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": 3.0,
+    "total_flos": 3.6014407804780544e+18,
+    "train_loss": 0.2428539801937665,
+    "train_runtime": 11457.3527,
+    "train_samples_per_second": 5.736,
+    "train_steps_per_second": 0.045
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-Math-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 4096,
+  "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": 10000,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.49.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c3847039514d7478686dd46c762ba578d4a3396a82eeb8ecb75d3d3fc20d1a
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93358ee0efbe823e1b41179badc9f501f927c6c529b7c831302bba7bdde48747
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba1c7a4fd83d19974b624fb132d63465584b7b283366315984567638c5574acc
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7150396ddc063df6b81c6042f0e1f01c2863eae532e3325cff3828889738bb2c
+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"
+  }
+}

runs/Aug21_13-44-52_air/events.out.tfevents.1755755226.air.3798089.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfaa94fad163da35742c19a7ac9d4860aeef4bf4317e4894ad72996bf9be3bcb
+size 16068

runs/Aug21_17-09-25_air/events.out.tfevents.1755767405.air.3828746.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29e9735cf26ceaffe397c9fe25137dbd2f9d0a739dae9d71d8391c72f8877521
+size 16633

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 +1,209 @@
+{
+  "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 messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "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": 3.0,
+    "total_flos": 3.6014407804780544e+18,
+    "train_loss": 0.2428539801937665,
+    "train_runtime": 11457.3527,
+    "train_samples_per_second": 5.736,
+    "train_steps_per_second": 0.045
+}

trainer_log.jsonl

@@ -0,0 +1,52 @@
+{"current_steps": 10, "total_steps": 516, "loss": 0.4976, "lr": 1.9230769230769234e-06, "epoch": 0.05813953488372093, "percentage": 1.94, "elapsed_time": "0:03:43", "remaining_time": "3:08:04"}
+{"current_steps": 20, "total_steps": 516, "loss": 0.4336, "lr": 3.846153846153847e-06, "epoch": 0.11627906976744186, "percentage": 3.88, "elapsed_time": "0:07:20", "remaining_time": "3:02:02"}
+{"current_steps": 30, "total_steps": 516, "loss": 0.3589, "lr": 5.769230769230769e-06, "epoch": 0.1744186046511628, "percentage": 5.81, "elapsed_time": "0:10:59", "remaining_time": "2:57:58"}
+{"current_steps": 40, "total_steps": 516, "loss": 0.3252, "lr": 7.692307692307694e-06, "epoch": 0.23255813953488372, "percentage": 7.75, "elapsed_time": "0:14:37", "remaining_time": "2:54:02"}
+{"current_steps": 50, "total_steps": 516, "loss": 0.3045, "lr": 9.615384615384616e-06, "epoch": 0.29069767441860467, "percentage": 9.69, "elapsed_time": "0:18:18", "remaining_time": "2:50:34"}
+{"current_steps": 60, "total_steps": 516, "loss": 0.3052, "lr": 9.99266706925562e-06, "epoch": 0.3488372093023256, "percentage": 11.63, "elapsed_time": "0:21:53", "remaining_time": "2:46:23"}
+{"current_steps": 70, "total_steps": 516, "loss": 0.2958, "lr": 9.962913897416029e-06, "epoch": 0.4069767441860465, "percentage": 13.57, "elapsed_time": "0:25:25", "remaining_time": "2:41:59"}
+{"current_steps": 80, "total_steps": 516, "loss": 0.2955, "lr": 9.91041841371078e-06, "epoch": 0.46511627906976744, "percentage": 15.5, "elapsed_time": "0:29:07", "remaining_time": "2:38:43"}
+{"current_steps": 90, "total_steps": 516, "loss": 0.2919, "lr": 9.835421176144035e-06, "epoch": 0.5232558139534884, "percentage": 17.44, "elapsed_time": "0:32:48", "remaining_time": "2:35:17"}
+{"current_steps": 100, "total_steps": 516, "loss": 0.2884, "lr": 9.738265855914014e-06, "epoch": 0.5813953488372093, "percentage": 19.38, "elapsed_time": "0:36:32", "remaining_time": "2:31:59"}
+{"current_steps": 110, "total_steps": 516, "loss": 0.2862, "lr": 9.619397662556434e-06, "epoch": 0.6395348837209303, "percentage": 21.32, "elapsed_time": "0:40:03", "remaining_time": "2:27:50"}
+{"current_steps": 120, "total_steps": 516, "loss": 0.282, "lr": 9.479361303793441e-06, "epoch": 0.6976744186046512, "percentage": 23.26, "elapsed_time": "0:43:36", "remaining_time": "2:23:55"}
+{"current_steps": 130, "total_steps": 516, "loss": 0.2834, "lr": 9.318798489436917e-06, "epoch": 0.7558139534883721, "percentage": 25.19, "elapsed_time": "0:47:20", "remaining_time": "2:20:34"}
+{"current_steps": 140, "total_steps": 516, "loss": 0.2789, "lr": 9.138444990784455e-06, "epoch": 0.813953488372093, "percentage": 27.13, "elapsed_time": "0:50:55", "remaining_time": "2:16:45"}
+{"current_steps": 150, "total_steps": 516, "loss": 0.2759, "lr": 8.93912726898311e-06, "epoch": 0.872093023255814, "percentage": 29.07, "elapsed_time": "0:54:25", "remaining_time": "2:12:48"}
+{"current_steps": 160, "total_steps": 516, "loss": 0.2791, "lr": 8.721758687811353e-06, "epoch": 0.9302325581395349, "percentage": 31.01, "elapsed_time": "0:58:07", "remaining_time": "2:09:19"}
+{"current_steps": 170, "total_steps": 516, "loss": 0.2738, "lr": 8.487335328233912e-06, "epoch": 0.9883720930232558, "percentage": 32.95, "elapsed_time": "1:01:49", "remaining_time": "2:05:50"}
+{"current_steps": 180, "total_steps": 516, "loss": 0.2461, "lr": 8.23693142390914e-06, "epoch": 1.0465116279069768, "percentage": 34.88, "elapsed_time": "1:05:27", "remaining_time": "2:02:12"}
+{"current_steps": 190, "total_steps": 516, "loss": 0.2321, "lr": 7.97169443856545e-06, "epoch": 1.1046511627906976, "percentage": 36.82, "elapsed_time": "1:09:04", "remaining_time": "1:58:30"}
+{"current_steps": 200, "total_steps": 516, "loss": 0.2334, "lr": 7.692839807804522e-06, "epoch": 1.1627906976744187, "percentage": 38.76, "elapsed_time": "1:12:50", "remaining_time": "1:55:06"}
+{"current_steps": 210, "total_steps": 516, "loss": 0.2314, "lr": 7.401645369426697e-06, "epoch": 1.2209302325581395, "percentage": 40.7, "elapsed_time": "1:16:29", "remaining_time": "1:51:27"}
+{"current_steps": 220, "total_steps": 516, "loss": 0.233, "lr": 7.099445507801324e-06, "epoch": 1.2790697674418605, "percentage": 42.64, "elapsed_time": "1:20:05", "remaining_time": "1:47:46"}
+{"current_steps": 230, "total_steps": 516, "loss": 0.2328, "lr": 6.7876250391152e-06, "epoch": 1.3372093023255813, "percentage": 44.57, "elapsed_time": "1:23:35", "remaining_time": "1:43:57"}
+{"current_steps": 240, "total_steps": 516, "loss": 0.2316, "lr": 6.467612865519674e-06, "epoch": 1.3953488372093024, "percentage": 46.51, "elapsed_time": "1:27:18", "remaining_time": "1:40:23"}
+{"current_steps": 250, "total_steps": 516, "loss": 0.2323, "lr": 6.14087542725593e-06, "epoch": 1.4534883720930232, "percentage": 48.45, "elapsed_time": "1:30:59", "remaining_time": "1:36:48"}
+{"current_steps": 260, "total_steps": 516, "loss": 0.2283, "lr": 5.808909982763825e-06, "epoch": 1.5116279069767442, "percentage": 50.39, "elapsed_time": "1:34:38", "remaining_time": "1:33:11"}
+{"current_steps": 270, "total_steps": 516, "loss": 0.2309, "lr": 5.473237747567805e-06, "epoch": 1.5697674418604652, "percentage": 52.33, "elapsed_time": "1:38:18", "remaining_time": "1:29:33"}
+{"current_steps": 280, "total_steps": 516, "loss": 0.2317, "lr": 5.1353969233806735e-06, "epoch": 1.627906976744186, "percentage": 54.26, "elapsed_time": "1:41:55", "remaining_time": "1:25:54"}
+{"current_steps": 290, "total_steps": 516, "loss": 0.2272, "lr": 4.796935649368936e-06, "epoch": 1.6860465116279069, "percentage": 56.2, "elapsed_time": "1:45:33", "remaining_time": "1:22:16"}
+{"current_steps": 300, "total_steps": 516, "loss": 0.2319, "lr": 4.459404907880293e-06, "epoch": 1.744186046511628, "percentage": 58.14, "elapsed_time": "1:49:12", "remaining_time": "1:18:37"}
+{"current_steps": 310, "total_steps": 516, "loss": 0.227, "lr": 4.1243514171423465e-06, "epoch": 1.802325581395349, "percentage": 60.08, "elapsed_time": "1:52:57", "remaining_time": "1:15:03"}
+{"current_steps": 320, "total_steps": 516, "loss": 0.2288, "lr": 3.7933105435014727e-06, "epoch": 1.8604651162790697, "percentage": 62.02, "elapsed_time": "1:56:37", "remaining_time": "1:11:26"}
+{"current_steps": 330, "total_steps": 516, "loss": 0.224, "lr": 3.4677992656811054e-06, "epoch": 1.9186046511627906, "percentage": 63.95, "elapsed_time": "2:00:23", "remaining_time": "1:07:51"}
+{"current_steps": 340, "total_steps": 516, "loss": 0.2293, "lr": 3.149309223300428e-06, "epoch": 1.9767441860465116, "percentage": 65.89, "elapsed_time": "2:04:01", "remaining_time": "1:04:12"}
+{"current_steps": 350, "total_steps": 516, "loss": 0.1976, "lr": 2.839299881508272e-06, "epoch": 2.0348837209302326, "percentage": 67.83, "elapsed_time": "2:07:40", "remaining_time": "1:00:33"}
+{"current_steps": 360, "total_steps": 516, "loss": 0.1831, "lr": 2.5391918430549635e-06, "epoch": 2.0930232558139537, "percentage": 69.77, "elapsed_time": "2:11:27", "remaining_time": "0:56:57"}
+{"current_steps": 370, "total_steps": 516, "loss": 0.1833, "lr": 2.250360338449226e-06, "epoch": 2.1511627906976742, "percentage": 71.71, "elapsed_time": "2:14:56", "remaining_time": "0:53:14"}
+{"current_steps": 380, "total_steps": 516, "loss": 0.187, "lr": 1.9741289240311757e-06, "epoch": 2.2093023255813953, "percentage": 73.64, "elapsed_time": "2:18:35", "remaining_time": "0:49:36"}
+{"current_steps": 390, "total_steps": 516, "loss": 0.1856, "lr": 1.7117634168396774e-06, "epoch": 2.2674418604651163, "percentage": 75.58, "elapsed_time": "2:22:15", "remaining_time": "0:45:57"}
+{"current_steps": 400, "total_steps": 516, "loss": 0.1812, "lr": 1.4644660940672628e-06, "epoch": 2.3255813953488373, "percentage": 77.52, "elapsed_time": "2:25:52", "remaining_time": "0:42:18"}
+{"current_steps": 410, "total_steps": 516, "loss": 0.183, "lr": 1.2333701836832812e-06, "epoch": 2.383720930232558, "percentage": 79.46, "elapsed_time": "2:29:34", "remaining_time": "0:38:40"}
+{"current_steps": 420, "total_steps": 516, "loss": 0.1825, "lr": 1.0195346714717813e-06, "epoch": 2.441860465116279, "percentage": 81.4, "elapsed_time": "2:33:16", "remaining_time": "0:35:01"}
+{"current_steps": 430, "total_steps": 516, "loss": 0.181, "lr": 8.239394482805996e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "2:37:01", "remaining_time": "0:31:24"}
+{"current_steps": 440, "total_steps": 516, "loss": 0.1856, "lr": 6.474808197191401e-07, "epoch": 2.558139534883721, "percentage": 85.27, "elapsed_time": "2:40:39", "remaining_time": "0:27:45"}
+{"current_steps": 450, "total_steps": 516, "loss": 0.18, "lr": 4.9096739888146e-07, "epoch": 2.616279069767442, "percentage": 87.21, "elapsed_time": "2:44:14", "remaining_time": "0:24:05"}
+{"current_steps": 460, "total_steps": 516, "loss": 0.1845, "lr": 3.5511640091604293e-07, "epoch": 2.6744186046511627, "percentage": 89.15, "elapsed_time": "2:47:55", "remaining_time": "0:20:26"}
+{"current_steps": 470, "total_steps": 516, "loss": 0.185, "lr": 2.4055035642222225e-07, "epoch": 2.7325581395348837, "percentage": 91.09, "elapsed_time": "2:51:33", "remaining_time": "0:16:47"}
+{"current_steps": 480, "total_steps": 516, "loss": 0.1811, "lr": 1.477942587339426e-07, "epoch": 2.7906976744186047, "percentage": 93.02, "elapsed_time": "2:55:14", "remaining_time": "0:13:08"}
+{"current_steps": 490, "total_steps": 516, "loss": 0.1841, "lr": 7.727315816331515e-08, "epoch": 2.8488372093023253, "percentage": 94.96, "elapsed_time": "2:58:55", "remaining_time": "0:09:29"}
+{"current_steps": 500, "total_steps": 516, "loss": 0.183, "lr": 2.9310214228202016e-08, "epoch": 2.9069767441860463, "percentage": 96.9, "elapsed_time": "3:02:28", "remaining_time": "0:05:50"}
+{"current_steps": 510, "total_steps": 516, "loss": 0.1837, "lr": 4.125214789427734e-09, "epoch": 2.9651162790697674, "percentage": 98.84, "elapsed_time": "3:07:40", "remaining_time": "0:02:12"}
+{"current_steps": 516, "total_steps": 516, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "3:10:55", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,399 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 516,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05813953488372093,
+      "grad_norm": 1.528863549232483,
+      "learning_rate": 1.9230769230769234e-06,
+      "loss": 0.4976,
+      "step": 10
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "grad_norm": 0.7564488053321838,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 0.4336,
+      "step": 20
+    },
+    {
+      "epoch": 0.1744186046511628,
+      "grad_norm": 1.0575538873672485,
+      "learning_rate": 5.769230769230769e-06,
+      "loss": 0.3589,
+      "step": 30
+    },
+    {
+      "epoch": 0.23255813953488372,
+      "grad_norm": 0.6464478969573975,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 0.3252,
+      "step": 40
+    },
+    {
+      "epoch": 0.29069767441860467,
+      "grad_norm": 0.43869853019714355,
+      "learning_rate": 9.615384615384616e-06,
+      "loss": 0.3045,
+      "step": 50
+    },
+    {
+      "epoch": 0.3488372093023256,
+      "grad_norm": 0.4740906357765198,
+      "learning_rate": 9.99266706925562e-06,
+      "loss": 0.3052,
+      "step": 60
+    },
+    {
+      "epoch": 0.4069767441860465,
+      "grad_norm": 0.4225959777832031,
+      "learning_rate": 9.962913897416029e-06,
+      "loss": 0.2958,
+      "step": 70
+    },
+    {
+      "epoch": 0.46511627906976744,
+      "grad_norm": 0.3857693374156952,
+      "learning_rate": 9.91041841371078e-06,
+      "loss": 0.2955,
+      "step": 80
+    },
+    {
+      "epoch": 0.5232558139534884,
+      "grad_norm": 0.3972570598125458,
+      "learning_rate": 9.835421176144035e-06,
+      "loss": 0.2919,
+      "step": 90
+    },
+    {
+      "epoch": 0.5813953488372093,
+      "grad_norm": 0.4061450660228729,
+      "learning_rate": 9.738265855914014e-06,
+      "loss": 0.2884,
+      "step": 100
+    },
+    {
+      "epoch": 0.6395348837209303,
+      "grad_norm": 0.39139261841773987,
+      "learning_rate": 9.619397662556434e-06,
+      "loss": 0.2862,
+      "step": 110
+    },
+    {
+      "epoch": 0.6976744186046512,
+      "grad_norm": 0.36877092719078064,
+      "learning_rate": 9.479361303793441e-06,
+      "loss": 0.282,
+      "step": 120
+    },
+    {
+      "epoch": 0.7558139534883721,
+      "grad_norm": 0.40923571586608887,
+      "learning_rate": 9.318798489436917e-06,
+      "loss": 0.2834,
+      "step": 130
+    },
+    {
+      "epoch": 0.813953488372093,
+      "grad_norm": 0.41997870802879333,
+      "learning_rate": 9.138444990784455e-06,
+      "loss": 0.2789,
+      "step": 140
+    },
+    {
+      "epoch": 0.872093023255814,
+      "grad_norm": 0.38587668538093567,
+      "learning_rate": 8.93912726898311e-06,
+      "loss": 0.2759,
+      "step": 150
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 0.3747125267982483,
+      "learning_rate": 8.721758687811353e-06,
+      "loss": 0.2791,
+      "step": 160
+    },
+    {
+      "epoch": 0.9883720930232558,
+      "grad_norm": 0.39039668440818787,
+      "learning_rate": 8.487335328233912e-06,
+      "loss": 0.2738,
+      "step": 170
+    },
+    {
+      "epoch": 1.0465116279069768,
+      "grad_norm": 0.36734411120414734,
+      "learning_rate": 8.23693142390914e-06,
+      "loss": 0.2461,
+      "step": 180
+    },
+    {
+      "epoch": 1.1046511627906976,
+      "grad_norm": 0.34951621294021606,
+      "learning_rate": 7.97169443856545e-06,
+      "loss": 0.2321,
+      "step": 190
+    },
+    {
+      "epoch": 1.1627906976744187,
+      "grad_norm": 0.4765775203704834,
+      "learning_rate": 7.692839807804522e-06,
+      "loss": 0.2334,
+      "step": 200
+    },
+    {
+      "epoch": 1.2209302325581395,
+      "grad_norm": 0.4162239730358124,
+      "learning_rate": 7.401645369426697e-06,
+      "loss": 0.2314,
+      "step": 210
+    },
+    {
+      "epoch": 1.2790697674418605,
+      "grad_norm": 0.3959456980228424,
+      "learning_rate": 7.099445507801324e-06,
+      "loss": 0.233,
+      "step": 220
+    },
+    {
+      "epoch": 1.3372093023255813,
+      "grad_norm": 0.39358898997306824,
+      "learning_rate": 6.7876250391152e-06,
+      "loss": 0.2328,
+      "step": 230
+    },
+    {
+      "epoch": 1.3953488372093024,
+      "grad_norm": 0.39183884859085083,
+      "learning_rate": 6.467612865519674e-06,
+      "loss": 0.2316,
+      "step": 240
+    },
+    {
+      "epoch": 1.4534883720930232,
+      "grad_norm": 0.3894769847393036,
+      "learning_rate": 6.14087542725593e-06,
+      "loss": 0.2323,
+      "step": 250
+    },
+    {
+      "epoch": 1.5116279069767442,
+      "grad_norm": 0.3784314692020416,
+      "learning_rate": 5.808909982763825e-06,
+      "loss": 0.2283,
+      "step": 260
+    },
+    {
+      "epoch": 1.5697674418604652,
+      "grad_norm": 0.3567565381526947,
+      "learning_rate": 5.473237747567805e-06,
+      "loss": 0.2309,
+      "step": 270
+    },
+    {
+      "epoch": 1.627906976744186,
+      "grad_norm": 0.4400705099105835,
+      "learning_rate": 5.1353969233806735e-06,
+      "loss": 0.2317,
+      "step": 280
+    },
+    {
+      "epoch": 1.6860465116279069,
+      "grad_norm": 0.38926878571510315,
+      "learning_rate": 4.796935649368936e-06,
+      "loss": 0.2272,
+      "step": 290
+    },
+    {
+      "epoch": 1.744186046511628,
+      "grad_norm": 0.37996888160705566,
+      "learning_rate": 4.459404907880293e-06,
+      "loss": 0.2319,
+      "step": 300
+    },
+    {
+      "epoch": 1.802325581395349,
+      "grad_norm": 0.4081181287765503,
+      "learning_rate": 4.1243514171423465e-06,
+      "loss": 0.227,
+      "step": 310
+    },
+    {
+      "epoch": 1.8604651162790697,
+      "grad_norm": 0.36687538027763367,
+      "learning_rate": 3.7933105435014727e-06,
+      "loss": 0.2288,
+      "step": 320
+    },
+    {
+      "epoch": 1.9186046511627906,
+      "grad_norm": 0.3728639483451843,
+      "learning_rate": 3.4677992656811054e-06,
+      "loss": 0.224,
+      "step": 330
+    },
+    {
+      "epoch": 1.9767441860465116,
+      "grad_norm": 0.3709273934364319,
+      "learning_rate": 3.149309223300428e-06,
+      "loss": 0.2293,
+      "step": 340
+    },
+    {
+      "epoch": 2.0348837209302326,
+      "grad_norm": 0.3464743196964264,
+      "learning_rate": 2.839299881508272e-06,
+      "loss": 0.1976,
+      "step": 350
+    },
+    {
+      "epoch": 2.0930232558139537,
+      "grad_norm": 0.3613881766796112,
+      "learning_rate": 2.5391918430549635e-06,
+      "loss": 0.1831,
+      "step": 360
+    },
+    {
+      "epoch": 2.1511627906976742,
+      "grad_norm": 0.37775981426239014,
+      "learning_rate": 2.250360338449226e-06,
+      "loss": 0.1833,
+      "step": 370
+    },
+    {
+      "epoch": 2.2093023255813953,
+      "grad_norm": 0.37163475155830383,
+      "learning_rate": 1.9741289240311757e-06,
+      "loss": 0.187,
+      "step": 380
+    },
+    {
+      "epoch": 2.2674418604651163,
+      "grad_norm": 0.3699796199798584,
+      "learning_rate": 1.7117634168396774e-06,
+      "loss": 0.1856,
+      "step": 390
+    },
+    {
+      "epoch": 2.3255813953488373,
+      "grad_norm": 0.36632710695266724,
+      "learning_rate": 1.4644660940672628e-06,
+      "loss": 0.1812,
+      "step": 400
+    },
+    {
+      "epoch": 2.383720930232558,
+      "grad_norm": 0.38165929913520813,
+      "learning_rate": 1.2333701836832812e-06,
+      "loss": 0.183,
+      "step": 410
+    },
+    {
+      "epoch": 2.441860465116279,
+      "grad_norm": 0.3638046681880951,
+      "learning_rate": 1.0195346714717813e-06,
+      "loss": 0.1825,
+      "step": 420
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.38040053844451904,
+      "learning_rate": 8.239394482805996e-07,
+      "loss": 0.181,
+      "step": 430
+    },
+    {
+      "epoch": 2.558139534883721,
+      "grad_norm": 0.3494938313961029,
+      "learning_rate": 6.474808197191401e-07,
+      "loss": 0.1856,
+      "step": 440
+    },
+    {
+      "epoch": 2.616279069767442,
+      "grad_norm": 0.3780662417411804,
+      "learning_rate": 4.9096739888146e-07,
+      "loss": 0.18,
+      "step": 450
+    },
+    {
+      "epoch": 2.6744186046511627,
+      "grad_norm": 0.3449888229370117,
+      "learning_rate": 3.5511640091604293e-07,
+      "loss": 0.1845,
+      "step": 460
+    },
+    {
+      "epoch": 2.7325581395348837,
+      "grad_norm": 0.44790518283843994,
+      "learning_rate": 2.4055035642222225e-07,
+      "loss": 0.185,
+      "step": 470
+    },
+    {
+      "epoch": 2.7906976744186047,
+      "grad_norm": 0.3460833728313446,
+      "learning_rate": 1.477942587339426e-07,
+      "loss": 0.1811,
+      "step": 480
+    },
+    {
+      "epoch": 2.8488372093023253,
+      "grad_norm": 0.3444211184978485,
+      "learning_rate": 7.727315816331515e-08,
+      "loss": 0.1841,
+      "step": 490
+    },
+    {
+      "epoch": 2.9069767441860463,
+      "grad_norm": 0.3577885925769806,
+      "learning_rate": 2.9310214228202016e-08,
+      "loss": 0.183,
+      "step": 500
+    },
+    {
+      "epoch": 2.9651162790697674,
+      "grad_norm": 0.3537665903568268,
+      "learning_rate": 4.125214789427734e-09,
+      "loss": 0.1837,
+      "step": 510
+    },
+    {
+      "epoch": 3.0,
+      "step": 516,
+      "total_flos": 3.6014407804780544e+18,
+      "train_loss": 0.2428539801937665,
+      "train_runtime": 11457.3527,
+      "train_samples_per_second": 5.736,
+      "train_steps_per_second": 0.045
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 516,
+  "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": 3.6014407804780544e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fae3c65aabb0d832f2be1d2c444b51e60234094f4448917daedc9e5d1556120
+size 7352