Model save

.gitattributes

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

README.md

@@ -0,0 +1,60 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+tags:
+- llama-factory
+- generated_from_trainer
+model-index:
+- name: ex45_qwen2.5_7b_61k_source_15kcw_3ep_cuda_amd_os
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# ex45_qwen2.5_7b_61k_source_15kcw_3ep_cuda_amd_os
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 3
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 6
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 144
+- total_eval_batch_size: 48
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.50.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.4.1
+- Tokenizers 0.21.0

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.50.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:987fee8cb2ee586ab9fc25c7110e5a6e883c373133af6bb70bf0b7313c2a172c
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf405df799ccca37b8119808831e69874328357f442be1112b1b6ad5fd629fc9
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12f8ce46e9e353b764675d6d08b91b78266d8d9d7482f683592cfba8ff6c8b8f
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b19b78e6a66441ab9972cbddeb17cc591a6a8597501ea5bf58d0aa0391192aa
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,210 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "low_cpu_mem_usage": true,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,90 @@
+{"current_steps": 10, "total_steps": 894, "loss": 0.0287, "lr": 2.222222222222222e-06, "epoch": 0.02237136465324385, "percentage": 1.12, "elapsed_time": "1:07:16", "remaining_time": "4 days, 3:06:44"}
+{"current_steps": 20, "total_steps": 894, "loss": 0.0077, "lr": 4.444444444444444e-06, "epoch": 0.0447427293064877, "percentage": 2.24, "elapsed_time": "2:13:52", "remaining_time": "4 days, 1:30:08"}
+{"current_steps": 30, "total_steps": 894, "loss": 0.0025, "lr": 6.666666666666667e-06, "epoch": 0.06711409395973154, "percentage": 3.36, "elapsed_time": "3:20:12", "remaining_time": "4 days, 0:06:09"}
+{"current_steps": 40, "total_steps": 894, "loss": 0.0017, "lr": 8.888888888888888e-06, "epoch": 0.0894854586129754, "percentage": 4.47, "elapsed_time": "4:26:25", "remaining_time": "3 days, 22:48:14"}
+{"current_steps": 50, "total_steps": 894, "loss": 0.0018, "lr": 1.1111111111111113e-05, "epoch": 0.11185682326621924, "percentage": 5.59, "elapsed_time": "5:32:22", "remaining_time": "3 days, 21:30:26"}
+{"current_steps": 60, "total_steps": 894, "loss": 0.0009, "lr": 1.3333333333333333e-05, "epoch": 0.1342281879194631, "percentage": 6.71, "elapsed_time": "6:39:08", "remaining_time": "3 days, 20:28:05"}
+{"current_steps": 70, "total_steps": 894, "loss": 0.002, "lr": 1.555555555555556e-05, "epoch": 0.15659955257270694, "percentage": 7.83, "elapsed_time": "7:45:41", "remaining_time": "3 days, 19:21:49"}
+{"current_steps": 80, "total_steps": 894, "loss": 0.0024, "lr": 1.7777777777777777e-05, "epoch": 0.1789709172259508, "percentage": 8.95, "elapsed_time": "8:51:48", "remaining_time": "3 days, 18:11:09"}
+{"current_steps": 90, "total_steps": 894, "loss": 0.0005, "lr": 2e-05, "epoch": 0.20134228187919462, "percentage": 10.07, "elapsed_time": "9:58:44", "remaining_time": "3 days, 17:08:48"}
+{"current_steps": 100, "total_steps": 894, "loss": 0.0019, "lr": 1.9992366874654684e-05, "epoch": 0.22371364653243847, "percentage": 11.19, "elapsed_time": "11:05:12", "remaining_time": "3 days, 16:01:41"}
+{"current_steps": 110, "total_steps": 894, "loss": 0.0012, "lr": 1.9969479151539238e-05, "epoch": 0.24608501118568232, "percentage": 12.3, "elapsed_time": "12:11:18", "remaining_time": "3 days, 14:52:12"}
+{"current_steps": 120, "total_steps": 894, "loss": 0.0008, "lr": 1.9931371771625545e-05, "epoch": 0.2684563758389262, "percentage": 13.42, "elapsed_time": "13:17:16", "remaining_time": "3 days, 13:42:26"}
+{"current_steps": 130, "total_steps": 894, "loss": 0.0011, "lr": 1.9878102910595097e-05, "epoch": 0.29082774049217003, "percentage": 14.54, "elapsed_time": "14:24:20", "remaining_time": "3 days, 12:39:42"}
+{"current_steps": 140, "total_steps": 894, "loss": 0.0018, "lr": 1.9809753890026543e-05, "epoch": 0.3131991051454139, "percentage": 15.66, "elapsed_time": "15:30:46", "remaining_time": "3 days, 11:32:52"}
+{"current_steps": 150, "total_steps": 894, "loss": 0.0008, "lr": 1.972642905324813e-05, "epoch": 0.33557046979865773, "percentage": 16.78, "elapsed_time": "16:36:35", "remaining_time": "3 days, 10:23:07"}
+{"current_steps": 160, "total_steps": 894, "loss": 0.001, "lr": 1.9628255606044562e-05, "epoch": 0.3579418344519016, "percentage": 17.9, "elapsed_time": "17:42:57", "remaining_time": "3 days, 9:16:17"}
+{"current_steps": 170, "total_steps": 894, "loss": 0.0007, "lr": 1.9515383422461457e-05, "epoch": 0.38031319910514544, "percentage": 19.02, "elapsed_time": "18:48:59", "remaining_time": "3 days, 8:08:10"}
+{"current_steps": 180, "total_steps": 894, "loss": 0.0009, "lr": 1.9387984816003868e-05, "epoch": 0.40268456375838924, "percentage": 20.13, "elapsed_time": "19:55:10", "remaining_time": "3 days, 7:00:51"}
+{"current_steps": 190, "total_steps": 894, "loss": 0.0012, "lr": 1.9246254276578175e-05, "epoch": 0.4250559284116331, "percentage": 21.25, "elapsed_time": "21:01:32", "remaining_time": "3 days, 5:54:21"}
+{"current_steps": 200, "total_steps": 894, "loss": 0.0018, "lr": 1.9090408173578923e-05, "epoch": 0.44742729306487694, "percentage": 22.37, "elapsed_time": "22:07:43", "remaining_time": "3 days, 4:47:12"}
+{"current_steps": 210, "total_steps": 894, "loss": 0.0012, "lr": 1.8920684425573865e-05, "epoch": 0.4697986577181208, "percentage": 23.49, "elapsed_time": "23:14:59", "remaining_time": "3 days, 3:43:40"}
+{"current_steps": 220, "total_steps": 894, "loss": 0.0006, "lr": 1.8737342137091523e-05, "epoch": 0.49217002237136465, "percentage": 24.61, "elapsed_time": "1 day, 0:20:41", "remaining_time": "3 days, 2:35:02"}
+{"current_steps": 230, "total_steps": 894, "loss": 0.0007, "lr": 1.854066120306571e-05, "epoch": 0.5145413870246085, "percentage": 25.73, "elapsed_time": "1 day, 1:26:49", "remaining_time": "3 days, 1:27:51"}
+{"current_steps": 240, "total_steps": 894, "loss": 0.0009, "lr": 1.8330941881540917e-05, "epoch": 0.5369127516778524, "percentage": 26.85, "elapsed_time": "1 day, 2:33:05", "remaining_time": "3 days, 0:21:10"}
+{"current_steps": 250, "total_steps": 894, "loss": 0.0021, "lr": 1.8108504335290852e-05, "epoch": 0.5592841163310962, "percentage": 27.96, "elapsed_time": "1 day, 3:39:17", "remaining_time": "2 days, 23:14:21"}
+{"current_steps": 260, "total_steps": 894, "loss": 0.0009, "lr": 1.787368814304992e-05, "epoch": 0.5816554809843401, "percentage": 29.08, "elapsed_time": "1 day, 4:45:18", "remaining_time": "2 days, 22:07:05"}
+{"current_steps": 270, "total_steps": 894, "loss": 0.0013, "lr": 1.762685178110382e-05, "epoch": 0.6040268456375839, "percentage": 30.2, "elapsed_time": "1 day, 5:51:11", "remaining_time": "2 days, 20:59:37"}
+{"current_steps": 280, "total_steps": 894, "loss": 0.0016, "lr": 1.7368372076030654e-05, "epoch": 0.6263982102908278, "percentage": 31.32, "elapsed_time": "1 day, 6:57:13", "remaining_time": "2 days, 19:52:37"}
+{"current_steps": 290, "total_steps": 894, "loss": 0.0009, "lr": 1.7098643629428035e-05, "epoch": 0.6487695749440716, "percentage": 32.44, "elapsed_time": "1 day, 8:03:19", "remaining_time": "2 days, 18:45:50"}
+{"current_steps": 300, "total_steps": 894, "loss": 0.0009, "lr": 1.681807821550438e-05, "epoch": 0.6711409395973155, "percentage": 33.56, "elapsed_time": "1 day, 9:10:17", "remaining_time": "2 days, 17:40:45"}
+{"current_steps": 310, "total_steps": 894, "loss": 0.0004, "lr": 1.6527104152454096e-05, "epoch": 0.6935123042505593, "percentage": 34.68, "elapsed_time": "1 day, 10:17:10", "remaining_time": "2 days, 16:35:27"}
+{"current_steps": 320, "total_steps": 894, "loss": 0.0026, "lr": 1.622616564857629e-05, "epoch": 0.7158836689038032, "percentage": 35.79, "elapsed_time": "1 day, 11:23:14", "remaining_time": "2 days, 15:28:33"}
+{"current_steps": 330, "total_steps": 894, "loss": 0.0014, "lr": 1.5915722124135227e-05, "epoch": 0.738255033557047, "percentage": 36.91, "elapsed_time": "1 day, 12:29:27", "remaining_time": "2 days, 14:21:58"}
+{"current_steps": 340, "total_steps": 894, "loss": 0.0017, "lr": 1.5596247509997843e-05, "epoch": 0.7606263982102909, "percentage": 38.03, "elapsed_time": "1 day, 13:35:08", "remaining_time": "2 days, 13:14:32"}
+{"current_steps": 350, "total_steps": 894, "loss": 0.0006, "lr": 1.5268229524119007e-05, "epoch": 0.7829977628635347, "percentage": 39.15, "elapsed_time": "1 day, 14:40:50", "remaining_time": "2 days, 12:07:15"}
+{"current_steps": 360, "total_steps": 894, "loss": 0.0012, "lr": 1.4932168926979074e-05, "epoch": 0.8053691275167785, "percentage": 40.27, "elapsed_time": "1 day, 15:47:24", "remaining_time": "2 days, 11:01:19"}
+{"current_steps": 370, "total_steps": 894, "loss": 0.0007, "lr": 1.4588578757110359e-05, "epoch": 0.8277404921700223, "percentage": 41.39, "elapsed_time": "1 day, 16:54:09", "remaining_time": "2 days, 9:55:36"}
+{"current_steps": 380, "total_steps": 894, "loss": 0.0043, "lr": 1.4237983547879664e-05, "epoch": 0.8501118568232662, "percentage": 42.51, "elapsed_time": "1 day, 18:00:29", "remaining_time": "2 days, 8:49:18"}
+{"current_steps": 390, "total_steps": 894, "loss": 0.0006, "lr": 1.3880918526722497e-05, "epoch": 0.87248322147651, "percentage": 43.62, "elapsed_time": "1 day, 19:06:48", "remaining_time": "2 days, 7:42:57"}
+{"current_steps": 400, "total_steps": 894, "loss": 0.0013, "lr": 1.3517928798051442e-05, "epoch": 0.8948545861297539, "percentage": 44.74, "elapsed_time": "1 day, 20:12:40", "remaining_time": "2 days, 6:36:03"}
+{"current_steps": 410, "total_steps": 894, "loss": 0.0018, "lr": 1.3149568511086104e-05, "epoch": 0.9172259507829977, "percentage": 45.86, "elapsed_time": "1 day, 21:20:16", "remaining_time": "2 days, 5:31:15"}
+{"current_steps": 420, "total_steps": 894, "loss": 0.0019, "lr": 1.2776400013875006e-05, "epoch": 0.9395973154362416, "percentage": 46.98, "elapsed_time": "1 day, 22:26:15", "remaining_time": "2 days, 4:24:29"}
+{"current_steps": 430, "total_steps": 894, "loss": 0.0032, "lr": 1.239899299480098e-05, "epoch": 0.9619686800894854, "percentage": 48.1, "elapsed_time": "1 day, 23:32:52", "remaining_time": "2 days, 3:18:26"}
+{"current_steps": 440, "total_steps": 894, "loss": 0.0031, "lr": 1.2017923612880579e-05, "epoch": 0.9843400447427293, "percentage": 49.22, "elapsed_time": "2 days, 0:38:59", "remaining_time": "2 days, 2:11:51"}
+{"current_steps": 450, "total_steps": 894, "loss": 0.0009, "lr": 1.1633773618185302e-05, "epoch": 1.0067114093959733, "percentage": 50.34, "elapsed_time": "2 days, 1:45:12", "remaining_time": "2 days, 1:05:24"}
+{"current_steps": 460, "total_steps": 894, "loss": 0.0025, "lr": 1.1247129463727329e-05, "epoch": 1.029082774049217, "percentage": 51.45, "elapsed_time": "2 days, 2:52:02", "remaining_time": "1 day, 23:59:32"}
+{"current_steps": 470, "total_steps": 894, "loss": 0.0004, "lr": 1.085858141016566e-05, "epoch": 1.0514541387024607, "percentage": 52.57, "elapsed_time": "2 days, 3:58:21", "remaining_time": "1 day, 22:53:09"}
+{"current_steps": 480, "total_steps": 894, "loss": 0.0003, "lr": 1.0468722624699401e-05, "epoch": 1.0738255033557047, "percentage": 53.69, "elapsed_time": "2 days, 5:04:37", "remaining_time": "1 day, 21:46:43"}
+{"current_steps": 490, "total_steps": 894, "loss": 0.0019, "lr": 1.007814827552384e-05, "epoch": 1.0961968680089484, "percentage": 54.81, "elapsed_time": "2 days, 6:10:42", "remaining_time": "1 day, 20:40:10"}
+{"current_steps": 500, "total_steps": 894, "loss": 0.0006, "lr": 9.68745462323176e-06, "epoch": 1.1185682326621924, "percentage": 55.93, "elapsed_time": "2 days, 7:17:07", "remaining_time": "1 day, 19:33:53"}
+{"current_steps": 510, "total_steps": 894, "loss": 0.001, "lr": 9.297238110547075e-06, "epoch": 1.1409395973154361, "percentage": 57.05, "elapsed_time": "2 days, 8:23:26", "remaining_time": "1 day, 18:27:32"}
+{"current_steps": 520, "total_steps": 894, "loss": 0.0002, "lr": 8.908094451780408e-06, "epoch": 1.1633109619686801, "percentage": 58.17, "elapsed_time": "2 days, 9:29:54", "remaining_time": "1 day, 17:21:16"}
+{"current_steps": 530, "total_steps": 894, "loss": 0.0006, "lr": 8.520617723396702e-06, "epoch": 1.1856823266219239, "percentage": 59.28, "elapsed_time": "2 days, 10:36:04", "remaining_time": "1 day, 16:14:49"}
+{"current_steps": 540, "total_steps": 894, "loss": 0.0002, "lr": 8.13539945708319e-06, "epoch": 1.2080536912751678, "percentage": 60.4, "elapsed_time": "2 days, 11:43:03", "remaining_time": "1 day, 15:08:53"}
+{"current_steps": 550, "total_steps": 894, "loss": 0.0011, "lr": 7.753027736702283e-06, "epoch": 1.2304250559284116, "percentage": 61.52, "elapsed_time": "2 days, 12:49:27", "remaining_time": "1 day, 14:02:34"}
+{"current_steps": 560, "total_steps": 894, "loss": 0.0004, "lr": 7.374086300508019e-06, "epoch": 1.2527964205816555, "percentage": 62.64, "elapsed_time": "2 days, 13:55:48", "remaining_time": "1 day, 12:56:13"}
+{"current_steps": 570, "total_steps": 894, "loss": 0.0003, "lr": 6.999153649996595e-06, "epoch": 1.2751677852348993, "percentage": 63.76, "elapsed_time": "2 days, 15:02:05", "remaining_time": "1 day, 11:49:49"}
+{"current_steps": 580, "total_steps": 894, "loss": 0.0004, "lr": 6.628802166751496e-06, "epoch": 1.2975391498881432, "percentage": 64.88, "elapsed_time": "2 days, 16:08:08", "remaining_time": "1 day, 10:43:18"}
+{"current_steps": 590, "total_steps": 894, "loss": 0.0006, "lr": 6.263597238631405e-06, "epoch": 1.319910514541387, "percentage": 66.0, "elapsed_time": "2 days, 17:14:38", "remaining_time": "1 day, 9:37:01"}
+{"current_steps": 600, "total_steps": 894, "loss": 0.0005, "lr": 5.904096396634935e-06, "epoch": 1.342281879194631, "percentage": 67.11, "elapsed_time": "2 days, 18:21:06", "remaining_time": "1 day, 8:30:44"}
+{"current_steps": 610, "total_steps": 894, "loss": 0.0003, "lr": 5.550848463759835e-06, "epoch": 1.3646532438478747, "percentage": 68.23, "elapsed_time": "2 days, 19:28:52", "remaining_time": "1 day, 7:25:03"}
+{"current_steps": 620, "total_steps": 894, "loss": 0.0005, "lr": 5.204392717156021e-06, "epoch": 1.3870246085011186, "percentage": 69.35, "elapsed_time": "2 days, 20:35:25", "remaining_time": "1 day, 6:18:45"}
+{"current_steps": 630, "total_steps": 894, "loss": 0.0022, "lr": 4.865258064851579e-06, "epoch": 1.4093959731543624, "percentage": 70.47, "elapsed_time": "2 days, 21:41:46", "remaining_time": "1 day, 5:12:21"}
+{"current_steps": 640, "total_steps": 894, "loss": 0.0008, "lr": 4.5339622383085095e-06, "epoch": 1.4317673378076063, "percentage": 71.59, "elapsed_time": "2 days, 22:47:48", "remaining_time": "1 day, 4:05:50"}
+{"current_steps": 650, "total_steps": 894, "loss": 0.0012, "lr": 4.211011002040885e-06, "epoch": 1.45413870246085, "percentage": 72.71, "elapsed_time": "2 days, 23:54:27", "remaining_time": "1 day, 2:59:34"}
+{"current_steps": 660, "total_steps": 894, "loss": 0.0023, "lr": 3.896897381502081e-06, "epoch": 1.476510067114094, "percentage": 73.83, "elapsed_time": "3 days, 1:00:53", "remaining_time": "1 day, 1:53:13"}
+{"current_steps": 670, "total_steps": 894, "loss": 0.0002, "lr": 3.592100910419738e-06, "epoch": 1.4988814317673378, "percentage": 74.94, "elapsed_time": "3 days, 2:07:05", "remaining_time": "1 day, 0:46:47"}
+{"current_steps": 680, "total_steps": 894, "loss": 0.0004, "lr": 3.297086898727583e-06, "epoch": 1.5212527964205815, "percentage": 76.06, "elapsed_time": "3 days, 3:13:15", "remaining_time": "23:40:20"}
+{"current_steps": 690, "total_steps": 894, "loss": 0.0005, "lr": 3.0123057222115835e-06, "epoch": 1.5436241610738255, "percentage": 77.18, "elapsed_time": "3 days, 4:20:04", "remaining_time": "22:34:06"}
+{"current_steps": 700, "total_steps": 894, "loss": 0.0007, "lr": 2.73819213495501e-06, "epoch": 1.5659955257270695, "percentage": 78.3, "elapsed_time": "3 days, 5:26:55", "remaining_time": "21:27:51"}
+{"current_steps": 710, "total_steps": 894, "loss": 0.0009, "lr": 2.4751646056319334e-06, "epoch": 1.5883668903803132, "percentage": 79.42, "elapsed_time": "3 days, 6:33:24", "remaining_time": "20:21:30"}
+{"current_steps": 720, "total_steps": 894, "loss": 0.0003, "lr": 2.2236246786624794e-06, "epoch": 1.610738255033557, "percentage": 80.54, "elapsed_time": "3 days, 7:39:39", "remaining_time": "19:15:05"}
+{"current_steps": 730, "total_steps": 894, "loss": 0.0007, "lr": 1.9839563612050273e-06, "epoch": 1.633109619686801, "percentage": 81.66, "elapsed_time": "3 days, 8:46:03", "remaining_time": "18:08:42"}
+{"current_steps": 740, "total_steps": 894, "loss": 0.0003, "lr": 1.7565255369212664e-06, "epoch": 1.6554809843400449, "percentage": 82.77, "elapsed_time": "3 days, 9:52:28", "remaining_time": "17:02:19"}
+{"current_steps": 750, "total_steps": 894, "loss": 0.0006, "lr": 1.5416794074090258e-06, "epoch": 1.6778523489932886, "percentage": 83.89, "elapsed_time": "3 days, 10:59:16", "remaining_time": "15:56:01"}
+{"current_steps": 760, "total_steps": 894, "loss": 0.0011, "lr": 1.339745962155613e-06, "epoch": 1.7002237136465324, "percentage": 85.01, "elapsed_time": "3 days, 12:05:25", "remaining_time": "14:49:35"}
+{"current_steps": 770, "total_steps": 894, "loss": 0.0006, "lr": 1.1510334778208332e-06, "epoch": 1.7225950782997763, "percentage": 86.13, "elapsed_time": "3 days, 13:11:34", "remaining_time": "13:43:09"}
+{"current_steps": 780, "total_steps": 894, "loss": 0.0007, "lr": 9.75830047614117e-07, "epoch": 1.7449664429530203, "percentage": 87.25, "elapsed_time": "3 days, 14:17:50", "remaining_time": "12:36:45"}
+{"current_steps": 790, "total_steps": 894, "loss": 0.0006, "lr": 8.144031414842012e-07, "epoch": 1.767337807606264, "percentage": 88.37, "elapsed_time": "3 days, 15:23:46", "remaining_time": "11:30:19"}
+{"current_steps": 800, "total_steps": 894, "loss": 0.0003, "lr": 6.669991977928103e-07, "epoch": 1.7897091722595078, "percentage": 89.49, "elapsed_time": "3 days, 16:30:13", "remaining_time": "10:23:57"}
+{"current_steps": 810, "total_steps": 894, "loss": 0.0009, "lr": 5.33843247095659e-07, "epoch": 1.8120805369127517, "percentage": 90.6, "elapsed_time": "3 days, 17:37:41", "remaining_time": "9:17:41"}
+{"current_steps": 820, "total_steps": 894, "loss": 0.0005, "lr": 4.1513856860517676e-07, "epoch": 1.8344519015659957, "percentage": 91.72, "elapsed_time": "3 days, 18:43:49", "remaining_time": "8:11:16"}
+{"current_steps": 830, "total_steps": 894, "loss": 0.0005, "lr": 3.110663798593616e-07, "epoch": 1.8568232662192394, "percentage": 92.84, "elapsed_time": "3 days, 19:49:54", "remaining_time": "7:04:51"}
+{"current_steps": 840, "total_steps": 894, "loss": 0.0005, "lr": 2.2178556007054876e-07, "epoch": 1.8791946308724832, "percentage": 93.96, "elapsed_time": "3 days, 20:56:46", "remaining_time": "5:58:30"}
+{"current_steps": 850, "total_steps": 894, "loss": 0.0007, "lr": 1.474324075764111e-07, "epoch": 1.901565995525727, "percentage": 95.08, "elapsed_time": "3 days, 22:02:46", "remaining_time": "4:52:05"}
+{"current_steps": 860, "total_steps": 894, "loss": 0.0006, "lr": 8.812043176351093e-08, "epoch": 1.9239373601789709, "percentage": 96.2, "elapsed_time": "3 days, 23:09:02", "remaining_time": "3:45:42"}
+{"current_steps": 870, "total_steps": 894, "loss": 0.0009, "lr": 4.394017978101905e-08, "epoch": 1.9463087248322148, "percentage": 97.32, "elapsed_time": "4 days, 0:15:23", "remaining_time": "2:39:19"}
+{"current_steps": 880, "total_steps": 894, "loss": 0.0012, "lr": 1.495909830917075e-08, "epoch": 1.9686800894854586, "percentage": 98.43, "elapsed_time": "4 days, 1:22:08", "remaining_time": "1:32:56"}
+{"current_steps": 890, "total_steps": 894, "loss": 0.0008, "lr": 1.2214305934699078e-09, "epoch": 1.9910514541387023, "percentage": 99.55, "elapsed_time": "4 days, 2:27:59", "remaining_time": "0:26:33"}
+{"current_steps": 894, "total_steps": 894, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "4 days, 2:55:26", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ef6e2c08d51112842fa1a84e15e09547bb4c8b5a0a05ccf13c0fa634d42659c
+size 7864