Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9690721649484537,
+    "total_flos": 1.8527734203290747e+18,
+    "train_loss": 0.5522520401411586,
+    "train_runtime": 15811.9484,
+    "train_samples_per_second": 2.351,
+    "train_steps_per_second": 0.005
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/leonardo_work/EUHPC_E03_068/eguha/models_cache/Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:227bb287c568da8d89c38b2f905fa26ca2a0a3b257e5d2cd1da5f79b326413e1
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cf4eb069beeb535fff7dacd507b4546a1a96af5e4dc76641b4d105a01f9fe00
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bae07a449c06a6f69bff388b655a5484df65e1fbd3a76cce57dbaa704d7771d0
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cf734729d1861b641be819c19663122397ea3d0a364ec3c70af77f8e866d04c
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9690721649484537,
+    "total_flos": 1.8527734203290747e+18,
+    "train_loss": 0.5522520401411586,
+    "train_runtime": 15811.9484,
+    "train_samples_per_second": 2.351,
+    "train_steps_per_second": 0.005
+}

trainer_log.jsonl

@@ -0,0 +1,73 @@
+{"current_steps": 1, "total_steps": 72, "loss": 0.8792, "lr": 1e-05, "epoch": 0.041237113402061855, "percentage": 1.39, "elapsed_time": "0:04:17", "remaining_time": "5:04:36"}
+{"current_steps": 2, "total_steps": 72, "loss": 0.8614, "lr": 2e-05, "epoch": 0.08247422680412371, "percentage": 2.78, "elapsed_time": "0:07:53", "remaining_time": "4:36:07"}
+{"current_steps": 3, "total_steps": 72, "loss": 0.7805, "lr": 3.0000000000000004e-05, "epoch": 0.12371134020618557, "percentage": 4.17, "elapsed_time": "0:11:31", "remaining_time": "4:25:09"}
+{"current_steps": 4, "total_steps": 72, "loss": 0.814, "lr": 4e-05, "epoch": 0.16494845360824742, "percentage": 5.56, "elapsed_time": "0:15:09", "remaining_time": "4:17:40"}
+{"current_steps": 5, "total_steps": 72, "loss": 0.9298, "lr": 5e-05, "epoch": 0.20618556701030927, "percentage": 6.94, "elapsed_time": "0:18:46", "remaining_time": "4:11:30"}
+{"current_steps": 6, "total_steps": 72, "loss": 0.8568, "lr": 6.000000000000001e-05, "epoch": 0.24742268041237114, "percentage": 8.33, "elapsed_time": "0:22:23", "remaining_time": "4:06:14"}
+{"current_steps": 7, "total_steps": 72, "loss": 0.7715, "lr": 7.000000000000001e-05, "epoch": 0.28865979381443296, "percentage": 9.72, "elapsed_time": "0:26:00", "remaining_time": "4:01:32"}
+{"current_steps": 8, "total_steps": 72, "loss": 0.7178, "lr": 8e-05, "epoch": 0.32989690721649484, "percentage": 11.11, "elapsed_time": "0:29:38", "remaining_time": "3:57:10"}
+{"current_steps": 9, "total_steps": 72, "loss": 0.7012, "lr": 7.99518182482069e-05, "epoch": 0.3711340206185567, "percentage": 12.5, "elapsed_time": "0:33:17", "remaining_time": "3:53:00"}
+{"current_steps": 10, "total_steps": 72, "loss": 0.7192, "lr": 7.980738906688788e-05, "epoch": 0.41237113402061853, "percentage": 13.89, "elapsed_time": "0:36:55", "remaining_time": "3:48:53"}
+{"current_steps": 11, "total_steps": 72, "loss": 0.668, "lr": 7.956706039859124e-05, "epoch": 0.4536082474226804, "percentage": 15.28, "elapsed_time": "0:40:33", "remaining_time": "3:44:55"}
+{"current_steps": 12, "total_steps": 72, "loss": 0.6467, "lr": 7.923141121612922e-05, "epoch": 0.4948453608247423, "percentage": 16.67, "elapsed_time": "0:44:01", "remaining_time": "3:40:08"}
+{"current_steps": 13, "total_steps": 72, "loss": 0.6382, "lr": 7.880125012778177e-05, "epoch": 0.5360824742268041, "percentage": 18.06, "elapsed_time": "0:47:25", "remaining_time": "3:35:12"}
+{"current_steps": 14, "total_steps": 72, "loss": 0.6351, "lr": 7.827761342928836e-05, "epoch": 0.5773195876288659, "percentage": 19.44, "elapsed_time": "0:51:04", "remaining_time": "3:31:34"}
+{"current_steps": 15, "total_steps": 72, "loss": 0.6166, "lr": 7.766176260732084e-05, "epoch": 0.6185567010309279, "percentage": 20.83, "elapsed_time": "0:54:42", "remaining_time": "3:27:52"}
+{"current_steps": 16, "total_steps": 72, "loss": 0.6185, "lr": 7.695518130045147e-05, "epoch": 0.6597938144329897, "percentage": 22.22, "elapsed_time": "0:58:19", "remaining_time": "3:24:08"}
+{"current_steps": 17, "total_steps": 72, "loss": 0.5974, "lr": 7.615957172493774e-05, "epoch": 0.7010309278350515, "percentage": 23.61, "elapsed_time": "1:01:56", "remaining_time": "3:20:23"}
+{"current_steps": 18, "total_steps": 72, "loss": 0.6219, "lr": 7.52768505739342e-05, "epoch": 0.7422680412371134, "percentage": 25.0, "elapsed_time": "1:05:33", "remaining_time": "3:16:39"}
+{"current_steps": 19, "total_steps": 72, "loss": 0.5906, "lr": 7.430914440001089e-05, "epoch": 0.7835051546391752, "percentage": 26.39, "elapsed_time": "1:09:11", "remaining_time": "3:13:00"}
+{"current_steps": 20, "total_steps": 72, "loss": 0.5944, "lr": 7.325878449210182e-05, "epoch": 0.8247422680412371, "percentage": 27.78, "elapsed_time": "1:12:48", "remaining_time": "3:09:18"}
+{"current_steps": 21, "total_steps": 72, "loss": 0.5681, "lr": 7.21283012592258e-05, "epoch": 0.865979381443299, "percentage": 29.17, "elapsed_time": "1:16:28", "remaining_time": "3:05:42"}
+{"current_steps": 22, "total_steps": 72, "loss": 0.569, "lr": 7.092041813450948e-05, "epoch": 0.9072164948453608, "percentage": 30.56, "elapsed_time": "1:20:07", "remaining_time": "3:02:06"}
+{"current_steps": 23, "total_steps": 72, "loss": 0.5688, "lr": 6.963804501419837e-05, "epoch": 0.9484536082474226, "percentage": 31.94, "elapsed_time": "1:23:46", "remaining_time": "2:58:28"}
+{"current_steps": 24, "total_steps": 72, "loss": 0.5538, "lr": 6.828427124746191e-05, "epoch": 0.9896907216494846, "percentage": 33.33, "elapsed_time": "1:27:21", "remaining_time": "2:54:42"}
+{"current_steps": 25, "total_steps": 72, "loss": 0.5439, "lr": 6.686235819388075e-05, "epoch": 1.0309278350515463, "percentage": 34.72, "elapsed_time": "1:31:50", "remaining_time": "2:52:40"}
+{"current_steps": 26, "total_steps": 72, "loss": 0.5383, "lr": 6.537573136654582e-05, "epoch": 1.0721649484536082, "percentage": 36.11, "elapsed_time": "1:35:24", "remaining_time": "2:48:47"}
+{"current_steps": 27, "total_steps": 72, "loss": 0.5447, "lr": 6.382797217969734e-05, "epoch": 1.1134020618556701, "percentage": 37.5, "elapsed_time": "1:39:01", "remaining_time": "2:45:02"}
+{"current_steps": 28, "total_steps": 72, "loss": 0.5319, "lr": 6.22228093207841e-05, "epoch": 1.1546391752577319, "percentage": 38.89, "elapsed_time": "1:42:39", "remaining_time": "2:41:19"}
+{"current_steps": 29, "total_steps": 72, "loss": 0.537, "lr": 6.056410976772887e-05, "epoch": 1.1958762886597938, "percentage": 40.28, "elapsed_time": "1:46:21", "remaining_time": "2:37:41"}
+{"current_steps": 30, "total_steps": 72, "loss": 0.5224, "lr": 5.8855869473039924e-05, "epoch": 1.2371134020618557, "percentage": 41.67, "elapsed_time": "1:50:00", "remaining_time": "2:34:00"}
+{"current_steps": 31, "total_steps": 72, "loss": 0.511, "lr": 5.710220373721129e-05, "epoch": 1.2783505154639174, "percentage": 43.06, "elapsed_time": "1:53:39", "remaining_time": "2:30:18"}
+{"current_steps": 32, "total_steps": 72, "loss": 0.518, "lr": 5.5307337294603595e-05, "epoch": 1.3195876288659794, "percentage": 44.44, "elapsed_time": "1:57:18", "remaining_time": "2:26:37"}
+{"current_steps": 33, "total_steps": 72, "loss": 0.5119, "lr": 5.347559413568881e-05, "epoch": 1.3608247422680413, "percentage": 45.83, "elapsed_time": "2:00:55", "remaining_time": "2:22:54"}
+{"current_steps": 34, "total_steps": 72, "loss": 0.5117, "lr": 5.16113870901785e-05, "epoch": 1.402061855670103, "percentage": 47.22, "elapsed_time": "2:04:33", "remaining_time": "2:19:13"}
+{"current_steps": 35, "total_steps": 72, "loss": 0.5076, "lr": 4.971920719613056e-05, "epoch": 1.443298969072165, "percentage": 48.61, "elapsed_time": "2:08:11", "remaining_time": "2:15:31"}
+{"current_steps": 36, "total_steps": 72, "loss": 0.503, "lr": 4.780361288064514e-05, "epoch": 1.4845360824742269, "percentage": 50.0, "elapsed_time": "2:11:53", "remaining_time": "2:11:53"}
+{"current_steps": 37, "total_steps": 72, "loss": 0.5098, "lr": 4.586921897821447e-05, "epoch": 1.5257731958762886, "percentage": 51.39, "elapsed_time": "2:15:23", "remaining_time": "2:08:04"}
+{"current_steps": 38, "total_steps": 72, "loss": 0.4945, "lr": 4.392068561318244e-05, "epoch": 1.5670103092783505, "percentage": 52.78, "elapsed_time": "2:18:49", "remaining_time": "2:04:12"}
+{"current_steps": 39, "total_steps": 72, "loss": 0.4953, "lr": 4.1962706973096726e-05, "epoch": 1.6082474226804124, "percentage": 54.17, "elapsed_time": "2:22:27", "remaining_time": "2:00:32"}
+{"current_steps": 40, "total_steps": 72, "loss": 0.501, "lr": 4e-05, "epoch": 1.6494845360824741, "percentage": 55.56, "elapsed_time": "2:26:05", "remaining_time": "1:56:52"}
+{"current_steps": 41, "total_steps": 72, "loss": 0.4918, "lr": 3.803729302690328e-05, "epoch": 1.690721649484536, "percentage": 56.94, "elapsed_time": "2:29:41", "remaining_time": "1:53:11"}
+{"current_steps": 42, "total_steps": 72, "loss": 0.4852, "lr": 3.6079314386817575e-05, "epoch": 1.731958762886598, "percentage": 58.33, "elapsed_time": "2:33:18", "remaining_time": "1:49:30"}
+{"current_steps": 43, "total_steps": 72, "loss": 0.4897, "lr": 3.4130781021785535e-05, "epoch": 1.7731958762886597, "percentage": 59.72, "elapsed_time": "2:36:56", "remaining_time": "1:45:50"}
+{"current_steps": 44, "total_steps": 72, "loss": 0.4919, "lr": 3.219638711935488e-05, "epoch": 1.8144329896907216, "percentage": 61.11, "elapsed_time": "2:40:33", "remaining_time": "1:42:10"}
+{"current_steps": 45, "total_steps": 72, "loss": 0.4846, "lr": 3.028079280386945e-05, "epoch": 1.8556701030927836, "percentage": 62.5, "elapsed_time": "2:44:10", "remaining_time": "1:38:30"}
+{"current_steps": 46, "total_steps": 72, "loss": 0.4865, "lr": 2.8388612909821515e-05, "epoch": 1.8969072164948453, "percentage": 63.89, "elapsed_time": "2:47:47", "remaining_time": "1:34:50"}
+{"current_steps": 47, "total_steps": 72, "loss": 0.4828, "lr": 2.6524405864311203e-05, "epoch": 1.9381443298969072, "percentage": 65.28, "elapsed_time": "2:51:24", "remaining_time": "1:31:10"}
+{"current_steps": 48, "total_steps": 72, "loss": 0.4896, "lr": 2.4692662705396412e-05, "epoch": 1.9793814432989691, "percentage": 66.67, "elapsed_time": "2:55:01", "remaining_time": "1:27:30"}
+{"current_steps": 49, "total_steps": 72, "loss": 0.4781, "lr": 2.2897796262788728e-05, "epoch": 2.020618556701031, "percentage": 68.06, "elapsed_time": "2:59:40", "remaining_time": "1:24:20"}
+{"current_steps": 50, "total_steps": 72, "loss": 0.4651, "lr": 2.1144130526960093e-05, "epoch": 2.0618556701030926, "percentage": 69.44, "elapsed_time": "3:03:17", "remaining_time": "1:20:38"}
+{"current_steps": 51, "total_steps": 72, "loss": 0.4684, "lr": 1.9435890232271136e-05, "epoch": 2.1030927835051547, "percentage": 70.83, "elapsed_time": "3:06:54", "remaining_time": "1:16:57"}
+{"current_steps": 52, "total_steps": 72, "loss": 0.4625, "lr": 1.7777190679215923e-05, "epoch": 2.1443298969072164, "percentage": 72.22, "elapsed_time": "3:10:32", "remaining_time": "1:13:17"}
+{"current_steps": 53, "total_steps": 72, "loss": 0.4694, "lr": 1.617202782030267e-05, "epoch": 2.1855670103092786, "percentage": 73.61, "elapsed_time": "3:14:11", "remaining_time": "1:09:36"}
+{"current_steps": 54, "total_steps": 72, "loss": 0.4671, "lr": 1.4624268633454187e-05, "epoch": 2.2268041237113403, "percentage": 75.0, "elapsed_time": "3:17:48", "remaining_time": "1:05:56"}
+{"current_steps": 55, "total_steps": 72, "loss": 0.4519, "lr": 1.3137641806119264e-05, "epoch": 2.268041237113402, "percentage": 76.39, "elapsed_time": "3:21:24", "remaining_time": "1:02:15"}
+{"current_steps": 56, "total_steps": 72, "loss": 0.4659, "lr": 1.1715728752538103e-05, "epoch": 2.3092783505154637, "percentage": 77.78, "elapsed_time": "3:25:01", "remaining_time": "0:58:34"}
+{"current_steps": 57, "total_steps": 72, "loss": 0.4603, "lr": 1.0361954985801646e-05, "epoch": 2.350515463917526, "percentage": 79.17, "elapsed_time": "3:28:37", "remaining_time": "0:54:54"}
+{"current_steps": 58, "total_steps": 72, "loss": 0.4613, "lr": 9.07958186549052e-06, "epoch": 2.3917525773195876, "percentage": 80.56, "elapsed_time": "3:32:12", "remaining_time": "0:51:13"}
+{"current_steps": 59, "total_steps": 72, "loss": 0.46, "lr": 7.871698740774208e-06, "epoch": 2.4329896907216497, "percentage": 81.94, "elapsed_time": "3:35:48", "remaining_time": "0:47:32"}
+{"current_steps": 60, "total_steps": 72, "loss": 0.458, "lr": 6.7412155078981865e-06, "epoch": 2.4742268041237114, "percentage": 83.33, "elapsed_time": "3:39:18", "remaining_time": "0:43:51"}
+{"current_steps": 61, "total_steps": 72, "loss": 0.456, "lr": 5.690855599989121e-06, "epoch": 2.515463917525773, "percentage": 84.72, "elapsed_time": "3:42:48", "remaining_time": "0:40:10"}
+{"current_steps": 62, "total_steps": 72, "loss": 0.4533, "lr": 4.723149426065803e-06, "epoch": 2.556701030927835, "percentage": 86.11, "elapsed_time": "3:46:24", "remaining_time": "0:36:30"}
+{"current_steps": 63, "total_steps": 72, "loss": 0.4668, "lr": 3.840428275062267e-06, "epoch": 2.597938144329897, "percentage": 87.5, "elapsed_time": "3:49:59", "remaining_time": "0:32:51"}
+{"current_steps": 64, "total_steps": 72, "loss": 0.4556, "lr": 3.0448186995485307e-06, "epoch": 2.6391752577319587, "percentage": 88.89, "elapsed_time": "3:53:35", "remaining_time": "0:29:11"}
+{"current_steps": 65, "total_steps": 72, "loss": 0.4621, "lr": 2.3382373926791722e-06, "epoch": 2.680412371134021, "percentage": 90.28, "elapsed_time": "3:57:11", "remaining_time": "0:25:32"}
+{"current_steps": 66, "total_steps": 72, "loss": 0.4479, "lr": 1.7223865707116472e-06, "epoch": 2.7216494845360826, "percentage": 91.67, "elapsed_time": "4:00:48", "remaining_time": "0:21:53"}
+{"current_steps": 67, "total_steps": 72, "loss": 0.4554, "lr": 1.1987498722182411e-06, "epoch": 2.7628865979381443, "percentage": 93.06, "elapsed_time": "4:04:24", "remaining_time": "0:18:14"}
+{"current_steps": 68, "total_steps": 72, "loss": 0.4546, "lr": 7.685887838707828e-07, "epoch": 2.804123711340206, "percentage": 94.44, "elapsed_time": "4:08:00", "remaining_time": "0:14:35"}
+{"current_steps": 69, "total_steps": 72, "loss": 0.4593, "lr": 4.3293960140875946e-07, "epoch": 2.845360824742268, "percentage": 95.83, "elapsed_time": "4:11:37", "remaining_time": "0:10:56"}
+{"current_steps": 70, "total_steps": 72, "loss": 0.4613, "lr": 1.926109331121273e-07, "epoch": 2.88659793814433, "percentage": 97.22, "elapsed_time": "4:15:13", "remaining_time": "0:07:17"}
+{"current_steps": 71, "total_steps": 72, "loss": 0.4534, "lr": 4.8181751793103806e-08, "epoch": 2.927835051546392, "percentage": 98.61, "elapsed_time": "4:18:43", "remaining_time": "0:03:38"}
+{"current_steps": 72, "total_steps": 72, "loss": 0.4659, "lr": 0.0, "epoch": 2.9690721649484537, "percentage": 100.0, "elapsed_time": "4:22:16", "remaining_time": "0:00:00"}
+{"current_steps": 72, "total_steps": 72, "epoch": 2.9690721649484537, "percentage": 100.0, "elapsed_time": "4:23:24", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,546 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9690721649484537,
+  "eval_steps": 500,
+  "global_step": 72,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.041237113402061855,
+      "grad_norm": 5.915778602285194,
+      "learning_rate": 1e-05,
+      "loss": 0.8792,
+      "step": 1
+    },
+    {
+      "epoch": 0.08247422680412371,
+      "grad_norm": 5.8603827031333084,
+      "learning_rate": 2e-05,
+      "loss": 0.8614,
+      "step": 2
+    },
+    {
+      "epoch": 0.12371134020618557,
+      "grad_norm": 2.389431167985615,
+      "learning_rate": 3.0000000000000004e-05,
+      "loss": 0.7805,
+      "step": 3
+    },
+    {
+      "epoch": 0.16494845360824742,
+      "grad_norm": 6.417214780576867,
+      "learning_rate": 4e-05,
+      "loss": 0.814,
+      "step": 4
+    },
+    {
+      "epoch": 0.20618556701030927,
+      "grad_norm": 11.939221948728905,
+      "learning_rate": 5e-05,
+      "loss": 0.9298,
+      "step": 5
+    },
+    {
+      "epoch": 0.24742268041237114,
+      "grad_norm": 6.9814740650793325,
+      "learning_rate": 6.000000000000001e-05,
+      "loss": 0.8568,
+      "step": 6
+    },
+    {
+      "epoch": 0.28865979381443296,
+      "grad_norm": 3.6246783341840567,
+      "learning_rate": 7.000000000000001e-05,
+      "loss": 0.7715,
+      "step": 7
+    },
+    {
+      "epoch": 0.32989690721649484,
+      "grad_norm": 3.6153784587221103,
+      "learning_rate": 8e-05,
+      "loss": 0.7178,
+      "step": 8
+    },
+    {
+      "epoch": 0.3711340206185567,
+      "grad_norm": 2.8561476958479033,
+      "learning_rate": 7.99518182482069e-05,
+      "loss": 0.7012,
+      "step": 9
+    },
+    {
+      "epoch": 0.41237113402061853,
+      "grad_norm": 4.7389040141058745,
+      "learning_rate": 7.980738906688788e-05,
+      "loss": 0.7192,
+      "step": 10
+    },
+    {
+      "epoch": 0.4536082474226804,
+      "grad_norm": 1.851735179019456,
+      "learning_rate": 7.956706039859124e-05,
+      "loss": 0.668,
+      "step": 11
+    },
+    {
+      "epoch": 0.4948453608247423,
+      "grad_norm": 2.566052664304911,
+      "learning_rate": 7.923141121612922e-05,
+      "loss": 0.6467,
+      "step": 12
+    },
+    {
+      "epoch": 0.5360824742268041,
+      "grad_norm": 2.109709868788535,
+      "learning_rate": 7.880125012778177e-05,
+      "loss": 0.6382,
+      "step": 13
+    },
+    {
+      "epoch": 0.5773195876288659,
+      "grad_norm": 1.1642435087248661,
+      "learning_rate": 7.827761342928836e-05,
+      "loss": 0.6351,
+      "step": 14
+    },
+    {
+      "epoch": 0.6185567010309279,
+      "grad_norm": 1.6106209130732594,
+      "learning_rate": 7.766176260732084e-05,
+      "loss": 0.6166,
+      "step": 15
+    },
+    {
+      "epoch": 0.6597938144329897,
+      "grad_norm": 1.6043870099285942,
+      "learning_rate": 7.695518130045147e-05,
+      "loss": 0.6185,
+      "step": 16
+    },
+    {
+      "epoch": 0.7010309278350515,
+      "grad_norm": 1.293862536715366,
+      "learning_rate": 7.615957172493774e-05,
+      "loss": 0.5974,
+      "step": 17
+    },
+    {
+      "epoch": 0.7422680412371134,
+      "grad_norm": 2.2409334842691684,
+      "learning_rate": 7.52768505739342e-05,
+      "loss": 0.6219,
+      "step": 18
+    },
+    {
+      "epoch": 0.7835051546391752,
+      "grad_norm": 1.4417193913598108,
+      "learning_rate": 7.430914440001089e-05,
+      "loss": 0.5906,
+      "step": 19
+    },
+    {
+      "epoch": 0.8247422680412371,
+      "grad_norm": 1.3514593246304274,
+      "learning_rate": 7.325878449210182e-05,
+      "loss": 0.5944,
+      "step": 20
+    },
+    {
+      "epoch": 0.865979381443299,
+      "grad_norm": 1.363145184880837,
+      "learning_rate": 7.21283012592258e-05,
+      "loss": 0.5681,
+      "step": 21
+    },
+    {
+      "epoch": 0.9072164948453608,
+      "grad_norm": 1.2754755318969895,
+      "learning_rate": 7.092041813450948e-05,
+      "loss": 0.569,
+      "step": 22
+    },
+    {
+      "epoch": 0.9484536082474226,
+      "grad_norm": 0.915459394115844,
+      "learning_rate": 6.963804501419837e-05,
+      "loss": 0.5688,
+      "step": 23
+    },
+    {
+      "epoch": 0.9896907216494846,
+      "grad_norm": 1.1109562944094746,
+      "learning_rate": 6.828427124746191e-05,
+      "loss": 0.5538,
+      "step": 24
+    },
+    {
+      "epoch": 1.0309278350515463,
+      "grad_norm": 0.8680910496687467,
+      "learning_rate": 6.686235819388075e-05,
+      "loss": 0.5439,
+      "step": 25
+    },
+    {
+      "epoch": 1.0721649484536082,
+      "grad_norm": 1.2171423374867043,
+      "learning_rate": 6.537573136654582e-05,
+      "loss": 0.5383,
+      "step": 26
+    },
+    {
+      "epoch": 1.1134020618556701,
+      "grad_norm": 1.0157065682371955,
+      "learning_rate": 6.382797217969734e-05,
+      "loss": 0.5447,
+      "step": 27
+    },
+    {
+      "epoch": 1.1546391752577319,
+      "grad_norm": 0.7994213284155107,
+      "learning_rate": 6.22228093207841e-05,
+      "loss": 0.5319,
+      "step": 28
+    },
+    {
+      "epoch": 1.1958762886597938,
+      "grad_norm": 0.8988540949081338,
+      "learning_rate": 6.056410976772887e-05,
+      "loss": 0.537,
+      "step": 29
+    },
+    {
+      "epoch": 1.2371134020618557,
+      "grad_norm": 1.045458971592603,
+      "learning_rate": 5.8855869473039924e-05,
+      "loss": 0.5224,
+      "step": 30
+    },
+    {
+      "epoch": 1.2783505154639174,
+      "grad_norm": 0.5299013843819147,
+      "learning_rate": 5.710220373721129e-05,
+      "loss": 0.511,
+      "step": 31
+    },
+    {
+      "epoch": 1.3195876288659794,
+      "grad_norm": 0.9465183460092941,
+      "learning_rate": 5.5307337294603595e-05,
+      "loss": 0.518,
+      "step": 32
+    },
+    {
+      "epoch": 1.3608247422680413,
+      "grad_norm": 0.9065353984406849,
+      "learning_rate": 5.347559413568881e-05,
+      "loss": 0.5119,
+      "step": 33
+    },
+    {
+      "epoch": 1.402061855670103,
+      "grad_norm": 0.5286929584512716,
+      "learning_rate": 5.16113870901785e-05,
+      "loss": 0.5117,
+      "step": 34
+    },
+    {
+      "epoch": 1.443298969072165,
+      "grad_norm": 0.892318482543648,
+      "learning_rate": 4.971920719613056e-05,
+      "loss": 0.5076,
+      "step": 35
+    },
+    {
+      "epoch": 1.4845360824742269,
+      "grad_norm": 0.4717303094088032,
+      "learning_rate": 4.780361288064514e-05,
+      "loss": 0.503,
+      "step": 36
+    },
+    {
+      "epoch": 1.5257731958762886,
+      "grad_norm": 0.7191312321422306,
+      "learning_rate": 4.586921897821447e-05,
+      "loss": 0.5098,
+      "step": 37
+    },
+    {
+      "epoch": 1.5670103092783505,
+      "grad_norm": 0.47146206682277086,
+      "learning_rate": 4.392068561318244e-05,
+      "loss": 0.4945,
+      "step": 38
+    },
+    {
+      "epoch": 1.6082474226804124,
+      "grad_norm": 0.7403012163582166,
+      "learning_rate": 4.1962706973096726e-05,
+      "loss": 0.4953,
+      "step": 39
+    },
+    {
+      "epoch": 1.6494845360824741,
+      "grad_norm": 0.4223331865451386,
+      "learning_rate": 4e-05,
+      "loss": 0.501,
+      "step": 40
+    },
+    {
+      "epoch": 1.690721649484536,
+      "grad_norm": 0.6840090672209329,
+      "learning_rate": 3.803729302690328e-05,
+      "loss": 0.4918,
+      "step": 41
+    },
+    {
+      "epoch": 1.731958762886598,
+      "grad_norm": 0.4650006670070441,
+      "learning_rate": 3.6079314386817575e-05,
+      "loss": 0.4852,
+      "step": 42
+    },
+    {
+      "epoch": 1.7731958762886597,
+      "grad_norm": 0.4894585869827011,
+      "learning_rate": 3.4130781021785535e-05,
+      "loss": 0.4897,
+      "step": 43
+    },
+    {
+      "epoch": 1.8144329896907216,
+      "grad_norm": 0.47462294184562975,
+      "learning_rate": 3.219638711935488e-05,
+      "loss": 0.4919,
+      "step": 44
+    },
+    {
+      "epoch": 1.8556701030927836,
+      "grad_norm": 0.33553667803311904,
+      "learning_rate": 3.028079280386945e-05,
+      "loss": 0.4846,
+      "step": 45
+    },
+    {
+      "epoch": 1.8969072164948453,
+      "grad_norm": 0.40264815726534753,
+      "learning_rate": 2.8388612909821515e-05,
+      "loss": 0.4865,
+      "step": 46
+    },
+    {
+      "epoch": 1.9381443298969072,
+      "grad_norm": 0.29046340066307474,
+      "learning_rate": 2.6524405864311203e-05,
+      "loss": 0.4828,
+      "step": 47
+    },
+    {
+      "epoch": 1.9793814432989691,
+      "grad_norm": 0.3630940519896004,
+      "learning_rate": 2.4692662705396412e-05,
+      "loss": 0.4896,
+      "step": 48
+    },
+    {
+      "epoch": 2.020618556701031,
+      "grad_norm": 0.29324409805459234,
+      "learning_rate": 2.2897796262788728e-05,
+      "loss": 0.4781,
+      "step": 49
+    },
+    {
+      "epoch": 2.0618556701030926,
+      "grad_norm": 0.29703895032031474,
+      "learning_rate": 2.1144130526960093e-05,
+      "loss": 0.4651,
+      "step": 50
+    },
+    {
+      "epoch": 2.1030927835051547,
+      "grad_norm": 0.32087301061531515,
+      "learning_rate": 1.9435890232271136e-05,
+      "loss": 0.4684,
+      "step": 51
+    },
+    {
+      "epoch": 2.1443298969072164,
+      "grad_norm": 0.21482829598588496,
+      "learning_rate": 1.7777190679215923e-05,
+      "loss": 0.4625,
+      "step": 52
+    },
+    {
+      "epoch": 2.1855670103092786,
+      "grad_norm": 0.25824983057026213,
+      "learning_rate": 1.617202782030267e-05,
+      "loss": 0.4694,
+      "step": 53
+    },
+    {
+      "epoch": 2.2268041237113403,
+      "grad_norm": 0.34339533921143434,
+      "learning_rate": 1.4624268633454187e-05,
+      "loss": 0.4671,
+      "step": 54
+    },
+    {
+      "epoch": 2.268041237113402,
+      "grad_norm": 0.21104502743064882,
+      "learning_rate": 1.3137641806119264e-05,
+      "loss": 0.4519,
+      "step": 55
+    },
+    {
+      "epoch": 2.3092783505154637,
+      "grad_norm": 0.24004005785815857,
+      "learning_rate": 1.1715728752538103e-05,
+      "loss": 0.4659,
+      "step": 56
+    },
+    {
+      "epoch": 2.350515463917526,
+      "grad_norm": 0.23313541333770835,
+      "learning_rate": 1.0361954985801646e-05,
+      "loss": 0.4603,
+      "step": 57
+    },
+    {
+      "epoch": 2.3917525773195876,
+      "grad_norm": 0.20350216506185997,
+      "learning_rate": 9.07958186549052e-06,
+      "loss": 0.4613,
+      "step": 58
+    },
+    {
+      "epoch": 2.4329896907216497,
+      "grad_norm": 0.20198630626376185,
+      "learning_rate": 7.871698740774208e-06,
+      "loss": 0.46,
+      "step": 59
+    },
+    {
+      "epoch": 2.4742268041237114,
+      "grad_norm": 0.194949563636136,
+      "learning_rate": 6.7412155078981865e-06,
+      "loss": 0.458,
+      "step": 60
+    },
+    {
+      "epoch": 2.515463917525773,
+      "grad_norm": 0.14941010498220864,
+      "learning_rate": 5.690855599989121e-06,
+      "loss": 0.456,
+      "step": 61
+    },
+    {
+      "epoch": 2.556701030927835,
+      "grad_norm": 0.15790500602219348,
+      "learning_rate": 4.723149426065803e-06,
+      "loss": 0.4533,
+      "step": 62
+    },
+    {
+      "epoch": 2.597938144329897,
+      "grad_norm": 0.1636000215831201,
+      "learning_rate": 3.840428275062267e-06,
+      "loss": 0.4668,
+      "step": 63
+    },
+    {
+      "epoch": 2.6391752577319587,
+      "grad_norm": 0.14421574699719078,
+      "learning_rate": 3.0448186995485307e-06,
+      "loss": 0.4556,
+      "step": 64
+    },
+    {
+      "epoch": 2.680412371134021,
+      "grad_norm": 0.12670796224434785,
+      "learning_rate": 2.3382373926791722e-06,
+      "loss": 0.4621,
+      "step": 65
+    },
+    {
+      "epoch": 2.7216494845360826,
+      "grad_norm": 0.11802437342505168,
+      "learning_rate": 1.7223865707116472e-06,
+      "loss": 0.4479,
+      "step": 66
+    },
+    {
+      "epoch": 2.7628865979381443,
+      "grad_norm": 0.11470202289963577,
+      "learning_rate": 1.1987498722182411e-06,
+      "loss": 0.4554,
+      "step": 67
+    },
+    {
+      "epoch": 2.804123711340206,
+      "grad_norm": 0.11064912896935304,
+      "learning_rate": 7.685887838707828e-07,
+      "loss": 0.4546,
+      "step": 68
+    },
+    {
+      "epoch": 2.845360824742268,
+      "grad_norm": 0.11098592310547126,
+      "learning_rate": 4.3293960140875946e-07,
+      "loss": 0.4593,
+      "step": 69
+    },
+    {
+      "epoch": 2.88659793814433,
+      "grad_norm": 0.11733219406123296,
+      "learning_rate": 1.926109331121273e-07,
+      "loss": 0.4613,
+      "step": 70
+    },
+    {
+      "epoch": 2.927835051546392,
+      "grad_norm": 0.1177256209521773,
+      "learning_rate": 4.8181751793103806e-08,
+      "loss": 0.4534,
+      "step": 71
+    },
+    {
+      "epoch": 2.9690721649484537,
+      "grad_norm": 0.10324701234321615,
+      "learning_rate": 0.0,
+      "loss": 0.4659,
+      "step": 72
+    },
+    {
+      "epoch": 2.9690721649484537,
+      "step": 72,
+      "total_flos": 1.8527734203290747e+18,
+      "train_loss": 0.5522520401411586,
+      "train_runtime": 15811.9484,
+      "train_samples_per_second": 2.351,
+      "train_steps_per_second": 0.005
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 72,
+  "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": 1.8527734203290747e+18,
+  "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:a69e77462d1b363c08300243869228de231de9a3a5e8fe92b53eb9f9fa439f63
+size 7352