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": 2.4710097421939507e+17,
+    "train_loss": 0.8453347384929657,
+    "train_runtime": 2641.4784,
+    "train_samples_per_second": 2.613,
+    "train_steps_per_second": 0.027
+}

config.json

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

generation_config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81d15dcb4c0bec65368460237f925fcd328849f9fdc7737709733bd6d71c6bae
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70262ff2d52fa8831611315ca93f88596479f13de64ba5cde039b40f606de9d7
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57ba3993e0b84f63ea33d505e56f9ab754f8918c1bc4c74941ba5fe37f6cc297
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b0510f2a679def565adecc25235c69aeb5a8d0fc5b9920cc546afb7ccd76f43
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 2.4710097421939507e+17,
+    "train_loss": 0.8453347384929657,
+    "train_runtime": 2641.4784,
+    "train_samples_per_second": 2.613,
+    "train_steps_per_second": 0.027
+}

trainer_log.jsonl

@@ -0,0 +1,73 @@
+{"current_steps": 1, "total_steps": 72, "loss": 1.222, "lr": 1.25e-06, "epoch": 0.041666666666666664, "percentage": 1.39, "elapsed_time": "0:00:59", "remaining_time": "1:10:57"}
+{"current_steps": 2, "total_steps": 72, "loss": 1.1779, "lr": 2.5e-06, "epoch": 0.08333333333333333, "percentage": 2.78, "elapsed_time": "0:01:34", "remaining_time": "0:54:55"}
+{"current_steps": 3, "total_steps": 72, "loss": 1.2291, "lr": 3.7500000000000005e-06, "epoch": 0.125, "percentage": 4.17, "elapsed_time": "0:02:08", "remaining_time": "0:49:11"}
+{"current_steps": 4, "total_steps": 72, "loss": 1.1662, "lr": 5e-06, "epoch": 0.16666666666666666, "percentage": 5.56, "elapsed_time": "0:02:42", "remaining_time": "0:46:01"}
+{"current_steps": 5, "total_steps": 72, "loss": 1.1464, "lr": 6.25e-06, "epoch": 0.20833333333333334, "percentage": 6.94, "elapsed_time": "0:03:16", "remaining_time": "0:43:54"}
+{"current_steps": 6, "total_steps": 72, "loss": 1.0867, "lr": 7.500000000000001e-06, "epoch": 0.25, "percentage": 8.33, "elapsed_time": "0:03:50", "remaining_time": "0:42:18"}
+{"current_steps": 7, "total_steps": 72, "loss": 1.0931, "lr": 8.750000000000001e-06, "epoch": 0.2916666666666667, "percentage": 9.72, "elapsed_time": "0:04:24", "remaining_time": "0:40:59"}
+{"current_steps": 8, "total_steps": 72, "loss": 1.0674, "lr": 1e-05, "epoch": 0.3333333333333333, "percentage": 11.11, "elapsed_time": "0:04:58", "remaining_time": "0:39:51"}
+{"current_steps": 9, "total_steps": 72, "loss": 1.0213, "lr": 9.993977281025862e-06, "epoch": 0.375, "percentage": 12.5, "elapsed_time": "0:05:33", "remaining_time": "0:38:51"}
+{"current_steps": 10, "total_steps": 72, "loss": 1.0397, "lr": 9.975923633360985e-06, "epoch": 0.4166666666666667, "percentage": 13.89, "elapsed_time": "0:06:07", "remaining_time": "0:37:59"}
+{"current_steps": 11, "total_steps": 72, "loss": 0.9833, "lr": 9.945882549823906e-06, "epoch": 0.4583333333333333, "percentage": 15.28, "elapsed_time": "0:06:41", "remaining_time": "0:37:08"}
+{"current_steps": 12, "total_steps": 72, "loss": 0.9242, "lr": 9.903926402016153e-06, "epoch": 0.5, "percentage": 16.67, "elapsed_time": "0:07:15", "remaining_time": "0:36:19"}
+{"current_steps": 13, "total_steps": 72, "loss": 0.9306, "lr": 9.850156265972722e-06, "epoch": 0.5416666666666666, "percentage": 18.06, "elapsed_time": "0:07:50", "remaining_time": "0:35:33"}
+{"current_steps": 14, "total_steps": 72, "loss": 0.9053, "lr": 9.784701678661045e-06, "epoch": 0.5833333333333334, "percentage": 19.44, "elapsed_time": "0:08:24", "remaining_time": "0:34:48"}
+{"current_steps": 15, "total_steps": 72, "loss": 0.912, "lr": 9.707720325915105e-06, "epoch": 0.625, "percentage": 20.83, "elapsed_time": "0:08:58", "remaining_time": "0:34:05"}
+{"current_steps": 16, "total_steps": 72, "loss": 0.8843, "lr": 9.619397662556434e-06, "epoch": 0.6666666666666666, "percentage": 22.22, "elapsed_time": "0:09:32", "remaining_time": "0:33:23"}
+{"current_steps": 17, "total_steps": 72, "loss": 0.8891, "lr": 9.519946465617217e-06, "epoch": 0.7083333333333334, "percentage": 23.61, "elapsed_time": "0:10:06", "remaining_time": "0:32:43"}
+{"current_steps": 18, "total_steps": 72, "loss": 0.8623, "lr": 9.409606321741776e-06, "epoch": 0.75, "percentage": 25.0, "elapsed_time": "0:10:41", "remaining_time": "0:32:03"}
+{"current_steps": 19, "total_steps": 72, "loss": 0.8788, "lr": 9.288643050001362e-06, "epoch": 0.7916666666666666, "percentage": 26.39, "elapsed_time": "0:11:15", "remaining_time": "0:31:23"}
+{"current_steps": 20, "total_steps": 72, "loss": 0.8561, "lr": 9.157348061512728e-06, "epoch": 0.8333333333333334, "percentage": 27.78, "elapsed_time": "0:11:49", "remaining_time": "0:30:44"}
+{"current_steps": 21, "total_steps": 72, "loss": 0.8625, "lr": 9.016037657403225e-06, "epoch": 0.875, "percentage": 29.17, "elapsed_time": "0:12:23", "remaining_time": "0:30:05"}
+{"current_steps": 22, "total_steps": 72, "loss": 0.8625, "lr": 8.865052266813686e-06, "epoch": 0.9166666666666666, "percentage": 30.56, "elapsed_time": "0:12:57", "remaining_time": "0:29:27"}
+{"current_steps": 23, "total_steps": 72, "loss": 0.8391, "lr": 8.704755626774796e-06, "epoch": 0.9583333333333334, "percentage": 31.94, "elapsed_time": "0:13:31", "remaining_time": "0:28:49"}
+{"current_steps": 24, "total_steps": 72, "loss": 0.8406, "lr": 8.535533905932739e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:14:05", "remaining_time": "0:28:11"}
+{"current_steps": 25, "total_steps": 72, "loss": 0.819, "lr": 8.357794774235094e-06, "epoch": 1.0416666666666667, "percentage": 34.72, "elapsed_time": "0:15:28", "remaining_time": "0:29:04"}
+{"current_steps": 26, "total_steps": 72, "loss": 0.8119, "lr": 8.171966420818227e-06, "epoch": 1.0833333333333333, "percentage": 36.11, "elapsed_time": "0:16:02", "remaining_time": "0:28:22"}
+{"current_steps": 27, "total_steps": 72, "loss": 0.7977, "lr": 7.978496522462167e-06, "epoch": 1.125, "percentage": 37.5, "elapsed_time": "0:16:36", "remaining_time": "0:27:40"}
+{"current_steps": 28, "total_steps": 72, "loss": 0.7925, "lr": 7.777851165098012e-06, "epoch": 1.1666666666666667, "percentage": 38.89, "elapsed_time": "0:17:10", "remaining_time": "0:26:59"}
+{"current_steps": 29, "total_steps": 72, "loss": 0.8107, "lr": 7.570513720966108e-06, "epoch": 1.2083333333333333, "percentage": 40.28, "elapsed_time": "0:17:44", "remaining_time": "0:26:19"}
+{"current_steps": 30, "total_steps": 72, "loss": 0.8226, "lr": 7.3569836841299905e-06, "epoch": 1.25, "percentage": 41.67, "elapsed_time": "0:18:19", "remaining_time": "0:25:38"}
+{"current_steps": 31, "total_steps": 72, "loss": 0.7941, "lr": 7.137775467151411e-06, "epoch": 1.2916666666666667, "percentage": 43.06, "elapsed_time": "0:18:53", "remaining_time": "0:24:58"}
+{"current_steps": 32, "total_steps": 72, "loss": 0.8032, "lr": 6.913417161825449e-06, "epoch": 1.3333333333333333, "percentage": 44.44, "elapsed_time": "0:19:27", "remaining_time": "0:24:19"}
+{"current_steps": 33, "total_steps": 72, "loss": 0.8029, "lr": 6.684449266961101e-06, "epoch": 1.375, "percentage": 45.83, "elapsed_time": "0:20:01", "remaining_time": "0:23:40"}
+{"current_steps": 34, "total_steps": 72, "loss": 0.8081, "lr": 6.451423386272312e-06, "epoch": 1.4166666666666667, "percentage": 47.22, "elapsed_time": "0:20:36", "remaining_time": "0:23:01"}
+{"current_steps": 35, "total_steps": 72, "loss": 0.7971, "lr": 6.21490089951632e-06, "epoch": 1.4583333333333333, "percentage": 48.61, "elapsed_time": "0:21:13", "remaining_time": "0:22:26"}
+{"current_steps": 36, "total_steps": 72, "loss": 0.7916, "lr": 5.975451610080643e-06, "epoch": 1.5, "percentage": 50.0, "elapsed_time": "0:21:47", "remaining_time": "0:21:47"}
+{"current_steps": 37, "total_steps": 72, "loss": 0.809, "lr": 5.733652372276809e-06, "epoch": 1.5416666666666665, "percentage": 51.39, "elapsed_time": "0:22:21", "remaining_time": "0:21:09"}
+{"current_steps": 38, "total_steps": 72, "loss": 0.7549, "lr": 5.490085701647805e-06, "epoch": 1.5833333333333335, "percentage": 52.78, "elapsed_time": "0:22:55", "remaining_time": "0:20:31"}
+{"current_steps": 39, "total_steps": 72, "loss": 0.8049, "lr": 5.245338371637091e-06, "epoch": 1.625, "percentage": 54.17, "elapsed_time": "0:23:30", "remaining_time": "0:19:53"}
+{"current_steps": 40, "total_steps": 72, "loss": 0.7711, "lr": 5e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "0:24:04", "remaining_time": "0:19:15"}
+{"current_steps": 41, "total_steps": 72, "loss": 0.7912, "lr": 4.75466162836291e-06, "epoch": 1.7083333333333335, "percentage": 56.94, "elapsed_time": "0:24:38", "remaining_time": "0:18:37"}
+{"current_steps": 42, "total_steps": 72, "loss": 0.7608, "lr": 4.509914298352197e-06, "epoch": 1.75, "percentage": 58.33, "elapsed_time": "0:25:12", "remaining_time": "0:18:00"}
+{"current_steps": 43, "total_steps": 72, "loss": 0.7955, "lr": 4.266347627723192e-06, "epoch": 1.7916666666666665, "percentage": 59.72, "elapsed_time": "0:25:46", "remaining_time": "0:17:23"}
+{"current_steps": 44, "total_steps": 72, "loss": 0.7885, "lr": 4.02454838991936e-06, "epoch": 1.8333333333333335, "percentage": 61.11, "elapsed_time": "0:26:20", "remaining_time": "0:16:45"}
+{"current_steps": 45, "total_steps": 72, "loss": 0.7789, "lr": 3.7850991004836813e-06, "epoch": 1.875, "percentage": 62.5, "elapsed_time": "0:26:55", "remaining_time": "0:16:09"}
+{"current_steps": 46, "total_steps": 72, "loss": 0.8068, "lr": 3.5485766137276894e-06, "epoch": 1.9166666666666665, "percentage": 63.89, "elapsed_time": "0:27:29", "remaining_time": "0:15:32"}
+{"current_steps": 47, "total_steps": 72, "loss": 0.7877, "lr": 3.3155507330389004e-06, "epoch": 1.9583333333333335, "percentage": 65.28, "elapsed_time": "0:28:03", "remaining_time": "0:14:55"}
+{"current_steps": 48, "total_steps": 72, "loss": 0.7909, "lr": 3.0865828381745515e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:28:37", "remaining_time": "0:14:18"}
+{"current_steps": 49, "total_steps": 72, "loss": 0.7664, "lr": 2.862224532848591e-06, "epoch": 2.0416666666666665, "percentage": 68.06, "elapsed_time": "0:29:51", "remaining_time": "0:14:00"}
+{"current_steps": 50, "total_steps": 72, "loss": 0.7636, "lr": 2.6430163158700116e-06, "epoch": 2.0833333333333335, "percentage": 69.44, "elapsed_time": "0:30:25", "remaining_time": "0:13:23"}
+{"current_steps": 51, "total_steps": 72, "loss": 0.7494, "lr": 2.429486279033892e-06, "epoch": 2.125, "percentage": 70.83, "elapsed_time": "0:30:59", "remaining_time": "0:12:45"}
+{"current_steps": 52, "total_steps": 72, "loss": 0.7597, "lr": 2.2221488349019903e-06, "epoch": 2.1666666666666665, "percentage": 72.22, "elapsed_time": "0:31:33", "remaining_time": "0:12:08"}
+{"current_steps": 53, "total_steps": 72, "loss": 0.7377, "lr": 2.0215034775378336e-06, "epoch": 2.2083333333333335, "percentage": 73.61, "elapsed_time": "0:32:08", "remaining_time": "0:11:31"}
+{"current_steps": 54, "total_steps": 72, "loss": 0.7584, "lr": 1.8280335791817733e-06, "epoch": 2.25, "percentage": 75.0, "elapsed_time": "0:32:42", "remaining_time": "0:10:54"}
+{"current_steps": 55, "total_steps": 72, "loss": 0.7593, "lr": 1.642205225764908e-06, "epoch": 2.2916666666666665, "percentage": 76.39, "elapsed_time": "0:33:16", "remaining_time": "0:10:17"}
+{"current_steps": 56, "total_steps": 72, "loss": 0.7555, "lr": 1.4644660940672628e-06, "epoch": 2.3333333333333335, "percentage": 77.78, "elapsed_time": "0:33:50", "remaining_time": "0:09:40"}
+{"current_steps": 57, "total_steps": 72, "loss": 0.7793, "lr": 1.2952443732252058e-06, "epoch": 2.375, "percentage": 79.17, "elapsed_time": "0:34:25", "remaining_time": "0:09:03"}
+{"current_steps": 58, "total_steps": 72, "loss": 0.7309, "lr": 1.134947733186315e-06, "epoch": 2.4166666666666665, "percentage": 80.56, "elapsed_time": "0:34:59", "remaining_time": "0:08:26"}
+{"current_steps": 59, "total_steps": 72, "loss": 0.7514, "lr": 9.83962342596776e-07, "epoch": 2.4583333333333335, "percentage": 81.94, "elapsed_time": "0:35:33", "remaining_time": "0:07:50"}
+{"current_steps": 60, "total_steps": 72, "loss": 0.7758, "lr": 8.426519384872733e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:36:07", "remaining_time": "0:07:13"}
+{"current_steps": 61, "total_steps": 72, "loss": 0.7473, "lr": 7.113569499986401e-07, "epoch": 2.5416666666666665, "percentage": 84.72, "elapsed_time": "0:36:41", "remaining_time": "0:06:37"}
+{"current_steps": 62, "total_steps": 72, "loss": 0.7523, "lr": 5.903936782582253e-07, "epoch": 2.5833333333333335, "percentage": 86.11, "elapsed_time": "0:37:15", "remaining_time": "0:06:00"}
+{"current_steps": 63, "total_steps": 72, "loss": 0.7441, "lr": 4.800535343827834e-07, "epoch": 2.625, "percentage": 87.5, "elapsed_time": "0:37:49", "remaining_time": "0:05:24"}
+{"current_steps": 64, "total_steps": 72, "loss": 0.7592, "lr": 3.8060233744356634e-07, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "0:38:24", "remaining_time": "0:04:48"}
+{"current_steps": 65, "total_steps": 72, "loss": 0.74, "lr": 2.9227967408489653e-07, "epoch": 2.7083333333333335, "percentage": 90.28, "elapsed_time": "0:38:58", "remaining_time": "0:04:11"}
+{"current_steps": 66, "total_steps": 72, "loss": 0.7528, "lr": 2.152983213389559e-07, "epoch": 2.75, "percentage": 91.67, "elapsed_time": "0:39:32", "remaining_time": "0:03:35"}
+{"current_steps": 67, "total_steps": 72, "loss": 0.7476, "lr": 1.4984373402728014e-07, "epoch": 2.7916666666666665, "percentage": 93.06, "elapsed_time": "0:40:06", "remaining_time": "0:02:59"}
+{"current_steps": 68, "total_steps": 72, "loss": 0.7626, "lr": 9.607359798384785e-08, "epoch": 2.8333333333333335, "percentage": 94.44, "elapsed_time": "0:40:40", "remaining_time": "0:02:23"}
+{"current_steps": 69, "total_steps": 72, "loss": 0.7476, "lr": 5.411745017609493e-08, "epoch": 2.875, "percentage": 95.83, "elapsed_time": "0:41:15", "remaining_time": "0:01:47"}
+{"current_steps": 70, "total_steps": 72, "loss": 0.7685, "lr": 2.4076366639015914e-08, "epoch": 2.9166666666666665, "percentage": 97.22, "elapsed_time": "0:41:49", "remaining_time": "0:01:11"}
+{"current_steps": 71, "total_steps": 72, "loss": 0.736, "lr": 6.022718974137976e-09, "epoch": 2.9583333333333335, "percentage": 98.61, "elapsed_time": "0:42:23", "remaining_time": "0:00:35"}
+{"current_steps": 72, "total_steps": 72, "loss": 0.7468, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:42:57", "remaining_time": "0:00:00"}
+{"current_steps": 72, "total_steps": 72, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:43:54", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,546 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 72,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.041666666666666664,
+      "grad_norm": 7.4461519509711245,
+      "learning_rate": 1.25e-06,
+      "loss": 1.222,
+      "step": 1
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 7.194929737353425,
+      "learning_rate": 2.5e-06,
+      "loss": 1.1779,
+      "step": 2
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 7.333967870950286,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 1.2291,
+      "step": 3
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 6.570794290680697,
+      "learning_rate": 5e-06,
+      "loss": 1.1662,
+      "step": 4
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 5.127918855747146,
+      "learning_rate": 6.25e-06,
+      "loss": 1.1464,
+      "step": 5
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 2.528659831516316,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.0867,
+      "step": 6
+    },
+    {
+      "epoch": 0.2916666666666667,
+      "grad_norm": 4.974882078396541,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 1.0931,
+      "step": 7
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 5.324763274797421,
+      "learning_rate": 1e-05,
+      "loss": 1.0674,
+      "step": 8
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 4.680608433921859,
+      "learning_rate": 9.993977281025862e-06,
+      "loss": 1.0213,
+      "step": 9
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 5.1315789257717945,
+      "learning_rate": 9.975923633360985e-06,
+      "loss": 1.0397,
+      "step": 10
+    },
+    {
+      "epoch": 0.4583333333333333,
+      "grad_norm": 3.6025890380547745,
+      "learning_rate": 9.945882549823906e-06,
+      "loss": 0.9833,
+      "step": 11
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.2633809022438287,
+      "learning_rate": 9.903926402016153e-06,
+      "loss": 0.9242,
+      "step": 12
+    },
+    {
+      "epoch": 0.5416666666666666,
+      "grad_norm": 2.523949643335755,
+      "learning_rate": 9.850156265972722e-06,
+      "loss": 0.9306,
+      "step": 13
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 2.3117675062860883,
+      "learning_rate": 9.784701678661045e-06,
+      "loss": 0.9053,
+      "step": 14
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 1.8591474201560603,
+      "learning_rate": 9.707720325915105e-06,
+      "loss": 0.912,
+      "step": 15
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.472720248225591,
+      "learning_rate": 9.619397662556434e-06,
+      "loss": 0.8843,
+      "step": 16
+    },
+    {
+      "epoch": 0.7083333333333334,
+      "grad_norm": 1.2895049049519833,
+      "learning_rate": 9.519946465617217e-06,
+      "loss": 0.8891,
+      "step": 17
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.1773227687641274,
+      "learning_rate": 9.409606321741776e-06,
+      "loss": 0.8623,
+      "step": 18
+    },
+    {
+      "epoch": 0.7916666666666666,
+      "grad_norm": 1.1404756655161843,
+      "learning_rate": 9.288643050001362e-06,
+      "loss": 0.8788,
+      "step": 19
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.8551371234751329,
+      "learning_rate": 9.157348061512728e-06,
+      "loss": 0.8561,
+      "step": 20
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.8093803560929222,
+      "learning_rate": 9.016037657403225e-06,
+      "loss": 0.8625,
+      "step": 21
+    },
+    {
+      "epoch": 0.9166666666666666,
+      "grad_norm": 0.7817687246884554,
+      "learning_rate": 8.865052266813686e-06,
+      "loss": 0.8625,
+      "step": 22
+    },
+    {
+      "epoch": 0.9583333333333334,
+      "grad_norm": 0.8101494321706375,
+      "learning_rate": 8.704755626774796e-06,
+      "loss": 0.8391,
+      "step": 23
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5093988051964708,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 0.8406,
+      "step": 24
+    },
+    {
+      "epoch": 1.0416666666666667,
+      "grad_norm": 0.5665482168782667,
+      "learning_rate": 8.357794774235094e-06,
+      "loss": 0.819,
+      "step": 25
+    },
+    {
+      "epoch": 1.0833333333333333,
+      "grad_norm": 0.5605222851113811,
+      "learning_rate": 8.171966420818227e-06,
+      "loss": 0.8119,
+      "step": 26
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 0.563011084024224,
+      "learning_rate": 7.978496522462167e-06,
+      "loss": 0.7977,
+      "step": 27
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.4370218328877668,
+      "learning_rate": 7.777851165098012e-06,
+      "loss": 0.7925,
+      "step": 28
+    },
+    {
+      "epoch": 1.2083333333333333,
+      "grad_norm": 0.4363576530088793,
+      "learning_rate": 7.570513720966108e-06,
+      "loss": 0.8107,
+      "step": 29
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.454199209193312,
+      "learning_rate": 7.3569836841299905e-06,
+      "loss": 0.8226,
+      "step": 30
+    },
+    {
+      "epoch": 1.2916666666666667,
+      "grad_norm": 0.43849188161106434,
+      "learning_rate": 7.137775467151411e-06,
+      "loss": 0.7941,
+      "step": 31
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.39461206608240496,
+      "learning_rate": 6.913417161825449e-06,
+      "loss": 0.8032,
+      "step": 32
+    },
+    {
+      "epoch": 1.375,
+      "grad_norm": 0.45668675578130913,
+      "learning_rate": 6.684449266961101e-06,
+      "loss": 0.8029,
+      "step": 33
+    },
+    {
+      "epoch": 1.4166666666666667,
+      "grad_norm": 0.43600043654014087,
+      "learning_rate": 6.451423386272312e-06,
+      "loss": 0.8081,
+      "step": 34
+    },
+    {
+      "epoch": 1.4583333333333333,
+      "grad_norm": 0.42108216786596225,
+      "learning_rate": 6.21490089951632e-06,
+      "loss": 0.7971,
+      "step": 35
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.35021427514409276,
+      "learning_rate": 5.975451610080643e-06,
+      "loss": 0.7916,
+      "step": 36
+    },
+    {
+      "epoch": 1.5416666666666665,
+      "grad_norm": 0.5456525909687769,
+      "learning_rate": 5.733652372276809e-06,
+      "loss": 0.809,
+      "step": 37
+    },
+    {
+      "epoch": 1.5833333333333335,
+      "grad_norm": 0.44917605026168267,
+      "learning_rate": 5.490085701647805e-06,
+      "loss": 0.7549,
+      "step": 38
+    },
+    {
+      "epoch": 1.625,
+      "grad_norm": 0.36337481633076185,
+      "learning_rate": 5.245338371637091e-06,
+      "loss": 0.8049,
+      "step": 39
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.35099097879704033,
+      "learning_rate": 5e-06,
+      "loss": 0.7711,
+      "step": 40
+    },
+    {
+      "epoch": 1.7083333333333335,
+      "grad_norm": 0.3474553408571236,
+      "learning_rate": 4.75466162836291e-06,
+      "loss": 0.7912,
+      "step": 41
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.40430012822618056,
+      "learning_rate": 4.509914298352197e-06,
+      "loss": 0.7608,
+      "step": 42
+    },
+    {
+      "epoch": 1.7916666666666665,
+      "grad_norm": 0.3638732435388027,
+      "learning_rate": 4.266347627723192e-06,
+      "loss": 0.7955,
+      "step": 43
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 0.3566549145751346,
+      "learning_rate": 4.02454838991936e-06,
+      "loss": 0.7885,
+      "step": 44
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 0.345560427391061,
+      "learning_rate": 3.7850991004836813e-06,
+      "loss": 0.7789,
+      "step": 45
+    },
+    {
+      "epoch": 1.9166666666666665,
+      "grad_norm": 0.32890679342787366,
+      "learning_rate": 3.5485766137276894e-06,
+      "loss": 0.8068,
+      "step": 46
+    },
+    {
+      "epoch": 1.9583333333333335,
+      "grad_norm": 0.30384650295902926,
+      "learning_rate": 3.3155507330389004e-06,
+      "loss": 0.7877,
+      "step": 47
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.315934146641292,
+      "learning_rate": 3.0865828381745515e-06,
+      "loss": 0.7909,
+      "step": 48
+    },
+    {
+      "epoch": 2.0416666666666665,
+      "grad_norm": 0.3088706026275368,
+      "learning_rate": 2.862224532848591e-06,
+      "loss": 0.7664,
+      "step": 49
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 0.2934756055775262,
+      "learning_rate": 2.6430163158700116e-06,
+      "loss": 0.7636,
+      "step": 50
+    },
+    {
+      "epoch": 2.125,
+      "grad_norm": 0.2781668159606118,
+      "learning_rate": 2.429486279033892e-06,
+      "loss": 0.7494,
+      "step": 51
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 0.26041364038043807,
+      "learning_rate": 2.2221488349019903e-06,
+      "loss": 0.7597,
+      "step": 52
+    },
+    {
+      "epoch": 2.2083333333333335,
+      "grad_norm": 0.28685389706179326,
+      "learning_rate": 2.0215034775378336e-06,
+      "loss": 0.7377,
+      "step": 53
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.2814318410441988,
+      "learning_rate": 1.8280335791817733e-06,
+      "loss": 0.7584,
+      "step": 54
+    },
+    {
+      "epoch": 2.2916666666666665,
+      "grad_norm": 0.2882795848313525,
+      "learning_rate": 1.642205225764908e-06,
+      "loss": 0.7593,
+      "step": 55
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.2678705990361174,
+      "learning_rate": 1.4644660940672628e-06,
+      "loss": 0.7555,
+      "step": 56
+    },
+    {
+      "epoch": 2.375,
+      "grad_norm": 0.29557635096062773,
+      "learning_rate": 1.2952443732252058e-06,
+      "loss": 0.7793,
+      "step": 57
+    },
+    {
+      "epoch": 2.4166666666666665,
+      "grad_norm": 0.2907068363495174,
+      "learning_rate": 1.134947733186315e-06,
+      "loss": 0.7309,
+      "step": 58
+    },
+    {
+      "epoch": 2.4583333333333335,
+      "grad_norm": 0.2657901924127417,
+      "learning_rate": 9.83962342596776e-07,
+      "loss": 0.7514,
+      "step": 59
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.24256134408455063,
+      "learning_rate": 8.426519384872733e-07,
+      "loss": 0.7758,
+      "step": 60
+    },
+    {
+      "epoch": 2.5416666666666665,
+      "grad_norm": 0.2640727281354079,
+      "learning_rate": 7.113569499986401e-07,
+      "loss": 0.7473,
+      "step": 61
+    },
+    {
+      "epoch": 2.5833333333333335,
+      "grad_norm": 0.24447100703685454,
+      "learning_rate": 5.903936782582253e-07,
+      "loss": 0.7523,
+      "step": 62
+    },
+    {
+      "epoch": 2.625,
+      "grad_norm": 0.255955912903117,
+      "learning_rate": 4.800535343827834e-07,
+      "loss": 0.7441,
+      "step": 63
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.2500055813341445,
+      "learning_rate": 3.8060233744356634e-07,
+      "loss": 0.7592,
+      "step": 64
+    },
+    {
+      "epoch": 2.7083333333333335,
+      "grad_norm": 0.2368922676632115,
+      "learning_rate": 2.9227967408489653e-07,
+      "loss": 0.74,
+      "step": 65
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.25004456778320516,
+      "learning_rate": 2.152983213389559e-07,
+      "loss": 0.7528,
+      "step": 66
+    },
+    {
+      "epoch": 2.7916666666666665,
+      "grad_norm": 0.23738559029873482,
+      "learning_rate": 1.4984373402728014e-07,
+      "loss": 0.7476,
+      "step": 67
+    },
+    {
+      "epoch": 2.8333333333333335,
+      "grad_norm": 0.23711273434333477,
+      "learning_rate": 9.607359798384785e-08,
+      "loss": 0.7626,
+      "step": 68
+    },
+    {
+      "epoch": 2.875,
+      "grad_norm": 0.24058387004215953,
+      "learning_rate": 5.411745017609493e-08,
+      "loss": 0.7476,
+      "step": 69
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "grad_norm": 0.23933234547011273,
+      "learning_rate": 2.4076366639015914e-08,
+      "loss": 0.7685,
+      "step": 70
+    },
+    {
+      "epoch": 2.9583333333333335,
+      "grad_norm": 0.22845877486050034,
+      "learning_rate": 6.022718974137976e-09,
+      "loss": 0.736,
+      "step": 71
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.23887168528712394,
+      "learning_rate": 0.0,
+      "loss": 0.7468,
+      "step": 72
+    },
+    {
+      "epoch": 3.0,
+      "step": 72,
+      "total_flos": 2.4710097421939507e+17,
+      "train_loss": 0.8453347384929657,
+      "train_runtime": 2641.4784,
+      "train_samples_per_second": 2.613,
+      "train_steps_per_second": 0.027
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 72,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.4710097421939507e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d512b3c612a60be486fb4d21ea671584133329c619f88bacda4bd60e21f4395
+size 7480