Training in progress, step 200

.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
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8145fd92651a1f709aadde8d9a99057aa495aa51323e5639d42e8cf74d0c1162
+size 4982131536

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d78b4d5ad883d6ba75b7f914199eccce03eb0d31dc497805a0018877f57b9b63
+size 4932949336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:054d92d64172c337687da320284205df9ee76707c195674ea5b041148f270d13
+size 2428723160

model.safetensors.index.json

@@ -0,0 +1,441 @@
+{
+  "metadata": {
+    "total_size": 12343754752
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ 'System: ' + system_message + '<|im_end|>' + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '<|im_end|>' + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,258 @@
+{"current_steps": 1, "total_steps": 258, "loss": 1.1103, "lr": 0.0, "epoch": 0.007722007722007722, "percentage": 0.39, "elapsed_time": "0:00:03", "remaining_time": "0:13:16", "throughput": 14744.58, "total_tokens": 45712}
+{"current_steps": 2, "total_steps": 258, "loss": 1.0548, "lr": 2.5e-06, "epoch": 0.015444015444015444, "percentage": 0.78, "elapsed_time": "0:00:05", "remaining_time": "0:10:58", "throughput": 17655.65, "total_tokens": 90856}
+{"current_steps": 3, "total_steps": 258, "loss": 0.9605, "lr": 5e-06, "epoch": 0.023166023166023165, "percentage": 1.16, "elapsed_time": "0:00:06", "remaining_time": "0:09:45", "throughput": 20489.53, "total_tokens": 141160}
+{"current_steps": 4, "total_steps": 258, "loss": 1.0066, "lr": 7.5e-06, "epoch": 0.03088803088803089, "percentage": 1.55, "elapsed_time": "0:00:08", "remaining_time": "0:09:18", "throughput": 21779.81, "total_tokens": 191560}
+{"current_steps": 5, "total_steps": 258, "loss": 0.935, "lr": 1e-05, "epoch": 0.03861003861003861, "percentage": 1.94, "elapsed_time": "0:00:10", "remaining_time": "0:08:51", "throughput": 22843.88, "total_tokens": 239792}
+{"current_steps": 6, "total_steps": 258, "loss": 0.9258, "lr": 1.25e-05, "epoch": 0.04633204633204633, "percentage": 2.33, "elapsed_time": "0:00:12", "remaining_time": "0:08:47", "throughput": 22823.44, "total_tokens": 286776}
+{"current_steps": 7, "total_steps": 258, "loss": 0.9268, "lr": 1.5e-05, "epoch": 0.05405405405405406, "percentage": 2.71, "elapsed_time": "0:00:14", "remaining_time": "0:08:32", "throughput": 23746.09, "total_tokens": 339256}
+{"current_steps": 8, "total_steps": 258, "loss": 1.0233, "lr": 1.75e-05, "epoch": 0.06177606177606178, "percentage": 3.1, "elapsed_time": "0:00:15", "remaining_time": "0:08:16", "throughput": 24463.92, "total_tokens": 388616}
+{"current_steps": 9, "total_steps": 258, "loss": 0.9468, "lr": 2e-05, "epoch": 0.0694980694980695, "percentage": 3.49, "elapsed_time": "0:00:17", "remaining_time": "0:08:04", "throughput": 24769.13, "total_tokens": 434136}
+{"current_steps": 10, "total_steps": 258, "loss": 0.8232, "lr": 2.25e-05, "epoch": 0.07722007722007722, "percentage": 3.88, "elapsed_time": "0:00:19", "remaining_time": "0:07:58", "throughput": 25152.45, "total_tokens": 485424}
+{"current_steps": 11, "total_steps": 258, "loss": 0.8575, "lr": 2.5e-05, "epoch": 0.08494208494208494, "percentage": 4.26, "elapsed_time": "0:00:20", "remaining_time": "0:07:46", "throughput": 25616.29, "total_tokens": 532232}
+{"current_steps": 12, "total_steps": 258, "loss": 0.8271, "lr": 2.7500000000000004e-05, "epoch": 0.09266409266409266, "percentage": 4.65, "elapsed_time": "0:00:22", "remaining_time": "0:07:36", "throughput": 25810.93, "total_tokens": 575152}
+{"current_steps": 13, "total_steps": 258, "loss": 0.7658, "lr": 3e-05, "epoch": 0.10038610038610038, "percentage": 5.04, "elapsed_time": "0:00:23", "remaining_time": "0:07:27", "throughput": 26132.92, "total_tokens": 620992}
+{"current_steps": 14, "total_steps": 258, "loss": 0.8374, "lr": 3.2500000000000004e-05, "epoch": 0.10810810810810811, "percentage": 5.43, "elapsed_time": "0:00:25", "remaining_time": "0:07:24", "throughput": 26317.53, "total_tokens": 671288}
+{"current_steps": 15, "total_steps": 258, "loss": 0.8107, "lr": 3.5e-05, "epoch": 0.11583011583011583, "percentage": 5.81, "elapsed_time": "0:00:27", "remaining_time": "0:07:22", "throughput": 26481.37, "total_tokens": 722848}
+{"current_steps": 16, "total_steps": 258, "loss": 0.8237, "lr": 3.7500000000000003e-05, "epoch": 0.12355212355212356, "percentage": 6.2, "elapsed_time": "0:00:28", "remaining_time": "0:07:16", "throughput": 26623.65, "total_tokens": 767632}
+{"current_steps": 17, "total_steps": 258, "loss": 0.7956, "lr": 4e-05, "epoch": 0.13127413127413126, "percentage": 6.59, "elapsed_time": "0:00:30", "remaining_time": "0:07:12", "throughput": 26772.48, "total_tokens": 816304}
+{"current_steps": 18, "total_steps": 258, "loss": 0.7785, "lr": 4.25e-05, "epoch": 0.138996138996139, "percentage": 6.98, "elapsed_time": "0:00:32", "remaining_time": "0:07:09", "throughput": 26884.55, "total_tokens": 865360}
+{"current_steps": 19, "total_steps": 258, "loss": 0.7208, "lr": 4.5e-05, "epoch": 0.14671814671814673, "percentage": 7.36, "elapsed_time": "0:00:34", "remaining_time": "0:07:08", "throughput": 27000.14, "total_tokens": 919800}
+{"current_steps": 20, "total_steps": 258, "loss": 0.7927, "lr": 4.75e-05, "epoch": 0.15444015444015444, "percentage": 7.75, "elapsed_time": "0:00:35", "remaining_time": "0:07:04", "throughput": 27069.83, "total_tokens": 965736}
+{"current_steps": 21, "total_steps": 258, "loss": 0.7329, "lr": 5e-05, "epoch": 0.16216216216216217, "percentage": 8.14, "elapsed_time": "0:00:37", "remaining_time": "0:07:03", "throughput": 27135.27, "total_tokens": 1017352}
+{"current_steps": 22, "total_steps": 258, "loss": 0.749, "lr": 4.999782204181027e-05, "epoch": 0.16988416988416988, "percentage": 8.53, "elapsed_time": "0:00:39", "remaining_time": "0:06:58", "throughput": 27178.94, "total_tokens": 1061344}
+{"current_steps": 23, "total_steps": 258, "loss": 0.7498, "lr": 4.999128854672123e-05, "epoch": 0.1776061776061776, "percentage": 8.91, "elapsed_time": "0:00:40", "remaining_time": "0:06:55", "throughput": 27279.07, "total_tokens": 1109672}
+{"current_steps": 24, "total_steps": 258, "loss": 0.6965, "lr": 4.9980400653107194e-05, "epoch": 0.18532818532818532, "percentage": 9.3, "elapsed_time": "0:00:42", "remaining_time": "0:06:53", "throughput": 27328.73, "total_tokens": 1159832}
+{"current_steps": 25, "total_steps": 258, "loss": 0.7161, "lr": 4.9965160258038346e-05, "epoch": 0.19305019305019305, "percentage": 9.69, "elapsed_time": "0:00:44", "remaining_time": "0:06:51", "throughput": 27392.4, "total_tokens": 1209240}
+{"current_steps": 26, "total_steps": 258, "loss": 0.712, "lr": 4.9945570016950135e-05, "epoch": 0.20077220077220076, "percentage": 10.08, "elapsed_time": "0:00:45", "remaining_time": "0:06:49", "throughput": 27479.41, "total_tokens": 1259568}
+{"current_steps": 27, "total_steps": 258, "loss": 0.8072, "lr": 4.9921633343180654e-05, "epoch": 0.2084942084942085, "percentage": 10.47, "elapsed_time": "0:00:47", "remaining_time": "0:06:45", "throughput": 27592.09, "total_tokens": 1308136}
+{"current_steps": 28, "total_steps": 258, "loss": 0.7463, "lr": 4.989335440737586e-05, "epoch": 0.21621621621621623, "percentage": 10.85, "elapsed_time": "0:00:49", "remaining_time": "0:06:43", "throughput": 27619.21, "total_tokens": 1356408}
+{"current_steps": 29, "total_steps": 258, "loss": 0.7338, "lr": 4.986073813676296e-05, "epoch": 0.22393822393822393, "percentage": 11.24, "elapsed_time": "0:00:50", "remaining_time": "0:06:39", "throughput": 27687.34, "total_tokens": 1402072}
+{"current_steps": 30, "total_steps": 258, "loss": 0.7493, "lr": 4.9823790214291836e-05, "epoch": 0.23166023166023167, "percentage": 11.63, "elapsed_time": "0:00:52", "remaining_time": "0:06:37", "throughput": 27778.61, "total_tokens": 1454592}
+{"current_steps": 31, "total_steps": 258, "loss": 0.742, "lr": 4.978251707764492e-05, "epoch": 0.23938223938223938, "percentage": 12.02, "elapsed_time": "0:00:53", "remaining_time": "0:06:35", "throughput": 27806.32, "total_tokens": 1500560}
+{"current_steps": 32, "total_steps": 258, "loss": 0.7456, "lr": 4.973692591811549e-05, "epoch": 0.2471042471042471, "percentage": 12.4, "elapsed_time": "0:00:55", "remaining_time": "0:06:32", "throughput": 27863.34, "total_tokens": 1546960}
+{"current_steps": 33, "total_steps": 258, "loss": 0.7668, "lr": 4.968702467935469e-05, "epoch": 0.2548262548262548, "percentage": 12.79, "elapsed_time": "0:00:57", "remaining_time": "0:06:30", "throughput": 27937.96, "total_tokens": 1598424}
+{"current_steps": 34, "total_steps": 258, "loss": 0.6724, "lr": 4.963282205598744e-05, "epoch": 0.2625482625482625, "percentage": 13.18, "elapsed_time": "0:00:58", "remaining_time": "0:06:26", "throughput": 27984.63, "total_tokens": 1643656}
+{"current_steps": 35, "total_steps": 258, "loss": 0.6785, "lr": 4.957432749209755e-05, "epoch": 0.2702702702702703, "percentage": 13.57, "elapsed_time": "0:01:00", "remaining_time": "0:06:27", "throughput": 27896.85, "total_tokens": 1698008}
+{"current_steps": 36, "total_steps": 258, "loss": 0.7382, "lr": 4.9511551179582174e-05, "epoch": 0.277992277992278, "percentage": 13.95, "elapsed_time": "0:01:02", "remaining_time": "0:06:24", "throughput": 27940.16, "total_tokens": 1743856}
+{"current_steps": 37, "total_steps": 258, "loss": 0.7075, "lr": 4.944450405637602e-05, "epoch": 0.2857142857142857, "percentage": 14.34, "elapsed_time": "0:01:04", "remaining_time": "0:06:23", "throughput": 27975.13, "total_tokens": 1797032}
+{"current_steps": 38, "total_steps": 258, "loss": 0.6504, "lr": 4.937319780454559e-05, "epoch": 0.29343629343629346, "percentage": 14.73, "elapsed_time": "0:01:05", "remaining_time": "0:06:21", "throughput": 28072.01, "total_tokens": 1847632}
+{"current_steps": 39, "total_steps": 258, "loss": 0.7049, "lr": 4.929764484825369e-05, "epoch": 0.30115830115830117, "percentage": 15.12, "elapsed_time": "0:01:07", "remaining_time": "0:06:18", "throughput": 28108.59, "total_tokens": 1895000}
+{"current_steps": 40, "total_steps": 258, "loss": 0.722, "lr": 4.921785835159472e-05, "epoch": 0.3088803088803089, "percentage": 15.5, "elapsed_time": "0:01:08", "remaining_time": "0:06:15", "throughput": 28126.6, "total_tokens": 1936384}
+{"current_steps": 41, "total_steps": 258, "loss": 0.7017, "lr": 4.9133852216300965e-05, "epoch": 0.3166023166023166, "percentage": 15.89, "elapsed_time": "0:01:10", "remaining_time": "0:06:13", "throughput": 28154.9, "total_tokens": 1984248}
+{"current_steps": 42, "total_steps": 258, "loss": 0.7098, "lr": 4.9045641079320484e-05, "epoch": 0.32432432432432434, "percentage": 16.28, "elapsed_time": "0:01:11", "remaining_time": "0:06:09", "throughput": 28205.86, "total_tokens": 2029000}
+{"current_steps": 43, "total_steps": 258, "loss": 0.7396, "lr": 4.89532403102667e-05, "epoch": 0.33204633204633205, "percentage": 16.67, "elapsed_time": "0:01:13", "remaining_time": "0:06:07", "throughput": 28269.31, "total_tokens": 2078944}
+{"current_steps": 44, "total_steps": 258, "loss": 0.7002, "lr": 4.8856666008740583e-05, "epoch": 0.33976833976833976, "percentage": 17.05, "elapsed_time": "0:01:15", "remaining_time": "0:06:05", "throughput": 28328.01, "total_tokens": 2126352}
+{"current_steps": 45, "total_steps": 258, "loss": 0.6856, "lr": 4.875593500152538e-05, "epoch": 0.3474903474903475, "percentage": 17.44, "elapsed_time": "0:01:16", "remaining_time": "0:06:02", "throughput": 28340.2, "total_tokens": 2172368}
+{"current_steps": 46, "total_steps": 258, "loss": 0.7011, "lr": 4.865106483965487e-05, "epoch": 0.3552123552123552, "percentage": 17.83, "elapsed_time": "0:01:18", "remaining_time": "0:06:00", "throughput": 28315.22, "total_tokens": 2217024}
+{"current_steps": 47, "total_steps": 258, "loss": 0.6443, "lr": 4.8542073795355294e-05, "epoch": 0.36293436293436293, "percentage": 18.22, "elapsed_time": "0:01:19", "remaining_time": "0:05:59", "throughput": 28341.47, "total_tokens": 2266472}
+{"current_steps": 48, "total_steps": 258, "loss": 0.696, "lr": 4.842898085886164e-05, "epoch": 0.37065637065637064, "percentage": 18.6, "elapsed_time": "0:01:21", "remaining_time": "0:05:57", "throughput": 28336.32, "total_tokens": 2318480}
+{"current_steps": 49, "total_steps": 258, "loss": 0.6868, "lr": 4.8311805735108894e-05, "epoch": 0.3783783783783784, "percentage": 18.99, "elapsed_time": "0:01:23", "remaining_time": "0:05:56", "throughput": 28336.68, "total_tokens": 2368432}
+{"current_steps": 50, "total_steps": 258, "loss": 0.6602, "lr": 4.81905688402987e-05, "epoch": 0.3861003861003861, "percentage": 19.38, "elapsed_time": "0:01:25", "remaining_time": "0:05:53", "throughput": 28368.15, "total_tokens": 2413104}
+{"current_steps": 51, "total_steps": 258, "loss": 0.7167, "lr": 4.806529129834208e-05, "epoch": 0.3938223938223938, "percentage": 19.77, "elapsed_time": "0:01:26", "remaining_time": "0:05:51", "throughput": 28392.74, "total_tokens": 2458232}
+{"current_steps": 52, "total_steps": 258, "loss": 0.664, "lr": 4.793599493717891e-05, "epoch": 0.4015444015444015, "percentage": 20.16, "elapsed_time": "0:01:28", "remaining_time": "0:05:48", "throughput": 28414.46, "total_tokens": 2501480}
+{"current_steps": 53, "total_steps": 258, "loss": 0.6674, "lr": 4.78027022849747e-05, "epoch": 0.4092664092664093, "percentage": 20.54, "elapsed_time": "0:01:29", "remaining_time": "0:05:46", "throughput": 28411.18, "total_tokens": 2548328}
+{"current_steps": 54, "total_steps": 258, "loss": 0.6494, "lr": 4.766543656619532e-05, "epoch": 0.416988416988417, "percentage": 20.93, "elapsed_time": "0:01:31", "remaining_time": "0:05:44", "throughput": 28409.05, "total_tokens": 2592744}
+{"current_steps": 55, "total_steps": 258, "loss": 0.6107, "lr": 4.752422169756048e-05, "epoch": 0.4247104247104247, "percentage": 21.32, "elapsed_time": "0:01:33", "remaining_time": "0:05:45", "throughput": 28326.88, "total_tokens": 2648832}
+{"current_steps": 56, "total_steps": 258, "loss": 0.682, "lr": 4.7379082283876566e-05, "epoch": 0.43243243243243246, "percentage": 21.71, "elapsed_time": "0:01:35", "remaining_time": "0:05:42", "throughput": 28355.05, "total_tokens": 2695656}
+{"current_steps": 57, "total_steps": 258, "loss": 0.6709, "lr": 4.723004361374953e-05, "epoch": 0.44015444015444016, "percentage": 22.09, "elapsed_time": "0:01:36", "remaining_time": "0:05:41", "throughput": 28396.92, "total_tokens": 2748024}
+{"current_steps": 58, "total_steps": 258, "loss": 0.6614, "lr": 4.707713165517877e-05, "epoch": 0.44787644787644787, "percentage": 22.48, "elapsed_time": "0:01:38", "remaining_time": "0:05:39", "throughput": 28436.21, "total_tokens": 2797448}
+{"current_steps": 59, "total_steps": 258, "loss": 0.6384, "lr": 4.692037305103247e-05, "epoch": 0.4555984555984556, "percentage": 22.87, "elapsed_time": "0:01:39", "remaining_time": "0:05:37", "throughput": 28450.59, "total_tokens": 2843456}
+{"current_steps": 60, "total_steps": 258, "loss": 0.7448, "lr": 4.675979511440549e-05, "epoch": 0.46332046332046334, "percentage": 23.26, "elapsed_time": "0:01:41", "remaining_time": "0:05:34", "throughput": 28457.82, "total_tokens": 2888008}
+{"current_steps": 61, "total_steps": 258, "loss": 0.6423, "lr": 4.659542582386041e-05, "epoch": 0.47104247104247104, "percentage": 23.64, "elapsed_time": "0:01:42", "remaining_time": "0:05:32", "throughput": 28466.05, "total_tokens": 2930816}
+{"current_steps": 62, "total_steps": 258, "loss": 0.6491, "lr": 4.642729381855262e-05, "epoch": 0.47876447876447875, "percentage": 24.03, "elapsed_time": "0:01:44", "remaining_time": "0:05:30", "throughput": 28488.68, "total_tokens": 2976920}
+{"current_steps": 63, "total_steps": 258, "loss": 0.6737, "lr": 4.625542839324036e-05, "epoch": 0.4864864864864865, "percentage": 24.42, "elapsed_time": "0:01:46", "remaining_time": "0:05:28", "throughput": 28513.45, "total_tokens": 3022496}
+{"current_steps": 64, "total_steps": 258, "loss": 0.6862, "lr": 4.607985949318047e-05, "epoch": 0.4942084942084942, "percentage": 24.81, "elapsed_time": "0:01:47", "remaining_time": "0:05:26", "throughput": 28524.65, "total_tokens": 3071824}
+{"current_steps": 65, "total_steps": 258, "loss": 0.6896, "lr": 4.5900617708910854e-05, "epoch": 0.5019305019305019, "percentage": 25.19, "elapsed_time": "0:01:49", "remaining_time": "0:05:24", "throughput": 28549.39, "total_tokens": 3119136}
+{"current_steps": 66, "total_steps": 258, "loss": 0.6843, "lr": 4.571773427092047e-05, "epoch": 0.5096525096525096, "percentage": 25.58, "elapsed_time": "0:01:50", "remaining_time": "0:05:22", "throughput": 28546.21, "total_tokens": 3160840}
+{"current_steps": 67, "total_steps": 258, "loss": 0.6204, "lr": 4.553124104420784e-05, "epoch": 0.5173745173745173, "percentage": 25.97, "elapsed_time": "0:01:52", "remaining_time": "0:05:19", "throughput": 28558.67, "total_tokens": 3205472}
+{"current_steps": 68, "total_steps": 258, "loss": 0.6787, "lr": 4.5341170522729006e-05, "epoch": 0.525096525096525, "percentage": 26.36, "elapsed_time": "0:01:53", "remaining_time": "0:05:18", "throughput": 28575.14, "total_tokens": 3255480}
+{"current_steps": 69, "total_steps": 258, "loss": 0.6485, "lr": 4.514755582373587e-05, "epoch": 0.5328185328185329, "percentage": 26.74, "elapsed_time": "0:01:55", "remaining_time": "0:05:16", "throughput": 28594.85, "total_tokens": 3306024}
+{"current_steps": 70, "total_steps": 258, "loss": 0.7085, "lr": 4.4950430682006e-05, "epoch": 0.5405405405405406, "percentage": 27.13, "elapsed_time": "0:01:57", "remaining_time": "0:05:14", "throughput": 28585.72, "total_tokens": 3350976}
+{"current_steps": 71, "total_steps": 258, "loss": 0.644, "lr": 4.4749829443964705e-05, "epoch": 0.5482625482625483, "percentage": 27.52, "elapsed_time": "0:01:59", "remaining_time": "0:05:13", "throughput": 28547.56, "total_tokens": 3400376}
+{"current_steps": 72, "total_steps": 258, "loss": 0.6924, "lr": 4.454578706170075e-05, "epoch": 0.555984555984556, "percentage": 27.91, "elapsed_time": "0:02:00", "remaining_time": "0:05:11", "throughput": 28559.42, "total_tokens": 3446016}
+{"current_steps": 73, "total_steps": 258, "loss": 0.6928, "lr": 4.433833908687633e-05, "epoch": 0.5637065637065637, "percentage": 28.29, "elapsed_time": "0:02:02", "remaining_time": "0:05:10", "throughput": 28532.53, "total_tokens": 3497296}
+{"current_steps": 74, "total_steps": 258, "loss": 0.6618, "lr": 4.4127521664532704e-05, "epoch": 0.5714285714285714, "percentage": 28.68, "elapsed_time": "0:02:04", "remaining_time": "0:05:08", "throughput": 28549.17, "total_tokens": 3543456}
+{"current_steps": 75, "total_steps": 258, "loss": 0.6724, "lr": 4.39133715267924e-05, "epoch": 0.5791505791505791, "percentage": 29.07, "elapsed_time": "0:02:05", "remaining_time": "0:05:06", "throughput": 28550.24, "total_tokens": 3587352}
+{"current_steps": 76, "total_steps": 258, "loss": 0.6643, "lr": 4.3695925986459115e-05, "epoch": 0.5868725868725869, "percentage": 29.46, "elapsed_time": "0:02:07", "remaining_time": "0:05:04", "throughput": 28590.15, "total_tokens": 3635888}
+{"current_steps": 77, "total_steps": 258, "loss": 0.6177, "lr": 4.347522293051648e-05, "epoch": 0.5945945945945946, "percentage": 29.84, "elapsed_time": "0:02:08", "remaining_time": "0:05:02", "throughput": 28619.48, "total_tokens": 3684128}
+{"current_steps": 78, "total_steps": 258, "loss": 0.6877, "lr": 4.3251300813526754e-05, "epoch": 0.6023166023166023, "percentage": 30.23, "elapsed_time": "0:02:10", "remaining_time": "0:05:01", "throughput": 28625.24, "total_tokens": 3733704}
+{"current_steps": 79, "total_steps": 258, "loss": 0.6013, "lr": 4.3024198650930625e-05, "epoch": 0.61003861003861, "percentage": 30.62, "elapsed_time": "0:02:11", "remaining_time": "0:04:58", "throughput": 28632.51, "total_tokens": 3777744}
+{"current_steps": 80, "total_steps": 258, "loss": 0.6559, "lr": 4.279395601224928e-05, "epoch": 0.6177606177606177, "percentage": 31.01, "elapsed_time": "0:02:13", "remaining_time": "0:04:57", "throughput": 28639.58, "total_tokens": 3828288}
+{"current_steps": 81, "total_steps": 258, "loss": 0.6037, "lr": 4.2560613014189966e-05, "epoch": 0.6254826254826255, "percentage": 31.4, "elapsed_time": "0:02:15", "remaining_time": "0:04:55", "throughput": 28619.5, "total_tokens": 3875936}
+{"current_steps": 82, "total_steps": 258, "loss": 0.6913, "lr": 4.2324210313656176e-05, "epoch": 0.6332046332046332, "percentage": 31.78, "elapsed_time": "0:02:16", "remaining_time": "0:04:53", "throughput": 28635.9, "total_tokens": 3921376}
+{"current_steps": 83, "total_steps": 258, "loss": 0.6669, "lr": 4.208478910066371e-05, "epoch": 0.640926640926641, "percentage": 32.17, "elapsed_time": "0:02:18", "remaining_time": "0:04:52", "throughput": 28646.89, "total_tokens": 3968400}
+{"current_steps": 84, "total_steps": 258, "loss": 0.6569, "lr": 4.184239109116393e-05, "epoch": 0.6486486486486487, "percentage": 32.56, "elapsed_time": "0:02:20", "remaining_time": "0:04:50", "throughput": 28635.84, "total_tokens": 4016608}
+{"current_steps": 85, "total_steps": 258, "loss": 0.6476, "lr": 4.159705851977521e-05, "epoch": 0.6563706563706564, "percentage": 32.95, "elapsed_time": "0:02:22", "remaining_time": "0:04:49", "throughput": 28600.6, "total_tokens": 4064472}
+{"current_steps": 86, "total_steps": 258, "loss": 0.6594, "lr": 4.134883413242421e-05, "epoch": 0.6640926640926641, "percentage": 33.33, "elapsed_time": "0:02:23", "remaining_time": "0:04:47", "throughput": 28621.93, "total_tokens": 4114672}
+{"current_steps": 87, "total_steps": 258, "loss": 0.5928, "lr": 4.109776117889789e-05, "epoch": 0.6718146718146718, "percentage": 33.72, "elapsed_time": "0:02:25", "remaining_time": "0:04:45", "throughput": 28625.6, "total_tokens": 4158376}
+{"current_steps": 88, "total_steps": 258, "loss": 0.6031, "lr": 4.084388340530791e-05, "epoch": 0.6795366795366795, "percentage": 34.11, "elapsed_time": "0:02:27", "remaining_time": "0:04:44", "throughput": 28614.3, "total_tokens": 4207504}
+{"current_steps": 89, "total_steps": 258, "loss": 0.689, "lr": 4.058724504646834e-05, "epoch": 0.6872586872586872, "percentage": 34.5, "elapsed_time": "0:02:29", "remaining_time": "0:04:42", "throughput": 28585.32, "total_tokens": 4259504}
+{"current_steps": 90, "total_steps": 258, "loss": 0.656, "lr": 4.032789081818843e-05, "epoch": 0.694980694980695, "percentage": 34.88, "elapsed_time": "0:02:30", "remaining_time": "0:04:40", "throughput": 28594.66, "total_tokens": 4303104}
+{"current_steps": 91, "total_steps": 258, "loss": 0.648, "lr": 4.0065865909481417e-05, "epoch": 0.7027027027027027, "percentage": 35.27, "elapsed_time": "0:02:32", "remaining_time": "0:04:39", "throughput": 28600.38, "total_tokens": 4352824}
+{"current_steps": 92, "total_steps": 258, "loss": 0.6309, "lr": 3.980121597469096e-05, "epoch": 0.7104247104247104, "percentage": 35.66, "elapsed_time": "0:02:33", "remaining_time": "0:04:37", "throughput": 28605.21, "total_tokens": 4398424}
+{"current_steps": 93, "total_steps": 258, "loss": 0.6175, "lr": 3.95339871255365e-05, "epoch": 0.7181467181467182, "percentage": 36.05, "elapsed_time": "0:02:35", "remaining_time": "0:04:35", "throughput": 28619.23, "total_tokens": 4446624}
+{"current_steps": 94, "total_steps": 258, "loss": 0.6144, "lr": 3.926422592307888e-05, "epoch": 0.7258687258687259, "percentage": 36.43, "elapsed_time": "0:02:36", "remaining_time": "0:04:33", "throughput": 28632.84, "total_tokens": 4493880}
+{"current_steps": 95, "total_steps": 258, "loss": 0.6541, "lr": 3.89919793696077e-05, "epoch": 0.7335907335907336, "percentage": 36.82, "elapsed_time": "0:02:38", "remaining_time": "0:04:32", "throughput": 28615.85, "total_tokens": 4541640}
+{"current_steps": 96, "total_steps": 258, "loss": 0.6422, "lr": 3.871729490045185e-05, "epoch": 0.7413127413127413, "percentage": 37.21, "elapsed_time": "0:02:40", "remaining_time": "0:04:30", "throughput": 28626.45, "total_tokens": 4589296}
+{"current_steps": 97, "total_steps": 258, "loss": 0.7102, "lr": 3.844022037571443e-05, "epoch": 0.749034749034749, "percentage": 37.6, "elapsed_time": "0:02:42", "remaining_time": "0:04:28", "throughput": 28631.99, "total_tokens": 4639848}
+{"current_steps": 98, "total_steps": 258, "loss": 0.6566, "lr": 3.81608040719339e-05, "epoch": 0.7567567567567568, "percentage": 37.98, "elapsed_time": "0:02:43", "remaining_time": "0:04:26", "throughput": 28643.78, "total_tokens": 4683808}
+{"current_steps": 99, "total_steps": 258, "loss": 0.6283, "lr": 3.78790946736724e-05, "epoch": 0.7644787644787645, "percentage": 38.37, "elapsed_time": "0:02:45", "remaining_time": "0:04:25", "throughput": 28649.98, "total_tokens": 4733296}
+{"current_steps": 100, "total_steps": 258, "loss": 0.6575, "lr": 3.759514126503324e-05, "epoch": 0.7722007722007722, "percentage": 38.76, "elapsed_time": "0:02:46", "remaining_time": "0:04:23", "throughput": 28644.47, "total_tokens": 4778416}
+{"current_steps": 101, "total_steps": 258, "loss": 0.6543, "lr": 3.7308993321108556e-05, "epoch": 0.7799227799227799, "percentage": 39.15, "elapsed_time": "0:02:48", "remaining_time": "0:04:21", "throughput": 28656.5, "total_tokens": 4828584}
+{"current_steps": 102, "total_steps": 258, "loss": 0.633, "lr": 3.702070069935898e-05, "epoch": 0.7876447876447876, "percentage": 39.53, "elapsed_time": "0:02:50", "remaining_time": "0:04:20", "throughput": 28669.61, "total_tokens": 4877424}
+{"current_steps": 103, "total_steps": 258, "loss": 0.6077, "lr": 3.673031363092666e-05, "epoch": 0.7953667953667953, "percentage": 39.92, "elapsed_time": "0:02:51", "remaining_time": "0:04:18", "throughput": 28680.65, "total_tokens": 4922312}
+{"current_steps": 104, "total_steps": 258, "loss": 0.6517, "lr": 3.6437882711883084e-05, "epoch": 0.803088803088803, "percentage": 40.31, "elapsed_time": "0:02:53", "remaining_time": "0:04:16", "throughput": 28705.48, "total_tokens": 4968208}
+{"current_steps": 105, "total_steps": 258, "loss": 0.6341, "lr": 3.6143458894413465e-05, "epoch": 0.8108108108108109, "percentage": 40.7, "elapsed_time": "0:02:54", "remaining_time": "0:04:14", "throughput": 28707.95, "total_tokens": 5018880}
+{"current_steps": 106, "total_steps": 258, "loss": 0.6487, "lr": 3.5847093477938956e-05, "epoch": 0.8185328185328186, "percentage": 41.09, "elapsed_time": "0:02:56", "remaining_time": "0:04:13", "throughput": 28700.78, "total_tokens": 5069312}
+{"current_steps": 107, "total_steps": 258, "loss": 0.616, "lr": 3.554883810017844e-05, "epoch": 0.8262548262548263, "percentage": 41.47, "elapsed_time": "0:02:58", "remaining_time": "0:04:11", "throughput": 28699.66, "total_tokens": 5113280}
+{"current_steps": 108, "total_steps": 258, "loss": 0.6359, "lr": 3.5248744728151345e-05, "epoch": 0.833976833976834, "percentage": 41.86, "elapsed_time": "0:02:59", "remaining_time": "0:04:09", "throughput": 28715.04, "total_tokens": 5158416}
+{"current_steps": 109, "total_steps": 258, "loss": 0.6607, "lr": 3.494686564912302e-05, "epoch": 0.8416988416988417, "percentage": 42.25, "elapsed_time": "0:03:01", "remaining_time": "0:04:08", "throughput": 28694.37, "total_tokens": 5209288}
+{"current_steps": 110, "total_steps": 258, "loss": 0.6322, "lr": 3.464325346149449e-05, "epoch": 0.8494208494208494, "percentage": 42.64, "elapsed_time": "0:03:03", "remaining_time": "0:04:06", "throughput": 28682.54, "total_tokens": 5264480}
+{"current_steps": 111, "total_steps": 258, "loss": 0.6312, "lr": 3.433796106563779e-05, "epoch": 0.8571428571428571, "percentage": 43.02, "elapsed_time": "0:03:04", "remaining_time": "0:04:04", "throughput": 28699.2, "total_tokens": 5308480}
+{"current_steps": 112, "total_steps": 258, "loss": 0.6205, "lr": 3.403104165467883e-05, "epoch": 0.8648648648648649, "percentage": 43.41, "elapsed_time": "0:03:06", "remaining_time": "0:04:03", "throughput": 28692.5, "total_tokens": 5355096}
+{"current_steps": 113, "total_steps": 258, "loss": 0.601, "lr": 3.3722548705229175e-05, "epoch": 0.8725868725868726, "percentage": 43.8, "elapsed_time": "0:03:08", "remaining_time": "0:04:01", "throughput": 28708.18, "total_tokens": 5401288}
+{"current_steps": 114, "total_steps": 258, "loss": 0.6556, "lr": 3.341253596806848e-05, "epoch": 0.8803088803088803, "percentage": 44.19, "elapsed_time": "0:03:10", "remaining_time": "0:04:00", "throughput": 28691.98, "total_tokens": 5453648}
+{"current_steps": 115, "total_steps": 258, "loss": 0.626, "lr": 3.310105745877915e-05, "epoch": 0.888030888030888, "percentage": 44.57, "elapsed_time": "0:03:11", "remaining_time": "0:03:58", "throughput": 28701.47, "total_tokens": 5502248}
+{"current_steps": 116, "total_steps": 258, "loss": 0.6515, "lr": 3.278816744833479e-05, "epoch": 0.8957528957528957, "percentage": 44.96, "elapsed_time": "0:03:13", "remaining_time": "0:03:56", "throughput": 28676.11, "total_tokens": 5550512}
+{"current_steps": 117, "total_steps": 258, "loss": 0.6625, "lr": 3.247392045364426e-05, "epoch": 0.9034749034749034, "percentage": 45.35, "elapsed_time": "0:03:15", "remaining_time": "0:03:55", "throughput": 28698.79, "total_tokens": 5603224}
+{"current_steps": 118, "total_steps": 258, "loss": 0.6464, "lr": 3.215837122805282e-05, "epoch": 0.9111969111969112, "percentage": 45.74, "elapsed_time": "0:03:16", "remaining_time": "0:03:53", "throughput": 28707.31, "total_tokens": 5653152}
+{"current_steps": 119, "total_steps": 258, "loss": 0.6134, "lr": 3.1841574751802076e-05, "epoch": 0.918918918918919, "percentage": 46.12, "elapsed_time": "0:03:18", "remaining_time": "0:03:51", "throughput": 28725.94, "total_tokens": 5699968}
+{"current_steps": 120, "total_steps": 258, "loss": 0.6139, "lr": 3.152358622245042e-05, "epoch": 0.9266409266409267, "percentage": 46.51, "elapsed_time": "0:03:20", "remaining_time": "0:03:50", "throughput": 28749.46, "total_tokens": 5750360}
+{"current_steps": 121, "total_steps": 258, "loss": 0.6017, "lr": 3.1204461045255604e-05, "epoch": 0.9343629343629344, "percentage": 46.9, "elapsed_time": "0:03:21", "remaining_time": "0:03:48", "throughput": 28755.47, "total_tokens": 5793216}
+{"current_steps": 122, "total_steps": 258, "loss": 0.6728, "lr": 3.088425482352107e-05, "epoch": 0.9420849420849421, "percentage": 47.29, "elapsed_time": "0:03:22", "remaining_time": "0:03:46", "throughput": 28764.78, "total_tokens": 5838920}
+{"current_steps": 123, "total_steps": 258, "loss": 0.6126, "lr": 3.056302334890786e-05, "epoch": 0.9498069498069498, "percentage": 47.67, "elapsed_time": "0:03:24", "remaining_time": "0:03:44", "throughput": 28738.36, "total_tokens": 5885064}
+{"current_steps": 124, "total_steps": 258, "loss": 0.5959, "lr": 3.024082259171367e-05, "epoch": 0.9575289575289575, "percentage": 48.06, "elapsed_time": "0:03:26", "remaining_time": "0:03:43", "throughput": 28750.03, "total_tokens": 5934624}
+{"current_steps": 125, "total_steps": 258, "loss": 0.6208, "lr": 2.9917708691120706e-05, "epoch": 0.9652509652509652, "percentage": 48.45, "elapsed_time": "0:03:28", "remaining_time": "0:03:41", "throughput": 28765.44, "total_tokens": 5987336}
+{"current_steps": 126, "total_steps": 258, "loss": 0.6215, "lr": 2.9593737945414264e-05, "epoch": 0.972972972972973, "percentage": 48.84, "elapsed_time": "0:03:29", "remaining_time": "0:03:39", "throughput": 28769.08, "total_tokens": 6035896}
+{"current_steps": 127, "total_steps": 258, "loss": 0.6738, "lr": 2.9268966802173436e-05, "epoch": 0.9806949806949807, "percentage": 49.22, "elapsed_time": "0:03:31", "remaining_time": "0:03:37", "throughput": 28781.5, "total_tokens": 6080816}
+{"current_steps": 128, "total_steps": 258, "loss": 0.5536, "lr": 2.8943451848435936e-05, "epoch": 0.9884169884169884, "percentage": 49.61, "elapsed_time": "0:03:32", "remaining_time": "0:03:36", "throughput": 28793.95, "total_tokens": 6126984}
+{"current_steps": 129, "total_steps": 258, "loss": 0.6399, "lr": 2.8617249800838513e-05, "epoch": 0.9961389961389961, "percentage": 50.0, "elapsed_time": "0:03:34", "remaining_time": "0:03:34", "throughput": 28783.52, "total_tokens": 6178704}
+{"current_steps": 130, "total_steps": 258, "loss": 0.6105, "lr": 2.8290417495734837e-05, "epoch": 1.0, "percentage": 50.39, "elapsed_time": "0:03:35", "remaining_time": "0:03:32", "throughput": 28773.56, "total_tokens": 6201760}
+{"current_steps": 131, "total_steps": 258, "loss": 0.4115, "lr": 2.7963011879292573e-05, "epoch": 1.0077220077220077, "percentage": 50.78, "elapsed_time": "0:03:37", "remaining_time": "0:03:30", "throughput": 28781.04, "total_tokens": 6246264}
+{"current_steps": 132, "total_steps": 258, "loss": 0.4188, "lr": 2.7635089997571196e-05, "epoch": 1.0154440154440154, "percentage": 51.16, "elapsed_time": "0:03:38", "remaining_time": "0:03:28", "throughput": 28792.4, "total_tokens": 6293720}
+{"current_steps": 133, "total_steps": 258, "loss": 0.3889, "lr": 2.7306708986582553e-05, "epoch": 1.0231660231660231, "percentage": 51.55, "elapsed_time": "0:03:40", "remaining_time": "0:03:27", "throughput": 28801.99, "total_tokens": 6348992}
+{"current_steps": 134, "total_steps": 258, "loss": 0.3809, "lr": 2.6977926062335617e-05, "epoch": 1.0308880308880308, "percentage": 51.94, "elapsed_time": "0:03:42", "remaining_time": "0:03:25", "throughput": 28795.36, "total_tokens": 6396000}
+{"current_steps": 135, "total_steps": 258, "loss": 0.352, "lr": 2.6648798510867386e-05, "epoch": 1.0386100386100385, "percentage": 52.33, "elapsed_time": "0:03:43", "remaining_time": "0:03:23", "throughput": 28793.93, "total_tokens": 6439376}
+{"current_steps": 136, "total_steps": 258, "loss": 0.3781, "lr": 2.6319383678261562e-05, "epoch": 1.0463320463320462, "percentage": 52.71, "elapsed_time": "0:03:45", "remaining_time": "0:03:22", "throughput": 28792.85, "total_tokens": 6484320}
+{"current_steps": 137, "total_steps": 258, "loss": 0.3875, "lr": 2.598973896065674e-05, "epoch": 1.054054054054054, "percentage": 53.1, "elapsed_time": "0:03:46", "remaining_time": "0:03:20", "throughput": 28796.15, "total_tokens": 6531032}
+{"current_steps": 138, "total_steps": 258, "loss": 0.3935, "lr": 2.565992179424591e-05, "epoch": 1.0617760617760619, "percentage": 53.49, "elapsed_time": "0:03:48", "remaining_time": "0:03:18", "throughput": 28794.95, "total_tokens": 6581096}
+{"current_steps": 139, "total_steps": 258, "loss": 0.3618, "lr": 2.5329989645268977e-05, "epoch": 1.0694980694980696, "percentage": 53.88, "elapsed_time": "0:03:50", "remaining_time": "0:03:17", "throughput": 28784.66, "total_tokens": 6632824}
+{"current_steps": 140, "total_steps": 258, "loss": 0.3463, "lr": 2.5e-05, "epoch": 1.0772200772200773, "percentage": 54.26, "elapsed_time": "0:03:52", "remaining_time": "0:03:15", "throughput": 28793.34, "total_tokens": 6681960}
+{"current_steps": 141, "total_steps": 258, "loss": 0.3834, "lr": 2.467001035473103e-05, "epoch": 1.084942084942085, "percentage": 54.65, "elapsed_time": "0:03:53", "remaining_time": "0:03:13", "throughput": 28814.5, "total_tokens": 6731624}
+{"current_steps": 142, "total_steps": 258, "loss": 0.3881, "lr": 2.43400782057541e-05, "epoch": 1.0926640926640927, "percentage": 55.04, "elapsed_time": "0:03:55", "remaining_time": "0:03:12", "throughput": 28812.52, "total_tokens": 6778008}
+{"current_steps": 143, "total_steps": 258, "loss": 0.3873, "lr": 2.401026103934327e-05, "epoch": 1.1003861003861004, "percentage": 55.43, "elapsed_time": "0:03:57", "remaining_time": "0:03:10", "throughput": 28794.97, "total_tokens": 6834336}
+{"current_steps": 144, "total_steps": 258, "loss": 0.3618, "lr": 2.368061632173844e-05, "epoch": 1.1081081081081081, "percentage": 55.81, "elapsed_time": "0:03:59", "remaining_time": "0:03:09", "throughput": 28788.98, "total_tokens": 6885472}
+{"current_steps": 145, "total_steps": 258, "loss": 0.3544, "lr": 2.3351201489132616e-05, "epoch": 1.1158301158301158, "percentage": 56.2, "elapsed_time": "0:04:00", "remaining_time": "0:03:07", "throughput": 28795.14, "total_tokens": 6935216}
+{"current_steps": 146, "total_steps": 258, "loss": 0.3961, "lr": 2.3022073937664386e-05, "epoch": 1.1235521235521235, "percentage": 56.59, "elapsed_time": "0:04:02", "remaining_time": "0:03:05", "throughput": 28806.45, "total_tokens": 6981112}
+{"current_steps": 147, "total_steps": 258, "loss": 0.4253, "lr": 2.2693291013417453e-05, "epoch": 1.1312741312741312, "percentage": 56.98, "elapsed_time": "0:04:03", "remaining_time": "0:03:04", "throughput": 28813.68, "total_tokens": 7027848}
+{"current_steps": 148, "total_steps": 258, "loss": 0.3765, "lr": 2.236491000242881e-05, "epoch": 1.138996138996139, "percentage": 57.36, "elapsed_time": "0:04:05", "remaining_time": "0:03:02", "throughput": 28822.94, "total_tokens": 7079048}
+{"current_steps": 149, "total_steps": 258, "loss": 0.3656, "lr": 2.2036988120707436e-05, "epoch": 1.1467181467181466, "percentage": 57.75, "elapsed_time": "0:04:07", "remaining_time": "0:03:00", "throughput": 28829.22, "total_tokens": 7125096}
+{"current_steps": 150, "total_steps": 258, "loss": 0.3588, "lr": 2.170958250426517e-05, "epoch": 1.1544401544401544, "percentage": 58.14, "elapsed_time": "0:04:08", "remaining_time": "0:02:59", "throughput": 28827.74, "total_tokens": 7169448}
+{"current_steps": 151, "total_steps": 258, "loss": 0.3807, "lr": 2.1382750199161496e-05, "epoch": 1.1621621621621623, "percentage": 58.53, "elapsed_time": "0:04:10", "remaining_time": "0:02:57", "throughput": 28839.42, "total_tokens": 7218200}
+{"current_steps": 152, "total_steps": 258, "loss": 0.3796, "lr": 2.1056548151564063e-05, "epoch": 1.16988416988417, "percentage": 58.91, "elapsed_time": "0:04:12", "remaining_time": "0:02:55", "throughput": 28836.48, "total_tokens": 7273032}
+{"current_steps": 153, "total_steps": 258, "loss": 0.3733, "lr": 2.073103319782656e-05, "epoch": 1.1776061776061777, "percentage": 59.3, "elapsed_time": "0:04:14", "remaining_time": "0:02:54", "throughput": 28830.98, "total_tokens": 7327712}
+{"current_steps": 154, "total_steps": 258, "loss": 0.3726, "lr": 2.0406262054585738e-05, "epoch": 1.1853281853281854, "percentage": 59.69, "elapsed_time": "0:04:15", "remaining_time": "0:02:52", "throughput": 28837.99, "total_tokens": 7370416}
+{"current_steps": 155, "total_steps": 258, "loss": 0.3359, "lr": 2.00822913088793e-05, "epoch": 1.193050193050193, "percentage": 60.08, "elapsed_time": "0:04:17", "remaining_time": "0:02:50", "throughput": 28839.08, "total_tokens": 7419056}
+{"current_steps": 156, "total_steps": 258, "loss": 0.3295, "lr": 1.975917740828634e-05, "epoch": 1.2007722007722008, "percentage": 60.47, "elapsed_time": "0:04:18", "remaining_time": "0:02:49", "throughput": 28841.29, "total_tokens": 7464800}
+{"current_steps": 157, "total_steps": 258, "loss": 0.3367, "lr": 1.9436976651092144e-05, "epoch": 1.2084942084942085, "percentage": 60.85, "elapsed_time": "0:04:20", "remaining_time": "0:02:47", "throughput": 28842.48, "total_tokens": 7512016}
+{"current_steps": 158, "total_steps": 258, "loss": 0.3835, "lr": 1.9115745176478946e-05, "epoch": 1.2162162162162162, "percentage": 61.24, "elapsed_time": "0:04:22", "remaining_time": "0:02:45", "throughput": 28842.99, "total_tokens": 7558192}
+{"current_steps": 159, "total_steps": 258, "loss": 0.3985, "lr": 1.879553895474441e-05, "epoch": 1.223938223938224, "percentage": 61.63, "elapsed_time": "0:04:23", "remaining_time": "0:02:44", "throughput": 28850.71, "total_tokens": 7606360}
+{"current_steps": 160, "total_steps": 258, "loss": 0.3976, "lr": 1.8476413777549585e-05, "epoch": 1.2316602316602316, "percentage": 62.02, "elapsed_time": "0:04:25", "remaining_time": "0:02:42", "throughput": 28851.76, "total_tokens": 7658256}
+{"current_steps": 161, "total_steps": 258, "loss": 0.3545, "lr": 1.815842524819793e-05, "epoch": 1.2393822393822393, "percentage": 62.4, "elapsed_time": "0:04:27", "remaining_time": "0:02:40", "throughput": 28849.03, "total_tokens": 7705928}
+{"current_steps": 162, "total_steps": 258, "loss": 0.3368, "lr": 1.784162877194719e-05, "epoch": 1.247104247104247, "percentage": 62.79, "elapsed_time": "0:04:28", "remaining_time": "0:02:39", "throughput": 28845.4, "total_tokens": 7754904}
+{"current_steps": 163, "total_steps": 258, "loss": 0.3615, "lr": 1.7526079546355744e-05, "epoch": 1.2548262548262548, "percentage": 63.18, "elapsed_time": "0:04:30", "remaining_time": "0:02:37", "throughput": 28856.24, "total_tokens": 7801208}
+{"current_steps": 164, "total_steps": 258, "loss": 0.3604, "lr": 1.7211832551665214e-05, "epoch": 1.2625482625482625, "percentage": 63.57, "elapsed_time": "0:04:31", "remaining_time": "0:02:35", "throughput": 28863.56, "total_tokens": 7846632}
+{"current_steps": 165, "total_steps": 258, "loss": 0.3581, "lr": 1.6898942541220856e-05, "epoch": 1.2702702702702702, "percentage": 63.95, "elapsed_time": "0:04:33", "remaining_time": "0:02:34", "throughput": 28870.14, "total_tokens": 7893448}
+{"current_steps": 166, "total_steps": 258, "loss": 0.3921, "lr": 1.6587464031931528e-05, "epoch": 1.2779922779922779, "percentage": 64.34, "elapsed_time": "0:04:35", "remaining_time": "0:02:32", "throughput": 28862.56, "total_tokens": 7941168}
+{"current_steps": 167, "total_steps": 258, "loss": 0.3761, "lr": 1.6277451294770834e-05, "epoch": 1.2857142857142856, "percentage": 64.73, "elapsed_time": "0:04:37", "remaining_time": "0:02:31", "throughput": 28833.27, "total_tokens": 7994968}
+{"current_steps": 168, "total_steps": 258, "loss": 0.3734, "lr": 1.5968958345321178e-05, "epoch": 1.2934362934362935, "percentage": 65.12, "elapsed_time": "0:04:38", "remaining_time": "0:02:29", "throughput": 28834.2, "total_tokens": 8040744}
+{"current_steps": 169, "total_steps": 258, "loss": 0.3848, "lr": 1.566203893436221e-05, "epoch": 1.3011583011583012, "percentage": 65.5, "elapsed_time": "0:04:40", "remaining_time": "0:02:27", "throughput": 28841.35, "total_tokens": 8090992}
+{"current_steps": 170, "total_steps": 258, "loss": 0.352, "lr": 1.5356746538505513e-05, "epoch": 1.308880308880309, "percentage": 65.89, "elapsed_time": "0:04:42", "remaining_time": "0:02:26", "throughput": 28853.27, "total_tokens": 8138688}
+{"current_steps": 171, "total_steps": 258, "loss": 0.4108, "lr": 1.5053134350876983e-05, "epoch": 1.3166023166023166, "percentage": 66.28, "elapsed_time": "0:04:44", "remaining_time": "0:02:24", "throughput": 28829.46, "total_tokens": 8188200}
+{"current_steps": 172, "total_steps": 258, "loss": 0.3828, "lr": 1.4751255271848662e-05, "epoch": 1.3243243243243243, "percentage": 66.67, "elapsed_time": "0:04:45", "remaining_time": "0:02:22", "throughput": 28831.35, "total_tokens": 8238184}
+{"current_steps": 173, "total_steps": 258, "loss": 0.3989, "lr": 1.4451161899821558e-05, "epoch": 1.332046332046332, "percentage": 67.05, "elapsed_time": "0:04:47", "remaining_time": "0:02:21", "throughput": 28842.91, "total_tokens": 8287400}
+{"current_steps": 174, "total_steps": 258, "loss": 0.3618, "lr": 1.4152906522061048e-05, "epoch": 1.3397683397683398, "percentage": 67.44, "elapsed_time": "0:04:48", "remaining_time": "0:02:19", "throughput": 28853.27, "total_tokens": 8332240}
+{"current_steps": 175, "total_steps": 258, "loss": 0.3418, "lr": 1.3856541105586545e-05, "epoch": 1.3474903474903475, "percentage": 67.83, "elapsed_time": "0:04:50", "remaining_time": "0:02:17", "throughput": 28862.28, "total_tokens": 8383952}
+{"current_steps": 176, "total_steps": 258, "loss": 0.4053, "lr": 1.3562117288116924e-05, "epoch": 1.3552123552123552, "percentage": 68.22, "elapsed_time": "0:04:52", "remaining_time": "0:02:16", "throughput": 28851.07, "total_tokens": 8430544}
+{"current_steps": 177, "total_steps": 258, "loss": 0.3397, "lr": 1.3269686369073347e-05, "epoch": 1.3629343629343629, "percentage": 68.6, "elapsed_time": "0:04:53", "remaining_time": "0:02:14", "throughput": 28852.73, "total_tokens": 8471896}
+{"current_steps": 178, "total_steps": 258, "loss": 0.4108, "lr": 1.2979299300641018e-05, "epoch": 1.3706563706563706, "percentage": 68.99, "elapsed_time": "0:04:55", "remaining_time": "0:02:12", "throughput": 28860.19, "total_tokens": 8517400}
+{"current_steps": 179, "total_steps": 258, "loss": 0.3822, "lr": 1.2691006678891446e-05, "epoch": 1.3783783783783785, "percentage": 69.38, "elapsed_time": "0:04:56", "remaining_time": "0:02:10", "throughput": 28864.12, "total_tokens": 8563608}
+{"current_steps": 180, "total_steps": 258, "loss": 0.3745, "lr": 1.240485873496677e-05, "epoch": 1.3861003861003862, "percentage": 69.77, "elapsed_time": "0:04:58", "remaining_time": "0:02:09", "throughput": 28877.29, "total_tokens": 8609832}
+{"current_steps": 181, "total_steps": 258, "loss": 0.3511, "lr": 1.2120905326327598e-05, "epoch": 1.393822393822394, "percentage": 70.16, "elapsed_time": "0:04:59", "remaining_time": "0:02:07", "throughput": 28885.96, "total_tokens": 8656152}
+{"current_steps": 182, "total_steps": 258, "loss": 0.4049, "lr": 1.1839195928066102e-05, "epoch": 1.4015444015444016, "percentage": 70.54, "elapsed_time": "0:05:01", "remaining_time": "0:02:05", "throughput": 28890.86, "total_tokens": 8704416}
+{"current_steps": 183, "total_steps": 258, "loss": 0.3483, "lr": 1.1559779624285564e-05, "epoch": 1.4092664092664093, "percentage": 70.93, "elapsed_time": "0:05:02", "remaining_time": "0:02:04", "throughput": 28882.96, "total_tokens": 8748368}
+{"current_steps": 184, "total_steps": 258, "loss": 0.3415, "lr": 1.128270509954816e-05, "epoch": 1.416988416988417, "percentage": 71.32, "elapsed_time": "0:05:04", "remaining_time": "0:02:02", "throughput": 28889.01, "total_tokens": 8798392}
+{"current_steps": 185, "total_steps": 258, "loss": 0.3737, "lr": 1.1008020630392302e-05, "epoch": 1.4247104247104247, "percentage": 71.71, "elapsed_time": "0:05:06", "remaining_time": "0:02:00", "throughput": 28888.46, "total_tokens": 8848240}
+{"current_steps": 186, "total_steps": 258, "loss": 0.3726, "lr": 1.0735774076921129e-05, "epoch": 1.4324324324324325, "percentage": 72.09, "elapsed_time": "0:05:08", "remaining_time": "0:01:59", "throughput": 28873.16, "total_tokens": 8896008}
+{"current_steps": 187, "total_steps": 258, "loss": 0.3553, "lr": 1.0466012874463507e-05, "epoch": 1.4401544401544402, "percentage": 72.48, "elapsed_time": "0:05:09", "remaining_time": "0:01:57", "throughput": 28865.61, "total_tokens": 8943224}
+{"current_steps": 188, "total_steps": 258, "loss": 0.3836, "lr": 1.0198784025309047e-05, "epoch": 1.4478764478764479, "percentage": 72.87, "elapsed_time": "0:05:11", "remaining_time": "0:01:55", "throughput": 28866.71, "total_tokens": 8989312}
+{"current_steps": 189, "total_steps": 258, "loss": 0.3777, "lr": 9.934134090518593e-06, "epoch": 1.4555984555984556, "percentage": 73.26, "elapsed_time": "0:05:13", "remaining_time": "0:01:54", "throughput": 28860.68, "total_tokens": 9042424}
+{"current_steps": 190, "total_steps": 258, "loss": 0.3654, "lr": 9.672109181811575e-06, "epoch": 1.4633204633204633, "percentage": 73.64, "elapsed_time": "0:05:14", "remaining_time": "0:01:52", "throughput": 28868.75, "total_tokens": 9086072}
+{"current_steps": 191, "total_steps": 258, "loss": 0.3514, "lr": 9.412754953531663e-06, "epoch": 1.471042471042471, "percentage": 74.03, "elapsed_time": "0:05:16", "remaining_time": "0:01:50", "throughput": 28881.94, "total_tokens": 9133240}
+{"current_steps": 192, "total_steps": 258, "loss": 0.3331, "lr": 9.156116594692096e-06, "epoch": 1.4787644787644787, "percentage": 74.42, "elapsed_time": "0:05:17", "remaining_time": "0:01:49", "throughput": 28886.7, "total_tokens": 9178152}
+{"current_steps": 193, "total_steps": 258, "loss": 0.3867, "lr": 8.902238821102111e-06, "epoch": 1.4864864864864864, "percentage": 74.81, "elapsed_time": "0:05:19", "remaining_time": "0:01:47", "throughput": 28896.16, "total_tokens": 9226432}
+{"current_steps": 194, "total_steps": 258, "loss": 0.3693, "lr": 8.651165867575797e-06, "epoch": 1.494208494208494, "percentage": 75.19, "elapsed_time": "0:05:21", "remaining_time": "0:01:45", "throughput": 28881.72, "total_tokens": 9278656}
+{"current_steps": 195, "total_steps": 258, "loss": 0.3375, "lr": 8.402941480224797e-06, "epoch": 1.5019305019305018, "percentage": 75.58, "elapsed_time": "0:05:22", "remaining_time": "0:01:44", "throughput": 28884.75, "total_tokens": 9323040}
+{"current_steps": 196, "total_steps": 258, "loss": 0.3639, "lr": 8.15760890883607e-06, "epoch": 1.5096525096525095, "percentage": 75.97, "elapsed_time": "0:05:24", "remaining_time": "0:01:42", "throughput": 28885.63, "total_tokens": 9373024}
+{"current_steps": 197, "total_steps": 258, "loss": 0.3713, "lr": 7.915210899336284e-06, "epoch": 1.5173745173745172, "percentage": 76.36, "elapsed_time": "0:05:26", "remaining_time": "0:01:40", "throughput": 28893.11, "total_tokens": 9421792}
+{"current_steps": 198, "total_steps": 258, "loss": 0.3818, "lr": 7.67578968634383e-06, "epoch": 1.525096525096525, "percentage": 76.74, "elapsed_time": "0:05:27", "remaining_time": "0:01:39", "throughput": 28891.31, "total_tokens": 9470992}
+{"current_steps": 199, "total_steps": 258, "loss": 0.3735, "lr": 7.439386985810037e-06, "epoch": 1.5328185328185329, "percentage": 77.13, "elapsed_time": "0:05:29", "remaining_time": "0:01:37", "throughput": 28898.05, "total_tokens": 9518240}
+{"current_steps": 200, "total_steps": 258, "loss": 0.3396, "lr": 7.206043987750729e-06, "epoch": 1.5405405405405406, "percentage": 77.52, "elapsed_time": "0:05:30", "remaining_time": "0:01:35", "throughput": 28911.07, "total_tokens": 9565296}
+{"current_steps": 201, "total_steps": 258, "loss": 0.3709, "lr": 6.9758013490693855e-06, "epoch": 1.5482625482625483, "percentage": 77.91, "elapsed_time": "0:06:00", "remaining_time": "0:01:42", "throughput": 26635.14, "total_tokens": 9614328}
+{"current_steps": 202, "total_steps": 258, "loss": 0.3403, "lr": 6.7486991864732505e-06, "epoch": 1.555984555984556, "percentage": 78.29, "elapsed_time": "0:06:02", "remaining_time": "0:01:40", "throughput": 26649.15, "total_tokens": 9660560}
+{"current_steps": 203, "total_steps": 258, "loss": 0.3864, "lr": 6.524777069483526e-06, "epoch": 1.5637065637065637, "percentage": 78.68, "elapsed_time": "0:06:04", "remaining_time": "0:01:38", "throughput": 26667.96, "total_tokens": 9711688}
+{"current_steps": 204, "total_steps": 258, "loss": 0.3351, "lr": 6.3040740135408864e-06, "epoch": 1.5714285714285714, "percentage": 79.07, "elapsed_time": "0:06:05", "remaining_time": "0:01:36", "throughput": 26681.77, "total_tokens": 9758240}
+{"current_steps": 205, "total_steps": 258, "loss": 0.3534, "lr": 6.086628473207606e-06, "epoch": 1.579150579150579, "percentage": 79.46, "elapsed_time": "0:06:07", "remaining_time": "0:01:34", "throughput": 26701.0, "total_tokens": 9806832}
+{"current_steps": 206, "total_steps": 258, "loss": 0.3478, "lr": 5.872478335467299e-06, "epoch": 1.586872586872587, "percentage": 79.84, "elapsed_time": "0:06:08", "remaining_time": "0:01:33", "throughput": 26715.34, "total_tokens": 9852096}
+{"current_steps": 207, "total_steps": 258, "loss": 0.3506, "lr": 5.661660913123673e-06, "epoch": 1.5945945945945947, "percentage": 80.23, "elapsed_time": "0:06:10", "remaining_time": "0:01:31", "throughput": 26725.4, "total_tokens": 9899240}
+{"current_steps": 208, "total_steps": 258, "loss": 0.3345, "lr": 5.454212938299255e-06, "epoch": 1.6023166023166024, "percentage": 80.62, "elapsed_time": "0:06:12", "remaining_time": "0:01:29", "throughput": 26738.21, "total_tokens": 9947712}
+{"current_steps": 209, "total_steps": 258, "loss": 0.3277, "lr": 5.250170556035302e-06, "epoch": 1.6100386100386102, "percentage": 81.01, "elapsed_time": "0:06:13", "remaining_time": "0:01:27", "throughput": 26750.59, "total_tokens": 9991232}
+{"current_steps": 210, "total_steps": 258, "loss": 0.3528, "lr": 5.049569317994013e-06, "epoch": 1.6177606177606179, "percentage": 81.4, "elapsed_time": "0:06:15", "remaining_time": "0:01:25", "throughput": 26760.39, "total_tokens": 10038696}
+{"current_steps": 211, "total_steps": 258, "loss": 0.4053, "lr": 4.852444176264129e-06, "epoch": 1.6254826254826256, "percentage": 81.78, "elapsed_time": "0:06:17", "remaining_time": "0:01:23", "throughput": 26761.54, "total_tokens": 10090976}
+{"current_steps": 212, "total_steps": 258, "loss": 0.3565, "lr": 4.658829477270996e-06, "epoch": 1.6332046332046333, "percentage": 82.17, "elapsed_time": "0:06:18", "remaining_time": "0:01:22", "throughput": 26773.78, "total_tokens": 10140048}
+{"current_steps": 213, "total_steps": 258, "loss": 0.3512, "lr": 4.46875895579216e-06, "epoch": 1.640926640926641, "percentage": 82.56, "elapsed_time": "0:06:20", "remaining_time": "0:01:20", "throughput": 26784.21, "total_tokens": 10187872}
+{"current_steps": 214, "total_steps": 258, "loss": 0.3825, "lr": 4.282265729079535e-06, "epoch": 1.6486486486486487, "percentage": 82.95, "elapsed_time": "0:06:22", "remaining_time": "0:01:18", "throughput": 26785.29, "total_tokens": 10234368}
+{"current_steps": 215, "total_steps": 258, "loss": 0.4136, "lr": 4.099382291089151e-06, "epoch": 1.6563706563706564, "percentage": 83.33, "elapsed_time": "0:06:23", "remaining_time": "0:01:16", "throughput": 26793.83, "total_tokens": 10284208}
+{"current_steps": 216, "total_steps": 258, "loss": 0.405, "lr": 3.920140506819539e-06, "epoch": 1.664092664092664, "percentage": 83.72, "elapsed_time": "0:06:25", "remaining_time": "0:01:14", "throughput": 26797.95, "total_tokens": 10331624}
+{"current_steps": 217, "total_steps": 258, "loss": 0.3698, "lr": 3.7445716067596503e-06, "epoch": 1.6718146718146718, "percentage": 84.11, "elapsed_time": "0:06:27", "remaining_time": "0:01:13", "throughput": 26805.91, "total_tokens": 10377720}
+{"current_steps": 218, "total_steps": 258, "loss": 0.3522, "lr": 3.5727061814473854e-06, "epoch": 1.6795366795366795, "percentage": 84.5, "elapsed_time": "0:06:28", "remaining_time": "0:01:11", "throughput": 26817.29, "total_tokens": 10430784}
+{"current_steps": 219, "total_steps": 258, "loss": 0.3673, "lr": 3.404574176139591e-06, "epoch": 1.6872586872586872, "percentage": 84.88, "elapsed_time": "0:06:30", "remaining_time": "0:01:09", "throughput": 26818.94, "total_tokens": 10477896}
+{"current_steps": 220, "total_steps": 258, "loss": 0.343, "lr": 3.240204885594514e-06, "epoch": 1.694980694980695, "percentage": 85.27, "elapsed_time": "0:06:32", "remaining_time": "0:01:07", "throughput": 26835.21, "total_tokens": 10524432}
+{"current_steps": 221, "total_steps": 258, "loss": 0.3153, "lr": 3.0796269489675344e-06, "epoch": 1.7027027027027026, "percentage": 85.66, "elapsed_time": "0:06:33", "remaining_time": "0:01:05", "throughput": 26848.47, "total_tokens": 10571912}
+{"current_steps": 222, "total_steps": 258, "loss": 0.382, "lr": 2.922868344821236e-06, "epoch": 1.7104247104247103, "percentage": 86.05, "elapsed_time": "0:06:35", "remaining_time": "0:01:04", "throughput": 26861.36, "total_tokens": 10622048}
+{"current_steps": 223, "total_steps": 258, "loss": 0.3516, "lr": 2.769956386250472e-06, "epoch": 1.718146718146718, "percentage": 86.43, "elapsed_time": "0:06:37", "remaining_time": "0:01:02", "throughput": 26865.96, "total_tokens": 10673328}
+{"current_steps": 224, "total_steps": 258, "loss": 0.3872, "lr": 2.6209177161234445e-06, "epoch": 1.7258687258687258, "percentage": 86.82, "elapsed_time": "0:06:38", "remaining_time": "0:01:00", "throughput": 26877.95, "total_tokens": 10721704}
+{"current_steps": 225, "total_steps": 258, "loss": 0.3911, "lr": 2.475778302439524e-06, "epoch": 1.7335907335907335, "percentage": 87.21, "elapsed_time": "0:06:40", "remaining_time": "0:00:58", "throughput": 26886.31, "total_tokens": 10769240}
+{"current_steps": 226, "total_steps": 258, "loss": 0.3444, "lr": 2.3345634338046875e-06, "epoch": 1.7413127413127412, "percentage": 87.6, "elapsed_time": "0:06:42", "remaining_time": "0:00:56", "throughput": 26896.05, "total_tokens": 10814464}
+{"current_steps": 227, "total_steps": 258, "loss": 0.3607, "lr": 2.1972977150253064e-06, "epoch": 1.7490347490347489, "percentage": 87.98, "elapsed_time": "0:06:43", "remaining_time": "0:00:55", "throughput": 26906.73, "total_tokens": 10859000}
+{"current_steps": 228, "total_steps": 258, "loss": 0.3212, "lr": 2.064005062821095e-06, "epoch": 1.7567567567567568, "percentage": 88.37, "elapsed_time": "0:06:45", "remaining_time": "0:00:53", "throughput": 26915.37, "total_tokens": 10906008}
+{"current_steps": 229, "total_steps": 258, "loss": 0.3509, "lr": 1.9347087016579278e-06, "epoch": 1.7644787644787645, "percentage": 88.76, "elapsed_time": "0:06:46", "remaining_time": "0:00:51", "throughput": 26925.46, "total_tokens": 10952840}
+{"current_steps": 230, "total_steps": 258, "loss": 0.3977, "lr": 1.8094311597013052e-06, "epoch": 1.7722007722007722, "percentage": 89.15, "elapsed_time": "0:06:48", "remaining_time": "0:00:49", "throughput": 26941.5, "total_tokens": 11001384}
+{"current_steps": 231, "total_steps": 258, "loss": 0.3902, "lr": 1.6881942648911076e-06, "epoch": 1.77992277992278, "percentage": 89.53, "elapsed_time": "0:06:50", "remaining_time": "0:00:47", "throughput": 26946.03, "total_tokens": 11049440}
+{"current_steps": 232, "total_steps": 258, "loss": 0.3339, "lr": 1.5710191411383662e-06, "epoch": 1.7876447876447876, "percentage": 89.92, "elapsed_time": "0:06:51", "remaining_time": "0:00:46", "throughput": 26949.02, "total_tokens": 11093928}
+{"current_steps": 233, "total_steps": 258, "loss": 0.3936, "lr": 1.4579262046447107e-06, "epoch": 1.7953667953667953, "percentage": 90.31, "elapsed_time": "0:06:53", "remaining_time": "0:00:44", "throughput": 26960.86, "total_tokens": 11140832}
+{"current_steps": 234, "total_steps": 258, "loss": 0.431, "lr": 1.3489351603451329e-06, "epoch": 1.803088803088803, "percentage": 90.7, "elapsed_time": "0:06:54", "remaining_time": "0:00:42", "throughput": 26968.09, "total_tokens": 11191600}
+{"current_steps": 235, "total_steps": 258, "loss": 0.3781, "lr": 1.2440649984746256e-06, "epoch": 1.810810810810811, "percentage": 91.09, "elapsed_time": "0:06:56", "remaining_time": "0:00:40", "throughput": 26976.81, "total_tokens": 11235984}
+{"current_steps": 236, "total_steps": 258, "loss": 0.3547, "lr": 1.1433339912594266e-06, "epoch": 1.8185328185328187, "percentage": 91.47, "elapsed_time": "0:06:57", "remaining_time": "0:00:38", "throughput": 26980.06, "total_tokens": 11276416}
+{"current_steps": 237, "total_steps": 258, "loss": 0.3693, "lr": 1.046759689733301e-06, "epoch": 1.8262548262548264, "percentage": 91.86, "elapsed_time": "0:06:59", "remaining_time": "0:00:37", "throughput": 26986.71, "total_tokens": 11328536}
+{"current_steps": 238, "total_steps": 258, "loss": 0.3981, "lr": 9.54358920679524e-07, "epoch": 1.833976833976834, "percentage": 92.25, "elapsed_time": "0:07:01", "remaining_time": "0:00:35", "throughput": 26991.36, "total_tokens": 11374664}
+{"current_steps": 239, "total_steps": 258, "loss": 0.3676, "lr": 8.661477836990339e-07, "epoch": 1.8416988416988418, "percentage": 92.64, "elapsed_time": "0:07:03", "remaining_time": "0:00:33", "throughput": 26990.79, "total_tokens": 11424256}
+{"current_steps": 240, "total_steps": 258, "loss": 0.3445, "lr": 7.821416484052879e-07, "epoch": 1.8494208494208495, "percentage": 93.02, "elapsed_time": "0:07:04", "remaining_time": "0:00:31", "throughput": 27001.02, "total_tokens": 11469272}
+{"current_steps": 241, "total_steps": 258, "loss": 0.3338, "lr": 7.02355151746309e-07, "epoch": 1.8571428571428572, "percentage": 93.41, "elapsed_time": "0:07:06", "remaining_time": "0:00:30", "throughput": 27011.88, "total_tokens": 11514592}
+{"current_steps": 242, "total_steps": 258, "loss": 0.3663, "lr": 6.268021954544096e-07, "epoch": 1.864864864864865, "percentage": 93.8, "elapsed_time": "0:07:07", "remaining_time": "0:00:28", "throughput": 27015.02, "total_tokens": 11559064}
+{"current_steps": 243, "total_steps": 258, "loss": 0.3489, "lr": 5.554959436239821e-07, "epoch": 1.8725868725868726, "percentage": 94.19, "elapsed_time": "0:07:09", "remaining_time": "0:00:26", "throughput": 27017.55, "total_tokens": 11609720}
+{"current_steps": 244, "total_steps": 258, "loss": 0.3652, "lr": 4.884488204178333e-07, "epoch": 1.8803088803088803, "percentage": 94.57, "elapsed_time": "0:07:11", "remaining_time": "0:00:24", "throughput": 27019.91, "total_tokens": 11657256}
+{"current_steps": 245, "total_steps": 258, "loss": 0.383, "lr": 4.256725079024554e-07, "epoch": 1.888030888030888, "percentage": 94.96, "elapsed_time": "0:07:13", "remaining_time": "0:00:22", "throughput": 27022.99, "total_tokens": 11704528}
+{"current_steps": 246, "total_steps": 258, "loss": 0.3409, "lr": 3.6717794401256445e-07, "epoch": 1.8957528957528957, "percentage": 95.35, "elapsed_time": "0:07:14", "remaining_time": "0:00:21", "throughput": 27035.69, "total_tokens": 11752560}
+{"current_steps": 247, "total_steps": 258, "loss": 0.3509, "lr": 3.129753206453201e-07, "epoch": 1.9034749034749034, "percentage": 95.74, "elapsed_time": "0:07:16", "remaining_time": "0:00:19", "throughput": 27041.46, "total_tokens": 11798928}
+{"current_steps": 248, "total_steps": 258, "loss": 0.3554, "lr": 2.630740818845123e-07, "epoch": 1.9111969111969112, "percentage": 96.12, "elapsed_time": "0:07:18", "remaining_time": "0:00:17", "throughput": 27049.09, "total_tokens": 11848456}
+{"current_steps": 249, "total_steps": 258, "loss": 0.3558, "lr": 2.174829223550806e-07, "epoch": 1.9189189189189189, "percentage": 96.51, "elapsed_time": "0:07:19", "remaining_time": "0:00:15", "throughput": 27053.23, "total_tokens": 11899192}
+{"current_steps": 250, "total_steps": 258, "loss": 0.3203, "lr": 1.762097857081646e-07, "epoch": 1.9266409266409266, "percentage": 96.9, "elapsed_time": "0:07:21", "remaining_time": "0:00:14", "throughput": 27060.42, "total_tokens": 11947904}
+{"current_steps": 251, "total_steps": 258, "loss": 0.3453, "lr": 1.3926186323703905e-07, "epoch": 1.9343629343629343, "percentage": 97.29, "elapsed_time": "0:07:23", "remaining_time": "0:00:12", "throughput": 27072.56, "total_tokens": 11997104}
+{"current_steps": 252, "total_steps": 258, "loss": 0.4025, "lr": 1.0664559262413831e-07, "epoch": 1.942084942084942, "percentage": 97.67, "elapsed_time": "0:07:24", "remaining_time": "0:00:10", "throughput": 27070.06, "total_tokens": 12045824}
+{"current_steps": 253, "total_steps": 258, "loss": 0.3787, "lr": 7.836665681935085e-08, "epoch": 1.9498069498069497, "percentage": 98.06, "elapsed_time": "0:07:26", "remaining_time": "0:00:08", "throughput": 27078.53, "total_tokens": 12096360}
+{"current_steps": 254, "total_steps": 258, "loss": 0.3231, "lr": 5.44299830498668e-08, "epoch": 1.9575289575289574, "percentage": 98.45, "elapsed_time": "0:07:28", "remaining_time": "0:00:07", "throughput": 27090.36, "total_tokens": 12141952}
+{"current_steps": 255, "total_steps": 258, "loss": 0.3742, "lr": 3.4839741961659176e-08, "epoch": 1.965250965250965, "percentage": 98.84, "elapsed_time": "0:07:29", "remaining_time": "0:00:05", "throughput": 27096.27, "total_tokens": 12193160}
+{"current_steps": 256, "total_steps": 258, "loss": 0.3486, "lr": 1.9599346892809622e-08, "epoch": 1.972972972972973, "percentage": 99.22, "elapsed_time": "0:07:31", "remaining_time": "0:00:03", "throughput": 27104.74, "total_tokens": 12237616}
+{"current_steps": 257, "total_steps": 258, "loss": 0.3704, "lr": 8.711453278778536e-09, "epoch": 1.9806949806949807, "percentage": 99.61, "elapsed_time": "0:07:33", "remaining_time": "0:00:01", "throughput": 27112.59, "total_tokens": 12283352}
+{"current_steps": 258, "total_steps": 258, "loss": 0.3474, "lr": 2.177958189733542e-09, "epoch": 1.9884169884169884, "percentage": 100.0, "elapsed_time": "0:07:34", "remaining_time": "0:00:00", "throughput": 27117.81, "total_tokens": 12333744}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33dafc5be3b77b926d34004685f93ddf6570db07bf7d94d4d8e0ea92712eefed
+size 5880