upload testing qwen_code_7B_test_swe_reasoning

.gitattributes

@@ -33,3 +33,5 @@ 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-108/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: qwen_code_32B_test_swe_reasoning_short_llm
+  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. -->
+
+# qwen_code_32B_test_swe_reasoning_short_llm
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) on the SWE-BENCH-400-reasoning-short-llm 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: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 3
+- gradient_accumulation_steps: 12
+- total_train_batch_size: 36
+- total_eval_batch_size: 24
+- 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: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.48.3
+- Pytorch 2.5.1+cu124
+- Datasets 2.21.0
+- 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
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.975169300225734,
+    "total_flos": 3.237704266625843e+16,
+    "train_loss": 0.7293182517643328,
+    "train_runtime": 6995.9355,
+    "train_samples_per_second": 0.569,
+    "train_steps_per_second": 0.015
+}

checkpoint-108/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-108/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-108/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": "4.48.3"
+}

checkpoint-108/global_step109/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0645158aaf419729ff155fa114fe3f9bccab3b03384d60431c0052041f296ce5
+size 30462476122

checkpoint-108/global_step109/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3ed669db2d9cc351719f36675182cdfd2514091683538b074a1cd8f009e6f80
+size 30462476122

checkpoint-108/global_step109/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a5ec86eb4468140fa7d521550278c6033ec604898820f01be12dbb24fcbd14e
+size 30462476122

checkpoint-108/global_step109/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f56f77a2e75172c1a70b32f78a1dcb7753bc8344099a8e703373d451045bb922
+size 165205

checkpoint-108/global_step109/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:663dc888b54d4263db741d8153b86fe5d6638598f5f067e194f8933cf492d83a
+size 165205

checkpoint-108/global_step109/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf2b394ec4903b4c7fcd7f2beb8736009415e0f0e6faf15d1cc3cd1ac7e2c3ac
+size 165205

checkpoint-108/latest

@@ -0,0 +1 @@
+global_step109

checkpoint-108/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:665ed4081835b9e11c2b96cf2a69488f7e0fa694d00fae8271a920ba2f2c36fe
+size 4877660776

checkpoint-108/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dbd6f925c107764703ac15070e75ffe4b41337d39a4bd5b5168494e883fce02
+size 4932751008

checkpoint-108/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1de73ab88909e6f4f7e6d4bfab8ad2e6238b8491a060c75672e50ede2ddcb9d4
+size 4330865200

checkpoint-108/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7045b566d18b7fd7d93652047d73d68e87b1362ed616903847f0919cf3221f7f
+size 1089994880

checkpoint-108/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-108/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da2bf9ae13691c39ee7fbd9eb497b0127d60b8594c24b2891098b3739c25d5b1
+size 14768

checkpoint-108/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:835f7198d4d5539c74a0ce15e3fbba2ee359088c79e0b77984b34308b954bd63
+size 14768

checkpoint-108/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19325cacb8d362ac4f02fb14163603ec88cb2fa312cb10277c2cad28943bdef3
+size 14768

checkpoint-108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aebd1e8280e985d9f798bcb47ecb586a86d5597a5e7d18c4776a0ebd2d41ce80
+size 1064

checkpoint-108/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
+  }
+}

checkpoint-108/tokenizer.json

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

checkpoint-108/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if 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": {},
+  "model_max_length": 16384,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-108/trainer_state.json

@@ -0,0 +1,789 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.975169300225734,
+  "eval_steps": 500,
+  "global_step": 108,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02708803611738149,
+      "grad_norm": 0.3197194327711118,
+      "learning_rate": 9.090909090909091e-07,
+      "loss": 1.2461,
+      "step": 1
+    },
+    {
+      "epoch": 0.05417607223476298,
+      "grad_norm": 0.31103611995893704,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 1.2148,
+      "step": 2
+    },
+    {
+      "epoch": 0.08126410835214447,
+      "grad_norm": 0.2337633531452293,
+      "learning_rate": 2.7272727272727272e-06,
+      "loss": 0.9726,
+      "step": 3
+    },
+    {
+      "epoch": 0.10835214446952596,
+      "grad_norm": 0.2732448083772183,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 1.1417,
+      "step": 4
+    },
+    {
+      "epoch": 0.13544018058690746,
+      "grad_norm": 0.18372677123914605,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 0.9526,
+      "step": 5
+    },
+    {
+      "epoch": 0.16252821670428894,
+      "grad_norm": 0.14598996204381387,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 1.0301,
+      "step": 6
+    },
+    {
+      "epoch": 0.18961625282167044,
+      "grad_norm": 0.12859546866157384,
+      "learning_rate": 6.363636363636364e-06,
+      "loss": 1.0107,
+      "step": 7
+    },
+    {
+      "epoch": 0.21670428893905191,
+      "grad_norm": 0.11328838489926579,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 1.0306,
+      "step": 8
+    },
+    {
+      "epoch": 0.24379232505643342,
+      "grad_norm": 0.1022283734283964,
+      "learning_rate": 8.181818181818183e-06,
+      "loss": 0.8963,
+      "step": 9
+    },
+    {
+      "epoch": 0.2708803611738149,
+      "grad_norm": 0.11790288806381347,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 1.0366,
+      "step": 10
+    },
+    {
+      "epoch": 0.2979683972911964,
+      "grad_norm": 0.12155066660752349,
+      "learning_rate": 1e-05,
+      "loss": 0.9005,
+      "step": 11
+    },
+    {
+      "epoch": 0.32505643340857787,
+      "grad_norm": 0.10987900474389686,
+      "learning_rate": 9.997377845227577e-06,
+      "loss": 0.8125,
+      "step": 12
+    },
+    {
+      "epoch": 0.35214446952595935,
+      "grad_norm": 0.1338371645473795,
+      "learning_rate": 9.98951413118856e-06,
+      "loss": 0.9944,
+      "step": 13
+    },
+    {
+      "epoch": 0.3792325056433409,
+      "grad_norm": 0.10584646720619653,
+      "learning_rate": 9.97641710583307e-06,
+      "loss": 0.8586,
+      "step": 14
+    },
+    {
+      "epoch": 0.40632054176072235,
+      "grad_norm": 0.07551668645041647,
+      "learning_rate": 9.958100506132127e-06,
+      "loss": 0.6047,
+      "step": 15
+    },
+    {
+      "epoch": 0.43340857787810383,
+      "grad_norm": 0.10339673320083177,
+      "learning_rate": 9.934583543669454e-06,
+      "loss": 0.8924,
+      "step": 16
+    },
+    {
+      "epoch": 0.4604966139954853,
+      "grad_norm": 0.08900126200269193,
+      "learning_rate": 9.905890884491196e-06,
+      "loss": 0.8502,
+      "step": 17
+    },
+    {
+      "epoch": 0.48758465011286684,
+      "grad_norm": 0.0755389181238505,
+      "learning_rate": 9.872052623234632e-06,
+      "loss": 0.8565,
+      "step": 18
+    },
+    {
+      "epoch": 0.5146726862302483,
+      "grad_norm": 0.08559033880567499,
+      "learning_rate": 9.833104251563058e-06,
+      "loss": 1.022,
+      "step": 19
+    },
+    {
+      "epoch": 0.5417607223476298,
+      "grad_norm": 0.06946932719559365,
+      "learning_rate": 9.789086620939936e-06,
+      "loss": 0.8234,
+      "step": 20
+    },
+    {
+      "epoch": 0.5688487584650113,
+      "grad_norm": 0.07510589474735027,
+      "learning_rate": 9.740045899781353e-06,
+      "loss": 0.8359,
+      "step": 21
+    },
+    {
+      "epoch": 0.5959367945823928,
+      "grad_norm": 0.06552207629817948,
+      "learning_rate": 9.68603352503172e-06,
+      "loss": 0.7305,
+      "step": 22
+    },
+    {
+      "epoch": 0.6230248306997742,
+      "grad_norm": 0.06750242477377788,
+      "learning_rate": 9.627106148213521e-06,
+      "loss": 0.7568,
+      "step": 23
+    },
+    {
+      "epoch": 0.6501128668171557,
+      "grad_norm": 0.07579791889142827,
+      "learning_rate": 9.563325576007702e-06,
+      "loss": 0.8188,
+      "step": 24
+    },
+    {
+      "epoch": 0.6772009029345373,
+      "grad_norm": 0.05385726475558828,
+      "learning_rate": 9.494758705426978e-06,
+      "loss": 0.6476,
+      "step": 25
+    },
+    {
+      "epoch": 0.7042889390519187,
+      "grad_norm": 0.0659922617401428,
+      "learning_rate": 9.421477453650118e-06,
+      "loss": 0.8316,
+      "step": 26
+    },
+    {
+      "epoch": 0.7313769751693002,
+      "grad_norm": 0.06724043516128614,
+      "learning_rate": 9.343558682590757e-06,
+      "loss": 0.8827,
+      "step": 27
+    },
+    {
+      "epoch": 0.7584650112866818,
+      "grad_norm": 0.057407448162910005,
+      "learning_rate": 9.261084118279846e-06,
+      "loss": 0.7524,
+      "step": 28
+    },
+    {
+      "epoch": 0.7855530474040632,
+      "grad_norm": 0.06600552654685582,
+      "learning_rate": 9.174140265146356e-06,
+      "loss": 0.8426,
+      "step": 29
+    },
+    {
+      "epoch": 0.8126410835214447,
+      "grad_norm": 0.05731937218952811,
+      "learning_rate": 9.082818315286054e-06,
+      "loss": 0.7681,
+      "step": 30
+    },
+    {
+      "epoch": 0.8397291196388262,
+      "grad_norm": 0.05814787595507311,
+      "learning_rate": 8.987214052813605e-06,
+      "loss": 0.7463,
+      "step": 31
+    },
+    {
+      "epoch": 0.8668171557562077,
+      "grad_norm": 0.06918050909180208,
+      "learning_rate": 8.887427753398249e-06,
+      "loss": 0.908,
+      "step": 32
+    },
+    {
+      "epoch": 0.8939051918735892,
+      "grad_norm": 0.0651707634722971,
+      "learning_rate": 8.783564079088478e-06,
+      "loss": 0.7965,
+      "step": 33
+    },
+    {
+      "epoch": 0.9209932279909706,
+      "grad_norm": 0.047559578658812544,
+      "learning_rate": 8.675731968536004e-06,
+      "loss": 0.6443,
+      "step": 34
+    },
+    {
+      "epoch": 0.9480812641083521,
+      "grad_norm": 0.05660630221337761,
+      "learning_rate": 8.564044522734147e-06,
+      "loss": 0.7452,
+      "step": 35
+    },
+    {
+      "epoch": 0.9751693002257337,
+      "grad_norm": 0.053852038093973535,
+      "learning_rate": 8.448618886390523e-06,
+      "loss": 0.736,
+      "step": 36
+    },
+    {
+      "epoch": 1.0270880361173815,
+      "grad_norm": 0.07449181460800067,
+      "learning_rate": 8.329576125058406e-06,
+      "loss": 1.4609,
+      "step": 37
+    },
+    {
+      "epoch": 1.054176072234763,
+      "grad_norm": 0.05525435344631101,
+      "learning_rate": 8.207041098155701e-06,
+      "loss": 0.6621,
+      "step": 38
+    },
+    {
+      "epoch": 1.0812641083521444,
+      "grad_norm": 0.05203784294919359,
+      "learning_rate": 8.081142328004638e-06,
+      "loss": 0.7746,
+      "step": 39
+    },
+    {
+      "epoch": 1.108352144469526,
+      "grad_norm": 0.05697857349793105,
+      "learning_rate": 7.952011865029614e-06,
+      "loss": 0.6824,
+      "step": 40
+    },
+    {
+      "epoch": 1.1354401805869074,
+      "grad_norm": 0.05062686469158285,
+      "learning_rate": 7.819785149254534e-06,
+      "loss": 0.6903,
+      "step": 41
+    },
+    {
+      "epoch": 1.162528216704289,
+      "grad_norm": 0.05481418216875255,
+      "learning_rate": 7.68460086824492e-06,
+      "loss": 0.7619,
+      "step": 42
+    },
+    {
+      "epoch": 1.1896162528216705,
+      "grad_norm": 0.05846015164093139,
+      "learning_rate": 7.546600811643816e-06,
+      "loss": 0.7389,
+      "step": 43
+    },
+    {
+      "epoch": 1.2167042889390518,
+      "grad_norm": 0.05413723610310761,
+      "learning_rate": 7.405929722454026e-06,
+      "loss": 0.6184,
+      "step": 44
+    },
+    {
+      "epoch": 1.2437923250564333,
+      "grad_norm": 0.05134366705233288,
+      "learning_rate": 7.262735145222696e-06,
+      "loss": 0.6454,
+      "step": 45
+    },
+    {
+      "epoch": 1.2708803611738149,
+      "grad_norm": 0.05310633803377862,
+      "learning_rate": 7.117167271287453e-06,
+      "loss": 0.6757,
+      "step": 46
+    },
+    {
+      "epoch": 1.2979683972911964,
+      "grad_norm": 0.053925607393482275,
+      "learning_rate": 6.969378781246436e-06,
+      "loss": 0.6576,
+      "step": 47
+    },
+    {
+      "epoch": 1.325056433408578,
+      "grad_norm": 0.057106251483552625,
+      "learning_rate": 6.819524684817439e-06,
+      "loss": 0.7626,
+      "step": 48
+    },
+    {
+      "epoch": 1.3521444695259595,
+      "grad_norm": 0.063954914765478,
+      "learning_rate": 6.667762158254104e-06,
+      "loss": 0.7258,
+      "step": 49
+    },
+    {
+      "epoch": 1.379232505643341,
+      "grad_norm": 0.06058570686117535,
+      "learning_rate": 6.514250379489754e-06,
+      "loss": 0.7189,
+      "step": 50
+    },
+    {
+      "epoch": 1.4063205417607223,
+      "grad_norm": 0.05938143369785303,
+      "learning_rate": 6.3591503611817155e-06,
+      "loss": 0.6971,
+      "step": 51
+    },
+    {
+      "epoch": 1.4334085778781038,
+      "grad_norm": 0.054558813521977216,
+      "learning_rate": 6.202624781831269e-06,
+      "loss": 0.6993,
+      "step": 52
+    },
+    {
+      "epoch": 1.4604966139954854,
+      "grad_norm": 0.05680279560956532,
+      "learning_rate": 6.044837815156377e-06,
+      "loss": 0.6718,
+      "step": 53
+    },
+    {
+      "epoch": 1.487584650112867,
+      "grad_norm": 0.057626144484000004,
+      "learning_rate": 5.885954957896115e-06,
+      "loss": 0.6387,
+      "step": 54
+    },
+    {
+      "epoch": 1.5146726862302482,
+      "grad_norm": 0.05199111492426588,
+      "learning_rate": 5.726142856227453e-06,
+      "loss": 0.5622,
+      "step": 55
+    },
+    {
+      "epoch": 1.5417607223476297,
+      "grad_norm": 0.05327168882426124,
+      "learning_rate": 5.5655691309764225e-06,
+      "loss": 0.7091,
+      "step": 56
+    },
+    {
+      "epoch": 1.5688487584650113,
+      "grad_norm": 0.057426996754366404,
+      "learning_rate": 5.404402201807022e-06,
+      "loss": 0.6517,
+      "step": 57
+    },
+    {
+      "epoch": 1.5959367945823928,
+      "grad_norm": 0.05495817026055581,
+      "learning_rate": 5.242811110572243e-06,
+      "loss": 0.6802,
+      "step": 58
+    },
+    {
+      "epoch": 1.6230248306997743,
+      "grad_norm": 0.05641482899916262,
+      "learning_rate": 5.080965344012509e-06,
+      "loss": 0.6902,
+      "step": 59
+    },
+    {
+      "epoch": 1.6501128668171559,
+      "grad_norm": 0.055534338239146296,
+      "learning_rate": 4.919034655987493e-06,
+      "loss": 0.6458,
+      "step": 60
+    },
+    {
+      "epoch": 1.6772009029345374,
+      "grad_norm": 0.0515923365198089,
+      "learning_rate": 4.757188889427761e-06,
+      "loss": 0.5779,
+      "step": 61
+    },
+    {
+      "epoch": 1.7042889390519187,
+      "grad_norm": 0.05349680772002036,
+      "learning_rate": 4.59559779819298e-06,
+      "loss": 0.6662,
+      "step": 62
+    },
+    {
+      "epoch": 1.7313769751693002,
+      "grad_norm": 0.05597651265383424,
+      "learning_rate": 4.434430869023579e-06,
+      "loss": 0.6427,
+      "step": 63
+    },
+    {
+      "epoch": 1.7584650112866818,
+      "grad_norm": 0.05367995560098686,
+      "learning_rate": 4.27385714377255e-06,
+      "loss": 0.5866,
+      "step": 64
+    },
+    {
+      "epoch": 1.785553047404063,
+      "grad_norm": 0.050110706315052135,
+      "learning_rate": 4.1140450421038865e-06,
+      "loss": 0.6308,
+      "step": 65
+    },
+    {
+      "epoch": 1.8126410835214446,
+      "grad_norm": 0.05304711612194916,
+      "learning_rate": 3.955162184843625e-06,
+      "loss": 0.6354,
+      "step": 66
+    },
+    {
+      "epoch": 1.8397291196388261,
+      "grad_norm": 0.05096383612475282,
+      "learning_rate": 3.7973752181687336e-06,
+      "loss": 0.5353,
+      "step": 67
+    },
+    {
+      "epoch": 1.8668171557562077,
+      "grad_norm": 0.0485852384541565,
+      "learning_rate": 3.6408496388182857e-06,
+      "loss": 0.6101,
+      "step": 68
+    },
+    {
+      "epoch": 1.8939051918735892,
+      "grad_norm": 0.05340977288546307,
+      "learning_rate": 3.4857496205102475e-06,
+      "loss": 0.6748,
+      "step": 69
+    },
+    {
+      "epoch": 1.9209932279909707,
+      "grad_norm": 0.05929668403153539,
+      "learning_rate": 3.3322378417458985e-06,
+      "loss": 0.7395,
+      "step": 70
+    },
+    {
+      "epoch": 1.9480812641083523,
+      "grad_norm": 0.05974704306446326,
+      "learning_rate": 3.180475315182563e-06,
+      "loss": 0.6742,
+      "step": 71
+    },
+    {
+      "epoch": 1.9751693002257338,
+      "grad_norm": 0.05601946443734337,
+      "learning_rate": 3.0306212187535653e-06,
+      "loss": 0.658,
+      "step": 72
+    },
+    {
+      "epoch": 2.0270880361173815,
+      "grad_norm": 0.0724237322260953,
+      "learning_rate": 2.882832728712551e-06,
+      "loss": 1.4064,
+      "step": 73
+    },
+    {
+      "epoch": 2.054176072234763,
+      "grad_norm": 0.06053838794404104,
+      "learning_rate": 2.7372648547773063e-06,
+      "loss": 0.656,
+      "step": 74
+    },
+    {
+      "epoch": 2.0812641083521446,
+      "grad_norm": 0.05100316572963111,
+      "learning_rate": 2.594070277545975e-06,
+      "loss": 0.5612,
+      "step": 75
+    },
+    {
+      "epoch": 2.108352144469526,
+      "grad_norm": 0.0622038616480431,
+      "learning_rate": 2.4533991883561868e-06,
+      "loss": 0.6891,
+      "step": 76
+    },
+    {
+      "epoch": 2.1354401805869077,
+      "grad_norm": 0.057916636244831204,
+      "learning_rate": 2.315399131755081e-06,
+      "loss": 0.638,
+      "step": 77
+    },
+    {
+      "epoch": 2.1625282167042887,
+      "grad_norm": 0.05395672544503171,
+      "learning_rate": 2.1802148507454675e-06,
+      "loss": 0.5861,
+      "step": 78
+    },
+    {
+      "epoch": 2.1896162528216703,
+      "grad_norm": 0.053864006071485976,
+      "learning_rate": 2.0479881349703885e-06,
+      "loss": 0.594,
+      "step": 79
+    },
+    {
+      "epoch": 2.216704288939052,
+      "grad_norm": 0.05830769530523658,
+      "learning_rate": 1.9188576719953635e-06,
+      "loss": 0.5802,
+      "step": 80
+    },
+    {
+      "epoch": 2.2437923250564333,
+      "grad_norm": 0.051099460392983014,
+      "learning_rate": 1.7929589018443016e-06,
+      "loss": 0.5442,
+      "step": 81
+    },
+    {
+      "epoch": 2.270880361173815,
+      "grad_norm": 0.05719841616517216,
+      "learning_rate": 1.6704238749415958e-06,
+      "loss": 0.7072,
+      "step": 82
+    },
+    {
+      "epoch": 2.2979683972911964,
+      "grad_norm": 0.06123931714369972,
+      "learning_rate": 1.5513811136094786e-06,
+      "loss": 0.6568,
+      "step": 83
+    },
+    {
+      "epoch": 2.325056433408578,
+      "grad_norm": 0.055793904401965494,
+      "learning_rate": 1.4359554772658551e-06,
+      "loss": 0.5966,
+      "step": 84
+    },
+    {
+      "epoch": 2.3521444695259595,
+      "grad_norm": 0.05953398956212439,
+      "learning_rate": 1.3242680314639995e-06,
+      "loss": 0.6587,
+      "step": 85
+    },
+    {
+      "epoch": 2.379232505643341,
+      "grad_norm": 0.05626639429332997,
+      "learning_rate": 1.2164359209115235e-06,
+      "loss": 0.5789,
+      "step": 86
+    },
+    {
+      "epoch": 2.4063205417607225,
+      "grad_norm": 0.059804679789879765,
+      "learning_rate": 1.1125722466017547e-06,
+      "loss": 0.654,
+      "step": 87
+    },
+    {
+      "epoch": 2.4334085778781036,
+      "grad_norm": 0.06250704904021064,
+      "learning_rate": 1.012785947186397e-06,
+      "loss": 0.6334,
+      "step": 88
+    },
+    {
+      "epoch": 2.460496613995485,
+      "grad_norm": 0.05303042611737511,
+      "learning_rate": 9.171816847139447e-07,
+      "loss": 0.5383,
+      "step": 89
+    },
+    {
+      "epoch": 2.4875846501128667,
+      "grad_norm": 0.04694109638497442,
+      "learning_rate": 8.258597348536452e-07,
+      "loss": 0.47,
+      "step": 90
+    },
+    {
+      "epoch": 2.514672686230248,
+      "grad_norm": 0.05089219899472816,
+      "learning_rate": 7.389158817201541e-07,
+      "loss": 0.5689,
+      "step": 91
+    },
+    {
+      "epoch": 2.5417607223476297,
+      "grad_norm": 0.05462955495836319,
+      "learning_rate": 6.564413174092443e-07,
+      "loss": 0.5717,
+      "step": 92
+    },
+    {
+      "epoch": 2.5688487584650113,
+      "grad_norm": 0.05361089763797038,
+      "learning_rate": 5.785225463498828e-07,
+      "loss": 0.5882,
+      "step": 93
+    },
+    {
+      "epoch": 2.595936794582393,
+      "grad_norm": 0.0545372370608364,
+      "learning_rate": 5.05241294573024e-07,
+      "loss": 0.5988,
+      "step": 94
+    },
+    {
+      "epoch": 2.6230248306997743,
+      "grad_norm": 0.05203946271783804,
+      "learning_rate": 4.3667442399229985e-07,
+      "loss": 0.5401,
+      "step": 95
+    },
+    {
+      "epoch": 2.650112866817156,
+      "grad_norm": 0.059286878607973235,
+      "learning_rate": 3.728938517864794e-07,
+      "loss": 0.6421,
+      "step": 96
+    },
+    {
+      "epoch": 2.6772009029345374,
+      "grad_norm": 0.05057841068074063,
+      "learning_rate": 3.1396647496828245e-07,
+      "loss": 0.4977,
+      "step": 97
+    },
+    {
+      "epoch": 2.704288939051919,
+      "grad_norm": 0.056645818127275836,
+      "learning_rate": 2.599541002186479e-07,
+      "loss": 0.6279,
+      "step": 98
+    },
+    {
+      "epoch": 2.7313769751693,
+      "grad_norm": 0.057378590315900785,
+      "learning_rate": 2.109133790600648e-07,
+      "loss": 0.5334,
+      "step": 99
+    },
+    {
+      "epoch": 2.758465011286682,
+      "grad_norm": 0.05201027382239277,
+      "learning_rate": 1.6689574843694433e-07,
+      "loss": 0.5393,
+      "step": 100
+    },
+    {
+      "epoch": 2.785553047404063,
+      "grad_norm": 0.046096574095139876,
+      "learning_rate": 1.2794737676536993e-07,
+      "loss": 0.4896,
+      "step": 101
+    },
+    {
+      "epoch": 2.8126410835214446,
+      "grad_norm": 0.05452191462883333,
+      "learning_rate": 9.410911550880474e-08,
+      "loss": 0.654,
+      "step": 102
+    },
+    {
+      "epoch": 2.839729119638826,
+      "grad_norm": 0.06330637115234866,
+      "learning_rate": 6.54164563305465e-08,
+      "loss": 0.6922,
+      "step": 103
+    },
+    {
+      "epoch": 2.8668171557562077,
+      "grad_norm": 0.06047053924162395,
+      "learning_rate": 4.189949386787462e-08,
+      "loss": 0.6493,
+      "step": 104
+    },
+    {
+      "epoch": 2.893905191873589,
+      "grad_norm": 0.05558730657663917,
+      "learning_rate": 2.358289416693027e-08,
+      "loss": 0.5759,
+      "step": 105
+    },
+    {
+      "epoch": 2.9209932279909707,
+      "grad_norm": 0.05598626490189069,
+      "learning_rate": 1.0485868811441757e-08,
+      "loss": 0.5835,
+      "step": 106
+    },
+    {
+      "epoch": 2.9480812641083523,
+      "grad_norm": 0.058320029820894966,
+      "learning_rate": 2.6221547724253337e-09,
+      "loss": 0.613,
+      "step": 107
+    },
+    {
+      "epoch": 2.975169300225734,
+      "grad_norm": 0.05592965040584475,
+      "learning_rate": 0.0,
+      "loss": 0.6081,
+      "step": 108
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.237704266625843e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dbd97f6b1ab3ee6d17a8cd9f26888387e4c1ad330038a684626001f7e502b7a
+size 7736

checkpoint-108/zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064,
+  "rope_scaling": {
+    "factor": 4.0,
+    "original_max_position_embeddings": 32768,
+    "type": "yarn"
+  }
+}

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": "4.48.3"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:665ed4081835b9e11c2b96cf2a69488f7e0fa694d00fae8271a920ba2f2c36fe
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dbd6f925c107764703ac15070e75ffe4b41337d39a4bd5b5168494e883fce02
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1de73ab88909e6f4f7e6d4bfab8ad2e6238b8491a060c75672e50ede2ddcb9d4
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7045b566d18b7fd7d93652047d73d68e87b1362ed616903847f0919cf3221f7f
+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 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if 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": {},
+  "model_max_length": 16384,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.975169300225734,
+    "total_flos": 3.237704266625843e+16,
+    "train_loss": 0.7293182517643328,
+    "train_runtime": 6995.9355,
+    "train_samples_per_second": 0.569,
+    "train_steps_per_second": 0.015
+}

trainer_log.jsonl

@@ -0,0 +1,109 @@
+{"current_steps": 1, "total_steps": 108, "loss": 1.2461, "lr": 9.090909090909091e-07, "epoch": 0.02708803611738149, "percentage": 0.93, "elapsed_time": "0:01:04", "remaining_time": "1:54:37"}
+{"current_steps": 2, "total_steps": 108, "loss": 1.2148, "lr": 1.8181818181818183e-06, "epoch": 0.05417607223476298, "percentage": 1.85, "elapsed_time": "0:01:59", "remaining_time": "1:45:22"}
+{"current_steps": 3, "total_steps": 108, "loss": 0.9726, "lr": 2.7272727272727272e-06, "epoch": 0.08126410835214447, "percentage": 2.78, "elapsed_time": "0:03:09", "remaining_time": "1:50:47"}
+{"current_steps": 4, "total_steps": 108, "loss": 1.1417, "lr": 3.6363636363636366e-06, "epoch": 0.10835214446952596, "percentage": 3.7, "elapsed_time": "0:04:06", "remaining_time": "1:46:43"}
+{"current_steps": 5, "total_steps": 108, "loss": 0.9526, "lr": 4.5454545454545455e-06, "epoch": 0.13544018058690746, "percentage": 4.63, "elapsed_time": "0:05:19", "remaining_time": "1:49:32"}
+{"current_steps": 6, "total_steps": 108, "loss": 1.0301, "lr": 5.4545454545454545e-06, "epoch": 0.16252821670428894, "percentage": 5.56, "elapsed_time": "0:06:24", "remaining_time": "1:48:54"}
+{"current_steps": 7, "total_steps": 108, "loss": 1.0107, "lr": 6.363636363636364e-06, "epoch": 0.18961625282167044, "percentage": 6.48, "elapsed_time": "0:07:17", "remaining_time": "1:45:18"}
+{"current_steps": 8, "total_steps": 108, "loss": 1.0306, "lr": 7.272727272727273e-06, "epoch": 0.21670428893905191, "percentage": 7.41, "elapsed_time": "0:08:21", "remaining_time": "1:44:26"}
+{"current_steps": 9, "total_steps": 108, "loss": 0.8963, "lr": 8.181818181818183e-06, "epoch": 0.24379232505643342, "percentage": 8.33, "elapsed_time": "0:09:23", "remaining_time": "1:43:19"}
+{"current_steps": 10, "total_steps": 108, "loss": 1.0366, "lr": 9.090909090909091e-06, "epoch": 0.2708803611738149, "percentage": 9.26, "elapsed_time": "0:10:25", "remaining_time": "1:42:09"}
+{"current_steps": 11, "total_steps": 108, "loss": 0.9005, "lr": 1e-05, "epoch": 0.2979683972911964, "percentage": 10.19, "elapsed_time": "0:11:21", "remaining_time": "1:40:10"}
+{"current_steps": 12, "total_steps": 108, "loss": 0.8125, "lr": 9.997377845227577e-06, "epoch": 0.32505643340857787, "percentage": 11.11, "elapsed_time": "0:12:32", "remaining_time": "1:40:18"}
+{"current_steps": 13, "total_steps": 108, "loss": 0.9944, "lr": 9.98951413118856e-06, "epoch": 0.35214446952595935, "percentage": 12.04, "elapsed_time": "0:13:30", "remaining_time": "1:38:41"}
+{"current_steps": 14, "total_steps": 108, "loss": 0.8586, "lr": 9.97641710583307e-06, "epoch": 0.3792325056433409, "percentage": 12.96, "elapsed_time": "0:14:30", "remaining_time": "1:37:24"}
+{"current_steps": 15, "total_steps": 108, "loss": 0.6047, "lr": 9.958100506132127e-06, "epoch": 0.40632054176072235, "percentage": 13.89, "elapsed_time": "0:15:41", "remaining_time": "1:37:15"}
+{"current_steps": 16, "total_steps": 108, "loss": 0.8924, "lr": 9.934583543669454e-06, "epoch": 0.43340857787810383, "percentage": 14.81, "elapsed_time": "0:16:34", "remaining_time": "1:35:16"}
+{"current_steps": 17, "total_steps": 108, "loss": 0.8502, "lr": 9.905890884491196e-06, "epoch": 0.4604966139954853, "percentage": 15.74, "elapsed_time": "0:17:45", "remaining_time": "1:35:03"}
+{"current_steps": 18, "total_steps": 108, "loss": 0.8565, "lr": 9.872052623234632e-06, "epoch": 0.48758465011286684, "percentage": 16.67, "elapsed_time": "0:18:48", "remaining_time": "1:34:04"}
+{"current_steps": 19, "total_steps": 108, "loss": 1.022, "lr": 9.833104251563058e-06, "epoch": 0.5146726862302483, "percentage": 17.59, "elapsed_time": "0:19:45", "remaining_time": "1:32:33"}
+{"current_steps": 20, "total_steps": 108, "loss": 0.8234, "lr": 9.789086620939936e-06, "epoch": 0.5417607223476298, "percentage": 18.52, "elapsed_time": "0:20:47", "remaining_time": "1:31:28"}
+{"current_steps": 21, "total_steps": 108, "loss": 0.8359, "lr": 9.740045899781353e-06, "epoch": 0.5688487584650113, "percentage": 19.44, "elapsed_time": "0:21:44", "remaining_time": "1:30:05"}
+{"current_steps": 22, "total_steps": 108, "loss": 0.7305, "lr": 9.68603352503172e-06, "epoch": 0.5959367945823928, "percentage": 20.37, "elapsed_time": "0:23:11", "remaining_time": "1:30:39"}
+{"current_steps": 23, "total_steps": 108, "loss": 0.7568, "lr": 9.627106148213521e-06, "epoch": 0.6230248306997742, "percentage": 21.3, "elapsed_time": "0:24:20", "remaining_time": "1:29:57"}
+{"current_steps": 24, "total_steps": 108, "loss": 0.8188, "lr": 9.563325576007702e-06, "epoch": 0.6501128668171557, "percentage": 22.22, "elapsed_time": "0:25:14", "remaining_time": "1:28:21"}
+{"current_steps": 25, "total_steps": 108, "loss": 0.6476, "lr": 9.494758705426978e-06, "epoch": 0.6772009029345373, "percentage": 23.15, "elapsed_time": "0:26:29", "remaining_time": "1:27:57"}
+{"current_steps": 26, "total_steps": 108, "loss": 0.8316, "lr": 9.421477453650118e-06, "epoch": 0.7042889390519187, "percentage": 24.07, "elapsed_time": "0:27:25", "remaining_time": "1:26:28"}
+{"current_steps": 27, "total_steps": 108, "loss": 0.8827, "lr": 9.343558682590757e-06, "epoch": 0.7313769751693002, "percentage": 25.0, "elapsed_time": "0:28:35", "remaining_time": "1:25:47"}
+{"current_steps": 28, "total_steps": 108, "loss": 0.7524, "lr": 9.261084118279846e-06, "epoch": 0.7584650112866818, "percentage": 25.93, "elapsed_time": "0:29:39", "remaining_time": "1:24:44"}
+{"current_steps": 29, "total_steps": 108, "loss": 0.8426, "lr": 9.174140265146356e-06, "epoch": 0.7855530474040632, "percentage": 26.85, "elapsed_time": "0:30:34", "remaining_time": "1:23:18"}
+{"current_steps": 30, "total_steps": 108, "loss": 0.7681, "lr": 9.082818315286054e-06, "epoch": 0.8126410835214447, "percentage": 27.78, "elapsed_time": "0:31:37", "remaining_time": "1:22:12"}
+{"current_steps": 31, "total_steps": 108, "loss": 0.7463, "lr": 8.987214052813605e-06, "epoch": 0.8397291196388262, "percentage": 28.7, "elapsed_time": "0:32:44", "remaining_time": "1:21:20"}
+{"current_steps": 32, "total_steps": 108, "loss": 0.908, "lr": 8.887427753398249e-06, "epoch": 0.8668171557562077, "percentage": 29.63, "elapsed_time": "0:33:45", "remaining_time": "1:20:09"}
+{"current_steps": 33, "total_steps": 108, "loss": 0.7965, "lr": 8.783564079088478e-06, "epoch": 0.8939051918735892, "percentage": 30.56, "elapsed_time": "0:34:46", "remaining_time": "1:19:01"}
+{"current_steps": 34, "total_steps": 108, "loss": 0.6443, "lr": 8.675731968536004e-06, "epoch": 0.9209932279909706, "percentage": 31.48, "elapsed_time": "0:36:09", "remaining_time": "1:18:42"}
+{"current_steps": 35, "total_steps": 108, "loss": 0.7452, "lr": 8.564044522734147e-06, "epoch": 0.9480812641083521, "percentage": 32.41, "elapsed_time": "0:37:19", "remaining_time": "1:17:49"}
+{"current_steps": 36, "total_steps": 108, "loss": 0.736, "lr": 8.448618886390523e-06, "epoch": 0.9751693002257337, "percentage": 33.33, "elapsed_time": "0:38:19", "remaining_time": "1:16:39"}
+{"current_steps": 37, "total_steps": 108, "loss": 1.4609, "lr": 8.329576125058406e-06, "epoch": 1.0270880361173815, "percentage": 34.26, "elapsed_time": "0:40:13", "remaining_time": "1:17:10"}
+{"current_steps": 38, "total_steps": 108, "loss": 0.6621, "lr": 8.207041098155701e-06, "epoch": 1.054176072234763, "percentage": 35.19, "elapsed_time": "0:41:10", "remaining_time": "1:15:51"}
+{"current_steps": 39, "total_steps": 108, "loss": 0.7746, "lr": 8.081142328004638e-06, "epoch": 1.0812641083521444, "percentage": 36.11, "elapsed_time": "0:42:06", "remaining_time": "1:14:29"}
+{"current_steps": 40, "total_steps": 108, "loss": 0.6824, "lr": 7.952011865029614e-06, "epoch": 1.108352144469526, "percentage": 37.04, "elapsed_time": "0:43:08", "remaining_time": "1:13:19"}
+{"current_steps": 41, "total_steps": 108, "loss": 0.6903, "lr": 7.819785149254534e-06, "epoch": 1.1354401805869074, "percentage": 37.96, "elapsed_time": "0:44:05", "remaining_time": "1:12:02"}
+{"current_steps": 42, "total_steps": 108, "loss": 0.7619, "lr": 7.68460086824492e-06, "epoch": 1.162528216704289, "percentage": 38.89, "elapsed_time": "0:45:09", "remaining_time": "1:10:57"}
+{"current_steps": 43, "total_steps": 108, "loss": 0.7389, "lr": 7.546600811643816e-06, "epoch": 1.1896162528216705, "percentage": 39.81, "elapsed_time": "0:46:11", "remaining_time": "1:09:49"}
+{"current_steps": 44, "total_steps": 108, "loss": 0.6184, "lr": 7.405929722454026e-06, "epoch": 1.2167042889390518, "percentage": 40.74, "elapsed_time": "0:47:14", "remaining_time": "1:08:43"}
+{"current_steps": 45, "total_steps": 108, "loss": 0.6454, "lr": 7.262735145222696e-06, "epoch": 1.2437923250564333, "percentage": 41.67, "elapsed_time": "0:48:15", "remaining_time": "1:07:33"}
+{"current_steps": 46, "total_steps": 108, "loss": 0.6757, "lr": 7.117167271287453e-06, "epoch": 1.2708803611738149, "percentage": 42.59, "elapsed_time": "0:49:12", "remaining_time": "1:06:19"}
+{"current_steps": 47, "total_steps": 108, "loss": 0.6576, "lr": 6.969378781246436e-06, "epoch": 1.2979683972911964, "percentage": 43.52, "elapsed_time": "0:50:09", "remaining_time": "1:05:05"}
+{"current_steps": 48, "total_steps": 108, "loss": 0.7626, "lr": 6.819524684817439e-06, "epoch": 1.325056433408578, "percentage": 44.44, "elapsed_time": "0:51:03", "remaining_time": "1:03:49"}
+{"current_steps": 49, "total_steps": 108, "loss": 0.7258, "lr": 6.667762158254104e-06, "epoch": 1.3521444695259595, "percentage": 45.37, "elapsed_time": "0:51:57", "remaining_time": "1:02:33"}
+{"current_steps": 50, "total_steps": 108, "loss": 0.7189, "lr": 6.514250379489754e-06, "epoch": 1.379232505643341, "percentage": 46.3, "elapsed_time": "0:52:50", "remaining_time": "1:01:17"}
+{"current_steps": 51, "total_steps": 108, "loss": 0.6971, "lr": 6.3591503611817155e-06, "epoch": 1.4063205417607223, "percentage": 47.22, "elapsed_time": "0:53:59", "remaining_time": "1:00:20"}
+{"current_steps": 52, "total_steps": 108, "loss": 0.6993, "lr": 6.202624781831269e-06, "epoch": 1.4334085778781038, "percentage": 48.15, "elapsed_time": "0:54:53", "remaining_time": "0:59:06"}
+{"current_steps": 53, "total_steps": 108, "loss": 0.6718, "lr": 6.044837815156377e-06, "epoch": 1.4604966139954854, "percentage": 49.07, "elapsed_time": "0:56:00", "remaining_time": "0:58:07"}
+{"current_steps": 54, "total_steps": 108, "loss": 0.6387, "lr": 5.885954957896115e-06, "epoch": 1.487584650112867, "percentage": 50.0, "elapsed_time": "0:57:12", "remaining_time": "0:57:12"}
+{"current_steps": 55, "total_steps": 108, "loss": 0.5622, "lr": 5.726142856227453e-06, "epoch": 1.5146726862302482, "percentage": 50.93, "elapsed_time": "0:58:22", "remaining_time": "0:56:15"}
+{"current_steps": 56, "total_steps": 108, "loss": 0.7091, "lr": 5.5655691309764225e-06, "epoch": 1.5417607223476297, "percentage": 51.85, "elapsed_time": "0:59:21", "remaining_time": "0:55:06"}
+{"current_steps": 57, "total_steps": 108, "loss": 0.6517, "lr": 5.404402201807022e-06, "epoch": 1.5688487584650113, "percentage": 52.78, "elapsed_time": "1:00:25", "remaining_time": "0:54:04"}
+{"current_steps": 58, "total_steps": 108, "loss": 0.6802, "lr": 5.242811110572243e-06, "epoch": 1.5959367945823928, "percentage": 53.7, "elapsed_time": "1:01:25", "remaining_time": "0:52:57"}
+{"current_steps": 59, "total_steps": 108, "loss": 0.6902, "lr": 5.080965344012509e-06, "epoch": 1.6230248306997743, "percentage": 54.63, "elapsed_time": "1:02:44", "remaining_time": "0:52:06"}
+{"current_steps": 60, "total_steps": 108, "loss": 0.6458, "lr": 4.919034655987493e-06, "epoch": 1.6501128668171559, "percentage": 55.56, "elapsed_time": "1:03:46", "remaining_time": "0:51:01"}
+{"current_steps": 61, "total_steps": 108, "loss": 0.5779, "lr": 4.757188889427761e-06, "epoch": 1.6772009029345374, "percentage": 56.48, "elapsed_time": "1:05:12", "remaining_time": "0:50:14"}
+{"current_steps": 62, "total_steps": 108, "loss": 0.6662, "lr": 4.59559779819298e-06, "epoch": 1.7042889390519187, "percentage": 57.41, "elapsed_time": "1:06:08", "remaining_time": "0:49:04"}
+{"current_steps": 63, "total_steps": 108, "loss": 0.6427, "lr": 4.434430869023579e-06, "epoch": 1.7313769751693002, "percentage": 58.33, "elapsed_time": "1:07:28", "remaining_time": "0:48:11"}
+{"current_steps": 64, "total_steps": 108, "loss": 0.5866, "lr": 4.27385714377255e-06, "epoch": 1.7584650112866818, "percentage": 59.26, "elapsed_time": "1:08:40", "remaining_time": "0:47:12"}
+{"current_steps": 65, "total_steps": 108, "loss": 0.6308, "lr": 4.1140450421038865e-06, "epoch": 1.785553047404063, "percentage": 60.19, "elapsed_time": "1:09:37", "remaining_time": "0:46:03"}
+{"current_steps": 66, "total_steps": 108, "loss": 0.6354, "lr": 3.955162184843625e-06, "epoch": 1.8126410835214446, "percentage": 61.11, "elapsed_time": "1:10:33", "remaining_time": "0:44:54"}
+{"current_steps": 67, "total_steps": 108, "loss": 0.5353, "lr": 3.7973752181687336e-06, "epoch": 1.8397291196388261, "percentage": 62.04, "elapsed_time": "1:11:56", "remaining_time": "0:44:01"}
+{"current_steps": 68, "total_steps": 108, "loss": 0.6101, "lr": 3.6408496388182857e-06, "epoch": 1.8668171557562077, "percentage": 62.96, "elapsed_time": "1:13:12", "remaining_time": "0:43:03"}
+{"current_steps": 69, "total_steps": 108, "loss": 0.6748, "lr": 3.4857496205102475e-06, "epoch": 1.8939051918735892, "percentage": 63.89, "elapsed_time": "1:14:16", "remaining_time": "0:41:58"}
+{"current_steps": 70, "total_steps": 108, "loss": 0.7395, "lr": 3.3322378417458985e-06, "epoch": 1.9209932279909707, "percentage": 64.81, "elapsed_time": "1:15:10", "remaining_time": "0:40:48"}
+{"current_steps": 71, "total_steps": 108, "loss": 0.6742, "lr": 3.180475315182563e-06, "epoch": 1.9480812641083523, "percentage": 65.74, "elapsed_time": "1:16:11", "remaining_time": "0:39:42"}
+{"current_steps": 72, "total_steps": 108, "loss": 0.658, "lr": 3.0306212187535653e-06, "epoch": 1.9751693002257338, "percentage": 66.67, "elapsed_time": "1:17:08", "remaining_time": "0:38:34"}
+{"current_steps": 73, "total_steps": 108, "loss": 1.4064, "lr": 2.882832728712551e-06, "epoch": 2.0270880361173815, "percentage": 67.59, "elapsed_time": "1:18:46", "remaining_time": "0:37:46"}
+{"current_steps": 74, "total_steps": 108, "loss": 0.656, "lr": 2.7372648547773063e-06, "epoch": 2.054176072234763, "percentage": 68.52, "elapsed_time": "1:19:58", "remaining_time": "0:36:44"}
+{"current_steps": 75, "total_steps": 108, "loss": 0.5612, "lr": 2.594070277545975e-06, "epoch": 2.0812641083521446, "percentage": 69.44, "elapsed_time": "1:21:10", "remaining_time": "0:35:42"}
+{"current_steps": 76, "total_steps": 108, "loss": 0.6891, "lr": 2.4533991883561868e-06, "epoch": 2.108352144469526, "percentage": 70.37, "elapsed_time": "1:22:13", "remaining_time": "0:34:37"}
+{"current_steps": 77, "total_steps": 108, "loss": 0.638, "lr": 2.315399131755081e-06, "epoch": 2.1354401805869077, "percentage": 71.3, "elapsed_time": "1:23:13", "remaining_time": "0:33:30"}
+{"current_steps": 78, "total_steps": 108, "loss": 0.5861, "lr": 2.1802148507454675e-06, "epoch": 2.1625282167042887, "percentage": 72.22, "elapsed_time": "1:24:20", "remaining_time": "0:32:26"}
+{"current_steps": 79, "total_steps": 108, "loss": 0.594, "lr": 2.0479881349703885e-06, "epoch": 2.1896162528216703, "percentage": 73.15, "elapsed_time": "1:25:25", "remaining_time": "0:31:21"}
+{"current_steps": 80, "total_steps": 108, "loss": 0.5802, "lr": 1.9188576719953635e-06, "epoch": 2.216704288939052, "percentage": 74.07, "elapsed_time": "1:26:40", "remaining_time": "0:30:20"}
+{"current_steps": 81, "total_steps": 108, "loss": 0.5442, "lr": 1.7929589018443016e-06, "epoch": 2.2437923250564333, "percentage": 75.0, "elapsed_time": "1:27:58", "remaining_time": "0:29:19"}
+{"current_steps": 82, "total_steps": 108, "loss": 0.7072, "lr": 1.6704238749415958e-06, "epoch": 2.270880361173815, "percentage": 75.93, "elapsed_time": "1:28:50", "remaining_time": "0:28:10"}
+{"current_steps": 83, "total_steps": 108, "loss": 0.6568, "lr": 1.5513811136094786e-06, "epoch": 2.2979683972911964, "percentage": 76.85, "elapsed_time": "1:29:51", "remaining_time": "0:27:03"}
+{"current_steps": 84, "total_steps": 108, "loss": 0.5966, "lr": 1.4359554772658551e-06, "epoch": 2.325056433408578, "percentage": 77.78, "elapsed_time": "1:30:49", "remaining_time": "0:25:56"}
+{"current_steps": 85, "total_steps": 108, "loss": 0.6587, "lr": 1.3242680314639995e-06, "epoch": 2.3521444695259595, "percentage": 78.7, "elapsed_time": "1:31:52", "remaining_time": "0:24:51"}
+{"current_steps": 86, "total_steps": 108, "loss": 0.5789, "lr": 1.2164359209115235e-06, "epoch": 2.379232505643341, "percentage": 79.63, "elapsed_time": "1:32:58", "remaining_time": "0:23:47"}
+{"current_steps": 87, "total_steps": 108, "loss": 0.654, "lr": 1.1125722466017547e-06, "epoch": 2.4063205417607225, "percentage": 80.56, "elapsed_time": "1:33:51", "remaining_time": "0:22:39"}
+{"current_steps": 88, "total_steps": 108, "loss": 0.6334, "lr": 1.012785947186397e-06, "epoch": 2.4334085778781036, "percentage": 81.48, "elapsed_time": "1:34:48", "remaining_time": "0:21:32"}
+{"current_steps": 89, "total_steps": 108, "loss": 0.5383, "lr": 9.171816847139447e-07, "epoch": 2.460496613995485, "percentage": 82.41, "elapsed_time": "1:35:42", "remaining_time": "0:20:26"}
+{"current_steps": 90, "total_steps": 108, "loss": 0.47, "lr": 8.258597348536452e-07, "epoch": 2.4875846501128667, "percentage": 83.33, "elapsed_time": "1:36:50", "remaining_time": "0:19:22"}
+{"current_steps": 91, "total_steps": 108, "loss": 0.5689, "lr": 7.389158817201541e-07, "epoch": 2.514672686230248, "percentage": 84.26, "elapsed_time": "1:37:52", "remaining_time": "0:18:16"}
+{"current_steps": 92, "total_steps": 108, "loss": 0.5717, "lr": 6.564413174092443e-07, "epoch": 2.5417607223476297, "percentage": 85.19, "elapsed_time": "1:39:13", "remaining_time": "0:17:15"}
+{"current_steps": 93, "total_steps": 108, "loss": 0.5882, "lr": 5.785225463498828e-07, "epoch": 2.5688487584650113, "percentage": 86.11, "elapsed_time": "1:40:28", "remaining_time": "0:16:12"}
+{"current_steps": 94, "total_steps": 108, "loss": 0.5988, "lr": 5.05241294573024e-07, "epoch": 2.595936794582393, "percentage": 87.04, "elapsed_time": "1:41:23", "remaining_time": "0:15:06"}
+{"current_steps": 95, "total_steps": 108, "loss": 0.5401, "lr": 4.3667442399229985e-07, "epoch": 2.6230248306997743, "percentage": 87.96, "elapsed_time": "1:42:28", "remaining_time": "0:14:01"}
+{"current_steps": 96, "total_steps": 108, "loss": 0.6421, "lr": 3.728938517864794e-07, "epoch": 2.650112866817156, "percentage": 88.89, "elapsed_time": "1:43:24", "remaining_time": "0:12:55"}
+{"current_steps": 97, "total_steps": 108, "loss": 0.4977, "lr": 3.1396647496828245e-07, "epoch": 2.6772009029345374, "percentage": 89.81, "elapsed_time": "1:44:26", "remaining_time": "0:11:50"}
+{"current_steps": 98, "total_steps": 108, "loss": 0.6279, "lr": 2.599541002186479e-07, "epoch": 2.704288939051919, "percentage": 90.74, "elapsed_time": "1:45:18", "remaining_time": "0:10:44"}
+{"current_steps": 99, "total_steps": 108, "loss": 0.5334, "lr": 2.109133790600648e-07, "epoch": 2.7313769751693, "percentage": 91.67, "elapsed_time": "1:46:24", "remaining_time": "0:09:40"}
+{"current_steps": 100, "total_steps": 108, "loss": 0.5393, "lr": 1.6689574843694433e-07, "epoch": 2.758465011286682, "percentage": 92.59, "elapsed_time": "1:47:18", "remaining_time": "0:08:35"}
+{"current_steps": 101, "total_steps": 108, "loss": 0.4896, "lr": 1.2794737676536993e-07, "epoch": 2.785553047404063, "percentage": 93.52, "elapsed_time": "1:48:29", "remaining_time": "0:07:31"}
+{"current_steps": 102, "total_steps": 108, "loss": 0.654, "lr": 9.410911550880474e-08, "epoch": 2.8126410835214446, "percentage": 94.44, "elapsed_time": "1:49:21", "remaining_time": "0:06:25"}
+{"current_steps": 103, "total_steps": 108, "loss": 0.6922, "lr": 6.54164563305465e-08, "epoch": 2.839729119638826, "percentage": 95.37, "elapsed_time": "1:50:13", "remaining_time": "0:05:21"}
+{"current_steps": 104, "total_steps": 108, "loss": 0.6493, "lr": 4.189949386787462e-08, "epoch": 2.8668171557562077, "percentage": 96.3, "elapsed_time": "1:51:16", "remaining_time": "0:04:16"}
+{"current_steps": 105, "total_steps": 108, "loss": 0.5759, "lr": 2.358289416693027e-08, "epoch": 2.893905191873589, "percentage": 97.22, "elapsed_time": "1:52:18", "remaining_time": "0:03:12"}
+{"current_steps": 106, "total_steps": 108, "loss": 0.5835, "lr": 1.0485868811441757e-08, "epoch": 2.9209932279909707, "percentage": 98.15, "elapsed_time": "1:53:18", "remaining_time": "0:02:08"}
+{"current_steps": 107, "total_steps": 108, "loss": 0.613, "lr": 2.6221547724253337e-09, "epoch": 2.9480812641083523, "percentage": 99.07, "elapsed_time": "1:54:18", "remaining_time": "0:01:04"}
+{"current_steps": 108, "total_steps": 108, "loss": 0.6081, "lr": 0.0, "epoch": 2.975169300225734, "percentage": 100.0, "elapsed_time": "1:55:30", "remaining_time": "0:00:00"}
+{"current_steps": 108, "total_steps": 108, "epoch": 2.975169300225734, "percentage": 100.0, "elapsed_time": "1:56:34", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,798 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.975169300225734,
+  "eval_steps": 500,
+  "global_step": 108,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02708803611738149,
+      "grad_norm": 0.3197194327711118,
+      "learning_rate": 9.090909090909091e-07,
+      "loss": 1.2461,
+      "step": 1
+    },
+    {
+      "epoch": 0.05417607223476298,
+      "grad_norm": 0.31103611995893704,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 1.2148,
+      "step": 2
+    },
+    {
+      "epoch": 0.08126410835214447,
+      "grad_norm": 0.2337633531452293,
+      "learning_rate": 2.7272727272727272e-06,
+      "loss": 0.9726,
+      "step": 3
+    },
+    {
+      "epoch": 0.10835214446952596,
+      "grad_norm": 0.2732448083772183,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 1.1417,
+      "step": 4
+    },
+    {
+      "epoch": 0.13544018058690746,
+      "grad_norm": 0.18372677123914605,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 0.9526,
+      "step": 5
+    },
+    {
+      "epoch": 0.16252821670428894,
+      "grad_norm": 0.14598996204381387,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 1.0301,
+      "step": 6
+    },
+    {
+      "epoch": 0.18961625282167044,
+      "grad_norm": 0.12859546866157384,
+      "learning_rate": 6.363636363636364e-06,
+      "loss": 1.0107,
+      "step": 7
+    },
+    {
+      "epoch": 0.21670428893905191,
+      "grad_norm": 0.11328838489926579,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 1.0306,
+      "step": 8
+    },
+    {
+      "epoch": 0.24379232505643342,
+      "grad_norm": 0.1022283734283964,
+      "learning_rate": 8.181818181818183e-06,
+      "loss": 0.8963,
+      "step": 9
+    },
+    {
+      "epoch": 0.2708803611738149,
+      "grad_norm": 0.11790288806381347,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 1.0366,
+      "step": 10
+    },
+    {
+      "epoch": 0.2979683972911964,
+      "grad_norm": 0.12155066660752349,
+      "learning_rate": 1e-05,
+      "loss": 0.9005,
+      "step": 11
+    },
+    {
+      "epoch": 0.32505643340857787,
+      "grad_norm": 0.10987900474389686,
+      "learning_rate": 9.997377845227577e-06,
+      "loss": 0.8125,
+      "step": 12
+    },
+    {
+      "epoch": 0.35214446952595935,
+      "grad_norm": 0.1338371645473795,
+      "learning_rate": 9.98951413118856e-06,
+      "loss": 0.9944,
+      "step": 13
+    },
+    {
+      "epoch": 0.3792325056433409,
+      "grad_norm": 0.10584646720619653,
+      "learning_rate": 9.97641710583307e-06,
+      "loss": 0.8586,
+      "step": 14
+    },
+    {
+      "epoch": 0.40632054176072235,
+      "grad_norm": 0.07551668645041647,
+      "learning_rate": 9.958100506132127e-06,
+      "loss": 0.6047,
+      "step": 15
+    },
+    {
+      "epoch": 0.43340857787810383,
+      "grad_norm": 0.10339673320083177,
+      "learning_rate": 9.934583543669454e-06,
+      "loss": 0.8924,
+      "step": 16
+    },
+    {
+      "epoch": 0.4604966139954853,
+      "grad_norm": 0.08900126200269193,
+      "learning_rate": 9.905890884491196e-06,
+      "loss": 0.8502,
+      "step": 17
+    },
+    {
+      "epoch": 0.48758465011286684,
+      "grad_norm": 0.0755389181238505,
+      "learning_rate": 9.872052623234632e-06,
+      "loss": 0.8565,
+      "step": 18
+    },
+    {
+      "epoch": 0.5146726862302483,
+      "grad_norm": 0.08559033880567499,
+      "learning_rate": 9.833104251563058e-06,
+      "loss": 1.022,
+      "step": 19
+    },
+    {
+      "epoch": 0.5417607223476298,
+      "grad_norm": 0.06946932719559365,
+      "learning_rate": 9.789086620939936e-06,
+      "loss": 0.8234,
+      "step": 20
+    },
+    {
+      "epoch": 0.5688487584650113,
+      "grad_norm": 0.07510589474735027,
+      "learning_rate": 9.740045899781353e-06,
+      "loss": 0.8359,
+      "step": 21
+    },
+    {
+      "epoch": 0.5959367945823928,
+      "grad_norm": 0.06552207629817948,
+      "learning_rate": 9.68603352503172e-06,
+      "loss": 0.7305,
+      "step": 22
+    },
+    {
+      "epoch": 0.6230248306997742,
+      "grad_norm": 0.06750242477377788,
+      "learning_rate": 9.627106148213521e-06,
+      "loss": 0.7568,
+      "step": 23
+    },
+    {
+      "epoch": 0.6501128668171557,
+      "grad_norm": 0.07579791889142827,
+      "learning_rate": 9.563325576007702e-06,
+      "loss": 0.8188,
+      "step": 24
+    },
+    {
+      "epoch": 0.6772009029345373,
+      "grad_norm": 0.05385726475558828,
+      "learning_rate": 9.494758705426978e-06,
+      "loss": 0.6476,
+      "step": 25
+    },
+    {
+      "epoch": 0.7042889390519187,
+      "grad_norm": 0.0659922617401428,
+      "learning_rate": 9.421477453650118e-06,
+      "loss": 0.8316,
+      "step": 26
+    },
+    {
+      "epoch": 0.7313769751693002,
+      "grad_norm": 0.06724043516128614,
+      "learning_rate": 9.343558682590757e-06,
+      "loss": 0.8827,
+      "step": 27
+    },
+    {
+      "epoch": 0.7584650112866818,
+      "grad_norm": 0.057407448162910005,
+      "learning_rate": 9.261084118279846e-06,
+      "loss": 0.7524,
+      "step": 28
+    },
+    {
+      "epoch": 0.7855530474040632,
+      "grad_norm": 0.06600552654685582,
+      "learning_rate": 9.174140265146356e-06,
+      "loss": 0.8426,
+      "step": 29
+    },
+    {
+      "epoch": 0.8126410835214447,
+      "grad_norm": 0.05731937218952811,
+      "learning_rate": 9.082818315286054e-06,
+      "loss": 0.7681,
+      "step": 30
+    },
+    {
+      "epoch": 0.8397291196388262,
+      "grad_norm": 0.05814787595507311,
+      "learning_rate": 8.987214052813605e-06,
+      "loss": 0.7463,
+      "step": 31
+    },
+    {
+      "epoch": 0.8668171557562077,
+      "grad_norm": 0.06918050909180208,
+      "learning_rate": 8.887427753398249e-06,
+      "loss": 0.908,
+      "step": 32
+    },
+    {
+      "epoch": 0.8939051918735892,
+      "grad_norm": 0.0651707634722971,
+      "learning_rate": 8.783564079088478e-06,
+      "loss": 0.7965,
+      "step": 33
+    },
+    {
+      "epoch": 0.9209932279909706,
+      "grad_norm": 0.047559578658812544,
+      "learning_rate": 8.675731968536004e-06,
+      "loss": 0.6443,
+      "step": 34
+    },
+    {
+      "epoch": 0.9480812641083521,
+      "grad_norm": 0.05660630221337761,
+      "learning_rate": 8.564044522734147e-06,
+      "loss": 0.7452,
+      "step": 35
+    },
+    {
+      "epoch": 0.9751693002257337,
+      "grad_norm": 0.053852038093973535,
+      "learning_rate": 8.448618886390523e-06,
+      "loss": 0.736,
+      "step": 36
+    },
+    {
+      "epoch": 1.0270880361173815,
+      "grad_norm": 0.07449181460800067,
+      "learning_rate": 8.329576125058406e-06,
+      "loss": 1.4609,
+      "step": 37
+    },
+    {
+      "epoch": 1.054176072234763,
+      "grad_norm": 0.05525435344631101,
+      "learning_rate": 8.207041098155701e-06,
+      "loss": 0.6621,
+      "step": 38
+    },
+    {
+      "epoch": 1.0812641083521444,
+      "grad_norm": 0.05203784294919359,
+      "learning_rate": 8.081142328004638e-06,
+      "loss": 0.7746,
+      "step": 39
+    },
+    {
+      "epoch": 1.108352144469526,
+      "grad_norm": 0.05697857349793105,
+      "learning_rate": 7.952011865029614e-06,
+      "loss": 0.6824,
+      "step": 40
+    },
+    {
+      "epoch": 1.1354401805869074,
+      "grad_norm": 0.05062686469158285,
+      "learning_rate": 7.819785149254534e-06,
+      "loss": 0.6903,
+      "step": 41
+    },
+    {
+      "epoch": 1.162528216704289,
+      "grad_norm": 0.05481418216875255,
+      "learning_rate": 7.68460086824492e-06,
+      "loss": 0.7619,
+      "step": 42
+    },
+    {
+      "epoch": 1.1896162528216705,
+      "grad_norm": 0.05846015164093139,
+      "learning_rate": 7.546600811643816e-06,
+      "loss": 0.7389,
+      "step": 43
+    },
+    {
+      "epoch": 1.2167042889390518,
+      "grad_norm": 0.05413723610310761,
+      "learning_rate": 7.405929722454026e-06,
+      "loss": 0.6184,
+      "step": 44
+    },
+    {
+      "epoch": 1.2437923250564333,
+      "grad_norm": 0.05134366705233288,
+      "learning_rate": 7.262735145222696e-06,
+      "loss": 0.6454,
+      "step": 45
+    },
+    {
+      "epoch": 1.2708803611738149,
+      "grad_norm": 0.05310633803377862,
+      "learning_rate": 7.117167271287453e-06,
+      "loss": 0.6757,
+      "step": 46
+    },
+    {
+      "epoch": 1.2979683972911964,
+      "grad_norm": 0.053925607393482275,
+      "learning_rate": 6.969378781246436e-06,
+      "loss": 0.6576,
+      "step": 47
+    },
+    {
+      "epoch": 1.325056433408578,
+      "grad_norm": 0.057106251483552625,
+      "learning_rate": 6.819524684817439e-06,
+      "loss": 0.7626,
+      "step": 48
+    },
+    {
+      "epoch": 1.3521444695259595,
+      "grad_norm": 0.063954914765478,
+      "learning_rate": 6.667762158254104e-06,
+      "loss": 0.7258,
+      "step": 49
+    },
+    {
+      "epoch": 1.379232505643341,
+      "grad_norm": 0.06058570686117535,
+      "learning_rate": 6.514250379489754e-06,
+      "loss": 0.7189,
+      "step": 50
+    },
+    {
+      "epoch": 1.4063205417607223,
+      "grad_norm": 0.05938143369785303,
+      "learning_rate": 6.3591503611817155e-06,
+      "loss": 0.6971,
+      "step": 51
+    },
+    {
+      "epoch": 1.4334085778781038,
+      "grad_norm": 0.054558813521977216,
+      "learning_rate": 6.202624781831269e-06,
+      "loss": 0.6993,
+      "step": 52
+    },
+    {
+      "epoch": 1.4604966139954854,
+      "grad_norm": 0.05680279560956532,
+      "learning_rate": 6.044837815156377e-06,
+      "loss": 0.6718,
+      "step": 53
+    },
+    {
+      "epoch": 1.487584650112867,
+      "grad_norm": 0.057626144484000004,
+      "learning_rate": 5.885954957896115e-06,
+      "loss": 0.6387,
+      "step": 54
+    },
+    {
+      "epoch": 1.5146726862302482,
+      "grad_norm": 0.05199111492426588,
+      "learning_rate": 5.726142856227453e-06,
+      "loss": 0.5622,
+      "step": 55
+    },
+    {
+      "epoch": 1.5417607223476297,
+      "grad_norm": 0.05327168882426124,
+      "learning_rate": 5.5655691309764225e-06,
+      "loss": 0.7091,
+      "step": 56
+    },
+    {
+      "epoch": 1.5688487584650113,
+      "grad_norm": 0.057426996754366404,
+      "learning_rate": 5.404402201807022e-06,
+      "loss": 0.6517,
+      "step": 57
+    },
+    {
+      "epoch": 1.5959367945823928,
+      "grad_norm": 0.05495817026055581,
+      "learning_rate": 5.242811110572243e-06,
+      "loss": 0.6802,
+      "step": 58
+    },
+    {
+      "epoch": 1.6230248306997743,
+      "grad_norm": 0.05641482899916262,
+      "learning_rate": 5.080965344012509e-06,
+      "loss": 0.6902,
+      "step": 59
+    },
+    {
+      "epoch": 1.6501128668171559,
+      "grad_norm": 0.055534338239146296,
+      "learning_rate": 4.919034655987493e-06,
+      "loss": 0.6458,
+      "step": 60
+    },
+    {
+      "epoch": 1.6772009029345374,
+      "grad_norm": 0.0515923365198089,
+      "learning_rate": 4.757188889427761e-06,
+      "loss": 0.5779,
+      "step": 61
+    },
+    {
+      "epoch": 1.7042889390519187,
+      "grad_norm": 0.05349680772002036,
+      "learning_rate": 4.59559779819298e-06,
+      "loss": 0.6662,
+      "step": 62
+    },
+    {
+      "epoch": 1.7313769751693002,
+      "grad_norm": 0.05597651265383424,
+      "learning_rate": 4.434430869023579e-06,
+      "loss": 0.6427,
+      "step": 63
+    },
+    {
+      "epoch": 1.7584650112866818,
+      "grad_norm": 0.05367995560098686,
+      "learning_rate": 4.27385714377255e-06,
+      "loss": 0.5866,
+      "step": 64
+    },
+    {
+      "epoch": 1.785553047404063,
+      "grad_norm": 0.050110706315052135,
+      "learning_rate": 4.1140450421038865e-06,
+      "loss": 0.6308,
+      "step": 65
+    },
+    {
+      "epoch": 1.8126410835214446,
+      "grad_norm": 0.05304711612194916,
+      "learning_rate": 3.955162184843625e-06,
+      "loss": 0.6354,
+      "step": 66
+    },
+    {
+      "epoch": 1.8397291196388261,
+      "grad_norm": 0.05096383612475282,
+      "learning_rate": 3.7973752181687336e-06,
+      "loss": 0.5353,
+      "step": 67
+    },
+    {
+      "epoch": 1.8668171557562077,
+      "grad_norm": 0.0485852384541565,
+      "learning_rate": 3.6408496388182857e-06,
+      "loss": 0.6101,
+      "step": 68
+    },
+    {
+      "epoch": 1.8939051918735892,
+      "grad_norm": 0.05340977288546307,
+      "learning_rate": 3.4857496205102475e-06,
+      "loss": 0.6748,
+      "step": 69
+    },
+    {
+      "epoch": 1.9209932279909707,
+      "grad_norm": 0.05929668403153539,
+      "learning_rate": 3.3322378417458985e-06,
+      "loss": 0.7395,
+      "step": 70
+    },
+    {
+      "epoch": 1.9480812641083523,
+      "grad_norm": 0.05974704306446326,
+      "learning_rate": 3.180475315182563e-06,
+      "loss": 0.6742,
+      "step": 71
+    },
+    {
+      "epoch": 1.9751693002257338,
+      "grad_norm": 0.05601946443734337,
+      "learning_rate": 3.0306212187535653e-06,
+      "loss": 0.658,
+      "step": 72
+    },
+    {
+      "epoch": 2.0270880361173815,
+      "grad_norm": 0.0724237322260953,
+      "learning_rate": 2.882832728712551e-06,
+      "loss": 1.4064,
+      "step": 73
+    },
+    {
+      "epoch": 2.054176072234763,
+      "grad_norm": 0.06053838794404104,
+      "learning_rate": 2.7372648547773063e-06,
+      "loss": 0.656,
+      "step": 74
+    },
+    {
+      "epoch": 2.0812641083521446,
+      "grad_norm": 0.05100316572963111,
+      "learning_rate": 2.594070277545975e-06,
+      "loss": 0.5612,
+      "step": 75
+    },
+    {
+      "epoch": 2.108352144469526,
+      "grad_norm": 0.0622038616480431,
+      "learning_rate": 2.4533991883561868e-06,
+      "loss": 0.6891,
+      "step": 76
+    },
+    {
+      "epoch": 2.1354401805869077,
+      "grad_norm": 0.057916636244831204,
+      "learning_rate": 2.315399131755081e-06,
+      "loss": 0.638,
+      "step": 77
+    },
+    {
+      "epoch": 2.1625282167042887,
+      "grad_norm": 0.05395672544503171,
+      "learning_rate": 2.1802148507454675e-06,
+      "loss": 0.5861,
+      "step": 78
+    },
+    {
+      "epoch": 2.1896162528216703,
+      "grad_norm": 0.053864006071485976,
+      "learning_rate": 2.0479881349703885e-06,
+      "loss": 0.594,
+      "step": 79
+    },
+    {
+      "epoch": 2.216704288939052,
+      "grad_norm": 0.05830769530523658,
+      "learning_rate": 1.9188576719953635e-06,
+      "loss": 0.5802,
+      "step": 80
+    },
+    {
+      "epoch": 2.2437923250564333,
+      "grad_norm": 0.051099460392983014,
+      "learning_rate": 1.7929589018443016e-06,
+      "loss": 0.5442,
+      "step": 81
+    },
+    {
+      "epoch": 2.270880361173815,
+      "grad_norm": 0.05719841616517216,
+      "learning_rate": 1.6704238749415958e-06,
+      "loss": 0.7072,
+      "step": 82
+    },
+    {
+      "epoch": 2.2979683972911964,
+      "grad_norm": 0.06123931714369972,
+      "learning_rate": 1.5513811136094786e-06,
+      "loss": 0.6568,
+      "step": 83
+    },
+    {
+      "epoch": 2.325056433408578,
+      "grad_norm": 0.055793904401965494,
+      "learning_rate": 1.4359554772658551e-06,
+      "loss": 0.5966,
+      "step": 84
+    },
+    {
+      "epoch": 2.3521444695259595,
+      "grad_norm": 0.05953398956212439,
+      "learning_rate": 1.3242680314639995e-06,
+      "loss": 0.6587,
+      "step": 85
+    },
+    {
+      "epoch": 2.379232505643341,
+      "grad_norm": 0.05626639429332997,
+      "learning_rate": 1.2164359209115235e-06,
+      "loss": 0.5789,
+      "step": 86
+    },
+    {
+      "epoch": 2.4063205417607225,
+      "grad_norm": 0.059804679789879765,
+      "learning_rate": 1.1125722466017547e-06,
+      "loss": 0.654,
+      "step": 87
+    },
+    {
+      "epoch": 2.4334085778781036,
+      "grad_norm": 0.06250704904021064,
+      "learning_rate": 1.012785947186397e-06,
+      "loss": 0.6334,
+      "step": 88
+    },
+    {
+      "epoch": 2.460496613995485,
+      "grad_norm": 0.05303042611737511,
+      "learning_rate": 9.171816847139447e-07,
+      "loss": 0.5383,
+      "step": 89
+    },
+    {
+      "epoch": 2.4875846501128667,
+      "grad_norm": 0.04694109638497442,
+      "learning_rate": 8.258597348536452e-07,
+      "loss": 0.47,
+      "step": 90
+    },
+    {
+      "epoch": 2.514672686230248,
+      "grad_norm": 0.05089219899472816,
+      "learning_rate": 7.389158817201541e-07,
+      "loss": 0.5689,
+      "step": 91
+    },
+    {
+      "epoch": 2.5417607223476297,
+      "grad_norm": 0.05462955495836319,
+      "learning_rate": 6.564413174092443e-07,
+      "loss": 0.5717,
+      "step": 92
+    },
+    {
+      "epoch": 2.5688487584650113,
+      "grad_norm": 0.05361089763797038,
+      "learning_rate": 5.785225463498828e-07,
+      "loss": 0.5882,
+      "step": 93
+    },
+    {
+      "epoch": 2.595936794582393,
+      "grad_norm": 0.0545372370608364,
+      "learning_rate": 5.05241294573024e-07,
+      "loss": 0.5988,
+      "step": 94
+    },
+    {
+      "epoch": 2.6230248306997743,
+      "grad_norm": 0.05203946271783804,
+      "learning_rate": 4.3667442399229985e-07,
+      "loss": 0.5401,
+      "step": 95
+    },
+    {
+      "epoch": 2.650112866817156,
+      "grad_norm": 0.059286878607973235,
+      "learning_rate": 3.728938517864794e-07,
+      "loss": 0.6421,
+      "step": 96
+    },
+    {
+      "epoch": 2.6772009029345374,
+      "grad_norm": 0.05057841068074063,
+      "learning_rate": 3.1396647496828245e-07,
+      "loss": 0.4977,
+      "step": 97
+    },
+    {
+      "epoch": 2.704288939051919,
+      "grad_norm": 0.056645818127275836,
+      "learning_rate": 2.599541002186479e-07,
+      "loss": 0.6279,
+      "step": 98
+    },
+    {
+      "epoch": 2.7313769751693,
+      "grad_norm": 0.057378590315900785,
+      "learning_rate": 2.109133790600648e-07,
+      "loss": 0.5334,
+      "step": 99
+    },
+    {
+      "epoch": 2.758465011286682,
+      "grad_norm": 0.05201027382239277,
+      "learning_rate": 1.6689574843694433e-07,
+      "loss": 0.5393,
+      "step": 100
+    },
+    {
+      "epoch": 2.785553047404063,
+      "grad_norm": 0.046096574095139876,
+      "learning_rate": 1.2794737676536993e-07,
+      "loss": 0.4896,
+      "step": 101
+    },
+    {
+      "epoch": 2.8126410835214446,
+      "grad_norm": 0.05452191462883333,
+      "learning_rate": 9.410911550880474e-08,
+      "loss": 0.654,
+      "step": 102
+    },
+    {
+      "epoch": 2.839729119638826,
+      "grad_norm": 0.06330637115234866,
+      "learning_rate": 6.54164563305465e-08,
+      "loss": 0.6922,
+      "step": 103
+    },
+    {
+      "epoch": 2.8668171557562077,
+      "grad_norm": 0.06047053924162395,
+      "learning_rate": 4.189949386787462e-08,
+      "loss": 0.6493,
+      "step": 104
+    },
+    {
+      "epoch": 2.893905191873589,
+      "grad_norm": 0.05558730657663917,
+      "learning_rate": 2.358289416693027e-08,
+      "loss": 0.5759,
+      "step": 105
+    },
+    {
+      "epoch": 2.9209932279909707,
+      "grad_norm": 0.05598626490189069,
+      "learning_rate": 1.0485868811441757e-08,
+      "loss": 0.5835,
+      "step": 106
+    },
+    {
+      "epoch": 2.9480812641083523,
+      "grad_norm": 0.058320029820894966,
+      "learning_rate": 2.6221547724253337e-09,
+      "loss": 0.613,
+      "step": 107
+    },
+    {
+      "epoch": 2.975169300225734,
+      "grad_norm": 0.05592965040584475,
+      "learning_rate": 0.0,
+      "loss": 0.6081,
+      "step": 108
+    },
+    {
+      "epoch": 2.975169300225734,
+      "step": 108,
+      "total_flos": 3.237704266625843e+16,
+      "train_loss": 0.7293182517643328,
+      "train_runtime": 6995.9355,
+      "train_samples_per_second": 0.569,
+      "train_steps_per_second": 0.015
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.237704266625843e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dbd97f6b1ab3ee6d17a8cd9f26888387e4c1ad330038a684626001f7e502b7a
+size 7736