Upload folder using huggingface_hub

.gitattributes

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

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: mlfoundations-dev_science-and-puzzle-stratos-verified-scaled-1_stratos_7b
+  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. -->
+
+# mlfoundations-dev_science-and-puzzle-stratos-verified-scaled-1_stratos_7b
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/science-and-puzzle-stratos-verified-scaled-1 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: 48
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 96
+- total_eval_batch_size: 384
+- optimizer: Use 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 4.46.1
+- Pytorch 2.5.0a0+b465a5843b.nv24.09
+- Datasets 3.0.2
+- Tokenizers 0.20.3

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": 2.9523809523809526,
+    "total_flos": 4.414815291519795e+16,
+    "train_loss": 0.7942085708341291,
+    "train_runtime": 1549.0803,
+    "train_samples_per_second": 5.81,
+    "train_steps_per_second": 0.06
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/p/data1/mmlaion/marianna/models/Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c97bab7012372cd25aee727a17fb0f1b87c9bda94f7207ebdfc907ea38117894
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e040f501b14e20db16429f85227fab87fa8a53898e9e9c177e68ad800c1bfccb
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2647005295f80d6a938bf0ca3e9ecbe038c7bc09abf71d3eb8234cf701849436
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2382eda2b45d41eb85f655d39f52148041c7df0aea6a79287b073acbe2d0c5c7
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9523809523809526,
+    "total_flos": 4.414815291519795e+16,
+    "train_loss": 0.7942085708341291,
+    "train_runtime": 1549.0803,
+    "train_samples_per_second": 5.81,
+    "train_steps_per_second": 0.06
+}

trainer_log.jsonl

@@ -0,0 +1,94 @@
+{"current_steps": 1, "total_steps": 93, "loss": 1.2203, "lr": 1.0000000000000002e-06, "epoch": 0.031746031746031744, "percentage": 1.08, "elapsed_time": "0:00:20", "remaining_time": "0:30:51"}
+{"current_steps": 2, "total_steps": 93, "loss": 1.189, "lr": 2.0000000000000003e-06, "epoch": 0.06349206349206349, "percentage": 2.15, "elapsed_time": "0:00:35", "remaining_time": "0:26:58"}
+{"current_steps": 3, "total_steps": 93, "loss": 1.1809, "lr": 3e-06, "epoch": 0.09523809523809523, "percentage": 3.23, "elapsed_time": "0:00:57", "remaining_time": "0:28:36"}
+{"current_steps": 4, "total_steps": 93, "loss": 1.2062, "lr": 4.000000000000001e-06, "epoch": 0.12698412698412698, "percentage": 4.3, "elapsed_time": "0:01:12", "remaining_time": "0:26:51"}
+{"current_steps": 5, "total_steps": 93, "loss": 1.145, "lr": 5e-06, "epoch": 0.15873015873015872, "percentage": 5.38, "elapsed_time": "0:01:25", "remaining_time": "0:24:58"}
+{"current_steps": 6, "total_steps": 93, "loss": 1.0964, "lr": 6e-06, "epoch": 0.19047619047619047, "percentage": 6.45, "elapsed_time": "0:01:38", "remaining_time": "0:23:52"}
+{"current_steps": 7, "total_steps": 93, "loss": 1.0475, "lr": 7e-06, "epoch": 0.2222222222222222, "percentage": 7.53, "elapsed_time": "0:01:50", "remaining_time": "0:22:42"}
+{"current_steps": 8, "total_steps": 93, "loss": 1.0532, "lr": 8.000000000000001e-06, "epoch": 0.25396825396825395, "percentage": 8.6, "elapsed_time": "0:02:13", "remaining_time": "0:23:35"}
+{"current_steps": 9, "total_steps": 93, "loss": 1.0309, "lr": 9e-06, "epoch": 0.2857142857142857, "percentage": 9.68, "elapsed_time": "0:02:32", "remaining_time": "0:23:46"}
+{"current_steps": 10, "total_steps": 93, "loss": 0.9628, "lr": 1e-05, "epoch": 0.31746031746031744, "percentage": 10.75, "elapsed_time": "0:02:56", "remaining_time": "0:24:28"}
+{"current_steps": 11, "total_steps": 93, "loss": 1.0365, "lr": 9.996418774081658e-06, "epoch": 0.3492063492063492, "percentage": 11.83, "elapsed_time": "0:03:07", "remaining_time": "0:23:15"}
+{"current_steps": 12, "total_steps": 93, "loss": 0.9864, "lr": 9.985680226398261e-06, "epoch": 0.38095238095238093, "percentage": 12.9, "elapsed_time": "0:03:27", "remaining_time": "0:23:22"}
+{"current_steps": 13, "total_steps": 93, "loss": 0.9294, "lr": 9.967799739815925e-06, "epoch": 0.4126984126984127, "percentage": 13.98, "elapsed_time": "0:03:41", "remaining_time": "0:22:42"}
+{"current_steps": 14, "total_steps": 93, "loss": 0.9062, "lr": 9.942802927959444e-06, "epoch": 0.4444444444444444, "percentage": 15.05, "elapsed_time": "0:03:57", "remaining_time": "0:22:19"}
+{"current_steps": 15, "total_steps": 93, "loss": 0.9183, "lr": 9.910725598521014e-06, "epoch": 0.47619047619047616, "percentage": 16.13, "elapsed_time": "0:04:14", "remaining_time": "0:22:04"}
+{"current_steps": 16, "total_steps": 93, "loss": 0.9214, "lr": 9.871613701966067e-06, "epoch": 0.5079365079365079, "percentage": 17.2, "elapsed_time": "0:04:34", "remaining_time": "0:22:00"}
+{"current_steps": 17, "total_steps": 93, "loss": 0.9156, "lr": 9.825523265709667e-06, "epoch": 0.5396825396825397, "percentage": 18.28, "elapsed_time": "0:04:48", "remaining_time": "0:21:29"}
+{"current_steps": 18, "total_steps": 93, "loss": 0.9121, "lr": 9.772520313857777e-06, "epoch": 0.5714285714285714, "percentage": 19.35, "elapsed_time": "0:05:01", "remaining_time": "0:20:56"}
+{"current_steps": 19, "total_steps": 93, "loss": 0.9107, "lr": 9.712680772628365e-06, "epoch": 0.6031746031746031, "percentage": 20.43, "elapsed_time": "0:05:18", "remaining_time": "0:20:39"}
+{"current_steps": 20, "total_steps": 93, "loss": 0.9157, "lr": 9.646090361587828e-06, "epoch": 0.6349206349206349, "percentage": 21.51, "elapsed_time": "0:05:32", "remaining_time": "0:20:13"}
+{"current_steps": 21, "total_steps": 93, "loss": 0.8809, "lr": 9.572844470858537e-06, "epoch": 0.6666666666666666, "percentage": 22.58, "elapsed_time": "0:05:45", "remaining_time": "0:19:44"}
+{"current_steps": 22, "total_steps": 93, "loss": 0.8773, "lr": 9.493048024473413e-06, "epoch": 0.6984126984126984, "percentage": 23.66, "elapsed_time": "0:06:00", "remaining_time": "0:19:22"}
+{"current_steps": 23, "total_steps": 93, "loss": 0.8795, "lr": 9.406815330073244e-06, "epoch": 0.7301587301587301, "percentage": 24.73, "elapsed_time": "0:06:16", "remaining_time": "0:19:06"}
+{"current_steps": 24, "total_steps": 93, "loss": 0.8653, "lr": 9.314269915162115e-06, "epoch": 0.7619047619047619, "percentage": 25.81, "elapsed_time": "0:06:31", "remaining_time": "0:18:45"}
+{"current_steps": 25, "total_steps": 93, "loss": 0.8549, "lr": 9.215544350155423e-06, "epoch": 0.7936507936507936, "percentage": 26.88, "elapsed_time": "0:06:48", "remaining_time": "0:18:29"}
+{"current_steps": 26, "total_steps": 93, "loss": 0.8575, "lr": 9.110780058474052e-06, "epoch": 0.8253968253968254, "percentage": 27.96, "elapsed_time": "0:06:59", "remaining_time": "0:18:02"}
+{"current_steps": 27, "total_steps": 93, "loss": 0.8772, "lr": 9.000127113956673e-06, "epoch": 0.8571428571428571, "percentage": 29.03, "elapsed_time": "0:07:13", "remaining_time": "0:17:38"}
+{"current_steps": 28, "total_steps": 93, "loss": 0.8504, "lr": 8.883744025880429e-06, "epoch": 0.8888888888888888, "percentage": 30.11, "elapsed_time": "0:07:32", "remaining_time": "0:17:30"}
+{"current_steps": 29, "total_steps": 93, "loss": 0.8381, "lr": 8.761797511897907e-06, "epoch": 0.9206349206349206, "percentage": 31.18, "elapsed_time": "0:07:54", "remaining_time": "0:17:27"}
+{"current_steps": 30, "total_steps": 93, "loss": 0.8618, "lr": 8.634462259215719e-06, "epoch": 0.9523809523809523, "percentage": 32.26, "elapsed_time": "0:08:10", "remaining_time": "0:17:10"}
+{"current_steps": 31, "total_steps": 93, "loss": 0.8329, "lr": 8.501920674356755e-06, "epoch": 0.9841269841269841, "percentage": 33.33, "elapsed_time": "0:08:31", "remaining_time": "0:17:03"}
+{"current_steps": 32, "total_steps": 93, "loss": 1.2444, "lr": 8.364362621864595e-06, "epoch": 1.0158730158730158, "percentage": 34.41, "elapsed_time": "0:08:47", "remaining_time": "0:16:45"}
+{"current_steps": 33, "total_steps": 93, "loss": 0.7497, "lr": 8.221985152324385e-06, "epoch": 1.0476190476190477, "percentage": 35.48, "elapsed_time": "0:09:04", "remaining_time": "0:16:30"}
+{"current_steps": 34, "total_steps": 93, "loss": 0.7877, "lr": 8.07499222008977e-06, "epoch": 1.0793650793650793, "percentage": 36.56, "elapsed_time": "0:09:16", "remaining_time": "0:16:06"}
+{"current_steps": 35, "total_steps": 93, "loss": 0.7231, "lr": 7.923594391120237e-06, "epoch": 1.1111111111111112, "percentage": 37.63, "elapsed_time": "0:09:33", "remaining_time": "0:15:50"}
+{"current_steps": 36, "total_steps": 93, "loss": 0.7928, "lr": 7.768008541347423e-06, "epoch": 1.1428571428571428, "percentage": 38.71, "elapsed_time": "0:09:46", "remaining_time": "0:15:29"}
+{"current_steps": 37, "total_steps": 93, "loss": 0.7977, "lr": 7.608457546002423e-06, "epoch": 1.1746031746031746, "percentage": 39.78, "elapsed_time": "0:10:02", "remaining_time": "0:15:11"}
+{"current_steps": 38, "total_steps": 93, "loss": 0.7296, "lr": 7.445169960349167e-06, "epoch": 1.2063492063492063, "percentage": 40.86, "elapsed_time": "0:10:14", "remaining_time": "0:14:49"}
+{"current_steps": 39, "total_steps": 93, "loss": 0.7695, "lr": 7.278379692281209e-06, "epoch": 1.2380952380952381, "percentage": 41.94, "elapsed_time": "0:10:34", "remaining_time": "0:14:38"}
+{"current_steps": 40, "total_steps": 93, "loss": 0.7304, "lr": 7.10832566725092e-06, "epoch": 1.2698412698412698, "percentage": 43.01, "elapsed_time": "0:10:51", "remaining_time": "0:14:23"}
+{"current_steps": 41, "total_steps": 93, "loss": 0.7772, "lr": 6.9352514860110876e-06, "epoch": 1.3015873015873016, "percentage": 44.09, "elapsed_time": "0:11:08", "remaining_time": "0:14:07"}
+{"current_steps": 42, "total_steps": 93, "loss": 0.7668, "lr": 6.759405075659165e-06, "epoch": 1.3333333333333333, "percentage": 45.16, "elapsed_time": "0:11:30", "remaining_time": "0:13:58"}
+{"current_steps": 43, "total_steps": 93, "loss": 0.6952, "lr": 6.58103833448412e-06, "epoch": 1.3650793650793651, "percentage": 46.24, "elapsed_time": "0:11:53", "remaining_time": "0:13:49"}
+{"current_steps": 44, "total_steps": 93, "loss": 0.7385, "lr": 6.4004067711245366e-06, "epoch": 1.3968253968253967, "percentage": 47.31, "elapsed_time": "0:12:12", "remaining_time": "0:13:35"}
+{"current_steps": 45, "total_steps": 93, "loss": 0.7493, "lr": 6.2177691385549595e-06, "epoch": 1.4285714285714286, "percentage": 48.39, "elapsed_time": "0:12:26", "remaining_time": "0:13:16"}
+{"current_steps": 46, "total_steps": 93, "loss": 0.7521, "lr": 6.033387063424765e-06, "epoch": 1.4603174603174602, "percentage": 49.46, "elapsed_time": "0:12:44", "remaining_time": "0:13:00"}
+{"current_steps": 47, "total_steps": 93, "loss": 0.74, "lr": 5.8475246712804845e-06, "epoch": 1.492063492063492, "percentage": 50.54, "elapsed_time": "0:13:01", "remaining_time": "0:12:44"}
+{"current_steps": 48, "total_steps": 93, "loss": 0.7292, "lr": 5.660448208208513e-06, "epoch": 1.5238095238095237, "percentage": 51.61, "elapsed_time": "0:13:17", "remaining_time": "0:12:27"}
+{"current_steps": 49, "total_steps": 93, "loss": 0.7254, "lr": 5.472425659440157e-06, "epoch": 1.5555555555555556, "percentage": 52.69, "elapsed_time": "0:13:32", "remaining_time": "0:12:09"}
+{"current_steps": 50, "total_steps": 93, "loss": 0.6899, "lr": 5.2837263654653715e-06, "epoch": 1.5873015873015874, "percentage": 53.76, "elapsed_time": "0:13:45", "remaining_time": "0:11:49"}
+{"current_steps": 51, "total_steps": 93, "loss": 0.7594, "lr": 5.094620636205096e-06, "epoch": 1.619047619047619, "percentage": 54.84, "elapsed_time": "0:14:01", "remaining_time": "0:11:32"}
+{"current_steps": 52, "total_steps": 93, "loss": 0.7108, "lr": 4.905379363794907e-06, "epoch": 1.6507936507936507, "percentage": 55.91, "elapsed_time": "0:14:12", "remaining_time": "0:11:12"}
+{"current_steps": 53, "total_steps": 93, "loss": 0.7786, "lr": 4.71627363453463e-06, "epoch": 1.6825396825396826, "percentage": 56.99, "elapsed_time": "0:14:31", "remaining_time": "0:10:57"}
+{"current_steps": 54, "total_steps": 93, "loss": 0.736, "lr": 4.527574340559844e-06, "epoch": 1.7142857142857144, "percentage": 58.06, "elapsed_time": "0:14:48", "remaining_time": "0:10:41"}
+{"current_steps": 55, "total_steps": 93, "loss": 0.7039, "lr": 4.33955179179149e-06, "epoch": 1.746031746031746, "percentage": 59.14, "elapsed_time": "0:15:10", "remaining_time": "0:10:28"}
+{"current_steps": 56, "total_steps": 93, "loss": 0.7556, "lr": 4.152475328719517e-06, "epoch": 1.7777777777777777, "percentage": 60.22, "elapsed_time": "0:15:27", "remaining_time": "0:10:12"}
+{"current_steps": 57, "total_steps": 93, "loss": 0.7253, "lr": 3.966612936575235e-06, "epoch": 1.8095238095238095, "percentage": 61.29, "elapsed_time": "0:15:43", "remaining_time": "0:09:55"}
+{"current_steps": 58, "total_steps": 93, "loss": 0.727, "lr": 3.782230861445041e-06, "epoch": 1.8412698412698414, "percentage": 62.37, "elapsed_time": "0:16:02", "remaining_time": "0:09:40"}
+{"current_steps": 59, "total_steps": 93, "loss": 0.7012, "lr": 3.5995932288754655e-06, "epoch": 1.873015873015873, "percentage": 63.44, "elapsed_time": "0:16:17", "remaining_time": "0:09:23"}
+{"current_steps": 60, "total_steps": 93, "loss": 0.7308, "lr": 3.4189616655158803e-06, "epoch": 1.9047619047619047, "percentage": 64.52, "elapsed_time": "0:16:36", "remaining_time": "0:09:07"}
+{"current_steps": 61, "total_steps": 93, "loss": 0.7106, "lr": 3.240594924340835e-06, "epoch": 1.9365079365079365, "percentage": 65.59, "elapsed_time": "0:16:50", "remaining_time": "0:08:50"}
+{"current_steps": 62, "total_steps": 93, "loss": 0.7345, "lr": 3.0647485139889145e-06, "epoch": 1.9682539682539684, "percentage": 66.67, "elapsed_time": "0:17:01", "remaining_time": "0:08:30"}
+{"current_steps": 63, "total_steps": 93, "loss": 1.0551, "lr": 2.89167433274908e-06, "epoch": 2.0, "percentage": 67.74, "elapsed_time": "0:17:19", "remaining_time": "0:08:15"}
+{"current_steps": 64, "total_steps": 93, "loss": 0.6545, "lr": 2.721620307718793e-06, "epoch": 2.0317460317460316, "percentage": 68.82, "elapsed_time": "0:17:33", "remaining_time": "0:07:57"}
+{"current_steps": 65, "total_steps": 93, "loss": 0.663, "lr": 2.554830039650834e-06, "epoch": 2.0634920634920633, "percentage": 69.89, "elapsed_time": "0:17:49", "remaining_time": "0:07:40"}
+{"current_steps": 66, "total_steps": 93, "loss": 0.6517, "lr": 2.391542453997578e-06, "epoch": 2.0952380952380953, "percentage": 70.97, "elapsed_time": "0:18:14", "remaining_time": "0:07:27"}
+{"current_steps": 67, "total_steps": 93, "loss": 0.6592, "lr": 2.2319914586525776e-06, "epoch": 2.126984126984127, "percentage": 72.04, "elapsed_time": "0:18:36", "remaining_time": "0:07:13"}
+{"current_steps": 68, "total_steps": 93, "loss": 0.6344, "lr": 2.0764056088797646e-06, "epoch": 2.1587301587301586, "percentage": 73.12, "elapsed_time": "0:18:49", "remaining_time": "0:06:55"}
+{"current_steps": 69, "total_steps": 93, "loss": 0.6435, "lr": 1.9250077799102323e-06, "epoch": 2.1904761904761907, "percentage": 74.19, "elapsed_time": "0:19:07", "remaining_time": "0:06:39"}
+{"current_steps": 70, "total_steps": 93, "loss": 0.6441, "lr": 1.7780148476756148e-06, "epoch": 2.2222222222222223, "percentage": 75.27, "elapsed_time": "0:19:26", "remaining_time": "0:06:23"}
+{"current_steps": 71, "total_steps": 93, "loss": 0.6532, "lr": 1.6356373781354058e-06, "epoch": 2.253968253968254, "percentage": 76.34, "elapsed_time": "0:19:40", "remaining_time": "0:06:05"}
+{"current_steps": 72, "total_steps": 93, "loss": 0.6232, "lr": 1.4980793256432474e-06, "epoch": 2.2857142857142856, "percentage": 77.42, "elapsed_time": "0:19:55", "remaining_time": "0:05:48"}
+{"current_steps": 73, "total_steps": 93, "loss": 0.6458, "lr": 1.3655377407842813e-06, "epoch": 2.317460317460317, "percentage": 78.49, "elapsed_time": "0:20:08", "remaining_time": "0:05:31"}
+{"current_steps": 74, "total_steps": 93, "loss": 0.656, "lr": 1.2382024881020937e-06, "epoch": 2.3492063492063493, "percentage": 79.57, "elapsed_time": "0:20:25", "remaining_time": "0:05:14"}
+{"current_steps": 75, "total_steps": 93, "loss": 0.645, "lr": 1.1162559741195733e-06, "epoch": 2.380952380952381, "percentage": 80.65, "elapsed_time": "0:20:40", "remaining_time": "0:04:57"}
+{"current_steps": 76, "total_steps": 93, "loss": 0.6403, "lr": 9.998728860433277e-07, "epoch": 2.4126984126984126, "percentage": 81.72, "elapsed_time": "0:21:00", "remaining_time": "0:04:41"}
+{"current_steps": 77, "total_steps": 93, "loss": 0.6259, "lr": 8.892199415259501e-07, "epoch": 2.4444444444444446, "percentage": 82.8, "elapsed_time": "0:21:18", "remaining_time": "0:04:25"}
+{"current_steps": 78, "total_steps": 93, "loss": 0.6414, "lr": 7.844556498445788e-07, "epoch": 2.4761904761904763, "percentage": 83.87, "elapsed_time": "0:21:32", "remaining_time": "0:04:08"}
+{"current_steps": 79, "total_steps": 93, "loss": 0.6576, "lr": 6.857300848378857e-07, "epoch": 2.507936507936508, "percentage": 84.95, "elapsed_time": "0:21:48", "remaining_time": "0:03:51"}
+{"current_steps": 80, "total_steps": 93, "loss": 0.6407, "lr": 5.931846699267558e-07, "epoch": 2.5396825396825395, "percentage": 86.02, "elapsed_time": "0:22:06", "remaining_time": "0:03:35"}
+{"current_steps": 81, "total_steps": 93, "loss": 0.6325, "lr": 5.0695197552659e-07, "epoch": 2.571428571428571, "percentage": 87.1, "elapsed_time": "0:22:19", "remaining_time": "0:03:18"}
+{"current_steps": 82, "total_steps": 93, "loss": 0.6668, "lr": 4.271555291414636e-07, "epoch": 2.6031746031746033, "percentage": 88.17, "elapsed_time": "0:22:36", "remaining_time": "0:03:01"}
+{"current_steps": 83, "total_steps": 93, "loss": 0.6518, "lr": 3.539096384121743e-07, "epoch": 2.634920634920635, "percentage": 89.25, "elapsed_time": "0:22:54", "remaining_time": "0:02:45"}
+{"current_steps": 84, "total_steps": 93, "loss": 0.6577, "lr": 2.873192273716369e-07, "epoch": 2.6666666666666665, "percentage": 90.32, "elapsed_time": "0:23:08", "remaining_time": "0:02:28"}
+{"current_steps": 85, "total_steps": 93, "loss": 0.6275, "lr": 2.274796861422246e-07, "epoch": 2.6984126984126986, "percentage": 91.4, "elapsed_time": "0:23:24", "remaining_time": "0:02:12"}
+{"current_steps": 86, "total_steps": 93, "loss": 0.6482, "lr": 1.7447673429033361e-07, "epoch": 2.7301587301587302, "percentage": 92.47, "elapsed_time": "0:23:43", "remaining_time": "0:01:55"}
+{"current_steps": 87, "total_steps": 93, "loss": 0.6572, "lr": 1.2838629803393343e-07, "epoch": 2.761904761904762, "percentage": 93.55, "elapsed_time": "0:23:57", "remaining_time": "0:01:39"}
+{"current_steps": 88, "total_steps": 93, "loss": 0.6501, "lr": 8.927440147898703e-08, "epoch": 2.7936507936507935, "percentage": 94.62, "elapsed_time": "0:24:12", "remaining_time": "0:01:22"}
+{"current_steps": 89, "total_steps": 93, "loss": 0.6563, "lr": 5.7197072040557356e-08, "epoch": 2.825396825396825, "percentage": 95.7, "elapsed_time": "0:24:24", "remaining_time": "0:01:05"}
+{"current_steps": 90, "total_steps": 93, "loss": 0.6311, "lr": 3.220026018407541e-08, "epoch": 2.857142857142857, "percentage": 96.77, "elapsed_time": "0:24:42", "remaining_time": "0:00:49"}
+{"current_steps": 91, "total_steps": 93, "loss": 0.6382, "lr": 1.431977360173975e-08, "epoch": 2.888888888888889, "percentage": 97.85, "elapsed_time": "0:25:01", "remaining_time": "0:00:33"}
+{"current_steps": 92, "total_steps": 93, "loss": 0.6362, "lr": 3.5812259183426457e-09, "epoch": 2.9206349206349205, "percentage": 98.92, "elapsed_time": "0:25:18", "remaining_time": "0:00:16"}
+{"current_steps": 93, "total_steps": 93, "loss": 0.6504, "lr": 0.0, "epoch": 2.9523809523809526, "percentage": 100.0, "elapsed_time": "0:25:29", "remaining_time": "0:00:00"}
+{"current_steps": 93, "total_steps": 93, "epoch": 2.9523809523809526, "percentage": 100.0, "elapsed_time": "0:25:43", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,693 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9523809523809526,
+  "eval_steps": 500,
+  "global_step": 93,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.031746031746031744,
+      "grad_norm": 6.954195499420166,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.2203,
+      "step": 1
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "grad_norm": 6.669704437255859,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.189,
+      "step": 2
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 6.46160364151001,
+      "learning_rate": 3e-06,
+      "loss": 1.1809,
+      "step": 3
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "grad_norm": 6.460859298706055,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.2062,
+      "step": 4
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "grad_norm": 4.658584117889404,
+      "learning_rate": 5e-06,
+      "loss": 1.145,
+      "step": 5
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 2.7389426231384277,
+      "learning_rate": 6e-06,
+      "loss": 1.0964,
+      "step": 6
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 2.538163423538208,
+      "learning_rate": 7e-06,
+      "loss": 1.0475,
+      "step": 7
+    },
+    {
+      "epoch": 0.25396825396825395,
+      "grad_norm": 4.949894905090332,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.0532,
+      "step": 8
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 4.93301248550415,
+      "learning_rate": 9e-06,
+      "loss": 1.0309,
+      "step": 9
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 4.911384582519531,
+      "learning_rate": 1e-05,
+      "loss": 0.9628,
+      "step": 10
+    },
+    {
+      "epoch": 0.3492063492063492,
+      "grad_norm": 5.402538299560547,
+      "learning_rate": 9.996418774081658e-06,
+      "loss": 1.0365,
+      "step": 11
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 3.6248297691345215,
+      "learning_rate": 9.985680226398261e-06,
+      "loss": 0.9864,
+      "step": 12
+    },
+    {
+      "epoch": 0.4126984126984127,
+      "grad_norm": 2.532926321029663,
+      "learning_rate": 9.967799739815925e-06,
+      "loss": 0.9294,
+      "step": 13
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 2.6525156497955322,
+      "learning_rate": 9.942802927959444e-06,
+      "loss": 0.9062,
+      "step": 14
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 2.8525216579437256,
+      "learning_rate": 9.910725598521014e-06,
+      "loss": 0.9183,
+      "step": 15
+    },
+    {
+      "epoch": 0.5079365079365079,
+      "grad_norm": 2.3344156742095947,
+      "learning_rate": 9.871613701966067e-06,
+      "loss": 0.9214,
+      "step": 16
+    },
+    {
+      "epoch": 0.5396825396825397,
+      "grad_norm": 1.8935717344284058,
+      "learning_rate": 9.825523265709667e-06,
+      "loss": 0.9156,
+      "step": 17
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 1.8605824708938599,
+      "learning_rate": 9.772520313857777e-06,
+      "loss": 0.9121,
+      "step": 18
+    },
+    {
+      "epoch": 0.6031746031746031,
+      "grad_norm": 2.0118088722229004,
+      "learning_rate": 9.712680772628365e-06,
+      "loss": 0.9107,
+      "step": 19
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 1.835178017616272,
+      "learning_rate": 9.646090361587828e-06,
+      "loss": 0.9157,
+      "step": 20
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.3269990682601929,
+      "learning_rate": 9.572844470858537e-06,
+      "loss": 0.8809,
+      "step": 21
+    },
+    {
+      "epoch": 0.6984126984126984,
+      "grad_norm": 1.1035341024398804,
+      "learning_rate": 9.493048024473413e-06,
+      "loss": 0.8773,
+      "step": 22
+    },
+    {
+      "epoch": 0.7301587301587301,
+      "grad_norm": 1.1755458116531372,
+      "learning_rate": 9.406815330073244e-06,
+      "loss": 0.8795,
+      "step": 23
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 1.2033437490463257,
+      "learning_rate": 9.314269915162115e-06,
+      "loss": 0.8653,
+      "step": 24
+    },
+    {
+      "epoch": 0.7936507936507936,
+      "grad_norm": 1.0419812202453613,
+      "learning_rate": 9.215544350155423e-06,
+      "loss": 0.8549,
+      "step": 25
+    },
+    {
+      "epoch": 0.8253968253968254,
+      "grad_norm": 1.1759586334228516,
+      "learning_rate": 9.110780058474052e-06,
+      "loss": 0.8575,
+      "step": 26
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.9946051836013794,
+      "learning_rate": 9.000127113956673e-06,
+      "loss": 0.8772,
+      "step": 27
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.8670427203178406,
+      "learning_rate": 8.883744025880429e-06,
+      "loss": 0.8504,
+      "step": 28
+    },
+    {
+      "epoch": 0.9206349206349206,
+      "grad_norm": 1.0277706384658813,
+      "learning_rate": 8.761797511897907e-06,
+      "loss": 0.8381,
+      "step": 29
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 1.037110686302185,
+      "learning_rate": 8.634462259215719e-06,
+      "loss": 0.8618,
+      "step": 30
+    },
+    {
+      "epoch": 0.9841269841269841,
+      "grad_norm": 0.8831559419631958,
+      "learning_rate": 8.501920674356755e-06,
+      "loss": 0.8329,
+      "step": 31
+    },
+    {
+      "epoch": 1.0158730158730158,
+      "grad_norm": 1.164239525794983,
+      "learning_rate": 8.364362621864595e-06,
+      "loss": 1.2444,
+      "step": 32
+    },
+    {
+      "epoch": 1.0476190476190477,
+      "grad_norm": 0.7643061876296997,
+      "learning_rate": 8.221985152324385e-06,
+      "loss": 0.7497,
+      "step": 33
+    },
+    {
+      "epoch": 1.0793650793650793,
+      "grad_norm": 0.7755542397499084,
+      "learning_rate": 8.07499222008977e-06,
+      "loss": 0.7877,
+      "step": 34
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.7520423531532288,
+      "learning_rate": 7.923594391120237e-06,
+      "loss": 0.7231,
+      "step": 35
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.7324318289756775,
+      "learning_rate": 7.768008541347423e-06,
+      "loss": 0.7928,
+      "step": 36
+    },
+    {
+      "epoch": 1.1746031746031746,
+      "grad_norm": 0.7791784405708313,
+      "learning_rate": 7.608457546002423e-06,
+      "loss": 0.7977,
+      "step": 37
+    },
+    {
+      "epoch": 1.2063492063492063,
+      "grad_norm": 0.7403120994567871,
+      "learning_rate": 7.445169960349167e-06,
+      "loss": 0.7296,
+      "step": 38
+    },
+    {
+      "epoch": 1.2380952380952381,
+      "grad_norm": 0.7689253091812134,
+      "learning_rate": 7.278379692281209e-06,
+      "loss": 0.7695,
+      "step": 39
+    },
+    {
+      "epoch": 1.2698412698412698,
+      "grad_norm": 0.8004273772239685,
+      "learning_rate": 7.10832566725092e-06,
+      "loss": 0.7304,
+      "step": 40
+    },
+    {
+      "epoch": 1.3015873015873016,
+      "grad_norm": 0.7878991961479187,
+      "learning_rate": 6.9352514860110876e-06,
+      "loss": 0.7772,
+      "step": 41
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.6795975565910339,
+      "learning_rate": 6.759405075659165e-06,
+      "loss": 0.7668,
+      "step": 42
+    },
+    {
+      "epoch": 1.3650793650793651,
+      "grad_norm": 0.704739511013031,
+      "learning_rate": 6.58103833448412e-06,
+      "loss": 0.6952,
+      "step": 43
+    },
+    {
+      "epoch": 1.3968253968253967,
+      "grad_norm": 0.7594010829925537,
+      "learning_rate": 6.4004067711245366e-06,
+      "loss": 0.7385,
+      "step": 44
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.7176108956336975,
+      "learning_rate": 6.2177691385549595e-06,
+      "loss": 0.7493,
+      "step": 45
+    },
+    {
+      "epoch": 1.4603174603174602,
+      "grad_norm": 0.6603548526763916,
+      "learning_rate": 6.033387063424765e-06,
+      "loss": 0.7521,
+      "step": 46
+    },
+    {
+      "epoch": 1.492063492063492,
+      "grad_norm": 0.6444355845451355,
+      "learning_rate": 5.8475246712804845e-06,
+      "loss": 0.74,
+      "step": 47
+    },
+    {
+      "epoch": 1.5238095238095237,
+      "grad_norm": 0.6790096163749695,
+      "learning_rate": 5.660448208208513e-06,
+      "loss": 0.7292,
+      "step": 48
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 0.6932204365730286,
+      "learning_rate": 5.472425659440157e-06,
+      "loss": 0.7254,
+      "step": 49
+    },
+    {
+      "epoch": 1.5873015873015874,
+      "grad_norm": 0.6378321647644043,
+      "learning_rate": 5.2837263654653715e-06,
+      "loss": 0.6899,
+      "step": 50
+    },
+    {
+      "epoch": 1.619047619047619,
+      "grad_norm": 0.6333246827125549,
+      "learning_rate": 5.094620636205096e-06,
+      "loss": 0.7594,
+      "step": 51
+    },
+    {
+      "epoch": 1.6507936507936507,
+      "grad_norm": 0.6145567297935486,
+      "learning_rate": 4.905379363794907e-06,
+      "loss": 0.7108,
+      "step": 52
+    },
+    {
+      "epoch": 1.6825396825396826,
+      "grad_norm": 0.6613467335700989,
+      "learning_rate": 4.71627363453463e-06,
+      "loss": 0.7786,
+      "step": 53
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.6900585889816284,
+      "learning_rate": 4.527574340559844e-06,
+      "loss": 0.736,
+      "step": 54
+    },
+    {
+      "epoch": 1.746031746031746,
+      "grad_norm": 0.6420705318450928,
+      "learning_rate": 4.33955179179149e-06,
+      "loss": 0.7039,
+      "step": 55
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.6300284266471863,
+      "learning_rate": 4.152475328719517e-06,
+      "loss": 0.7556,
+      "step": 56
+    },
+    {
+      "epoch": 1.8095238095238095,
+      "grad_norm": 0.6154489517211914,
+      "learning_rate": 3.966612936575235e-06,
+      "loss": 0.7253,
+      "step": 57
+    },
+    {
+      "epoch": 1.8412698412698414,
+      "grad_norm": 0.6132723689079285,
+      "learning_rate": 3.782230861445041e-06,
+      "loss": 0.727,
+      "step": 58
+    },
+    {
+      "epoch": 1.873015873015873,
+      "grad_norm": 0.5928071737289429,
+      "learning_rate": 3.5995932288754655e-06,
+      "loss": 0.7012,
+      "step": 59
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.6650770902633667,
+      "learning_rate": 3.4189616655158803e-06,
+      "loss": 0.7308,
+      "step": 60
+    },
+    {
+      "epoch": 1.9365079365079365,
+      "grad_norm": 0.6282082200050354,
+      "learning_rate": 3.240594924340835e-06,
+      "loss": 0.7106,
+      "step": 61
+    },
+    {
+      "epoch": 1.9682539682539684,
+      "grad_norm": 0.6715153455734253,
+      "learning_rate": 3.0647485139889145e-06,
+      "loss": 0.7345,
+      "step": 62
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.9630666971206665,
+      "learning_rate": 2.89167433274908e-06,
+      "loss": 1.0551,
+      "step": 63
+    },
+    {
+      "epoch": 2.0317460317460316,
+      "grad_norm": 0.650049090385437,
+      "learning_rate": 2.721620307718793e-06,
+      "loss": 0.6545,
+      "step": 64
+    },
+    {
+      "epoch": 2.0634920634920633,
+      "grad_norm": 0.6307027339935303,
+      "learning_rate": 2.554830039650834e-06,
+      "loss": 0.663,
+      "step": 65
+    },
+    {
+      "epoch": 2.0952380952380953,
+      "grad_norm": 0.6141909956932068,
+      "learning_rate": 2.391542453997578e-06,
+      "loss": 0.6517,
+      "step": 66
+    },
+    {
+      "epoch": 2.126984126984127,
+      "grad_norm": 0.5963830351829529,
+      "learning_rate": 2.2319914586525776e-06,
+      "loss": 0.6592,
+      "step": 67
+    },
+    {
+      "epoch": 2.1587301587301586,
+      "grad_norm": 0.5949491858482361,
+      "learning_rate": 2.0764056088797646e-06,
+      "loss": 0.6344,
+      "step": 68
+    },
+    {
+      "epoch": 2.1904761904761907,
+      "grad_norm": 0.556513249874115,
+      "learning_rate": 1.9250077799102323e-06,
+      "loss": 0.6435,
+      "step": 69
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.5953860282897949,
+      "learning_rate": 1.7780148476756148e-06,
+      "loss": 0.6441,
+      "step": 70
+    },
+    {
+      "epoch": 2.253968253968254,
+      "grad_norm": 0.5638564825057983,
+      "learning_rate": 1.6356373781354058e-06,
+      "loss": 0.6532,
+      "step": 71
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.5923030972480774,
+      "learning_rate": 1.4980793256432474e-06,
+      "loss": 0.6232,
+      "step": 72
+    },
+    {
+      "epoch": 2.317460317460317,
+      "grad_norm": 0.6088098883628845,
+      "learning_rate": 1.3655377407842813e-06,
+      "loss": 0.6458,
+      "step": 73
+    },
+    {
+      "epoch": 2.3492063492063493,
+      "grad_norm": 0.6067098379135132,
+      "learning_rate": 1.2382024881020937e-06,
+      "loss": 0.656,
+      "step": 74
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.5940206050872803,
+      "learning_rate": 1.1162559741195733e-06,
+      "loss": 0.645,
+      "step": 75
+    },
+    {
+      "epoch": 2.4126984126984126,
+      "grad_norm": 0.5515071153640747,
+      "learning_rate": 9.998728860433277e-07,
+      "loss": 0.6403,
+      "step": 76
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.5683124661445618,
+      "learning_rate": 8.892199415259501e-07,
+      "loss": 0.6259,
+      "step": 77
+    },
+    {
+      "epoch": 2.4761904761904763,
+      "grad_norm": 0.5827770829200745,
+      "learning_rate": 7.844556498445788e-07,
+      "loss": 0.6414,
+      "step": 78
+    },
+    {
+      "epoch": 2.507936507936508,
+      "grad_norm": 0.5769144296646118,
+      "learning_rate": 6.857300848378857e-07,
+      "loss": 0.6576,
+      "step": 79
+    },
+    {
+      "epoch": 2.5396825396825395,
+      "grad_norm": 0.5475329160690308,
+      "learning_rate": 5.931846699267558e-07,
+      "loss": 0.6407,
+      "step": 80
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.5876216292381287,
+      "learning_rate": 5.0695197552659e-07,
+      "loss": 0.6325,
+      "step": 81
+    },
+    {
+      "epoch": 2.6031746031746033,
+      "grad_norm": 0.604129433631897,
+      "learning_rate": 4.271555291414636e-07,
+      "loss": 0.6668,
+      "step": 82
+    },
+    {
+      "epoch": 2.634920634920635,
+      "grad_norm": 0.5568438172340393,
+      "learning_rate": 3.539096384121743e-07,
+      "loss": 0.6518,
+      "step": 83
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.587763249874115,
+      "learning_rate": 2.873192273716369e-07,
+      "loss": 0.6577,
+      "step": 84
+    },
+    {
+      "epoch": 2.6984126984126986,
+      "grad_norm": 0.5559731125831604,
+      "learning_rate": 2.274796861422246e-07,
+      "loss": 0.6275,
+      "step": 85
+    },
+    {
+      "epoch": 2.7301587301587302,
+      "grad_norm": 0.5531145930290222,
+      "learning_rate": 1.7447673429033361e-07,
+      "loss": 0.6482,
+      "step": 86
+    },
+    {
+      "epoch": 2.761904761904762,
+      "grad_norm": 0.5806328654289246,
+      "learning_rate": 1.2838629803393343e-07,
+      "loss": 0.6572,
+      "step": 87
+    },
+    {
+      "epoch": 2.7936507936507935,
+      "grad_norm": 0.5545519590377808,
+      "learning_rate": 8.927440147898703e-08,
+      "loss": 0.6501,
+      "step": 88
+    },
+    {
+      "epoch": 2.825396825396825,
+      "grad_norm": 0.5604863166809082,
+      "learning_rate": 5.7197072040557356e-08,
+      "loss": 0.6563,
+      "step": 89
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.5688309073448181,
+      "learning_rate": 3.220026018407541e-08,
+      "loss": 0.6311,
+      "step": 90
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 0.55904221534729,
+      "learning_rate": 1.431977360173975e-08,
+      "loss": 0.6382,
+      "step": 91
+    },
+    {
+      "epoch": 2.9206349206349205,
+      "grad_norm": 0.5599652528762817,
+      "learning_rate": 3.5812259183426457e-09,
+      "loss": 0.6362,
+      "step": 92
+    },
+    {
+      "epoch": 2.9523809523809526,
+      "grad_norm": 0.5760123133659363,
+      "learning_rate": 0.0,
+      "loss": 0.6504,
+      "step": 93
+    },
+    {
+      "epoch": 2.9523809523809526,
+      "step": 93,
+      "total_flos": 4.414815291519795e+16,
+      "train_loss": 0.7942085708341291,
+      "train_runtime": 1549.0803,
+      "train_samples_per_second": 5.81,
+      "train_steps_per_second": 0.06
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 93,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.414815291519795e+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 sha256:056c4d7c9973f0692bfe6acb66f39dce6bed422b52149aa0f1560159c041777e
+size 7608