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": 2.9835189309576835,
+    "total_flos": 234603226333184.0,
+    "train_loss": 0.20078422256878445,
+    "train_runtime": 13460.8563,
+    "train_samples_per_second": 16.011,
+    "train_steps_per_second": 0.031
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B",
+  "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": 131072,
+  "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": 131072,
+  "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 sha256:4c2d8326261275fb84b6fa9b61784159c0c9a3e26ded21f186c0629231c0e5bc
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f90947b2f08e17292955f93a6efce6d7caac9e5f70afeb5b62b5ad5e393c146
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3aad1b8d0c0bd46a5a5354a44df73c7abfe56edcb4fc80da77bcb6b2233ac34
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0bc1fb8ec8dfc614dfb20971fab57aef35ddb437e5c35fa81f1ed2037f887cf
+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 +1,209 @@
+{
+  "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": "{% set system_message = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n' %}{% 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' %}{{ '### Instruction:\n' + content + '\n\n### Response:\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\n\n' }}{% 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": 2.9835189309576835,
+    "total_flos": 234603226333184.0,
+    "train_loss": 0.20078422256878445,
+    "train_runtime": 13460.8563,
+    "train_samples_per_second": 16.011,
+    "train_steps_per_second": 0.031
+}

trainer_log.jsonl

@@ -0,0 +1,43 @@
+{"current_steps": 10, "total_steps": 420, "loss": 0.8475, "lr": 4.761904761904762e-06, "epoch": 0.07126948775055679, "percentage": 2.38, "elapsed_time": "0:05:37", "remaining_time": "3:50:53"}
+{"current_steps": 20, "total_steps": 420, "loss": 0.5121, "lr": 9.523809523809525e-06, "epoch": 0.14253897550111358, "percentage": 4.76, "elapsed_time": "0:10:55", "remaining_time": "3:38:21"}
+{"current_steps": 30, "total_steps": 420, "loss": 0.4342, "lr": 1.4285714285714287e-05, "epoch": 0.21380846325167038, "percentage": 7.14, "elapsed_time": "0:16:23", "remaining_time": "3:33:07"}
+{"current_steps": 40, "total_steps": 420, "loss": 0.3944, "lr": 1.904761904761905e-05, "epoch": 0.28507795100222716, "percentage": 9.52, "elapsed_time": "0:21:33", "remaining_time": "3:24:49"}
+{"current_steps": 50, "total_steps": 420, "loss": 0.3626, "lr": 1.997790438338385e-05, "epoch": 0.35634743875278396, "percentage": 11.9, "elapsed_time": "0:26:41", "remaining_time": "3:17:31"}
+{"current_steps": 60, "total_steps": 420, "loss": 0.3474, "lr": 1.9888308262251286e-05, "epoch": 0.42761692650334077, "percentage": 14.29, "elapsed_time": "0:32:02", "remaining_time": "3:12:12"}
+{"current_steps": 70, "total_steps": 420, "loss": 0.3277, "lr": 1.973044870579824e-05, "epoch": 0.49888641425389757, "percentage": 16.67, "elapsed_time": "0:37:13", "remaining_time": "3:06:07"}
+{"current_steps": 80, "total_steps": 420, "loss": 0.3141, "lr": 1.9505415489478293e-05, "epoch": 0.5701559020044543, "percentage": 19.05, "elapsed_time": "0:42:30", "remaining_time": "3:00:38"}
+{"current_steps": 90, "total_steps": 420, "loss": 0.2979, "lr": 1.921476211870408e-05, "epoch": 0.6414253897550112, "percentage": 21.43, "elapsed_time": "0:47:42", "remaining_time": "2:54:57"}
+{"current_steps": 100, "total_steps": 420, "loss": 0.2871, "lr": 1.8860495104301346e-05, "epoch": 0.7126948775055679, "percentage": 23.81, "elapsed_time": "0:53:11", "remaining_time": "2:50:11"}
+{"current_steps": 110, "total_steps": 420, "loss": 0.2723, "lr": 1.844506011066308e-05, "epoch": 0.7839643652561247, "percentage": 26.19, "elapsed_time": "0:58:17", "remaining_time": "2:44:17"}
+{"current_steps": 120, "total_steps": 420, "loss": 0.2681, "lr": 1.7971325072229227e-05, "epoch": 0.8552338530066815, "percentage": 28.57, "elapsed_time": "1:03:42", "remaining_time": "2:39:16"}
+{"current_steps": 130, "total_steps": 420, "loss": 0.2559, "lr": 1.7442560394846518e-05, "epoch": 0.9265033407572383, "percentage": 30.95, "elapsed_time": "1:09:00", "remaining_time": "2:33:57"}
+{"current_steps": 140, "total_steps": 420, "loss": 0.2437, "lr": 1.686241637868734e-05, "epoch": 0.9977728285077951, "percentage": 33.33, "elapsed_time": "1:14:21", "remaining_time": "2:28:42"}
+{"current_steps": 150, "total_steps": 420, "loss": 0.1816, "lr": 1.6234898018587336e-05, "epoch": 1.064142538975501, "percentage": 35.71, "elapsed_time": "1:19:26", "remaining_time": "2:22:59"}
+{"current_steps": 160, "total_steps": 420, "loss": 0.1727, "lr": 1.5564337355766412e-05, "epoch": 1.135412026726058, "percentage": 38.1, "elapsed_time": "1:24:54", "remaining_time": "2:17:58"}
+{"current_steps": 170, "total_steps": 420, "loss": 0.1644, "lr": 1.4855363571801523e-05, "epoch": 1.2066815144766148, "percentage": 40.48, "elapsed_time": "1:30:09", "remaining_time": "2:12:34"}
+{"current_steps": 180, "total_steps": 420, "loss": 0.1631, "lr": 1.4112871031306118e-05, "epoch": 1.2779510022271716, "percentage": 42.86, "elapsed_time": "1:35:17", "remaining_time": "2:07:02"}
+{"current_steps": 190, "total_steps": 420, "loss": 0.1615, "lr": 1.3341985493931877e-05, "epoch": 1.3492204899777283, "percentage": 45.24, "elapsed_time": "1:40:19", "remaining_time": "2:01:26"}
+{"current_steps": 200, "total_steps": 420, "loss": 0.1601, "lr": 1.2548028728946548e-05, "epoch": 1.4204899777282851, "percentage": 47.62, "elapsed_time": "1:45:35", "remaining_time": "1:56:09"}
+{"current_steps": 210, "total_steps": 420, "loss": 0.1583, "lr": 1.1736481776669307e-05, "epoch": 1.4917594654788418, "percentage": 50.0, "elapsed_time": "1:50:41", "remaining_time": "1:50:41"}
+{"current_steps": 220, "total_steps": 420, "loss": 0.1541, "lr": 1.0912947110386484e-05, "epoch": 1.5630289532293986, "percentage": 52.38, "elapsed_time": "1:55:45", "remaining_time": "1:45:13"}
+{"current_steps": 230, "total_steps": 420, "loss": 0.154, "lr": 1.0083109959960974e-05, "epoch": 1.6342984409799555, "percentage": 54.76, "elapsed_time": "2:01:30", "remaining_time": "1:40:22"}
+{"current_steps": 240, "total_steps": 420, "loss": 0.1536, "lr": 9.252699064135759e-06, "epoch": 1.7055679287305123, "percentage": 57.14, "elapsed_time": "2:06:48", "remaining_time": "1:35:06"}
+{"current_steps": 250, "total_steps": 420, "loss": 0.1509, "lr": 8.427447122476148e-06, "epoch": 1.7768374164810692, "percentage": 59.52, "elapsed_time": "2:12:09", "remaining_time": "1:29:51"}
+{"current_steps": 260, "total_steps": 420, "loss": 0.1475, "lr": 7.613051219968624e-06, "epoch": 1.8481069042316258, "percentage": 61.9, "elapsed_time": "2:18:35", "remaining_time": "1:25:17"}
+{"current_steps": 270, "total_steps": 420, "loss": 0.1478, "lr": 6.815133497483157e-06, "epoch": 1.9193763919821827, "percentage": 64.29, "elapsed_time": "2:24:04", "remaining_time": "1:20:02"}
+{"current_steps": 280, "total_steps": 420, "loss": 0.1469, "lr": 6.039202339608432e-06, "epoch": 1.9906458797327393, "percentage": 66.67, "elapsed_time": "2:29:15", "remaining_time": "1:14:37"}
+{"current_steps": 290, "total_steps": 420, "loss": 0.0958, "lr": 5.290614347797802e-06, "epoch": 2.057015590200445, "percentage": 69.05, "elapsed_time": "2:34:32", "remaining_time": "1:09:16"}
+{"current_steps": 300, "total_steps": 420, "loss": 0.0776, "lr": 4.5745373613424075e-06, "epoch": 2.128285077951002, "percentage": 71.43, "elapsed_time": "2:39:58", "remaining_time": "1:03:59"}
+{"current_steps": 310, "total_steps": 420, "loss": 0.0776, "lr": 3.89591478145437e-06, "epoch": 2.199554565701559, "percentage": 73.81, "elapsed_time": "2:45:12", "remaining_time": "0:58:37"}
+{"current_steps": 320, "total_steps": 420, "loss": 0.0754, "lr": 3.2594314447468457e-06, "epoch": 2.270824053452116, "percentage": 76.19, "elapsed_time": "2:50:31", "remaining_time": "0:53:17"}
+{"current_steps": 330, "total_steps": 420, "loss": 0.0748, "lr": 2.669481281701739e-06, "epoch": 2.3420935412026727, "percentage": 78.57, "elapsed_time": "2:55:54", "remaining_time": "0:47:58"}
+{"current_steps": 340, "total_steps": 420, "loss": 0.0704, "lr": 2.130136983393112e-06, "epoch": 2.4133630289532295, "percentage": 80.95, "elapsed_time": "3:01:14", "remaining_time": "0:42:38"}
+{"current_steps": 350, "total_steps": 420, "loss": 0.0742, "lr": 1.6451218858706374e-06, "epoch": 2.4846325167037864, "percentage": 83.33, "elapsed_time": "3:06:23", "remaining_time": "0:37:16"}
+{"current_steps": 360, "total_steps": 420, "loss": 0.0733, "lr": 1.2177842662977136e-06, "epoch": 2.5559020044543432, "percentage": 85.71, "elapsed_time": "3:11:30", "remaining_time": "0:31:55"}
+{"current_steps": 370, "total_steps": 420, "loss": 0.0717, "lr": 8.510742282896545e-07, "epoch": 2.6271714922048996, "percentage": 88.1, "elapsed_time": "3:16:46", "remaining_time": "0:26:35"}
+{"current_steps": 380, "total_steps": 420, "loss": 0.0709, "lr": 5.475233360227516e-07, "epoch": 2.6984409799554565, "percentage": 90.48, "elapsed_time": "3:21:55", "remaining_time": "0:21:15"}
+{"current_steps": 390, "total_steps": 420, "loss": 0.0723, "lr": 3.0922713770922155e-07, "epoch": 2.7697104677060134, "percentage": 92.86, "elapsed_time": "3:27:17", "remaining_time": "0:15:56"}
+{"current_steps": 400, "total_steps": 420, "loss": 0.0727, "lr": 1.3783069908621772e-07, "epoch": 2.8409799554565702, "percentage": 95.24, "elapsed_time": "3:32:35", "remaining_time": "0:10:37"}
+{"current_steps": 410, "total_steps": 420, "loss": 0.0727, "lr": 3.451724678784518e-08, "epoch": 2.912249443207127, "percentage": 97.62, "elapsed_time": "3:37:52", "remaining_time": "0:05:18"}
+{"current_steps": 420, "total_steps": 420, "loss": 0.072, "lr": 0.0, "epoch": 2.9835189309576835, "percentage": 100.0, "elapsed_time": "3:43:12", "remaining_time": "0:00:00"}
+{"current_steps": 420, "total_steps": 420, "epoch": 2.9835189309576835, "percentage": 100.0, "elapsed_time": "3:44:17", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,336 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9835189309576835,
+  "eval_steps": 500,
+  "global_step": 420,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07126948775055679,
+      "grad_norm": 3.7971609533442936,
+      "learning_rate": 4.761904761904762e-06,
+      "loss": 0.8475,
+      "step": 10
+    },
+    {
+      "epoch": 0.14253897550111358,
+      "grad_norm": 0.9295260271504954,
+      "learning_rate": 9.523809523809525e-06,
+      "loss": 0.5121,
+      "step": 20
+    },
+    {
+      "epoch": 0.21380846325167038,
+      "grad_norm": 0.7378111786994856,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 0.4342,
+      "step": 30
+    },
+    {
+      "epoch": 0.28507795100222716,
+      "grad_norm": 0.706728951221838,
+      "learning_rate": 1.904761904761905e-05,
+      "loss": 0.3944,
+      "step": 40
+    },
+    {
+      "epoch": 0.35634743875278396,
+      "grad_norm": 0.8090312873781099,
+      "learning_rate": 1.997790438338385e-05,
+      "loss": 0.3626,
+      "step": 50
+    },
+    {
+      "epoch": 0.42761692650334077,
+      "grad_norm": 0.6955054433411858,
+      "learning_rate": 1.9888308262251286e-05,
+      "loss": 0.3474,
+      "step": 60
+    },
+    {
+      "epoch": 0.49888641425389757,
+      "grad_norm": 0.6161974091570769,
+      "learning_rate": 1.973044870579824e-05,
+      "loss": 0.3277,
+      "step": 70
+    },
+    {
+      "epoch": 0.5701559020044543,
+      "grad_norm": 0.6402632736940507,
+      "learning_rate": 1.9505415489478293e-05,
+      "loss": 0.3141,
+      "step": 80
+    },
+    {
+      "epoch": 0.6414253897550112,
+      "grad_norm": 0.6353304250627707,
+      "learning_rate": 1.921476211870408e-05,
+      "loss": 0.2979,
+      "step": 90
+    },
+    {
+      "epoch": 0.7126948775055679,
+      "grad_norm": 0.6366565830233913,
+      "learning_rate": 1.8860495104301346e-05,
+      "loss": 0.2871,
+      "step": 100
+    },
+    {
+      "epoch": 0.7839643652561247,
+      "grad_norm": 0.6354146476657556,
+      "learning_rate": 1.844506011066308e-05,
+      "loss": 0.2723,
+      "step": 110
+    },
+    {
+      "epoch": 0.8552338530066815,
+      "grad_norm": 0.5882708445945315,
+      "learning_rate": 1.7971325072229227e-05,
+      "loss": 0.2681,
+      "step": 120
+    },
+    {
+      "epoch": 0.9265033407572383,
+      "grad_norm": 0.5762368078327551,
+      "learning_rate": 1.7442560394846518e-05,
+      "loss": 0.2559,
+      "step": 130
+    },
+    {
+      "epoch": 0.9977728285077951,
+      "grad_norm": 0.5958357402554844,
+      "learning_rate": 1.686241637868734e-05,
+      "loss": 0.2437,
+      "step": 140
+    },
+    {
+      "epoch": 1.064142538975501,
+      "grad_norm": 0.6936917056904216,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 0.1816,
+      "step": 150
+    },
+    {
+      "epoch": 1.135412026726058,
+      "grad_norm": 0.5744999045875022,
+      "learning_rate": 1.5564337355766412e-05,
+      "loss": 0.1727,
+      "step": 160
+    },
+    {
+      "epoch": 1.2066815144766148,
+      "grad_norm": 0.5316452824085909,
+      "learning_rate": 1.4855363571801523e-05,
+      "loss": 0.1644,
+      "step": 170
+    },
+    {
+      "epoch": 1.2779510022271716,
+      "grad_norm": 0.4952795924197091,
+      "learning_rate": 1.4112871031306118e-05,
+      "loss": 0.1631,
+      "step": 180
+    },
+    {
+      "epoch": 1.3492204899777283,
+      "grad_norm": 0.4880859442135627,
+      "learning_rate": 1.3341985493931877e-05,
+      "loss": 0.1615,
+      "step": 190
+    },
+    {
+      "epoch": 1.4204899777282851,
+      "grad_norm": 0.4845969774780985,
+      "learning_rate": 1.2548028728946548e-05,
+      "loss": 0.1601,
+      "step": 200
+    },
+    {
+      "epoch": 1.4917594654788418,
+      "grad_norm": 0.5021044989896025,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.1583,
+      "step": 210
+    },
+    {
+      "epoch": 1.5630289532293986,
+      "grad_norm": 0.44605081296525473,
+      "learning_rate": 1.0912947110386484e-05,
+      "loss": 0.1541,
+      "step": 220
+    },
+    {
+      "epoch": 1.6342984409799555,
+      "grad_norm": 0.46635765009201846,
+      "learning_rate": 1.0083109959960974e-05,
+      "loss": 0.154,
+      "step": 230
+    },
+    {
+      "epoch": 1.7055679287305123,
+      "grad_norm": 0.45234389725218227,
+      "learning_rate": 9.252699064135759e-06,
+      "loss": 0.1536,
+      "step": 240
+    },
+    {
+      "epoch": 1.7768374164810692,
+      "grad_norm": 0.47812323330213485,
+      "learning_rate": 8.427447122476148e-06,
+      "loss": 0.1509,
+      "step": 250
+    },
+    {
+      "epoch": 1.8481069042316258,
+      "grad_norm": 0.4452592705770747,
+      "learning_rate": 7.613051219968624e-06,
+      "loss": 0.1475,
+      "step": 260
+    },
+    {
+      "epoch": 1.9193763919821827,
+      "grad_norm": 0.447493408892927,
+      "learning_rate": 6.815133497483157e-06,
+      "loss": 0.1478,
+      "step": 270
+    },
+    {
+      "epoch": 1.9906458797327393,
+      "grad_norm": 0.4643827774343368,
+      "learning_rate": 6.039202339608432e-06,
+      "loss": 0.1469,
+      "step": 280
+    },
+    {
+      "epoch": 2.057015590200445,
+      "grad_norm": 0.5296378146178365,
+      "learning_rate": 5.290614347797802e-06,
+      "loss": 0.0958,
+      "step": 290
+    },
+    {
+      "epoch": 2.128285077951002,
+      "grad_norm": 0.4045550908197575,
+      "learning_rate": 4.5745373613424075e-06,
+      "loss": 0.0776,
+      "step": 300
+    },
+    {
+      "epoch": 2.199554565701559,
+      "grad_norm": 0.4040354519811954,
+      "learning_rate": 3.89591478145437e-06,
+      "loss": 0.0776,
+      "step": 310
+    },
+    {
+      "epoch": 2.270824053452116,
+      "grad_norm": 0.42857601545200796,
+      "learning_rate": 3.2594314447468457e-06,
+      "loss": 0.0754,
+      "step": 320
+    },
+    {
+      "epoch": 2.3420935412026727,
+      "grad_norm": 0.3670300653980398,
+      "learning_rate": 2.669481281701739e-06,
+      "loss": 0.0748,
+      "step": 330
+    },
+    {
+      "epoch": 2.4133630289532295,
+      "grad_norm": 0.3902364845802205,
+      "learning_rate": 2.130136983393112e-06,
+      "loss": 0.0704,
+      "step": 340
+    },
+    {
+      "epoch": 2.4846325167037864,
+      "grad_norm": 0.377128443473291,
+      "learning_rate": 1.6451218858706374e-06,
+      "loss": 0.0742,
+      "step": 350
+    },
+    {
+      "epoch": 2.5559020044543432,
+      "grad_norm": 0.3930553430015275,
+      "learning_rate": 1.2177842662977136e-06,
+      "loss": 0.0733,
+      "step": 360
+    },
+    {
+      "epoch": 2.6271714922048996,
+      "grad_norm": 0.3590982366224671,
+      "learning_rate": 8.510742282896545e-07,
+      "loss": 0.0717,
+      "step": 370
+    },
+    {
+      "epoch": 2.6984409799554565,
+      "grad_norm": 0.3746976787822436,
+      "learning_rate": 5.475233360227516e-07,
+      "loss": 0.0709,
+      "step": 380
+    },
+    {
+      "epoch": 2.7697104677060134,
+      "grad_norm": 0.36100542307641714,
+      "learning_rate": 3.0922713770922155e-07,
+      "loss": 0.0723,
+      "step": 390
+    },
+    {
+      "epoch": 2.8409799554565702,
+      "grad_norm": 0.3896273158596708,
+      "learning_rate": 1.3783069908621772e-07,
+      "loss": 0.0727,
+      "step": 400
+    },
+    {
+      "epoch": 2.912249443207127,
+      "grad_norm": 0.385255671671692,
+      "learning_rate": 3.451724678784518e-08,
+      "loss": 0.0727,
+      "step": 410
+    },
+    {
+      "epoch": 2.9835189309576835,
+      "grad_norm": 0.38370569586805797,
+      "learning_rate": 0.0,
+      "loss": 0.072,
+      "step": 420
+    },
+    {
+      "epoch": 2.9835189309576835,
+      "step": 420,
+      "total_flos": 234603226333184.0,
+      "train_loss": 0.20078422256878445,
+      "train_runtime": 13460.8563,
+      "train_samples_per_second": 16.011,
+      "train_steps_per_second": 0.031
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 420,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 250,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 234603226333184.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63cce84652a550378c64e724aed2908ae7cbea34f581f2c3466f2a7a75945a23
+size 7544