Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-40/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-40/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
+}

checkpoint-40/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/home/bmm-system/data/private/zhangdan/checkpoint/Qwen2___5-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-40/generation_config.json

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

checkpoint-40/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d71e24d6df5618f650cfabef8183f38eaced0110755c1c4f4b3b450b962f2a6
+size 4877660776

checkpoint-40/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e7ae61b8da1299f64263640d640aedee329d73cb8196e2569013f77e9a757c8
+size 4932751008

checkpoint-40/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3b9ede04c259c23262b5c8022d87ab4308c49a01e9e8e8603d598a628081f33
+size 4330865200

checkpoint-40/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:593165dc0381e391bb2440e356cb3a81f19a73ab7ec37830bafaeb499f0b1085
+size 1089994880

checkpoint-40/model.safetensors.index.json

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

checkpoint-40/special_tokens_map.json

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

checkpoint-40/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
+size 11422063

checkpoint-40/tokenizer_config.json

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

checkpoint-40/trainer_state.json

@@ -0,0 +1,625 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.12698412698412698,
+  "eval_steps": 10,
+  "global_step": 40,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 812.0535888671875,
+      "epoch": 0.0031746031746031746,
+      "grad_norm": 0.6747706068004278,
+      "kl": 0.0,
+      "learning_rate": 1e-07,
+      "loss": 0.0232,
+      "reward": 1.1002280712127686,
+      "reward_std": 0.5235787630081177,
+      "rewards/": 4.2868547439575195,
+      "rewards/math_compute_score": 0.3035714328289032,
+      "step": 1
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 731.0178833007812,
+      "epoch": 0.006349206349206349,
+      "grad_norm": 1.0124723128865283,
+      "kl": 0.0,
+      "learning_rate": 2e-07,
+      "loss": 0.0538,
+      "reward": 1.1068390607833862,
+      "reward_std": 0.5650051832199097,
+      "rewards/": 3.8199093341827393,
+      "rewards/math_compute_score": 0.4285714626312256,
+      "step": 2
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 458.6964416503906,
+      "epoch": 0.009523809523809525,
+      "grad_norm": 1.5015414049019933,
+      "kl": 5.269050598144531e-05,
+      "learning_rate": 3e-07,
+      "loss": 0.0232,
+      "reward": 0.8488561511039734,
+      "reward_std": 0.8017136454582214,
+      "rewards/": 3.315708875656128,
+      "rewards/math_compute_score": 0.2321428656578064,
+      "step": 3
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 834.2678833007812,
+      "epoch": 0.012698412698412698,
+      "grad_norm": 1.2882090786497908,
+      "kl": 0.00011491775512695312,
+      "learning_rate": 4e-07,
+      "loss": 0.1304,
+      "reward": 0.9289307594299316,
+      "reward_std": 0.6540186405181885,
+      "rewards/": 3.8589391708374023,
+      "rewards/math_compute_score": 0.196428582072258,
+      "step": 4
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 751.357177734375,
+      "epoch": 0.015873015873015872,
+      "grad_norm": 0.799369181972436,
+      "kl": 5.936622619628906e-05,
+      "learning_rate": 5e-07,
+      "loss": 0.1161,
+      "reward": 0.7978726029396057,
+      "reward_std": 0.636299729347229,
+      "rewards/": 3.560791254043579,
+      "rewards/math_compute_score": 0.1071428656578064,
+      "step": 5
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 548.5714721679688,
+      "epoch": 0.01904761904761905,
+      "grad_norm": 1.6270226868358386,
+      "kl": 5.054473876953125e-05,
+      "learning_rate": 6e-07,
+      "loss": 0.1076,
+      "reward": 1.0075056552886963,
+      "reward_std": 0.7211081981658936,
+      "rewards/": 3.6089565753936768,
+      "rewards/math_compute_score": 0.3571428656578064,
+      "step": 6
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 421.4464416503906,
+      "epoch": 0.022222222222222223,
+      "grad_norm": 1.3908312836081718,
+      "kl": 4.8160552978515625e-05,
+      "learning_rate": 7e-07,
+      "loss": 0.0121,
+      "reward": 1.1225308179855347,
+      "reward_std": 0.6700603365898132,
+      "rewards/": 3.8983678817749023,
+      "rewards/math_compute_score": 0.4285714626312256,
+      "step": 7
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 658.1607666015625,
+      "epoch": 0.025396825396825397,
+      "grad_norm": 1.0145073915584033,
+      "kl": 7.152557373046875e-05,
+      "learning_rate": 8e-07,
+      "loss": 0.0495,
+      "reward": 0.9618025422096252,
+      "reward_std": 0.7162732481956482,
+      "rewards/": 4.023298263549805,
+      "rewards/math_compute_score": 0.196428582072258,
+      "step": 8
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 621.607177734375,
+      "epoch": 0.02857142857142857,
+      "grad_norm": 1.2828333873329154,
+      "kl": 8.58306884765625e-05,
+      "learning_rate": 9e-07,
+      "loss": -0.0267,
+      "reward": 0.9028041362762451,
+      "reward_std": 0.6590547561645508,
+      "rewards/": 4.1568779945373535,
+      "rewards/math_compute_score": 0.0892857164144516,
+      "step": 9
+    },
+    {
+      "epoch": 0.031746031746031744,
+      "grad_norm": 1.4662195694932412,
+      "learning_rate": 1e-06,
+      "loss": 0.1349,
+      "step": 10
+    },
+    {
+      "epoch": 0.031746031746031744,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 630.4202677408854,
+      "eval_kl": 0.00014241536458333334,
+      "eval_loss": 0.07422296702861786,
+      "eval_reward": 0.8999532461166382,
+      "eval_reward_std": 0.7095595002174377,
+      "eval_rewards/": 3.8330995241800943,
+      "eval_rewards/math_compute_score": 0.16666667784253755,
+      "eval_runtime": 102.9544,
+      "eval_samples_per_second": 0.194,
+      "eval_steps_per_second": 0.01,
+      "step": 10
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 612.2857360839844,
+      "epoch": 0.03492063492063492,
+      "grad_norm": 1.596068950301634,
+      "kl": 0.00014925003051757812,
+      "learning_rate": 9.99973476170006e-07,
+      "loss": 0.0213,
+      "reward": 0.9062910377979279,
+      "reward_std": 0.6523332297801971,
+      "rewards/": 3.6743122339248657,
+      "rewards/math_compute_score": 0.2142857313156128,
+      "step": 11
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 561.6428833007812,
+      "epoch": 0.0380952380952381,
+      "grad_norm": 3.778965074531409,
+      "kl": 0.0015869140625,
+      "learning_rate": 9.998939074940787e-07,
+      "loss": -0.1082,
+      "reward": 0.9064244031906128,
+      "reward_std": 0.5411514639854431,
+      "rewards/": 3.603550672531128,
+      "rewards/math_compute_score": 0.2321428656578064,
+      "step": 12
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 582.8392944335938,
+      "epoch": 0.04126984126984127,
+      "grad_norm": 2.8421007863418613,
+      "kl": 0.00180816650390625,
+      "learning_rate": 9.997613024140818e-07,
+      "loss": 0.1193,
+      "reward": 0.8694162368774414,
+      "reward_std": 0.5822046995162964,
+      "rewards/": 3.2756524085998535,
+      "rewards/math_compute_score": 0.267857164144516,
+      "step": 13
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 695.2857666015625,
+      "epoch": 0.044444444444444446,
+      "grad_norm": 1.2082539599844009,
+      "kl": 0.001373291015625,
+      "learning_rate": 9.995756749987941e-07,
+      "loss": 0.0225,
+      "reward": 0.849557101726532,
+      "reward_std": 0.6740785837173462,
+      "rewards/": 3.3906426429748535,
+      "rewards/math_compute_score": 0.2142857313156128,
+      "step": 14
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 784.5892944335938,
+      "epoch": 0.047619047619047616,
+      "grad_norm": 0.9475069699355427,
+      "kl": 0.00136566162109375,
+      "learning_rate": 9.993370449424152e-07,
+      "loss": 0.0734,
+      "reward": 1.1941686868667603,
+      "reward_std": 0.45438313484191895,
+      "rewards/": 3.8279857635498047,
+      "rewards/math_compute_score": 0.535714328289032,
+      "step": 15
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 512.2857666015625,
+      "epoch": 0.050793650793650794,
+      "grad_norm": 1.6304500476497015,
+      "kl": 0.0024566650390625,
+      "learning_rate": 9.990454375624776e-07,
+      "loss": 0.0487,
+      "reward": 1.0498645305633545,
+      "reward_std": 0.5710386633872986,
+      "rewards/": 3.6064651012420654,
+      "rewards/math_compute_score": 0.4107142984867096,
+      "step": 16
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 845.4107666015625,
+      "epoch": 0.05396825396825397,
+      "grad_norm": 1.0831133154787667,
+      "kl": 0.00138092041015625,
+      "learning_rate": 9.987008837971594e-07,
+      "loss": -0.0317,
+      "reward": 1.179338812828064,
+      "reward_std": 0.4696131944656372,
+      "rewards/": 4.396693706512451,
+      "rewards/math_compute_score": 0.3750000298023224,
+      "step": 17
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 529.5178833007812,
+      "epoch": 0.05714285714285714,
+      "grad_norm": 4.401529637845949,
+      "kl": 0.002197265625,
+      "learning_rate": 9.98303420202003e-07,
+      "loss": 0.1209,
+      "reward": 1.0693953037261963,
+      "reward_std": 0.6161165237426758,
+      "rewards/": 3.489833354949951,
+      "rewards/math_compute_score": 0.4642857313156128,
+      "step": 18
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 699.9107666015625,
+      "epoch": 0.06031746031746032,
+      "grad_norm": 1.0680027943685277,
+      "kl": 0.0022430419921875,
+      "learning_rate": 9.978530889460349e-07,
+      "loss": 0.2142,
+      "reward": 1.0860700607299805,
+      "reward_std": 0.46314889192581177,
+      "rewards/": 3.2874932289123535,
+      "rewards/math_compute_score": 0.535714328289032,
+      "step": 19
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "grad_norm": 0.9277167375388953,
+      "learning_rate": 9.973499378072946e-07,
+      "loss": 0.1731,
+      "step": 20
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 658.7607421875,
+      "eval_kl": 0.018397013346354168,
+      "eval_loss": 0.06885600090026855,
+      "eval_reward": 1.1295154492060344,
+      "eval_reward_std": 0.605679452419281,
+      "eval_rewards/": 4.028529723485311,
+      "eval_rewards/math_compute_score": 0.4047619203726451,
+      "eval_runtime": 101.5839,
+      "eval_samples_per_second": 0.197,
+      "eval_steps_per_second": 0.01,
+      "step": 20
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 521.2857513427734,
+      "epoch": 0.06666666666666667,
+      "grad_norm": 2.285178708700221,
+      "kl": 0.0033416748046875,
+      "learning_rate": 9.967940201677625e-07,
+      "loss": 0.248,
+      "reward": 1.1929408311843872,
+      "reward_std": 0.6199489831924438,
+      "rewards/": 3.857561469078064,
+      "rewards/math_compute_score": 0.5267857313156128,
+      "step": 21
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 562.9285888671875,
+      "epoch": 0.06984126984126984,
+      "grad_norm": 1.0300685938786647,
+      "kl": 0.0030975341796875,
+      "learning_rate": 9.96185395007699e-07,
+      "loss": 0.1345,
+      "reward": 1.1726387739181519,
+      "reward_std": 0.49179807305336,
+      "rewards/": 3.577479839324951,
+      "rewards/math_compute_score": 0.5714285969734192,
+      "step": 22
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 509.2857360839844,
+      "epoch": 0.07301587301587302,
+      "grad_norm": 64.0671180453378,
+      "kl": 0.003570556640625,
+      "learning_rate": 9.95524126899385e-07,
+      "loss": 0.2195,
+      "reward": 1.2044923305511475,
+      "reward_std": 0.4964686334133148,
+      "rewards/": 3.665318250656128,
+      "rewards/math_compute_score": 0.5892857313156128,
+      "step": 23
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 537.8392944335938,
+      "epoch": 0.0761904761904762,
+      "grad_norm": 1.2437235826313204,
+      "kl": 0.002685546875,
+      "learning_rate": 9.94810286000272e-07,
+      "loss": -0.0234,
+      "reward": 1.2946465015411377,
+      "reward_std": 0.6178387403488159,
+      "rewards/": 4.1160888671875,
+      "rewards/math_compute_score": 0.5892857313156128,
+      "step": 24
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 541.9285888671875,
+      "epoch": 0.07936507936507936,
+      "grad_norm": 1.0493823155600928,
+      "kl": 0.002593994140625,
+      "learning_rate": 9.940439480455385e-07,
+      "loss": 0.1932,
+      "reward": 1.2854353189468384,
+      "reward_std": 0.37659183144569397,
+      "rewards/": 3.9271764755249023,
+      "rewards/math_compute_score": 0.625,
+      "step": 25
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 614.9464721679688,
+      "epoch": 0.08253968253968254,
+      "grad_norm": 0.8518264309351387,
+      "kl": 0.0031585693359375,
+      "learning_rate": 9.932251943400553e-07,
+      "loss": 0.1074,
+      "reward": 1.274550199508667,
+      "reward_std": 0.5471729040145874,
+      "rewards/": 4.1584649085998535,
+      "rewards/math_compute_score": 0.5535714626312256,
+      "step": 26
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 730.8214721679688,
+      "epoch": 0.08571428571428572,
+      "grad_norm": 0.6822773446685868,
+      "kl": 0.0024566650390625,
+      "learning_rate": 9.923541117497585e-07,
+      "loss": 0.0992,
+      "reward": 1.0367571115493774,
+      "reward_std": 0.6219119429588318,
+      "rewards/": 3.898071527481079,
+      "rewards/math_compute_score": 0.3214285969734192,
+      "step": 27
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 490.71429443359375,
+      "epoch": 0.08888888888888889,
+      "grad_norm": 1.1232996974013019,
+      "kl": 0.0037384033203125,
+      "learning_rate": 9.914307926924344e-07,
+      "loss": 0.1689,
+      "reward": 1.2891323566436768,
+      "reward_std": 0.47750726342201233,
+      "rewards/": 3.7313756942749023,
+      "rewards/math_compute_score": 0.6785714626312256,
+      "step": 28
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 545.2678833007812,
+      "epoch": 0.09206349206349207,
+      "grad_norm": 0.850986187002516,
+      "kl": 0.0032196044921875,
+      "learning_rate": 9.904553351279136e-07,
+      "loss": 0.1372,
+      "reward": 1.2297661304473877,
+      "reward_std": 0.4732263386249542,
+      "rewards/": 3.5059728622436523,
+      "rewards/math_compute_score": 0.660714328289032,
+      "step": 29
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 0.9732473101916553,
+      "learning_rate": 9.894278425476788e-07,
+      "loss": 0.1516,
+      "step": 30
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 642.7809651692709,
+      "eval_kl": 0.01214599609375,
+      "eval_loss": 0.07186427712440491,
+      "eval_reward": 1.1157209475835164,
+      "eval_reward_std": 0.6078123847643534,
+      "eval_rewards/": 3.864319086074829,
+      "eval_rewards/math_compute_score": 0.4285714526971181,
+      "eval_runtime": 102.5446,
+      "eval_samples_per_second": 0.195,
+      "eval_steps_per_second": 0.01,
+      "step": 30
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 539.6785888671875,
+      "epoch": 0.09841269841269841,
+      "grad_norm": 0.9713322753025198,
+      "kl": 0.002471923828125,
+      "learning_rate": 9.88348423963884e-07,
+      "loss": 0.1589,
+      "reward": 1.271599531173706,
+      "reward_std": 0.5087720453739166,
+      "rewards/": 4.143711805343628,
+      "rewards/math_compute_score": 0.5535714626312256,
+      "step": 31
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 528.1785888671875,
+      "epoch": 0.10158730158730159,
+      "grad_norm": 0.9806294151614033,
+      "kl": 0.01055908203125,
+      "learning_rate": 9.872171938977893e-07,
+      "loss": 0.1268,
+      "reward": 1.424546718597412,
+      "reward_std": 0.6000874638557434,
+      "rewards/": 4.4798760414123535,
+      "rewards/math_compute_score": 0.660714328289032,
+      "step": 32
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 485.4464416503906,
+      "epoch": 0.10476190476190476,
+      "grad_norm": 0.9073742544318019,
+      "kl": 0.004669189453125,
+      "learning_rate": 9.860342723676104e-07,
+      "loss": 0.0342,
+      "reward": 1.3068233728408813,
+      "reward_std": 0.4275137186050415,
+      "rewards/": 3.9626879692077637,
+      "rewards/math_compute_score": 0.6428571939468384,
+      "step": 33
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 496.5714416503906,
+      "epoch": 0.10793650793650794,
+      "grad_norm": 0.9066417457017405,
+      "kl": 0.0050048828125,
+      "learning_rate": 9.847997848757854e-07,
+      "loss": -0.0179,
+      "reward": 1.2185356616973877,
+      "reward_std": 0.5638229250907898,
+      "rewards/": 3.6641063690185547,
+      "rewards/math_compute_score": 0.6071428656578064,
+      "step": 34
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 507.5535888671875,
+      "epoch": 0.1111111111111111,
+      "grad_norm": 0.9277314587258759,
+      "kl": 0.0032806396484375,
+      "learning_rate": 9.835138623956602e-07,
+      "loss": 0.1597,
+      "reward": 1.3688966035842896,
+      "reward_std": 0.5674116015434265,
+      "rewards/": 4.273054122924805,
+      "rewards/math_compute_score": 0.6428571939468384,
+      "step": 35
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 543.5,
+      "epoch": 0.11428571428571428,
+      "grad_norm": 1.3488452721591695,
+      "kl": 0.004241943359375,
+      "learning_rate": 9.821766413575914e-07,
+      "loss": 0.0152,
+      "reward": 1.4376815557479858,
+      "reward_std": 0.4473975896835327,
+      "rewards/": 4.5455498695373535,
+      "rewards/math_compute_score": 0.660714328289032,
+      "step": 36
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 469.7857360839844,
+      "epoch": 0.11746031746031746,
+      "grad_norm": 1.0517039769336485,
+      "kl": 0.005889892578125,
+      "learning_rate": 9.80788263634473e-07,
+      "loss": 0.0032,
+      "reward": 1.3583706617355347,
+      "reward_std": 0.43741995096206665,
+      "rewards/": 4.577567100524902,
+      "rewards/math_compute_score": 0.5535714626312256,
+      "step": 37
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 536.732177734375,
+      "epoch": 0.12063492063492064,
+      "grad_norm": 1.0091010102420597,
+      "kl": 0.00482177734375,
+      "learning_rate": 9.793488765266838e-07,
+      "loss": -0.0272,
+      "reward": 1.3230539560317993,
+      "reward_std": 0.41071969270706177,
+      "rewards/": 4.615269660949707,
+      "rewards/math_compute_score": 0.5,
+      "step": 38
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 612.0,
+      "epoch": 0.12380952380952381,
+      "grad_norm": 0.8094839662349015,
+      "kl": 0.006195068359375,
+      "learning_rate": 9.778586327464597e-07,
+      "loss": -0.0217,
+      "reward": 1.3509767055511475,
+      "reward_std": 0.4637759327888489,
+      "rewards/": 4.3263115882873535,
+      "rewards/math_compute_score": 0.6071428656578064,
+      "step": 39
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "grad_norm": 1.0991359951502255,
+      "learning_rate": 9.763176904016913e-07,
+      "loss": 0.1502,
+      "step": 40
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 694.2035929361979,
+      "eval_kl": 0.2585856119791667,
+      "eval_loss": 0.17596088349819183,
+      "eval_reward": 1.3381081422170003,
+      "eval_reward_std": 0.6337080001831055,
+      "eval_rewards/": 4.452445189158122,
+      "eval_rewards/math_compute_score": 0.5595238407452902,
+      "eval_runtime": 101.9501,
+      "eval_samples_per_second": 0.196,
+      "eval_steps_per_second": 0.01,
+      "step": 40
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 315,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 40,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-40/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fc3d36607ba0c9abe076fb2ecd2935fb9bcae96aaf5b19721477275dce73f05
+size 8312

up.log

@@ -0,0 +1,2146 @@
+nohup: ignoring input
+Start hashing 16 files.
+Finished hashing 16 files.
+
+
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:   1%|▏         | 67.1MB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:   1%|▏         | 67.1MB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:   2%|▏         | 67.1MB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors:   6%|▌         | 67.1MB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:   1%|▏         | 67.1MB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:   1%|▏         | 67.1MB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:   2%|▏         | 67.1MB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors:   6%|▌         | 67.1MB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:   3%|▎         |  151MB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:   3%|▎         |  151MB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:   3%|▎         |  151MB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors:  14%|█▍        |  151MB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:   5%|▍         |  226MB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:   5%|▍         |  235MB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:   5%|▌         |  226MB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors:  21%|██        |  226MB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:   6%|▋         |  310MB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:   7%|▋         |  319MB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:   7%|▋         |  310MB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors:  28%|██▊       |  310MB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:   8%|▊         |  394MB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:   8%|▊         |  394MB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:   9%|▉         |  386MB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors:  35%|███▌      |  386MB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  10%|▉         |  470MB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  10%|▉         |  470MB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  11%|█         |  461MB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors:  42%|███��▏     |  461MB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  11%|█         |  545MB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  11%|█         |  545MB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  12%|█▏        |  537MB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors:  50%|█████     |  545MB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  13%|█▎        |  621MB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  13%|█▎        |  629MB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  14%|█▍        |  621MB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors:  58%|█████▊    |  629MB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  14%|█▍        |  705MB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  15%|█▍        |  713MB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  16%|█▌        |  696MB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors:  65%|██████▍   |  705MB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  16%|█▌        |  789MB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  16%|█▌        |  788MB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  18%|█▊        |  780MB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors:  72%|███████▏  |  788MB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  18%|█▊        |  864MB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  18%|█▊        |  872MB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  20%|█▉        |  864MB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors:  80%|████████  |  872MB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  19%|█▉        |  948MB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  20%|█▉        |  956MB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  22%|██▏       |  939MB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors:  87%|████████▋ |  948MB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  21%|██        | 1.03GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  21%|██        | 1.03GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  24%|██▎       | 1.02GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors:  95%|█████████▍| 1.03GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  22%|██▏       | 1.11GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  23%|██▎       | 1.12GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  25%|██▌       | 1.10GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  24%|██▍       | 1.19GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  25%|██▍       | 1.20GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  27%|██▋       | 1.18GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  26%|██▌       | 1.28GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  26%|██▌       | 1.27GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  29%|██▉       | 1.26GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  28%|██▊       | 1.36GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  28%|██▊       | 1.36GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  31%|███       | 1.34GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  29%|██▉       | 1.43GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  30%|██▉       | 1.44GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  33%|███▎      | 1.43GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  31%|███       | 1.51GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  31%|███       | 1.52GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  35%|███▍      | 1.50GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  32%|███▏      | 1.59GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  33%|███▎      | 1.60GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  36%|███▋      | 1.58GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  34%|███▍      | 1.68GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  35%|███▍      | 1.69GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  38%|███▊      | 1.65GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  36%|███▌      | 1.75GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  36%|███▋      | 1.77GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  40%|████      | 1.74GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  37%|███▋      | 1.84GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  38%|███▊      | 1.85GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  42%|████▏     | 1.82GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  39%|███▉      | 1.91GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  40%|███▉      | 1.93GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  44%|████▍     | 1.90GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  40%|████      | 1.99GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  41%|████      | 2.00GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  46%|████▌     | 1.97GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  42%|████▏     | 2.06GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  42%|████▏     | 2.07GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  47%|████▋     | 2.06GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  43%|████▎     | 2.14GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  44%|████▍     | 2.16GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  49%|████▉     | 2.13GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  45%|████▍     | 2.21GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  46%|████▌     | 2.22GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  51%|█████     | 2.21GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  47%|████▋     | 2.30GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  47%|████▋     | 2.31GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  53%|█████▎    | 2.29GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  48%|████▊     | 2.37GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  49%|████▊     | 2.37GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  55%|█████▍    | 2.37GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  50%|████▉     | 2.45GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  50%|█████     | 2.46GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  56%|█████▋    | 2.44GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  51%|█████     | 2.52GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  52%|█████▏    | 2.54GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  58%|█████▊    | 2.52GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  53%|█████▎    | 2.61GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  54%|█████▎    | 2.62GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  60%|██████    | 2.60GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  55%|█████▍    | 2.69GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  55%|█████▌    | 2.70GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  62%|██████▏   | 2.68GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  56%|█████▋    | 2.78GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  57%|█████▋    | 2.78GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  64%|██████▎   | 2.76GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  58%|█████▊    | 2.85GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  59%|█████▉    | 2.87GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  66%|██████▌   | 2.84GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  60%|█████▉    | 2.94GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  60%|██████    | 2.94GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  68%|██████▊   | 2.93GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  61%|██████    | 3.01GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  62%|██████▏   | 3.03GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  70%|██████▉   | 3.01GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  63%|██████▎   | 3.10GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  64%|██████▎   | 3.10GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  71%|███████▏  | 3.09GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  64%|██████▍   | 3.18GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  65%|██████▌   | 3.19GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  73%|███████▎  | 3.17GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  66%|██████▌   | 3.25GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  67%|██████▋   | 3.25GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  75%|███████▍  | 3.25GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  68%|██████▊   | 3.33GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  68%|██████▊   | 3.33GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  77%|███████▋  | 3.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  69%|██████▉   | 3.41GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  70%|██████▉   | 3.40GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  79%|███████▊  | 3.41GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  71%|███████   | 3.49GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  71%|███████▏  | 3.48GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  80%|████████  | 3.48GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  72%|███████▏  | 3.57GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  73%|███████▎  | 3.56GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  82%|████████▏ | 3.56GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  74%|███████▍  | 3.64GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  75%|███████▍  | 3.64GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  84%|████████▍ | 3.64GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  75%|███████▌  | 3.72GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  76%|███████▌  | 3.72GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  86%|████████▌ | 3.72GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  77%|███████▋  | 3.78GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  78%|███████▊  | 3.79GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  88%|████████▊ | 3.80GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  78%|███████▊  | 3.86GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  79%|███████▉  | 3.87GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  89%|████████▉ | 3.88GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  80%|███████▉  | 3.94GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  81%|████████  | 3.95GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  91%|█████████ | 3.95GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  82%|████████▏ | 4.03GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  83%|████████▎ | 4.03GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  93%|█████████▎| 4.03GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  83%|████████▎ | 4.11GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  84%|████████▍ | 4.11GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  95%|█████████▌| 4.12GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  85%|████████▍ | 4.19GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  86%|████████▌ | 4.19GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  97%|█████████▋| 4.19GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  87%|████████▋ | 4.27GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  88%|████████▊ | 4.27GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors:  99%|█████████▉| 4.28GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  88%|████████▊ | 4.35GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  89%|████████▉ | 4.34GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  90%|████████▉ | 4.43GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  91%|█████████ | 4.43GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  91%|█████████▏| 4.50GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  92%|█████████▏| 4.50GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  93%|█████████▎| 4.59GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  94%|█████████▍| 4.59GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  95%|█████████▍| 4.67GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  96%|█████████▌| 4.66GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  96%|█████████▋| 4.75GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  97%|█████████▋| 4.75GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  98%|█████████▊| 4.82GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors:  99%|█████████▉| 4.83GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors:  99%|█████████▉| 4.91GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors: 100%|█████████▉| 4.88GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors: 100%|██████████| 4.93GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors: 100%|█████████▉| 4.88GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors: 100%|██████████| 4.93GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors: 100%|█████████▉| 4.88GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors: 100%|██████████| 4.93GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors: 100%|█████████▉| 4.88GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors: 100%|██████████| 4.93GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors: 100%|█████████▉| 4.88GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors: 100%|██████████| 4.93GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors: 100%|█████████▉| 4.88GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors: 100%|██████████| 4.93GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors: 100%|█████████▉| 4.88GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors: 100%|██████████| 4.93GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors: 100%|█████████▉| 4.88GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors: 100%|██████████| 4.93GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors: 100%|█████████▉| 4.88GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors: 100%|██████████| 4.93GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors: 100%|█████████▉| 4.88GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors: 100%|██████████| 4.93GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors: 100%|█████████▉| 4.88GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|█████████��| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors: 100%|██████████| 4.93GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors: 100%|██████████| 4.88GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors: 100%|██████████| 4.93GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors: 100%|██████████| 4.88GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors: 100%|██████████| 4.93GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors: 100%|██████████| 4.88GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors: 100%|██████████| 4.93GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors: 100%|██████████| 4.88GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors: 100%|██████████| 4.93GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors: 100%|██████████| 4.88GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
+
+
  ...0002-of-00004.safetensors: 100%|██████████| 4.93GB / 4.93GB            
+
+
+
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
+
+
+
+
  ...0001-of-00004.safetensors: 100%|██████████| 4.88GB / 4.88GB            
+
+
+
+
+
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
+
+
+
+
+
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB            
+
+
  ...oint-40/training_args.bin: 100%|██████████| 8.31kB / 8.31kB            
+
  ...0002-of-00004.safetensors: 100%|██████████| 4.93GB / 4.93GB            
+
  ...ckpoint-40/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
+
  ...0001-of-00004.safetensors: 100%|██████████| 4.88GB / 4.88GB            
+
  ...0003-of-00004.safetensors: 100%|██████████| 4.33GB / 4.33GB            
+
  ...0004-of-00004.safetensors: 100%|██████████| 1.09GB / 1.09GB