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": 2.961439588688946,
+    "total_flos": 1.8527734208659456e+18,
+    "train_loss": 0.7965062566929393,
+    "train_runtime": 15726.6597,
+    "train_samples_per_second": 2.373,
+    "train_steps_per_second": 0.005
+}

config.json

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

generation_config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d0bbab5241025772a96059624ac88e87bfea1eb9182f3d68797a247fe97b56b
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a774e21016c4e71538d870a090fc91ad544db01cad5ab9717ce414fa2bf1e6
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c90179f29b1ce5efc4240b2525e1b185a1511b65b66f207dc8afddc403051f5b
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e717d933ecd5e07b5494be390bff71745961a63a72babad383862711d1c464a4
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.961439588688946,
+    "total_flos": 1.8527734208659456e+18,
+    "train_loss": 0.7965062566929393,
+    "train_runtime": 15726.6597,
+    "train_samples_per_second": 2.373,
+    "train_steps_per_second": 0.005
+}

trainer_log.jsonl

@@ -0,0 +1,73 @@
+{"current_steps": 1, "total_steps": 72, "loss": 1.2112, "lr": 1e-05, "epoch": 0.04113110539845758, "percentage": 1.39, "elapsed_time": "0:04:17", "remaining_time": "5:04:36"}
+{"current_steps": 2, "total_steps": 72, "loss": 1.2033, "lr": 2e-05, "epoch": 0.08226221079691516, "percentage": 2.78, "elapsed_time": "0:07:53", "remaining_time": "4:36:26"}
+{"current_steps": 3, "total_steps": 72, "loss": 1.0955, "lr": 3.0000000000000004e-05, "epoch": 0.12339331619537275, "percentage": 4.17, "elapsed_time": "0:11:30", "remaining_time": "4:24:38"}
+{"current_steps": 4, "total_steps": 72, "loss": 1.1047, "lr": 4e-05, "epoch": 0.16452442159383032, "percentage": 5.56, "elapsed_time": "0:15:04", "remaining_time": "4:16:15"}
+{"current_steps": 5, "total_steps": 72, "loss": 1.1423, "lr": 5e-05, "epoch": 0.20565552699228792, "percentage": 6.94, "elapsed_time": "0:18:37", "remaining_time": "4:09:28"}
+{"current_steps": 6, "total_steps": 72, "loss": 1.0961, "lr": 6.000000000000001e-05, "epoch": 0.2467866323907455, "percentage": 8.33, "elapsed_time": "0:22:09", "remaining_time": "4:03:43"}
+{"current_steps": 7, "total_steps": 72, "loss": 1.0179, "lr": 7.000000000000001e-05, "epoch": 0.2879177377892031, "percentage": 9.72, "elapsed_time": "0:25:43", "remaining_time": "3:58:48"}
+{"current_steps": 8, "total_steps": 72, "loss": 1.001, "lr": 8e-05, "epoch": 0.32904884318766064, "percentage": 11.11, "elapsed_time": "0:29:17", "remaining_time": "3:54:20"}
+{"current_steps": 9, "total_steps": 72, "loss": 0.9559, "lr": 7.99518182482069e-05, "epoch": 0.37017994858611825, "percentage": 12.5, "elapsed_time": "0:32:52", "remaining_time": "3:50:04"}
+{"current_steps": 10, "total_steps": 72, "loss": 0.9333, "lr": 7.980738906688788e-05, "epoch": 0.41131105398457585, "percentage": 13.89, "elapsed_time": "0:36:26", "remaining_time": "3:45:54"}
+{"current_steps": 11, "total_steps": 72, "loss": 0.8816, "lr": 7.956706039859124e-05, "epoch": 0.4524421593830334, "percentage": 15.28, "elapsed_time": "0:39:59", "remaining_time": "3:41:47"}
+{"current_steps": 12, "total_steps": 72, "loss": 0.8995, "lr": 7.923141121612922e-05, "epoch": 0.493573264781491, "percentage": 16.67, "elapsed_time": "0:43:28", "remaining_time": "3:37:20"}
+{"current_steps": 13, "total_steps": 72, "loss": 1.3647, "lr": 7.880125012778177e-05, "epoch": 0.5347043701799485, "percentage": 18.06, "elapsed_time": "0:46:50", "remaining_time": "3:32:34"}
+{"current_steps": 14, "total_steps": 72, "loss": 1.1214, "lr": 7.827761342928836e-05, "epoch": 0.5758354755784062, "percentage": 19.44, "elapsed_time": "0:50:23", "remaining_time": "3:28:47"}
+{"current_steps": 15, "total_steps": 72, "loss": 1.115, "lr": 7.766176260732084e-05, "epoch": 0.6169665809768637, "percentage": 20.83, "elapsed_time": "0:53:57", "remaining_time": "3:25:04"}
+{"current_steps": 16, "total_steps": 72, "loss": 0.9562, "lr": 7.695518130045147e-05, "epoch": 0.6580976863753213, "percentage": 22.22, "elapsed_time": "0:57:30", "remaining_time": "3:21:15"}
+{"current_steps": 17, "total_steps": 72, "loss": 0.9133, "lr": 7.615957172493774e-05, "epoch": 0.699228791773779, "percentage": 23.61, "elapsed_time": "1:01:04", "remaining_time": "3:17:35"}
+{"current_steps": 18, "total_steps": 72, "loss": 0.8791, "lr": 7.52768505739342e-05, "epoch": 0.7403598971722365, "percentage": 25.0, "elapsed_time": "1:04:37", "remaining_time": "3:13:51"}
+{"current_steps": 19, "total_steps": 72, "loss": 0.8744, "lr": 7.430914440001089e-05, "epoch": 0.781491002570694, "percentage": 26.39, "elapsed_time": "1:08:32", "remaining_time": "3:11:11"}
+{"current_steps": 20, "total_steps": 72, "loss": 0.8437, "lr": 7.325878449210182e-05, "epoch": 0.8226221079691517, "percentage": 27.78, "elapsed_time": "1:13:10", "remaining_time": "3:10:15"}
+{"current_steps": 21, "total_steps": 72, "loss": 0.8163, "lr": 7.21283012592258e-05, "epoch": 0.8637532133676092, "percentage": 29.17, "elapsed_time": "1:17:06", "remaining_time": "3:07:16"}
+{"current_steps": 22, "total_steps": 72, "loss": 0.8066, "lr": 7.092041813450948e-05, "epoch": 0.9048843187660668, "percentage": 30.56, "elapsed_time": "1:20:52", "remaining_time": "3:03:49"}
+{"current_steps": 23, "total_steps": 72, "loss": 0.8061, "lr": 6.963804501419837e-05, "epoch": 0.9460154241645244, "percentage": 31.94, "elapsed_time": "1:24:29", "remaining_time": "2:59:59"}
+{"current_steps": 24, "total_steps": 72, "loss": 0.7991, "lr": 6.828427124746191e-05, "epoch": 0.987146529562982, "percentage": 33.33, "elapsed_time": "1:28:08", "remaining_time": "2:56:17"}
+{"current_steps": 25, "total_steps": 72, "loss": 0.8015, "lr": 6.686235819388075e-05, "epoch": 1.0282776349614395, "percentage": 34.72, "elapsed_time": "1:32:54", "remaining_time": "2:54:39"}
+{"current_steps": 26, "total_steps": 72, "loss": 0.7812, "lr": 6.537573136654582e-05, "epoch": 1.069408740359897, "percentage": 36.11, "elapsed_time": "1:36:29", "remaining_time": "2:50:42"}
+{"current_steps": 27, "total_steps": 72, "loss": 0.7926, "lr": 6.382797217969734e-05, "epoch": 1.1105398457583548, "percentage": 37.5, "elapsed_time": "1:40:04", "remaining_time": "2:46:47"}
+{"current_steps": 28, "total_steps": 72, "loss": 0.7228, "lr": 6.22228093207841e-05, "epoch": 1.1516709511568124, "percentage": 38.89, "elapsed_time": "1:43:38", "remaining_time": "2:42:51"}
+{"current_steps": 29, "total_steps": 72, "loss": 0.7668, "lr": 6.056410976772887e-05, "epoch": 1.19280205655527, "percentage": 40.28, "elapsed_time": "1:47:13", "remaining_time": "2:38:59"}
+{"current_steps": 30, "total_steps": 72, "loss": 0.7555, "lr": 5.8855869473039924e-05, "epoch": 1.2339331619537275, "percentage": 41.67, "elapsed_time": "1:50:47", "remaining_time": "2:35:07"}
+{"current_steps": 31, "total_steps": 72, "loss": 0.725, "lr": 5.710220373721129e-05, "epoch": 1.275064267352185, "percentage": 43.06, "elapsed_time": "1:54:22", "remaining_time": "2:31:16"}
+{"current_steps": 32, "total_steps": 72, "loss": 0.755, "lr": 5.5307337294603595e-05, "epoch": 1.3161953727506428, "percentage": 44.44, "elapsed_time": "1:57:56", "remaining_time": "2:27:25"}
+{"current_steps": 33, "total_steps": 72, "loss": 0.734, "lr": 5.347559413568881e-05, "epoch": 1.3573264781491003, "percentage": 45.83, "elapsed_time": "2:01:29", "remaining_time": "2:23:34"}
+{"current_steps": 34, "total_steps": 72, "loss": 0.7788, "lr": 5.16113870901785e-05, "epoch": 1.398457583547558, "percentage": 47.22, "elapsed_time": "2:05:02", "remaining_time": "2:19:45"}
+{"current_steps": 35, "total_steps": 72, "loss": 0.7554, "lr": 4.971920719613056e-05, "epoch": 1.4395886889460154, "percentage": 48.61, "elapsed_time": "2:08:38", "remaining_time": "2:15:59"}
+{"current_steps": 36, "total_steps": 72, "loss": 0.7256, "lr": 4.780361288064514e-05, "epoch": 1.480719794344473, "percentage": 50.0, "elapsed_time": "2:12:11", "remaining_time": "2:12:11"}
+{"current_steps": 37, "total_steps": 72, "loss": 0.7338, "lr": 4.586921897821447e-05, "epoch": 1.5218508997429305, "percentage": 51.39, "elapsed_time": "2:15:38", "remaining_time": "2:08:18"}
+{"current_steps": 38, "total_steps": 72, "loss": 0.7109, "lr": 4.392068561318244e-05, "epoch": 1.562982005141388, "percentage": 52.78, "elapsed_time": "2:19:03", "remaining_time": "2:04:25"}
+{"current_steps": 39, "total_steps": 72, "loss": 0.7282, "lr": 4.1962706973096726e-05, "epoch": 1.6041131105398456, "percentage": 54.17, "elapsed_time": "2:22:37", "remaining_time": "2:00:40"}
+{"current_steps": 40, "total_steps": 72, "loss": 0.7073, "lr": 4e-05, "epoch": 1.6452442159383034, "percentage": 55.56, "elapsed_time": "2:26:10", "remaining_time": "1:56:56"}
+{"current_steps": 41, "total_steps": 72, "loss": 0.7067, "lr": 3.803729302690328e-05, "epoch": 1.686375321336761, "percentage": 56.94, "elapsed_time": "2:29:43", "remaining_time": "1:53:12"}
+{"current_steps": 42, "total_steps": 72, "loss": 0.6925, "lr": 3.6079314386817575e-05, "epoch": 1.7275064267352185, "percentage": 58.33, "elapsed_time": "2:33:17", "remaining_time": "1:49:29"}
+{"current_steps": 43, "total_steps": 72, "loss": 0.6938, "lr": 3.4130781021785535e-05, "epoch": 1.7686375321336762, "percentage": 59.72, "elapsed_time": "2:36:51", "remaining_time": "1:45:47"}
+{"current_steps": 44, "total_steps": 72, "loss": 0.7192, "lr": 3.219638711935488e-05, "epoch": 1.8097686375321338, "percentage": 61.11, "elapsed_time": "2:40:24", "remaining_time": "1:42:04"}
+{"current_steps": 45, "total_steps": 72, "loss": 0.733, "lr": 3.028079280386945e-05, "epoch": 1.8508997429305913, "percentage": 62.5, "elapsed_time": "2:43:57", "remaining_time": "1:38:22"}
+{"current_steps": 46, "total_steps": 72, "loss": 0.7089, "lr": 2.8388612909821515e-05, "epoch": 1.8920308483290489, "percentage": 63.89, "elapsed_time": "2:47:31", "remaining_time": "1:34:41"}
+{"current_steps": 47, "total_steps": 72, "loss": 0.6901, "lr": 2.6524405864311203e-05, "epoch": 1.9331619537275064, "percentage": 65.28, "elapsed_time": "2:51:04", "remaining_time": "1:30:59"}
+{"current_steps": 48, "total_steps": 72, "loss": 0.6814, "lr": 2.4692662705396412e-05, "epoch": 1.974293059125964, "percentage": 66.67, "elapsed_time": "2:54:37", "remaining_time": "1:27:18"}
+{"current_steps": 49, "total_steps": 72, "loss": 0.6945, "lr": 2.2897796262788728e-05, "epoch": 2.0154241645244215, "percentage": 68.06, "elapsed_time": "2:59:11", "remaining_time": "1:24:06"}
+{"current_steps": 50, "total_steps": 72, "loss": 0.6808, "lr": 2.1144130526960093e-05, "epoch": 2.056555269922879, "percentage": 69.44, "elapsed_time": "3:02:41", "remaining_time": "1:20:23"}
+{"current_steps": 51, "total_steps": 72, "loss": 0.6365, "lr": 1.9435890232271136e-05, "epoch": 2.0976863753213366, "percentage": 70.83, "elapsed_time": "3:06:14", "remaining_time": "1:16:41"}
+{"current_steps": 52, "total_steps": 72, "loss": 0.6733, "lr": 1.7777190679215923e-05, "epoch": 2.138817480719794, "percentage": 72.22, "elapsed_time": "3:09:48", "remaining_time": "1:13:00"}
+{"current_steps": 53, "total_steps": 72, "loss": 0.6676, "lr": 1.617202782030267e-05, "epoch": 2.179948586118252, "percentage": 73.61, "elapsed_time": "3:13:22", "remaining_time": "1:09:19"}
+{"current_steps": 54, "total_steps": 72, "loss": 0.6436, "lr": 1.4624268633454187e-05, "epoch": 2.2210796915167097, "percentage": 75.0, "elapsed_time": "3:16:55", "remaining_time": "1:05:38"}
+{"current_steps": 55, "total_steps": 72, "loss": 0.6417, "lr": 1.3137641806119264e-05, "epoch": 2.2622107969151672, "percentage": 76.39, "elapsed_time": "3:20:29", "remaining_time": "1:01:58"}
+{"current_steps": 56, "total_steps": 72, "loss": 0.6674, "lr": 1.1715728752538103e-05, "epoch": 2.303341902313625, "percentage": 77.78, "elapsed_time": "3:24:02", "remaining_time": "0:58:17"}
+{"current_steps": 57, "total_steps": 72, "loss": 0.6733, "lr": 1.0361954985801646e-05, "epoch": 2.3444730077120823, "percentage": 79.17, "elapsed_time": "3:27:37", "remaining_time": "0:54:38"}
+{"current_steps": 58, "total_steps": 72, "loss": 0.6748, "lr": 9.07958186549052e-06, "epoch": 2.38560411311054, "percentage": 80.56, "elapsed_time": "3:31:11", "remaining_time": "0:50:58"}
+{"current_steps": 59, "total_steps": 72, "loss": 0.6552, "lr": 7.871698740774208e-06, "epoch": 2.4267352185089974, "percentage": 81.94, "elapsed_time": "3:34:45", "remaining_time": "0:47:19"}
+{"current_steps": 60, "total_steps": 72, "loss": 0.6551, "lr": 6.7412155078981865e-06, "epoch": 2.467866323907455, "percentage": 83.33, "elapsed_time": "3:38:17", "remaining_time": "0:43:39"}
+{"current_steps": 61, "total_steps": 72, "loss": 0.6501, "lr": 5.690855599989121e-06, "epoch": 2.5089974293059125, "percentage": 84.72, "elapsed_time": "3:41:43", "remaining_time": "0:39:59"}
+{"current_steps": 62, "total_steps": 72, "loss": 0.6848, "lr": 4.723149426065803e-06, "epoch": 2.55012853470437, "percentage": 86.11, "elapsed_time": "3:45:17", "remaining_time": "0:36:20"}
+{"current_steps": 63, "total_steps": 72, "loss": 0.6778, "lr": 3.840428275062267e-06, "epoch": 2.5912596401028276, "percentage": 87.5, "elapsed_time": "3:48:51", "remaining_time": "0:32:41"}
+{"current_steps": 64, "total_steps": 72, "loss": 0.6546, "lr": 3.0448186995485307e-06, "epoch": 2.6323907455012856, "percentage": 88.89, "elapsed_time": "3:52:27", "remaining_time": "0:29:03"}
+{"current_steps": 65, "total_steps": 72, "loss": 0.6539, "lr": 2.3382373926791722e-06, "epoch": 2.6735218508997427, "percentage": 90.28, "elapsed_time": "3:56:01", "remaining_time": "0:25:25"}
+{"current_steps": 66, "total_steps": 72, "loss": 0.6565, "lr": 1.7223865707116472e-06, "epoch": 2.7146529562982007, "percentage": 91.67, "elapsed_time": "3:59:35", "remaining_time": "0:21:46"}
+{"current_steps": 67, "total_steps": 72, "loss": 0.661, "lr": 1.1987498722182411e-06, "epoch": 2.7557840616966582, "percentage": 93.06, "elapsed_time": "4:03:09", "remaining_time": "0:18:08"}
+{"current_steps": 68, "total_steps": 72, "loss": 0.6437, "lr": 7.685887838707828e-07, "epoch": 2.796915167095116, "percentage": 94.44, "elapsed_time": "4:06:44", "remaining_time": "0:14:30"}
+{"current_steps": 69, "total_steps": 72, "loss": 0.6573, "lr": 4.3293960140875946e-07, "epoch": 2.8380462724935733, "percentage": 95.83, "elapsed_time": "4:10:16", "remaining_time": "0:10:52"}
+{"current_steps": 70, "total_steps": 72, "loss": 0.6578, "lr": 1.926109331121273e-07, "epoch": 2.879177377892031, "percentage": 97.22, "elapsed_time": "4:13:51", "remaining_time": "0:07:15"}
+{"current_steps": 71, "total_steps": 72, "loss": 0.6636, "lr": 4.8181751793103806e-08, "epoch": 2.9203084832904884, "percentage": 98.61, "elapsed_time": "4:17:25", "remaining_time": "0:03:37"}
+{"current_steps": 72, "total_steps": 72, "loss": 0.6851, "lr": 0.0, "epoch": 2.961439588688946, "percentage": 100.0, "elapsed_time": "4:20:51", "remaining_time": "0:00:00"}
+{"current_steps": 72, "total_steps": 72, "epoch": 2.961439588688946, "percentage": 100.0, "elapsed_time": "4:21:59", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,546 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.961439588688946,
+  "eval_steps": 500,
+  "global_step": 72,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04113110539845758,
+      "grad_norm": 7.505963400690382,
+      "learning_rate": 1e-05,
+      "loss": 1.2112,
+      "step": 1
+    },
+    {
+      "epoch": 0.08226221079691516,
+      "grad_norm": 7.356186238669317,
+      "learning_rate": 2e-05,
+      "loss": 1.2033,
+      "step": 2
+    },
+    {
+      "epoch": 0.12339331619537275,
+      "grad_norm": 3.0048904658734727,
+      "learning_rate": 3.0000000000000004e-05,
+      "loss": 1.0955,
+      "step": 3
+    },
+    {
+      "epoch": 0.16452442159383032,
+      "grad_norm": 6.36114145034298,
+      "learning_rate": 4e-05,
+      "loss": 1.1047,
+      "step": 4
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 10.359843085593981,
+      "learning_rate": 5e-05,
+      "loss": 1.1423,
+      "step": 5
+    },
+    {
+      "epoch": 0.2467866323907455,
+      "grad_norm": 9.570786412238004,
+      "learning_rate": 6.000000000000001e-05,
+      "loss": 1.0961,
+      "step": 6
+    },
+    {
+      "epoch": 0.2879177377892031,
+      "grad_norm": 4.002098022114451,
+      "learning_rate": 7.000000000000001e-05,
+      "loss": 1.0179,
+      "step": 7
+    },
+    {
+      "epoch": 0.32904884318766064,
+      "grad_norm": 6.556063319489556,
+      "learning_rate": 8e-05,
+      "loss": 1.001,
+      "step": 8
+    },
+    {
+      "epoch": 0.37017994858611825,
+      "grad_norm": 3.3371605789599936,
+      "learning_rate": 7.99518182482069e-05,
+      "loss": 0.9559,
+      "step": 9
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 4.738531982713494,
+      "learning_rate": 7.980738906688788e-05,
+      "loss": 0.9333,
+      "step": 10
+    },
+    {
+      "epoch": 0.4524421593830334,
+      "grad_norm": 1.87006689152797,
+      "learning_rate": 7.956706039859124e-05,
+      "loss": 0.8816,
+      "step": 11
+    },
+    {
+      "epoch": 0.493573264781491,
+      "grad_norm": 2.7434579077206185,
+      "learning_rate": 7.923141121612922e-05,
+      "loss": 0.8995,
+      "step": 12
+    },
+    {
+      "epoch": 0.5347043701799485,
+      "grad_norm": 3467.8732774954487,
+      "learning_rate": 7.880125012778177e-05,
+      "loss": 1.3647,
+      "step": 13
+    },
+    {
+      "epoch": 0.5758354755784062,
+      "grad_norm": 133.2570329158543,
+      "learning_rate": 7.827761342928836e-05,
+      "loss": 1.1214,
+      "step": 14
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 7.727688786518845,
+      "learning_rate": 7.766176260732084e-05,
+      "loss": 1.115,
+      "step": 15
+    },
+    {
+      "epoch": 0.6580976863753213,
+      "grad_norm": 3.2378430343165197,
+      "learning_rate": 7.695518130045147e-05,
+      "loss": 0.9562,
+      "step": 16
+    },
+    {
+      "epoch": 0.699228791773779,
+      "grad_norm": 3.1322739271072155,
+      "learning_rate": 7.615957172493774e-05,
+      "loss": 0.9133,
+      "step": 17
+    },
+    {
+      "epoch": 0.7403598971722365,
+      "grad_norm": 1.9169576643194344,
+      "learning_rate": 7.52768505739342e-05,
+      "loss": 0.8791,
+      "step": 18
+    },
+    {
+      "epoch": 0.781491002570694,
+      "grad_norm": 2.864205412778019,
+      "learning_rate": 7.430914440001089e-05,
+      "loss": 0.8744,
+      "step": 19
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 2.0469710844500004,
+      "learning_rate": 7.325878449210182e-05,
+      "loss": 0.8437,
+      "step": 20
+    },
+    {
+      "epoch": 0.8637532133676092,
+      "grad_norm": 1.5602757799799256,
+      "learning_rate": 7.21283012592258e-05,
+      "loss": 0.8163,
+      "step": 21
+    },
+    {
+      "epoch": 0.9048843187660668,
+      "grad_norm": 1.6138062024410365,
+      "learning_rate": 7.092041813450948e-05,
+      "loss": 0.8066,
+      "step": 22
+    },
+    {
+      "epoch": 0.9460154241645244,
+      "grad_norm": 1.442421712274646,
+      "learning_rate": 6.963804501419837e-05,
+      "loss": 0.8061,
+      "step": 23
+    },
+    {
+      "epoch": 0.987146529562982,
+      "grad_norm": 1.3909793893073785,
+      "learning_rate": 6.828427124746191e-05,
+      "loss": 0.7991,
+      "step": 24
+    },
+    {
+      "epoch": 1.0282776349614395,
+      "grad_norm": 1.657918916902319,
+      "learning_rate": 6.686235819388075e-05,
+      "loss": 0.8015,
+      "step": 25
+    },
+    {
+      "epoch": 1.069408740359897,
+      "grad_norm": 0.9889091886636525,
+      "learning_rate": 6.537573136654582e-05,
+      "loss": 0.7812,
+      "step": 26
+    },
+    {
+      "epoch": 1.1105398457583548,
+      "grad_norm": 1.3704671912825952,
+      "learning_rate": 6.382797217969734e-05,
+      "loss": 0.7926,
+      "step": 27
+    },
+    {
+      "epoch": 1.1516709511568124,
+      "grad_norm": 0.9506521248836005,
+      "learning_rate": 6.22228093207841e-05,
+      "loss": 0.7228,
+      "step": 28
+    },
+    {
+      "epoch": 1.19280205655527,
+      "grad_norm": 1.5680043206556113,
+      "learning_rate": 6.056410976772887e-05,
+      "loss": 0.7668,
+      "step": 29
+    },
+    {
+      "epoch": 1.2339331619537275,
+      "grad_norm": 1.3501885829973919,
+      "learning_rate": 5.8855869473039924e-05,
+      "loss": 0.7555,
+      "step": 30
+    },
+    {
+      "epoch": 1.275064267352185,
+      "grad_norm": 0.9547913828055845,
+      "learning_rate": 5.710220373721129e-05,
+      "loss": 0.725,
+      "step": 31
+    },
+    {
+      "epoch": 1.3161953727506428,
+      "grad_norm": 1.8774395119545788,
+      "learning_rate": 5.5307337294603595e-05,
+      "loss": 0.755,
+      "step": 32
+    },
+    {
+      "epoch": 1.3573264781491003,
+      "grad_norm": 1.0854804422279138,
+      "learning_rate": 5.347559413568881e-05,
+      "loss": 0.734,
+      "step": 33
+    },
+    {
+      "epoch": 1.398457583547558,
+      "grad_norm": 2.1138176180114816,
+      "learning_rate": 5.16113870901785e-05,
+      "loss": 0.7788,
+      "step": 34
+    },
+    {
+      "epoch": 1.4395886889460154,
+      "grad_norm": 1.92017713591059,
+      "learning_rate": 4.971920719613056e-05,
+      "loss": 0.7554,
+      "step": 35
+    },
+    {
+      "epoch": 1.480719794344473,
+      "grad_norm": 1.2804852892330112,
+      "learning_rate": 4.780361288064514e-05,
+      "loss": 0.7256,
+      "step": 36
+    },
+    {
+      "epoch": 1.5218508997429305,
+      "grad_norm": 1.3475442269076388,
+      "learning_rate": 4.586921897821447e-05,
+      "loss": 0.7338,
+      "step": 37
+    },
+    {
+      "epoch": 1.562982005141388,
+      "grad_norm": 0.9473059503968736,
+      "learning_rate": 4.392068561318244e-05,
+      "loss": 0.7109,
+      "step": 38
+    },
+    {
+      "epoch": 1.6041131105398456,
+      "grad_norm": 0.9553750204204094,
+      "learning_rate": 4.1962706973096726e-05,
+      "loss": 0.7282,
+      "step": 39
+    },
+    {
+      "epoch": 1.6452442159383034,
+      "grad_norm": 1.0283072786747305,
+      "learning_rate": 4e-05,
+      "loss": 0.7073,
+      "step": 40
+    },
+    {
+      "epoch": 1.686375321336761,
+      "grad_norm": 0.9323255244453362,
+      "learning_rate": 3.803729302690328e-05,
+      "loss": 0.7067,
+      "step": 41
+    },
+    {
+      "epoch": 1.7275064267352185,
+      "grad_norm": 0.8182590422692471,
+      "learning_rate": 3.6079314386817575e-05,
+      "loss": 0.6925,
+      "step": 42
+    },
+    {
+      "epoch": 1.7686375321336762,
+      "grad_norm": 0.8566301144202072,
+      "learning_rate": 3.4130781021785535e-05,
+      "loss": 0.6938,
+      "step": 43
+    },
+    {
+      "epoch": 1.8097686375321338,
+      "grad_norm": 0.6239790903608581,
+      "learning_rate": 3.219638711935488e-05,
+      "loss": 0.7192,
+      "step": 44
+    },
+    {
+      "epoch": 1.8508997429305913,
+      "grad_norm": 0.5932044061702046,
+      "learning_rate": 3.028079280386945e-05,
+      "loss": 0.733,
+      "step": 45
+    },
+    {
+      "epoch": 1.8920308483290489,
+      "grad_norm": 0.6306348146434794,
+      "learning_rate": 2.8388612909821515e-05,
+      "loss": 0.7089,
+      "step": 46
+    },
+    {
+      "epoch": 1.9331619537275064,
+      "grad_norm": 0.4724425382586096,
+      "learning_rate": 2.6524405864311203e-05,
+      "loss": 0.6901,
+      "step": 47
+    },
+    {
+      "epoch": 1.974293059125964,
+      "grad_norm": 0.4762926669457546,
+      "learning_rate": 2.4692662705396412e-05,
+      "loss": 0.6814,
+      "step": 48
+    },
+    {
+      "epoch": 2.0154241645244215,
+      "grad_norm": 0.4199202805040583,
+      "learning_rate": 2.2897796262788728e-05,
+      "loss": 0.6945,
+      "step": 49
+    },
+    {
+      "epoch": 2.056555269922879,
+      "grad_norm": 0.45885166710096664,
+      "learning_rate": 2.1144130526960093e-05,
+      "loss": 0.6808,
+      "step": 50
+    },
+    {
+      "epoch": 2.0976863753213366,
+      "grad_norm": 0.32562983446598953,
+      "learning_rate": 1.9435890232271136e-05,
+      "loss": 0.6365,
+      "step": 51
+    },
+    {
+      "epoch": 2.138817480719794,
+      "grad_norm": 0.3210042920043292,
+      "learning_rate": 1.7777190679215923e-05,
+      "loss": 0.6733,
+      "step": 52
+    },
+    {
+      "epoch": 2.179948586118252,
+      "grad_norm": 0.34332499720764603,
+      "learning_rate": 1.617202782030267e-05,
+      "loss": 0.6676,
+      "step": 53
+    },
+    {
+      "epoch": 2.2210796915167097,
+      "grad_norm": 0.3175801116989568,
+      "learning_rate": 1.4624268633454187e-05,
+      "loss": 0.6436,
+      "step": 54
+    },
+    {
+      "epoch": 2.2622107969151672,
+      "grad_norm": 0.25381278521642503,
+      "learning_rate": 1.3137641806119264e-05,
+      "loss": 0.6417,
+      "step": 55
+    },
+    {
+      "epoch": 2.303341902313625,
+      "grad_norm": 0.2761078182253337,
+      "learning_rate": 1.1715728752538103e-05,
+      "loss": 0.6674,
+      "step": 56
+    },
+    {
+      "epoch": 2.3444730077120823,
+      "grad_norm": 0.319866122750778,
+      "learning_rate": 1.0361954985801646e-05,
+      "loss": 0.6733,
+      "step": 57
+    },
+    {
+      "epoch": 2.38560411311054,
+      "grad_norm": 0.2502069014138021,
+      "learning_rate": 9.07958186549052e-06,
+      "loss": 0.6748,
+      "step": 58
+    },
+    {
+      "epoch": 2.4267352185089974,
+      "grad_norm": 0.2757113804590555,
+      "learning_rate": 7.871698740774208e-06,
+      "loss": 0.6552,
+      "step": 59
+    },
+    {
+      "epoch": 2.467866323907455,
+      "grad_norm": 0.2194870871294771,
+      "learning_rate": 6.7412155078981865e-06,
+      "loss": 0.6551,
+      "step": 60
+    },
+    {
+      "epoch": 2.5089974293059125,
+      "grad_norm": 0.19634205347852157,
+      "learning_rate": 5.690855599989121e-06,
+      "loss": 0.6501,
+      "step": 61
+    },
+    {
+      "epoch": 2.55012853470437,
+      "grad_norm": 0.2184412340906883,
+      "learning_rate": 4.723149426065803e-06,
+      "loss": 0.6848,
+      "step": 62
+    },
+    {
+      "epoch": 2.5912596401028276,
+      "grad_norm": 0.19302466559591314,
+      "learning_rate": 3.840428275062267e-06,
+      "loss": 0.6778,
+      "step": 63
+    },
+    {
+      "epoch": 2.6323907455012856,
+      "grad_norm": 0.1727663709267336,
+      "learning_rate": 3.0448186995485307e-06,
+      "loss": 0.6546,
+      "step": 64
+    },
+    {
+      "epoch": 2.6735218508997427,
+      "grad_norm": 0.14455584412454298,
+      "learning_rate": 2.3382373926791722e-06,
+      "loss": 0.6539,
+      "step": 65
+    },
+    {
+      "epoch": 2.7146529562982007,
+      "grad_norm": 0.139478914199975,
+      "learning_rate": 1.7223865707116472e-06,
+      "loss": 0.6565,
+      "step": 66
+    },
+    {
+      "epoch": 2.7557840616966582,
+      "grad_norm": 0.1309078853776337,
+      "learning_rate": 1.1987498722182411e-06,
+      "loss": 0.661,
+      "step": 67
+    },
+    {
+      "epoch": 2.796915167095116,
+      "grad_norm": 0.120992405410613,
+      "learning_rate": 7.685887838707828e-07,
+      "loss": 0.6437,
+      "step": 68
+    },
+    {
+      "epoch": 2.8380462724935733,
+      "grad_norm": 0.12297660011279088,
+      "learning_rate": 4.3293960140875946e-07,
+      "loss": 0.6573,
+      "step": 69
+    },
+    {
+      "epoch": 2.879177377892031,
+      "grad_norm": 0.11164038809008547,
+      "learning_rate": 1.926109331121273e-07,
+      "loss": 0.6578,
+      "step": 70
+    },
+    {
+      "epoch": 2.9203084832904884,
+      "grad_norm": 0.1270006627072105,
+      "learning_rate": 4.8181751793103806e-08,
+      "loss": 0.6636,
+      "step": 71
+    },
+    {
+      "epoch": 2.961439588688946,
+      "grad_norm": 0.11459271467853557,
+      "learning_rate": 0.0,
+      "loss": 0.6851,
+      "step": 72
+    },
+    {
+      "epoch": 2.961439588688946,
+      "step": 72,
+      "total_flos": 1.8527734208659456e+18,
+      "train_loss": 0.7965062566929393,
+      "train_runtime": 15726.6597,
+      "train_samples_per_second": 2.373,
+      "train_steps_per_second": 0.005
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 72,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.8527734208659456e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6de932bd0a32b8986e1f1b6b5e3e07c4ae1732e82901be6cd64e8d64633c73f4
+size 7416