Upload folder using huggingface_hub

config.json

@@ -0,0 +1,72 @@
+{
+  "_name_or_path": "deepseek-ai/deepseek-coder-1.3b-base",
+  "architectures": [
+    "DetikzifyForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 32013,
+  "concat_patches": 2,
+  "eos_token_id": 32014,
+  "feature_layer": 26,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "max_position_embeddings": 16384,
+  "mlp_bias": false,
+  "mm_hidden_size": 2304,
+  "model_type": "detikzify",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "num_patches": 364,
+  "patch_token_id": 32013,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "rope_type": "linear",
+    "type": "linear"
+  },
+  "rope_theta": 100000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "use_cache": false,
+  "use_mm_proj": true,
+  "vision_config": {
+    "architecture": "vit_so400m_patch14_siglip_384",
+    "classifier": "head",
+    "crop_mode": "center",
+    "crop_pct": 0.9,
+    "custom_load": false,
+    "first_conv": "patch_embed.proj",
+    "fixed_input_size": true,
+    "hf_hub_filename": "open_clip_pytorch_model.bin",
+    "hf_hub_id": "timm/ViT-SO400M-14-SigLIP-384",
+    "input_size": [
+      3,
+      384,
+      384
+    ],
+    "interpolation": "bicubic",
+    "mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "num_classes": 0,
+    "pool_size": null,
+    "std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "tag": "webli",
+    "url": ""
+  },
+  "vision_tower": "vit_so400m_patch14_siglip_384.webli",
+  "vocab_size": 32256
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 32013,
+  "eos_token_id": 32014,
+  "pad_token_id": 32018,
+  "transformers_version": "4.46.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0183ae9a8c3c9c1ddaeafcb0f1979d49fb7c66c9ab61db07ce8bf14c1571334e
+size 4986380064

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5381661b30b86602ae8e1f1b01b2387bc529c4481f25ba007143812b6610e66
+size 418415560

model.safetensors.index.json

@@ -0,0 +1,228 @@
+{
+  "metadata": {
+    "total_size": 5404770304
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.mm_projector.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.weight": "model-00002-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

trainer_state.json

@@ -0,0 +1,777 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.996154016179656,
+  "eval_steps": 500,
+  "global_step": 1059,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02829229477034614,
+      "grad_norm": 94.11492156982422,
+      "learning_rate": 1.25e-05,
+      "loss": 0.8265,
+      "step": 10
+    },
+    {
+      "epoch": 0.05658458954069228,
+      "grad_norm": 75.07470703125,
+      "learning_rate": 2.5e-05,
+      "loss": 0.737,
+      "step": 20
+    },
+    {
+      "epoch": 0.08487688431103842,
+      "grad_norm": 63.67890930175781,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.7199,
+      "step": 30
+    },
+    {
+      "epoch": 0.11316917908138456,
+      "grad_norm": 64.5537109375,
+      "learning_rate": 3.9994011512354455e-05,
+      "loss": 0.7145,
+      "step": 40
+    },
+    {
+      "epoch": 0.1414614738517307,
+      "grad_norm": 63.26422119140625,
+      "learning_rate": 3.996968942743186e-05,
+      "loss": 0.6906,
+      "step": 50
+    },
+    {
+      "epoch": 0.16975376862207683,
+      "grad_norm": 52.657257080078125,
+      "learning_rate": 3.9926682204807304e-05,
+      "loss": 0.6766,
+      "step": 60
+    },
+    {
+      "epoch": 0.19804606339242298,
+      "grad_norm": 55.939781188964844,
+      "learning_rate": 3.986503008526067e-05,
+      "loss": 0.6663,
+      "step": 70
+    },
+    {
+      "epoch": 0.22633835816276912,
+      "grad_norm": 49.46023941040039,
+      "learning_rate": 3.978479075513446e-05,
+      "loss": 0.6651,
+      "step": 80
+    },
+    {
+      "epoch": 0.25463065293311526,
+      "grad_norm": 53.444976806640625,
+      "learning_rate": 3.968603929235803e-05,
+      "loss": 0.6687,
+      "step": 90
+    },
+    {
+      "epoch": 0.2829229477034614,
+      "grad_norm": 49.93338394165039,
+      "learning_rate": 3.956886809619913e-05,
+      "loss": 0.6596,
+      "step": 100
+    },
+    {
+      "epoch": 0.3112152424738075,
+      "grad_norm": 54.019474029541016,
+      "learning_rate": 3.94333868008082e-05,
+      "loss": 0.6334,
+      "step": 110
+    },
+    {
+      "epoch": 0.33950753724415367,
+      "grad_norm": 49.52291488647461,
+      "learning_rate": 3.927972217263646e-05,
+      "loss": 0.636,
+      "step": 120
+    },
+    {
+      "epoch": 0.3677998320144998,
+      "grad_norm": 46.9410400390625,
+      "learning_rate": 3.9108017991823674e-05,
+      "loss": 0.6273,
+      "step": 130
+    },
+    {
+      "epoch": 0.39609212678484595,
+      "grad_norm": 48.465641021728516,
+      "learning_rate": 3.891843491766674e-05,
+      "loss": 0.6225,
+      "step": 140
+    },
+    {
+      "epoch": 0.42438442155519207,
+      "grad_norm": 47.92714309692383,
+      "learning_rate": 3.871115033829478e-05,
+      "loss": 0.6358,
+      "step": 150
+    },
+    {
+      "epoch": 0.45267671632553824,
+      "grad_norm": 47.684757232666016,
+      "learning_rate": 3.8486358204691505e-05,
+      "loss": 0.6201,
+      "step": 160
+    },
+    {
+      "epoch": 0.48096901109588436,
+      "grad_norm": 48.77947235107422,
+      "learning_rate": 3.824426884922018e-05,
+      "loss": 0.6139,
+      "step": 170
+    },
+    {
+      "epoch": 0.5092613058662305,
+      "grad_norm": 49.815006256103516,
+      "learning_rate": 3.798510878882086e-05,
+      "loss": 0.6247,
+      "step": 180
+    },
+    {
+      "epoch": 0.5375536006365766,
+      "grad_norm": 49.60624694824219,
+      "learning_rate": 3.7709120513064196e-05,
+      "loss": 0.6125,
+      "step": 190
+    },
+    {
+      "epoch": 0.5658458954069228,
+      "grad_norm": 47.29824447631836,
+      "learning_rate": 3.741656225726005e-05,
+      "loss": 0.6129,
+      "step": 200
+    },
+    {
+      "epoch": 0.5941381901772689,
+      "grad_norm": 50.14078903198242,
+      "learning_rate": 3.710770776083311e-05,
+      "loss": 0.5902,
+      "step": 210
+    },
+    {
+      "epoch": 0.622430484947615,
+      "grad_norm": 48.83024215698242,
+      "learning_rate": 3.6782846011191855e-05,
+      "loss": 0.6121,
+      "step": 220
+    },
+    {
+      "epoch": 0.6507227797179612,
+      "grad_norm": 45.325504302978516,
+      "learning_rate": 3.644228097333025e-05,
+      "loss": 0.6009,
+      "step": 230
+    },
+    {
+      "epoch": 0.6790150744883073,
+      "grad_norm": 51.53373718261719,
+      "learning_rate": 3.60863313054153e-05,
+      "loss": 0.6118,
+      "step": 240
+    },
+    {
+      "epoch": 0.7073073692586535,
+      "grad_norm": 44.46132278442383,
+      "learning_rate": 3.571533006062664e-05,
+      "loss": 0.6042,
+      "step": 250
+    },
+    {
+      "epoch": 0.7355996640289996,
+      "grad_norm": 47.890625,
+      "learning_rate": 3.5329624375527e-05,
+      "loss": 0.6029,
+      "step": 260
+    },
+    {
+      "epoch": 0.7638919587993458,
+      "grad_norm": 45.87557601928711,
+      "learning_rate": 3.492957514525522e-05,
+      "loss": 0.5924,
+      "step": 270
+    },
+    {
+      "epoch": 0.7921842535696919,
+      "grad_norm": 46.6375617980957,
+      "learning_rate": 3.4515556685845706e-05,
+      "loss": 0.5839,
+      "step": 280
+    },
+    {
+      "epoch": 0.820476548340038,
+      "grad_norm": 46.20927810668945,
+      "learning_rate": 3.4087956383990355e-05,
+      "loss": 0.5976,
+      "step": 290
+    },
+    {
+      "epoch": 0.8487688431103841,
+      "grad_norm": 44.299476623535156,
+      "learning_rate": 3.36471743345705e-05,
+      "loss": 0.5871,
+      "step": 300
+    },
+    {
+      "epoch": 0.8770611378807303,
+      "grad_norm": 44.8925895690918,
+      "learning_rate": 3.3193622966298155e-05,
+      "loss": 0.5729,
+      "step": 310
+    },
+    {
+      "epoch": 0.9053534326510765,
+      "grad_norm": 43.60881042480469,
+      "learning_rate": 3.272772665581681e-05,
+      "loss": 0.5951,
+      "step": 320
+    },
+    {
+      "epoch": 0.9336457274214226,
+      "grad_norm": 44.73467254638672,
+      "learning_rate": 3.2249921330622894e-05,
+      "loss": 0.5865,
+      "step": 330
+    },
+    {
+      "epoch": 0.9619380221917687,
+      "grad_norm": 44.39530563354492,
+      "learning_rate": 3.176065406117928e-05,
+      "loss": 0.5677,
+      "step": 340
+    },
+    {
+      "epoch": 0.9902303169621148,
+      "grad_norm": 45.78221893310547,
+      "learning_rate": 3.126038264260272e-05,
+      "loss": 0.5811,
+      "step": 350
+    },
+    {
+      "epoch": 1.018522611732461,
+      "grad_norm": 42.54255676269531,
+      "learning_rate": 3.0749575166316376e-05,
+      "loss": 0.529,
+      "step": 360
+    },
+    {
+      "epoch": 1.0468149065028072,
+      "grad_norm": 44.1485595703125,
+      "learning_rate": 3.022870958206845e-05,
+      "loss": 0.5104,
+      "step": 370
+    },
+    {
+      "epoch": 1.0751072012731533,
+      "grad_norm": 43.59065628051758,
+      "learning_rate": 2.9698273250726593e-05,
+      "loss": 0.4912,
+      "step": 380
+    },
+    {
+      "epoch": 1.1033994960434994,
+      "grad_norm": 47.90654373168945,
+      "learning_rate": 2.915876248826653e-05,
+      "loss": 0.5007,
+      "step": 390
+    },
+    {
+      "epoch": 1.1316917908138455,
+      "grad_norm": 48.12900924682617,
+      "learning_rate": 2.861068210138169e-05,
+      "loss": 0.4924,
+      "step": 400
+    },
+    {
+      "epoch": 1.1599840855841916,
+      "grad_norm": 45.788028717041016,
+      "learning_rate": 2.8054544915148163e-05,
+      "loss": 0.4999,
+      "step": 410
+    },
+    {
+      "epoch": 1.1882763803545378,
+      "grad_norm": 48.016265869140625,
+      "learning_rate": 2.7490871293187226e-05,
+      "loss": 0.4968,
+      "step": 420
+    },
+    {
+      "epoch": 1.2165686751248839,
+      "grad_norm": 47.503753662109375,
+      "learning_rate": 2.69201886507741e-05,
+      "loss": 0.4911,
+      "step": 430
+    },
+    {
+      "epoch": 1.24486096989523,
+      "grad_norm": 43.9008674621582,
+      "learning_rate": 2.6343030961348684e-05,
+      "loss": 0.4914,
+      "step": 440
+    },
+    {
+      "epoch": 1.2731532646655763,
+      "grad_norm": 51.55910110473633,
+      "learning_rate": 2.575993825689005e-05,
+      "loss": 0.4984,
+      "step": 450
+    },
+    {
+      "epoch": 1.3014455594359224,
+      "grad_norm": 46.89332962036133,
+      "learning_rate": 2.5171456122622006e-05,
+      "loss": 0.4913,
+      "step": 460
+    },
+    {
+      "epoch": 1.3297378542062686,
+      "grad_norm": 45.62400817871094,
+      "learning_rate": 2.4578135186522716e-05,
+      "loss": 0.4908,
+      "step": 470
+    },
+    {
+      "epoch": 1.3580301489766147,
+      "grad_norm": 43.19487380981445,
+      "learning_rate": 2.3980530604115896e-05,
+      "loss": 0.4899,
+      "step": 480
+    },
+    {
+      "epoch": 1.3863224437469608,
+      "grad_norm": 47.675411224365234,
+      "learning_rate": 2.337920153902571e-05,
+      "loss": 0.5022,
+      "step": 490
+    },
+    {
+      "epoch": 1.414614738517307,
+      "grad_norm": 46.81362533569336,
+      "learning_rate": 2.277471063978137e-05,
+      "loss": 0.497,
+      "step": 500
+    },
+    {
+      "epoch": 1.442907033287653,
+      "grad_norm": 43.024845123291016,
+      "learning_rate": 2.2167623513361045e-05,
+      "loss": 0.486,
+      "step": 510
+    },
+    {
+      "epoch": 1.4711993280579991,
+      "grad_norm": 48.46063995361328,
+      "learning_rate": 2.1558508195967576e-05,
+      "loss": 0.4925,
+      "step": 520
+    },
+    {
+      "epoch": 1.4994916228283452,
+      "grad_norm": 45.760868072509766,
+      "learning_rate": 2.0947934621531258e-05,
+      "loss": 0.4904,
+      "step": 530
+    },
+    {
+      "epoch": 1.5277839175986916,
+      "grad_norm": 50.22765350341797,
+      "learning_rate": 2.0336474088436904e-05,
+      "loss": 0.4893,
+      "step": 540
+    },
+    {
+      "epoch": 1.5560762123690375,
+      "grad_norm": 46.728614807128906,
+      "learning_rate": 1.9724698724974343e-05,
+      "loss": 0.4863,
+      "step": 550
+    },
+    {
+      "epoch": 1.5843685071393838,
+      "grad_norm": 47.76382064819336,
+      "learning_rate": 1.9113180954012247e-05,
+      "loss": 0.4944,
+      "step": 560
+    },
+    {
+      "epoch": 1.61266080190973,
+      "grad_norm": 49.77993392944336,
+      "learning_rate": 1.8502492957396484e-05,
+      "loss": 0.4774,
+      "step": 570
+    },
+    {
+      "epoch": 1.640953096680076,
+      "grad_norm": 46.18117904663086,
+      "learning_rate": 1.7893206140573852e-05,
+      "loss": 0.4694,
+      "step": 580
+    },
+    {
+      "epoch": 1.6692453914504222,
+      "grad_norm": 46.24747085571289,
+      "learning_rate": 1.7285890597942336e-05,
+      "loss": 0.4756,
+      "step": 590
+    },
+    {
+      "epoch": 1.6975376862207683,
+      "grad_norm": 46.43058776855469,
+      "learning_rate": 1.668111457942811e-05,
+      "loss": 0.4783,
+      "step": 600
+    },
+    {
+      "epoch": 1.7258299809911144,
+      "grad_norm": 46.958919525146484,
+      "learning_rate": 1.607944395878828e-05,
+      "loss": 0.4776,
+      "step": 610
+    },
+    {
+      "epoch": 1.7541222757614605,
+      "grad_norm": 42.604576110839844,
+      "learning_rate": 1.548144170413705e-05,
+      "loss": 0.4751,
+      "step": 620
+    },
+    {
+      "epoch": 1.7824145705318069,
+      "grad_norm": 46.214046478271484,
+      "learning_rate": 1.4887667351190508e-05,
+      "loss": 0.4736,
+      "step": 630
+    },
+    {
+      "epoch": 1.8107068653021527,
+      "grad_norm": 46.578739166259766,
+      "learning_rate": 1.4298676479723158e-05,
+      "loss": 0.4765,
+      "step": 640
+    },
+    {
+      "epoch": 1.838999160072499,
+      "grad_norm": 49.75358581542969,
+      "learning_rate": 1.3715020193725801e-05,
+      "loss": 0.4639,
+      "step": 650
+    },
+    {
+      "epoch": 1.867291454842845,
+      "grad_norm": 49.36628341674805,
+      "learning_rate": 1.3137244605751364e-05,
+      "loss": 0.4865,
+      "step": 660
+    },
+    {
+      "epoch": 1.8955837496131913,
+      "grad_norm": 49.271121978759766,
+      "learning_rate": 1.2565890325931096e-05,
+      "loss": 0.4635,
+      "step": 670
+    },
+    {
+      "epoch": 1.9238760443835374,
+      "grad_norm": 42.75962829589844,
+      "learning_rate": 1.2001491956139177e-05,
+      "loss": 0.4753,
+      "step": 680
+    },
+    {
+      "epoch": 1.9521683391538835,
+      "grad_norm": 44.49867630004883,
+      "learning_rate": 1.1444577589779206e-05,
+      "loss": 0.4657,
+      "step": 690
+    },
+    {
+      "epoch": 1.9804606339242297,
+      "grad_norm": 46.07305908203125,
+      "learning_rate": 1.0895668317660404e-05,
+      "loss": 0.4668,
+      "step": 700
+    },
+    {
+      "epoch": 2.008752928694576,
+      "grad_norm": 53.604557037353516,
+      "learning_rate": 1.0355277740426017e-05,
+      "loss": 0.444,
+      "step": 710
+    },
+    {
+      "epoch": 2.037045223464922,
+      "grad_norm": 52.05387878417969,
+      "learning_rate": 9.823911487990083e-06,
+      "loss": 0.3918,
+      "step": 720
+    },
+    {
+      "epoch": 2.065337518235268,
+      "grad_norm": 52.156349182128906,
+      "learning_rate": 9.302066746432183e-06,
+      "loss": 0.387,
+      "step": 730
+    },
+    {
+      "epoch": 2.0936298130056143,
+      "grad_norm": 51.72985076904297,
+      "learning_rate": 8.790231792792914e-06,
+      "loss": 0.3875,
+      "step": 740
+    },
+    {
+      "epoch": 2.1219221077759602,
+      "grad_norm": 53.109046936035156,
+      "learning_rate": 8.28888553820526e-06,
+      "loss": 0.3921,
+      "step": 750
+    },
+    {
+      "epoch": 2.1502144025463066,
+      "grad_norm": 51.85807418823242,
+      "learning_rate": 7.798497079789513e-06,
+      "loss": 0.3933,
+      "step": 760
+    },
+    {
+      "epoch": 2.1785066973166525,
+      "grad_norm": 53.21246337890625,
+      "learning_rate": 7.319525261730822e-06,
+      "loss": 0.3889,
+      "step": 770
+    },
+    {
+      "epoch": 2.206798992086999,
+      "grad_norm": 52.26942443847656,
+      "learning_rate": 6.852418245950195e-06,
+      "loss": 0.3938,
+      "step": 780
+    },
+    {
+      "epoch": 2.235091286857345,
+      "grad_norm": 52.105838775634766,
+      "learning_rate": 6.397613092770641e-06,
+      "loss": 0.3934,
+      "step": 790
+    },
+    {
+      "epoch": 2.263383581627691,
+      "grad_norm": 50.32993698120117,
+      "learning_rate": 5.955535351970754e-06,
+      "loss": 0.3884,
+      "step": 800
+    },
+    {
+      "epoch": 2.2916758763980374,
+      "grad_norm": 52.58189392089844,
+      "learning_rate": 5.5265986646085e-06,
+      "loss": 0.3894,
+      "step": 810
+    },
+    {
+      "epoch": 2.3199681711683833,
+      "grad_norm": 51.35353469848633,
+      "learning_rate": 5.111204375987615e-06,
+      "loss": 0.385,
+      "step": 820
+    },
+    {
+      "epoch": 2.3482604659387296,
+      "grad_norm": 52.65754318237305,
+      "learning_rate": 4.709741160128878e-06,
+      "loss": 0.372,
+      "step": 830
+    },
+    {
+      "epoch": 2.3765527607090755,
+      "grad_norm": 52.932281494140625,
+      "learning_rate": 4.322584656097577e-06,
+      "loss": 0.3782,
+      "step": 840
+    },
+    {
+      "epoch": 2.404845055479422,
+      "grad_norm": 48.66704177856445,
+      "learning_rate": 3.950097116527449e-06,
+      "loss": 0.3919,
+      "step": 850
+    },
+    {
+      "epoch": 2.4331373502497677,
+      "grad_norm": 52.752803802490234,
+      "learning_rate": 3.592627068669983e-06,
+      "loss": 0.3823,
+      "step": 860
+    },
+    {
+      "epoch": 2.461429645020114,
+      "grad_norm": 52.2065544128418,
+      "learning_rate": 3.2505089882861964e-06,
+      "loss": 0.3767,
+      "step": 870
+    },
+    {
+      "epoch": 2.48972193979046,
+      "grad_norm": 50.5092887878418,
+      "learning_rate": 2.9240629866860538e-06,
+      "loss": 0.3719,
+      "step": 880
+    },
+    {
+      "epoch": 2.5180142345608063,
+      "grad_norm": 54.0071907043457,
+      "learning_rate": 2.6135945112083506e-06,
+      "loss": 0.3793,
+      "step": 890
+    },
+    {
+      "epoch": 2.5463065293311526,
+      "grad_norm": 51.075164794921875,
+      "learning_rate": 2.3193940594212917e-06,
+      "loss": 0.3789,
+      "step": 900
+    },
+    {
+      "epoch": 2.5745988241014985,
+      "grad_norm": 53.48076629638672,
+      "learning_rate": 2.0417369073111936e-06,
+      "loss": 0.3817,
+      "step": 910
+    },
+    {
+      "epoch": 2.602891118871845,
+      "grad_norm": 54.31864929199219,
+      "learning_rate": 1.7808828517136612e-06,
+      "loss": 0.3857,
+      "step": 920
+    },
+    {
+      "epoch": 2.6311834136421908,
+      "grad_norm": 51.0897216796875,
+      "learning_rate": 1.5370759672281744e-06,
+      "loss": 0.3776,
+      "step": 930
+    },
+    {
+      "epoch": 2.659475708412537,
+      "grad_norm": 53.861427307128906,
+      "learning_rate": 1.3105443778436388e-06,
+      "loss": 0.3766,
+      "step": 940
+    },
+    {
+      "epoch": 2.687768003182883,
+      "grad_norm": 49.185302734375,
+      "learning_rate": 1.1015000434884682e-06,
+      "loss": 0.384,
+      "step": 950
+    },
+    {
+      "epoch": 2.7160602979532293,
+      "grad_norm": 53.21417999267578,
+      "learning_rate": 9.101385617050007e-07,
+      "loss": 0.3723,
+      "step": 960
+    },
+    {
+      "epoch": 2.7443525927235752,
+      "grad_norm": 54.70134353637695,
+      "learning_rate": 7.366389846337841e-07,
+      "loss": 0.3815,
+      "step": 970
+    },
+    {
+      "epoch": 2.7726448874939216,
+      "grad_norm": 53.2882194519043,
+      "learning_rate": 5.811636514789598e-07,
+      "loss": 0.3806,
+      "step": 980
+    },
+    {
+      "epoch": 2.800937182264268,
+      "grad_norm": 52.69584274291992,
+      "learning_rate": 4.43858036611573e-07,
+      "loss": 0.3814,
+      "step": 990
+    },
+    {
+      "epoch": 2.829229477034614,
+      "grad_norm": 55.783634185791016,
+      "learning_rate": 3.2485061345282286e-07,
+      "loss": 0.3838,
+      "step": 1000
+    },
+    {
+      "epoch": 2.85752177180496,
+      "grad_norm": 49.773502349853516,
+      "learning_rate": 2.2425273426471162e-07,
+      "loss": 0.3829,
+      "step": 1010
+    },
+    {
+      "epoch": 2.885814066575306,
+      "grad_norm": 50.421417236328125,
+      "learning_rate": 1.421585259605318e-07,
+      "loss": 0.3802,
+      "step": 1020
+    },
+    {
+      "epoch": 2.9141063613456524,
+      "grad_norm": 56.082252502441406,
+      "learning_rate": 7.864480203266356e-08,
+      "loss": 0.3815,
+      "step": 1030
+    },
+    {
+      "epoch": 2.9423986561159983,
+      "grad_norm": 52.35788345336914,
+      "learning_rate": 3.37709906801198e-08,
+      "loss": 0.3846,
+      "step": 1040
+    },
+    {
+      "epoch": 2.9706909508863446,
+      "grad_norm": 51.95500564575195,
+      "learning_rate": 7.579079203074991e-09,
+      "loss": 0.3727,
+      "step": 1050
+    },
+    {
+      "epoch": 2.996154016179656,
+      "step": 1059,
+      "total_flos": 9.569143748664361e+17,
+      "train_loss": 0.5005588545002275,
+      "train_runtime": 18779.252,
+      "train_samples_per_second": 7.227,
+      "train_steps_per_second": 0.056
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1059,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.569143748664361e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41af23b2587193d2b8b4bb7a5278d799739d44dae9cc2f64568bfb087a9fdb5c
+size 5304