 1200, "total_steps": 1584, "loss": 1.4372, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.906649047373246e-06, "epoch": 0.76, "percentage": 75.76, "elapsed_time": "0:59:10", "remaining_time": "0:18:56"}
+{"current_steps": 1210, "total_steps": 1584, "loss": 1.4542, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.568066579746901e-06, "epoch": 0.76, "percentage": 76.39, "elapsed_time": "0:59:40", "remaining_time": "0:18:26"}
+{"current_steps": 1220, "total_steps": 1584, "loss": 1.4426, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.2367342463579475e-06, "epoch": 0.77, "percentage": 77.02, "elapsed_time": "1:00:09", "remaining_time": "0:17:56"}
+{"current_steps": 1230, "total_steps": 1584, "loss": 1.4292, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.912782375579412e-06, "epoch": 0.78, "percentage": 77.65, "elapsed_time": "1:00:38", "remaining_time": "0:17:27"}
+{"current_steps": 1240, "total_steps": 1584, "loss": 1.432, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.596338392706077e-06, "epoch": 0.78, "percentage": 78.28, "elapsed_time": "1:01:08", "remaining_time": "0:16:57"}
+{"current_steps": 1250, "total_steps": 1584, "loss": 1.4427, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.2875267698322325e-06, "epoch": 0.79, "percentage": 78.91, "elapsed_time": "1:01:37", "remaining_time": "0:16:27"}
+{"current_steps": 1260, "total_steps": 1584, "loss": 1.4199, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.986468976890993e-06, "epoch": 0.8, "percentage": 79.55, "elapsed_time": "1:02:06", "remaining_time": "0:15:58"}
+{"current_steps": 1270, "total_steps": 1584, "loss": 1.4253, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.693283433874565e-06, "epoch": 0.8, "percentage": 80.18, "elapsed_time": "1:02:35", "remaining_time": "0:15:28"}
+{"current_steps": 1280, "total_steps": 1584, "loss": 1.4382, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.408085464254183e-06, "epoch": 0.81, "percentage": 80.81, "elapsed_time": "1:03:04", "remaining_time": "0:14:58"}
+{"current_steps": 1290, "total_steps": 1584, "loss": 1.439, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.130987249617993e-06, "epoch": 0.81, "percentage": 81.44, "elapsed_time": "1:03:33", "remaining_time": "0:14:29"}
+{"current_steps": 1300, "total_steps": 1584, "loss": 1.4322, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.8620977855448935e-06, "epoch": 0.82, "percentage": 82.07, "elapsed_time": "1:04:03", "remaining_time": "0:13:59"}
+{"current_steps": 1310, "total_steps": 1584, "loss": 1.4305, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.601522838731461e-06, "epoch": 0.83, "percentage": 82.7, "elapsed_time": "1:04:32", "remaining_time": "0:13:30"}
+{"current_steps": 1320, "total_steps": 1584, "loss": 1.4188, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3493649053890326e-06, "epoch": 0.83, "percentage": 83.33, "elapsed_time": "1:05:02", "remaining_time": "0:13:00"}
+{"current_steps": 1330, "total_steps": 1584, "loss": 1.4426, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.1057231709272077e-06, "epoch": 0.84, "percentage": 83.96, "elapsed_time": "1:05:31", "remaining_time": "0:12:30"}
+{"current_steps": 1340, "total_steps": 1584, "loss": 1.4185, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8706934709395892e-06, "epoch": 0.85, "percentage": 84.6, "elapsed_time": "1:06:00", "remaining_time": "0:12:01"}
+{"current_steps": 1350, "total_steps": 1584, "loss": 1.4276, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6443682535072177e-06, "epoch": 0.85, "percentage": 85.23, "elapsed_time": "1:06:29", "remaining_time": "0:11:31"}
+{"current_steps": 1360, "total_steps": 1584, "loss": 1.4174, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4268365428344736e-06, "epoch": 0.86, "percentage": 85.86, "elapsed_time": "1:06:59", "remaining_time": "0:11:02"}
+{"current_steps": 1370, "total_steps": 1584, "loss": 1.441, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.21818390423168e-06, "epoch": 0.86, "percentage": 86.49, "elapsed_time": "1:07:28", "remaining_time": "0:10:32"}
+{"current_steps": 1380, "total_steps": 1584, "loss": 1.4322, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0184924104583613e-06, "epoch": 0.87, "percentage": 87.12, "elapsed_time": "1:07:58", "remaining_time": "0:10:02"}
+{"current_steps": 1390, "total_steps": 1584, "loss": 1.411, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8278406094401623e-06, "epoch": 0.88, "percentage": 87.75, "elapsed_time": "1:08:28", "remaining_time": "0:09:33"}
+{"current_steps": 1400, "total_steps": 1584, "loss": 1.4368, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6463034933723337e-06, "epoch": 0.88, "percentage": 88.38, "elapsed_time": "1:08:57", "remaining_time": "0:09:03"}
+{"current_steps": 1410, "total_steps": 1584, "loss": 1.396, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4739524692218314e-06, "epoch": 0.89, "percentage": 89.02, "elapsed_time": "1:09:26", "remaining_time": "0:08:34"}
+{"current_steps": 1420, "total_steps": 1584, "loss": 1.439, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3108553306396265e-06, "epoch": 0.9, "percentage": 89.65, "elapsed_time": "1:09:55", "remaining_time": "0:08:04"}
+{"current_steps": 1430, "total_steps": 1584, "loss": 1.4113, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1570762312943295e-06, "epoch": 0.9, "percentage": 90.28, "elapsed_time": "1:10:25", "remaining_time": "0:07:35"}
+{"current_steps": 1440, "total_steps": 1584, "loss": 1.4438, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0126756596375686e-06, "epoch": 0.91, "percentage": 90.91, "elapsed_time": "1:10:54", "remaining_time": "0:07:05"}
+{"current_steps": 1450, "total_steps": 1584, "loss": 1.4365, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.777104151110826e-07, "epoch": 0.91, "percentage": 91.54, "elapsed_time": "1:11:24", "remaining_time": "0:06:35"}
+{"current_steps": 1460, "total_steps": 1584, "loss": 1.4355, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.522335858048707e-07, "epoch": 0.92, "percentage": 92.17, "elapsed_time": "1:11:53", "remaining_time": "0:06:06"}
+{"current_steps": 1470, "total_steps": 1584, "loss": 1.431, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.362945275751736e-07, "epoch": 0.93, "percentage": 92.8, "elapsed_time": "1:12:23", "remaining_time": "0:05:36"}
+{"current_steps": 1480, "total_steps": 1584, "loss": 1.4057, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.299388446305343e-07, "epoch": 0.93, "percentage": 93.43, "elapsed_time": "1:12:52", "remaining_time": "0:05:07"}
+{"current_steps": 1490, "total_steps": 1584, "loss": 1.421, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.3320837159353813e-07, "epoch": 0.94, "percentage": 94.07, "elapsed_time": "1:13:21", "remaining_time": "0:04:37"}
+{"current_steps": 1500, "total_steps": 1584, "loss": 1.4319, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.4614115704533767e-07, "epoch": 0.95, "percentage": 94.7, "elapsed_time": "1:13:51", "remaining_time": "0:04:08"}
+{"current_steps": 1510, "total_steps": 1584, "loss": 1.4295, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.687714485593462e-07, "epoch": 0.95, "percentage": 95.33, "elapsed_time": "1:14:20", "remaining_time": "0:03:38"}
+{"current_steps": 1520, "total_steps": 1584, "loss": 1.4294, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.011296792301165e-07, "epoch": 0.96, "percentage": 95.96, "elapsed_time": "1:14:49", "remaining_time": "0:03:09"}
+{"current_steps": 1530, "total_steps": 1584, "loss": 1.4562, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4324245570256633e-07, "epoch": 0.97, "percentage": 96.59, "elapsed_time": "1:15:19", "remaining_time": "0:02:39"}
+{"current_steps": 1540, "total_steps": 1584, "loss": 1.4447, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.513254770636137e-08, "epoch": 0.97, "percentage": 97.22, "elapsed_time": "1:15:48", "remaining_time": "0:02:09"}
+{"current_steps": 1550, "total_steps": 1584, "loss": 1.4229, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.681887909952388e-08, "epoch": 0.98, "percentage": 97.85, "elapsed_time": "1:16:18", "remaining_time": "0:01:40"}
+{"current_steps": 1560, "total_steps": 1584, "loss": 1.4458, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.831652042480093e-08, "epoch": 0.98, "percentage": 98.48, "elapsed_time": "1:16:47", "remaining_time": "0:01:10"}
+{"current_steps": 1570, "total_steps": 1584, "loss": 1.4267, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.636682981720158e-09, "epoch": 0.99, "percentage": 99.12, "elapsed_time": "1:17:16", "remaining_time": "0:00:41"}
+{"current_steps": 1580, "total_steps": 1584, "loss": 1.4373, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.867144166728846e-10, "epoch": 1.0, "percentage": 99.75, "elapsed_time": "1:17:45", "remaining_time": "0:00:11"}
+{"current_steps": 1584, "total_steps": 1584, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "1:17:57", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9995267392333176,
+  "eval_steps": 500,
+  "global_step": 1584,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.7190074920654297,
+      "learning_rate": 4.9995083170283816e-05,
+      "loss": 2.9245,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.431870222091675,
+      "learning_rate": 4.998033461515242e-05,
+      "loss": 2.0053,
+      "step": 20
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.3315682411193848,
+      "learning_rate": 4.9955760135896534e-05,
+      "loss": 1.888,
+      "step": 30
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 3.2937276363372803,
+      "learning_rate": 4.992136939879856e-05,
+      "loss": 1.8447,
+      "step": 40
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.7375714778900146,
+      "learning_rate": 4.9877175931330346e-05,
+      "loss": 1.8212,
+      "step": 50
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.15061092376709,
+      "learning_rate": 4.982319711683221e-05,
+      "loss": 1.793,
+      "step": 60
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.0427424907684326,
+      "learning_rate": 4.975945418767529e-05,
+      "loss": 1.756,
+      "step": 70
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.107785224914551,
+      "learning_rate": 4.968597221690986e-05,
+      "loss": 1.7285,
+      "step": 80
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.100552558898926,
+      "learning_rate": 4.96027801084029e-05,
+      "loss": 1.7297,
+      "step": 90
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.2227377891540527,
+      "learning_rate": 4.950991058546893e-05,
+      "loss": 1.7602,
+      "step": 100
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.535144567489624,
+      "learning_rate": 4.940740017799833e-05,
+      "loss": 1.7433,
+      "step": 110
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.6522979736328125,
+      "learning_rate": 4.929528920808854e-05,
+      "loss": 1.7363,
+      "step": 120
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.8091869354248047,
+      "learning_rate": 4.917362177418342e-05,
+      "loss": 1.6872,
+      "step": 130
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.1017510890960693,
+      "learning_rate": 4.904244573372733e-05,
+      "loss": 1.7084,
+      "step": 140
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.6424258947372437,
+      "learning_rate": 4.8901812684340564e-05,
+      "loss": 1.6997,
+      "step": 150
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.4547488689422607,
+      "learning_rate": 4.8751777943523634e-05,
+      "loss": 1.6747,
+      "step": 160
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.6251146793365479,
+      "learning_rate": 4.8592400526898314e-05,
+      "loss": 1.6836,
+      "step": 170
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.098386526107788,
+      "learning_rate": 4.842374312499405e-05,
+      "loss": 1.6552,
+      "step": 180
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.2387640476226807,
+      "learning_rate": 4.824587207858888e-05,
+      "loss": 1.6489,
+      "step": 190
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.7299611568450928,
+      "learning_rate": 4.805885735261454e-05,
+      "loss": 1.6576,
+      "step": 200
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.5701665878295898,
+      "learning_rate": 4.786277250863599e-05,
+      "loss": 1.6533,
+      "step": 210
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.417296886444092,
+      "learning_rate": 4.765769467591625e-05,
+      "loss": 1.6356,
+      "step": 220
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.2636029720306396,
+      "learning_rate": 4.744370452107789e-05,
+      "loss": 1.6389,
+      "step": 230
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.576324224472046,
+      "learning_rate": 4.722088621637309e-05,
+      "loss": 1.6546,
+      "step": 240
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.9720542430877686,
+      "learning_rate": 4.698932740657479e-05,
+      "loss": 1.6354,
+      "step": 250
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.5250279903411865,
+      "learning_rate": 4.6749119174501975e-05,
+      "loss": 1.6342,
+      "step": 260
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 2.4737966060638428,
+      "learning_rate": 4.6500356005192514e-05,
+      "loss": 1.6407,
+      "step": 270
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.2792372703552246,
+      "learning_rate": 4.6243135748737864e-05,
+      "loss": 1.6339,
+      "step": 280
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.5593037605285645,
+      "learning_rate": 4.597755958179406e-05,
+      "loss": 1.6095,
+      "step": 290
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.3141404390335083,
+      "learning_rate": 4.570373196778427e-05,
+      "loss": 1.6036,
+      "step": 300
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.2617065906524658,
+      "learning_rate": 4.5421760615808474e-05,
+      "loss": 1.6244,
+      "step": 310
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.64117431640625,
+      "learning_rate": 4.513175643827647e-05,
+      "loss": 1.6449,
+      "step": 320
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.7132749557495117,
+      "learning_rate": 4.4833833507280884e-05,
+      "loss": 1.5948,
+      "step": 330
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 2.1323654651641846,
+      "learning_rate": 4.4528109009727336e-05,
+      "loss": 1.627,
+      "step": 340
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.253115653991699,
+      "learning_rate": 4.42147032012394e-05,
+      "loss": 1.6151,
+      "step": 350
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.6143097877502441,
+      "learning_rate": 4.389373935885646e-05,
+      "loss": 1.5838,
+      "step": 360
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.3353707790374756,
+      "learning_rate": 4.356534373254316e-05,
+      "loss": 1.5935,
+      "step": 370
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.283742904663086,
+      "learning_rate": 4.322964549552943e-05,
+      "loss": 1.6015,
+      "step": 380
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.437249779701233,
+      "learning_rate": 4.288677669350066e-05,
+      "loss": 1.577,
+      "step": 390
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.5190638303756714,
+      "learning_rate": 4.2536872192658036e-05,
+      "loss": 1.5843,
+      "step": 400
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.1320886611938477,
+      "learning_rate": 4.218006962666934e-05,
+      "loss": 1.6145,
+      "step": 410
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.0696591138839722,
+      "learning_rate": 4.181650934253132e-05,
+      "loss": 1.5601,
+      "step": 420
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.3149545192718506,
+      "learning_rate": 4.144633434536467e-05,
+      "loss": 1.5664,
+      "step": 430
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.3661577701568604,
+      "learning_rate": 4.1069690242163484e-05,
+      "loss": 1.6002,
+      "step": 440
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.6984481811523438,
+      "learning_rate": 4.06867251845213e-05,
+      "loss": 1.576,
+      "step": 450
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.2728784084320068,
+      "learning_rate": 4.0297589810356165e-05,
+      "loss": 1.5448,
+      "step": 460
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.4147616624832153,
+      "learning_rate": 3.9902437184657784e-05,
+      "loss": 1.5595,
+      "step": 470
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.2289011478424072,
+      "learning_rate": 3.9501422739279956e-05,
+      "loss": 1.5628,
+      "step": 480
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.5690233707427979,
+      "learning_rate": 3.909470421180201e-05,
+      "loss": 1.5731,
+      "step": 490
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.4935098886489868,
+      "learning_rate": 3.8682441583483314e-05,
+      "loss": 1.545,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.2939772605895996,
+      "learning_rate": 3.8264797016335205e-05,
+      "loss": 1.5793,
+      "step": 510
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.2150651216506958,
+      "learning_rate": 3.7841934789335164e-05,
+      "loss": 1.5378,
+      "step": 520
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.2153139114379883,
+      "learning_rate": 3.741402123380828e-05,
+      "loss": 1.5345,
+      "step": 530
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.290591835975647,
+      "learning_rate": 3.6981224668001424e-05,
+      "loss": 1.5517,
+      "step": 540
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.1924967765808105,
+      "learning_rate": 3.654371533087586e-05,
+      "loss": 1.5472,
+      "step": 550
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.6345056295394897,
+      "learning_rate": 3.610166531514436e-05,
+      "loss": 1.5564,
+      "step": 560
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.185119867324829,
+      "learning_rate": 3.565524849957921e-05,
+      "loss": 1.5574,
+      "step": 570
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.3646321296691895,
+      "learning_rate": 3.520464048061758e-05,
+      "loss": 1.5584,
+      "step": 580
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.2333228588104248,
+      "learning_rate": 3.47500185032913e-05,
+      "loss": 1.518,
+      "step": 590
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.3945318460464478,
+      "learning_rate": 3.4291561391508185e-05,
+      "loss": 1.5339,
+      "step": 600
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.304306149482727,
+      "learning_rate": 3.3829449477712324e-05,
+      "loss": 1.5339,
+      "step": 610
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.6393932104110718,
+      "learning_rate": 3.336386453195088e-05,
+      "loss": 1.5399,
+      "step": 620
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.2000635862350464,
+      "learning_rate": 3.2894989690375626e-05,
+      "loss": 1.5233,
+      "step": 630
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.1479601860046387,
+      "learning_rate": 3.2423009383206876e-05,
+      "loss": 1.538,
+      "step": 640
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.1483389139175415,
+      "learning_rate": 3.194810926218861e-05,
+      "loss": 1.528,
+      "step": 650
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.2403253316879272,
+      "learning_rate": 3.147047612756302e-05,
+      "loss": 1.5307,
+      "step": 660
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.3997712135314941,
+      "learning_rate": 3.099029785459328e-05,
+      "loss": 1.4915,
+      "step": 670
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.2010352611541748,
+      "learning_rate": 3.0507763319663517e-05,
+      "loss": 1.5268,
+      "step": 680
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.0670932531356812,
+      "learning_rate": 3.002306232598497e-05,
+      "loss": 1.5273,
+      "step": 690
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.2283655405044556,
+      "learning_rate": 2.9536385528937567e-05,
+      "loss": 1.5273,
+      "step": 700
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.1306476593017578,
+      "learning_rate": 2.9047924361076345e-05,
+      "loss": 1.5072,
+      "step": 710
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.1699943542480469,
+      "learning_rate": 2.8557870956832132e-05,
+      "loss": 1.4856,
+      "step": 720
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.2550854682922363,
+      "learning_rate": 2.8066418076936167e-05,
+      "loss": 1.4983,
+      "step": 730
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.0610970258712769,
+      "learning_rate": 2.7573759032598366e-05,
+      "loss": 1.5518,
+      "step": 740
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.1754754781723022,
+      "learning_rate": 2.7080087609469062e-05,
+      "loss": 1.4998,
+      "step": 750
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.1955766677856445,
+      "learning_rate": 2.6585597991414114e-05,
+      "loss": 1.5109,
+      "step": 760
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.0891656875610352,
+      "learning_rate": 2.6090484684133404e-05,
+      "loss": 1.5007,
+      "step": 770
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.0880335569381714,
+      "learning_rate": 2.5594942438652688e-05,
+      "loss": 1.5049,
+      "step": 780
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.345954418182373,
+      "learning_rate": 2.509916617471903e-05,
+      "loss": 1.5154,
+      "step": 790
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.1668224334716797,
+      "learning_rate": 2.46033509041298e-05,
+      "loss": 1.4883,
+      "step": 800
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.055127501487732,
+      "learning_rate": 2.410769165402549e-05,
+      "loss": 1.5053,
+      "step": 810
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.0528500080108643,
+      "learning_rate": 2.3612383390176503e-05,
+      "loss": 1.4871,
+      "step": 820
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.328258991241455,
+      "learning_rate": 2.3117620940294048e-05,
+      "loss": 1.5037,
+      "step": 830
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.0326772928237915,
+      "learning_rate": 2.2623598917395438e-05,
+      "loss": 1.4525,
+      "step": 840
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.057058811187744,
+      "learning_rate": 2.213051164325366e-05,
+      "loss": 1.4898,
+      "step": 850
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.1190940141677856,
+      "learning_rate": 2.1638553071961708e-05,
+      "loss": 1.488,
+      "step": 860
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.1501041650772095,
+      "learning_rate": 2.1147916713641367e-05,
+      "loss": 1.4711,
+      "step": 870
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.090022325515747,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 1.488,
+      "step": 880
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.0642565488815308,
+      "learning_rate": 2.017138200005236e-05,
+      "loss": 1.4791,
+      "step": 890
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.3562296628952026,
+      "learning_rate": 1.9685867761175584e-05,
+      "loss": 1.4956,
+      "step": 900
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.2069261074066162,
+      "learning_rate": 1.9202443816963425e-05,
+      "loss": 1.4918,
+      "step": 910
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.3227437734603882,
+      "learning_rate": 1.872130032047302e-05,
+      "loss": 1.4577,
+      "step": 920
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.0784181356430054,
+      "learning_rate": 1.824262652775568e-05,
+      "loss": 1.4888,
+      "step": 930
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.000135898590088,
+      "learning_rate": 1.7766610723413684e-05,
+      "loss": 1.4673,
+      "step": 940
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.136026382446289,
+      "learning_rate": 1.7293440146539196e-05,
+      "loss": 1.4779,
+      "step": 950
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.123252272605896,
+      "learning_rate": 1.682330091706446e-05,
+      "loss": 1.4583,
+      "step": 960
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.0559343099594116,
+      "learning_rate": 1.6356377962552238e-05,
+      "loss": 1.4471,
+      "step": 970
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.0266658067703247,
+      "learning_rate": 1.589285494545514e-05,
+      "loss": 1.4632,
+      "step": 980
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.1371444463729858,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 1.4732,
+      "step": 990
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.1203784942626953,
+      "learning_rate": 1.4976736614834664e-05,
+      "loss": 1.452,
+      "step": 1000
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.0037944316864014,
+      "learning_rate": 1.4524501653137787e-05,
+      "loss": 1.461,
+      "step": 1010
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.1353282928466797,
+      "learning_rate": 1.4076387190766017e-05,
+      "loss": 1.4538,
+      "step": 1020
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.1203887462615967,
+      "learning_rate": 1.363256949191972e-05,
+      "loss": 1.4681,
+      "step": 1030
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.0686651468276978,
+      "learning_rate": 1.3193223130682936e-05,
+      "loss": 1.4548,
+      "step": 1040
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.0339988470077515,
+      "learning_rate": 1.2758520922355226e-05,
+      "loss": 1.4535,
+      "step": 1050
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.4555269479751587,
+      "learning_rate": 1.2328633855475429e-05,
+      "loss": 1.4621,
+      "step": 1060
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.0318940877914429,
+      "learning_rate": 1.1903731024563966e-05,
+      "loss": 1.4621,
+      "step": 1070
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.084612488746643,
+      "learning_rate": 1.148397956361007e-05,
+      "loss": 1.4636,
+      "step": 1080
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.0705621242523193,
+      "learning_rate": 1.106954458033026e-05,
+      "loss": 1.4495,
+      "step": 1090
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.050857424736023,
+      "learning_rate": 1.0660589091223855e-05,
+      "loss": 1.4395,
+      "step": 1100
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.0744839906692505,
+      "learning_rate": 1.025727395745095e-05,
+      "loss": 1.4583,
+      "step": 1110
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.0446105003356934,
+      "learning_rate": 9.859757821558337e-06,
+      "loss": 1.4606,
+      "step": 1120
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.1479051113128662,
+      "learning_rate": 9.468197045077976e-06,
+      "loss": 1.454,
+      "step": 1130
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.985953152179718,
+      "learning_rate": 9.082745647022797e-06,
+      "loss": 1.4654,
+      "step": 1140
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.1085201501846313,
+      "learning_rate": 8.703555243303835e-06,
+      "loss": 1.4526,
+      "step": 1150
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.2304482460021973,
+      "learning_rate": 8.330774987092712e-06,
+      "loss": 1.448,
+      "step": 1160
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.0740071535110474,
+      "learning_rate": 7.96455151015272e-06,
+      "loss": 1.4606,
+      "step": 1170
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.0380760431289673,
+      "learning_rate": 7.605028865161809e-06,
+      "loss": 1.4661,
+      "step": 1180
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.1115810871124268,
+      "learning_rate": 7.25234846904993e-06,
+      "loss": 1.4567,
+      "step": 1190
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.9248858094215393,
+      "learning_rate": 6.906649047373246e-06,
+      "loss": 1.4372,
+      "step": 1200
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.0288389921188354,
+      "learning_rate": 6.568066579746901e-06,
+      "loss": 1.4542,
+      "step": 1210
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.0125763416290283,
+      "learning_rate": 6.2367342463579475e-06,
+      "loss": 1.4426,
+      "step": 1220
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.9536031484603882,
+      "learning_rate": 5.912782375579412e-06,
+      "loss": 1.4292,
+      "step": 1230
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.993061363697052,
+      "learning_rate": 5.596338392706077e-06,
+      "loss": 1.432,
+      "step": 1240
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.9642956852912903,
+      "learning_rate": 5.2875267698322325e-06,
+      "loss": 1.4427,
+      "step": 1250
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.9925894737243652,
+      "learning_rate": 4.986468976890993e-06,
+      "loss": 1.4199,
+      "step": 1260
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.0030889511108398,
+      "learning_rate": 4.693283433874565e-06,
+      "loss": 1.4253,
+      "step": 1270
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.986602783203125,
+      "learning_rate": 4.408085464254183e-06,
+      "loss": 1.4382,
+      "step": 1280
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.9463419318199158,
+      "learning_rate": 4.130987249617993e-06,
+      "loss": 1.439,
+      "step": 1290
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.9418216347694397,
+      "learning_rate": 3.8620977855448935e-06,
+      "loss": 1.4322,
+      "step": 1300
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.067226529121399,
+      "learning_rate": 3.601522838731461e-06,
+      "loss": 1.4305,
+      "step": 1310
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.9662885665893555,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 1.4188,
+      "step": 1320
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.1397868394851685,
+      "learning_rate": 3.1057231709272077e-06,
+      "loss": 1.4426,
+      "step": 1330
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.0030759572982788,
+      "learning_rate": 2.8706934709395892e-06,
+      "loss": 1.4185,
+      "step": 1340
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.9549908638000488,
+      "learning_rate": 2.6443682535072177e-06,
+      "loss": 1.4276,
+      "step": 1350
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.9839365482330322,
+      "learning_rate": 2.4268365428344736e-06,
+      "loss": 1.4174,
+      "step": 1360
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.954189121723175,
+      "learning_rate": 2.21818390423168e-06,
+      "loss": 1.441,
+      "step": 1370
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.9914742708206177,
+      "learning_rate": 2.0184924104583613e-06,
+      "loss": 1.4322,
+      "step": 1380
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.9965653419494629,
+      "learning_rate": 1.8278406094401623e-06,
+      "loss": 1.411,
+      "step": 1390
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.0744175910949707,
+      "learning_rate": 1.6463034933723337e-06,
+      "loss": 1.4368,
+      "step": 1400
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.9871243238449097,
+      "learning_rate": 1.4739524692218314e-06,
+      "loss": 1.396,
+      "step": 1410
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.9976981282234192,
+      "learning_rate": 1.3108553306396265e-06,
+      "loss": 1.439,
+      "step": 1420
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.9817109704017639,
+      "learning_rate": 1.1570762312943295e-06,
+      "loss": 1.4113,
+      "step": 1430
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.9741029143333435,
+      "learning_rate": 1.0126756596375686e-06,
+      "loss": 1.4438,
+      "step": 1440
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.0171328783035278,
+      "learning_rate": 8.777104151110826e-07,
+      "loss": 1.4365,
+      "step": 1450
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.980021595954895,
+      "learning_rate": 7.522335858048707e-07,
+      "loss": 1.4355,
+      "step": 1460
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.9966154098510742,
+      "learning_rate": 6.362945275751736e-07,
+      "loss": 1.431,
+      "step": 1470
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.9687898755073547,
+      "learning_rate": 5.299388446305343e-07,
+      "loss": 1.4057,
+      "step": 1480
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.9906119704246521,
+      "learning_rate": 4.3320837159353813e-07,
+      "loss": 1.421,
+      "step": 1490
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.0227527618408203,
+      "learning_rate": 3.4614115704533767e-07,
+      "loss": 1.4319,
+      "step": 1500
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.0115277767181396,
+      "learning_rate": 2.687714485593462e-07,
+      "loss": 1.4295,
+      "step": 1510
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.993654727935791,
+      "learning_rate": 2.011296792301165e-07,
+      "loss": 1.4294,
+      "step": 1520
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.8775748014450073,
+      "learning_rate": 1.4324245570256633e-07,
+      "loss": 1.4562,
+      "step": 1530
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.9754842519760132,
+      "learning_rate": 9.513254770636137e-08,
+      "loss": 1.4447,
+      "step": 1540
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.9996697902679443,
+      "learning_rate": 5.681887909952388e-08,
+      "loss": 1.4229,
+      "step": 1550
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.9914098381996155,
+      "learning_rate": 2.831652042480093e-08,
+      "loss": 1.4458,
+      "step": 1560
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.9639108777046204,
+      "learning_rate": 9.636682981720158e-09,
+      "loss": 1.4267,
+      "step": 1570
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9515108466148376,
+      "learning_rate": 7.867144166728846e-10,
+      "loss": 1.4373,
+      "step": 1580
+    },
+    {
+      "epoch": 1.0,
+      "step": 1584,
+      "total_flos": 1.1098698583858217e+18,
+      "train_loss": 1.5383612829627413,
+      "train_runtime": 4681.1872,
+      "train_samples_per_second": 21.666,
+      "train_steps_per_second": 0.338
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1584,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "total_flos": 1.1098698583858217e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5f270ab83bb6b8b6198abab8938484e33528253ff0e05545853f6357e16e105
+size 4603