Upload model

.gitattributes

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

README.md

@@ -0,0 +1,60 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: meta_chat_reasoning_75_25_system_100k
+  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. -->
+
+# meta_chat_reasoning_75_25_system_100k
+
+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/meta_chat_reasoning_75_25_system_100k 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: 8e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 512
+- total_train_batch_size: 512
+- total_eval_batch_size: 4096
+- 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: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.6.0+cu124
+- Datasets 3.1.0
+- 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": 5.0,
+    "total_flos": 2180898493562880.0,
+    "train_loss": 0.4967416850420145,
+    "train_runtime": 5886.6032,
+    "train_samples_per_second": 11.151,
+    "train_steps_per_second": 0.022
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/leonardo_work/EUHPC_E03_068/DCFT_shared/hub/models--Qwen--Qwen2.5-7B-Instruct/snapshots/a09a35458c702b33eeacc393d103063234e8bc28",
+  "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:d1c7cb4f332018861ae7bbc643b7875c0a07a415bdc4c26c12c790fe6ff1ae58
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e124b0bb72e94f7e839bfc29fa2c791ae486f1af1c1f7e949b0942de8527e6a
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92e8e7c3e5aa536b553c83a76de1ad7f75d91fd5788559e053117efeb35cfbfe
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:835c9ba2ea4671803dde767723d50002aaf7e6a4d906175c43b07ef0581536d7
+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
+  }
+}

start_end.json

@@ -0,0 +1 @@
+{"start_time": "2025-04-30 22:46:23", "end_time": "2025-05-01 00:26:18"}

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": 5.0,
+    "total_flos": 2180898493562880.0,
+    "train_loss": 0.4967416850420145,
+    "train_runtime": 5886.6032,
+    "train_samples_per_second": 11.151,
+    "train_steps_per_second": 0.022
+}

trainer_log.jsonl

@@ -0,0 +1,131 @@
+{"current_steps": 1, "total_steps": 130, "loss": 0.8846, "lr": 6.153846153846155e-06, "epoch": 0.038461538461538464, "percentage": 0.77, "elapsed_time": "0:48:58", "remaining_time": "4 days, 9:16:43"}
+{"current_steps": 2, "total_steps": 130, "loss": 0.9166, "lr": 1.230769230769231e-05, "epoch": 0.07692307692307693, "percentage": 1.54, "elapsed_time": "0:57:26", "remaining_time": "2 days, 13:16:07"}
+{"current_steps": 3, "total_steps": 130, "loss": 0.8465, "lr": 1.8461538461538465e-05, "epoch": 0.11538461538461539, "percentage": 2.31, "elapsed_time": "0:58:24", "remaining_time": "1 day, 17:12:45"}
+{"current_steps": 4, "total_steps": 130, "loss": 0.822, "lr": 2.461538461538462e-05, "epoch": 0.15384615384615385, "percentage": 3.08, "elapsed_time": "0:59:16", "remaining_time": "1 day, 7:07:08"}
+{"current_steps": 5, "total_steps": 130, "loss": 0.815, "lr": 3.0769230769230774e-05, "epoch": 0.19230769230769232, "percentage": 3.85, "elapsed_time": "1:00:15", "remaining_time": "1 day, 1:06:29"}
+{"current_steps": 6, "total_steps": 130, "loss": 0.7895, "lr": 3.692307692307693e-05, "epoch": 0.23076923076923078, "percentage": 4.62, "elapsed_time": "1:01:10", "remaining_time": "21:04:25"}
+{"current_steps": 7, "total_steps": 130, "loss": 0.7446, "lr": 4.307692307692308e-05, "epoch": 0.2692307692307692, "percentage": 5.38, "elapsed_time": "1:01:23", "remaining_time": "17:58:50"}
+{"current_steps": 8, "total_steps": 130, "loss": 0.7037, "lr": 4.923076923076924e-05, "epoch": 0.3076923076923077, "percentage": 6.15, "elapsed_time": "1:01:36", "remaining_time": "15:39:38"}
+{"current_steps": 9, "total_steps": 130, "loss": 0.6895, "lr": 5.538461538461539e-05, "epoch": 0.34615384615384615, "percentage": 6.92, "elapsed_time": "1:01:50", "remaining_time": "13:51:20"}
+{"current_steps": 10, "total_steps": 130, "loss": 0.6774, "lr": 6.153846153846155e-05, "epoch": 0.38461538461538464, "percentage": 7.69, "elapsed_time": "1:02:03", "remaining_time": "12:24:42"}
+{"current_steps": 11, "total_steps": 130, "loss": 0.6652, "lr": 6.76923076923077e-05, "epoch": 0.4230769230769231, "percentage": 8.46, "elapsed_time": "1:02:16", "remaining_time": "11:13:43"}
+{"current_steps": 12, "total_steps": 130, "loss": 0.6615, "lr": 7.384615384615386e-05, "epoch": 0.46153846153846156, "percentage": 9.23, "elapsed_time": "1:02:29", "remaining_time": "10:14:34"}
+{"current_steps": 13, "total_steps": 130, "loss": 0.6622, "lr": 8e-05, "epoch": 0.5, "percentage": 10.0, "elapsed_time": "1:02:42", "remaining_time": "9:24:26"}
+{"current_steps": 14, "total_steps": 130, "loss": 0.639, "lr": 7.998558110683542e-05, "epoch": 0.5384615384615384, "percentage": 10.77, "elapsed_time": "1:03:29", "remaining_time": "8:46:07"}
+{"current_steps": 15, "total_steps": 130, "loss": 0.6532, "lr": 7.994233482256567e-05, "epoch": 0.5769230769230769, "percentage": 11.54, "elapsed_time": "1:03:43", "remaining_time": "8:08:31"}
+{"current_steps": 16, "total_steps": 130, "loss": 0.6315, "lr": 7.987029232536841e-05, "epoch": 0.6153846153846154, "percentage": 12.31, "elapsed_time": "1:03:57", "remaining_time": "7:35:41"}
+{"current_steps": 17, "total_steps": 130, "loss": 0.6489, "lr": 7.976950555389713e-05, "epoch": 0.6538461538461539, "percentage": 13.08, "elapsed_time": "1:04:10", "remaining_time": "7:06:37"}
+{"current_steps": 18, "total_steps": 130, "loss": 0.6411, "lr": 7.964004716983635e-05, "epoch": 0.6923076923076923, "percentage": 13.85, "elapsed_time": "1:04:24", "remaining_time": "6:40:46"}
+{"current_steps": 19, "total_steps": 130, "loss": 0.6203, "lr": 7.948201050551651e-05, "epoch": 0.7307692307692307, "percentage": 14.62, "elapsed_time": "1:04:38", "remaining_time": "6:17:37"}
+{"current_steps": 20, "total_steps": 130, "loss": 0.6131, "lr": 7.929550949662659e-05, "epoch": 0.7692307692307693, "percentage": 15.38, "elapsed_time": "1:04:52", "remaining_time": "5:56:48"}
+{"current_steps": 21, "total_steps": 130, "loss": 0.6114, "lr": 7.908067860007268e-05, "epoch": 0.8076923076923077, "percentage": 16.15, "elapsed_time": "1:05:06", "remaining_time": "5:37:54"}
+{"current_steps": 22, "total_steps": 130, "loss": 0.6072, "lr": 7.883767269704209e-05, "epoch": 0.8461538461538461, "percentage": 16.92, "elapsed_time": "1:05:19", "remaining_time": "5:20:40"}
+{"current_steps": 23, "total_steps": 130, "loss": 0.6592, "lr": 7.85666669813425e-05, "epoch": 0.8846153846153846, "percentage": 17.69, "elapsed_time": "1:05:33", "remaining_time": "5:04:58"}
+{"current_steps": 24, "total_steps": 130, "loss": 0.7024, "lr": 7.826785683309702e-05, "epoch": 0.9230769230769231, "percentage": 18.46, "elapsed_time": "1:05:46", "remaining_time": "4:50:30"}
+{"current_steps": 25, "total_steps": 130, "loss": 0.6472, "lr": 7.794145767788582e-05, "epoch": 0.9615384615384616, "percentage": 19.23, "elapsed_time": "1:05:59", "remaining_time": "4:37:11"}
+{"current_steps": 26, "total_steps": 130, "loss": 0.6101, "lr": 7.758770483143634e-05, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "1:06:13", "remaining_time": "4:24:54"}
+{"current_steps": 27, "total_steps": 130, "loss": 0.5858, "lr": 7.720685332997354e-05, "epoch": 1.0384615384615385, "percentage": 20.77, "elapsed_time": "1:07:13", "remaining_time": "4:16:26"}
+{"current_steps": 28, "total_steps": 130, "loss": 0.5946, "lr": 7.679917774635298e-05, "epoch": 1.0769230769230769, "percentage": 21.54, "elapsed_time": "1:07:27", "remaining_time": "4:05:43"}
+{"current_steps": 29, "total_steps": 130, "loss": 0.5729, "lr": 7.636497199210895e-05, "epoch": 1.1153846153846154, "percentage": 22.31, "elapsed_time": "1:07:40", "remaining_time": "3:55:42"}
+{"current_steps": 30, "total_steps": 130, "loss": 0.5639, "lr": 7.590454910556058e-05, "epoch": 1.1538461538461537, "percentage": 23.08, "elapsed_time": "1:07:54", "remaining_time": "3:46:21"}
+{"current_steps": 31, "total_steps": 130, "loss": 0.5644, "lr": 7.541824102612839e-05, "epoch": 1.1923076923076923, "percentage": 23.85, "elapsed_time": "1:08:07", "remaining_time": "3:37:34"}
+{"current_steps": 32, "total_steps": 130, "loss": 0.5588, "lr": 7.490639835502458e-05, "epoch": 1.2307692307692308, "percentage": 24.62, "elapsed_time": "1:08:20", "remaining_time": "3:29:18"}
+{"current_steps": 33, "total_steps": 130, "loss": 0.5441, "lr": 7.436939010248868e-05, "epoch": 1.2692307692307692, "percentage": 25.38, "elapsed_time": "1:08:34", "remaining_time": "3:21:35"}
+{"current_steps": 34, "total_steps": 130, "loss": 0.5531, "lr": 7.38076034217518e-05, "epoch": 1.3076923076923077, "percentage": 26.15, "elapsed_time": "1:08:48", "remaining_time": "3:14:16"}
+{"current_steps": 35, "total_steps": 130, "loss": 0.5536, "lr": 7.322144332992047e-05, "epoch": 1.3461538461538463, "percentage": 26.92, "elapsed_time": "1:09:02", "remaining_time": "3:07:23"}
+{"current_steps": 36, "total_steps": 130, "loss": 0.5593, "lr": 7.261133241598177e-05, "epoch": 1.3846153846153846, "percentage": 27.69, "elapsed_time": "1:09:15", "remaining_time": "3:00:49"}
+{"current_steps": 37, "total_steps": 130, "loss": 0.5499, "lr": 7.197771053614006e-05, "epoch": 1.4230769230769231, "percentage": 28.46, "elapsed_time": "1:09:28", "remaining_time": "2:54:37"}
+{"current_steps": 38, "total_steps": 130, "loss": 0.5419, "lr": 7.13210344967049e-05, "epoch": 1.4615384615384617, "percentage": 29.23, "elapsed_time": "1:09:41", "remaining_time": "2:48:44"}
+{"current_steps": 39, "total_steps": 130, "loss": 0.5339, "lr": 7.064177772475912e-05, "epoch": 1.5, "percentage": 30.0, "elapsed_time": "1:09:54", "remaining_time": "2:43:06"}
+{"current_steps": 40, "total_steps": 130, "loss": 0.527, "lr": 6.994042992684406e-05, "epoch": 1.5384615384615383, "percentage": 30.77, "elapsed_time": "1:10:06", "remaining_time": "2:37:45"}
+{"current_steps": 41, "total_steps": 130, "loss": 0.5261, "lr": 6.921749673590813e-05, "epoch": 1.5769230769230769, "percentage": 31.54, "elapsed_time": "1:10:19", "remaining_time": "2:32:39"}
+{"current_steps": 42, "total_steps": 130, "loss": 0.5374, "lr": 6.847349934677363e-05, "epoch": 1.6153846153846154, "percentage": 32.31, "elapsed_time": "1:10:32", "remaining_time": "2:27:48"}
+{"current_steps": 43, "total_steps": 130, "loss": 0.5247, "lr": 6.770897414038398e-05, "epoch": 1.6538461538461537, "percentage": 33.08, "elapsed_time": "1:10:46", "remaining_time": "2:23:10"}
+{"current_steps": 44, "total_steps": 130, "loss": 0.521, "lr": 6.69244722971028e-05, "epoch": 1.6923076923076923, "percentage": 33.85, "elapsed_time": "1:10:59", "remaining_time": "2:18:45"}
+{"current_steps": 45, "total_steps": 130, "loss": 0.5124, "lr": 6.61205593993434e-05, "epoch": 1.7307692307692308, "percentage": 34.62, "elapsed_time": "1:11:12", "remaining_time": "2:14:30"}
+{"current_steps": 46, "total_steps": 130, "loss": 0.5237, "lr": 6.529781502381509e-05, "epoch": 1.7692307692307692, "percentage": 35.38, "elapsed_time": "1:11:25", "remaining_time": "2:10:26"}
+{"current_steps": 47, "total_steps": 130, "loss": 0.5083, "lr": 6.44568323236805e-05, "epoch": 1.8076923076923077, "percentage": 36.15, "elapsed_time": "1:11:38", "remaining_time": "2:06:31"}
+{"current_steps": 48, "total_steps": 130, "loss": 0.5125, "lr": 6.359821760092493e-05, "epoch": 1.8461538461538463, "percentage": 36.92, "elapsed_time": "1:11:52", "remaining_time": "2:02:47"}
+{"current_steps": 49, "total_steps": 130, "loss": 0.5228, "lr": 6.272258986924624e-05, "epoch": 1.8846153846153846, "percentage": 37.69, "elapsed_time": "1:12:06", "remaining_time": "1:59:11"}
+{"current_steps": 50, "total_steps": 130, "loss": 0.5133, "lr": 6.183058040778018e-05, "epoch": 1.9230769230769231, "percentage": 38.46, "elapsed_time": "1:12:20", "remaining_time": "1:55:44"}
+{"current_steps": 51, "total_steps": 130, "loss": 0.5203, "lr": 6.092283230598311e-05, "epoch": 1.9615384615384617, "percentage": 39.23, "elapsed_time": "1:12:33", "remaining_time": "1:52:24"}
+{"current_steps": 52, "total_steps": 130, "loss": 0.4988, "lr": 6.000000000000001e-05, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "1:12:47", "remaining_time": "1:49:11"}
+{"current_steps": 53, "total_steps": 130, "loss": 0.4568, "lr": 5.9062748800852315e-05, "epoch": 2.0384615384615383, "percentage": 40.77, "elapsed_time": "1:13:50", "remaining_time": "1:47:16"}
+{"current_steps": 54, "total_steps": 130, "loss": 0.4675, "lr": 5.8111754414785504e-05, "epoch": 2.076923076923077, "percentage": 41.54, "elapsed_time": "1:14:03", "remaining_time": "1:44:14"}
+{"current_steps": 55, "total_steps": 130, "loss": 0.4636, "lr": 5.714770245612217e-05, "epoch": 2.1153846153846154, "percentage": 42.31, "elapsed_time": "1:14:17", "remaining_time": "1:41:18"}
+{"current_steps": 56, "total_steps": 130, "loss": 0.467, "lr": 5.61712879529722e-05, "epoch": 2.1538461538461537, "percentage": 43.08, "elapsed_time": "1:14:33", "remaining_time": "1:38:31"}
+{"current_steps": 57, "total_steps": 130, "loss": 0.4668, "lr": 5.5183214846155864e-05, "epoch": 2.1923076923076925, "percentage": 43.85, "elapsed_time": "1:14:46", "remaining_time": "1:35:46"}
+{"current_steps": 58, "total_steps": 130, "loss": 0.4574, "lr": 5.4184195481701425e-05, "epoch": 2.230769230769231, "percentage": 44.62, "elapsed_time": "1:15:02", "remaining_time": "1:33:08"}
+{"current_steps": 59, "total_steps": 130, "loss": 0.4591, "lr": 5.317495009728319e-05, "epoch": 2.269230769230769, "percentage": 45.38, "elapsed_time": "1:15:20", "remaining_time": "1:30:39"}
+{"current_steps": 60, "total_steps": 130, "loss": 0.4739, "lr": 5.215620630296988e-05, "epoch": 2.3076923076923075, "percentage": 46.15, "elapsed_time": "1:15:36", "remaining_time": "1:28:12"}
+{"current_steps": 61, "total_steps": 130, "loss": 0.4548, "lr": 5.112869855665811e-05, "epoch": 2.3461538461538463, "percentage": 46.92, "elapsed_time": "1:15:54", "remaining_time": "1:25:51"}
+{"current_steps": 62, "total_steps": 130, "loss": 0.4584, "lr": 5.0093167634568874e-05, "epoch": 2.3846153846153846, "percentage": 47.69, "elapsed_time": "1:16:12", "remaining_time": "1:23:35"}
+{"current_steps": 63, "total_steps": 130, "loss": 0.4633, "lr": 4.9050360097188904e-05, "epoch": 2.423076923076923, "percentage": 48.46, "elapsed_time": "1:16:30", "remaining_time": "1:21:22"}
+{"current_steps": 64, "total_steps": 130, "loss": 0.4624, "lr": 4.8001027751041784e-05, "epoch": 2.4615384615384617, "percentage": 49.23, "elapsed_time": "1:16:48", "remaining_time": "1:19:12"}
+{"current_steps": 65, "total_steps": 130, "loss": 0.4492, "lr": 4.694592710667723e-05, "epoch": 2.5, "percentage": 50.0, "elapsed_time": "1:17:05", "remaining_time": "1:17:05"}
+{"current_steps": 66, "total_steps": 130, "loss": 0.4573, "lr": 4.588581883326865e-05, "epoch": 2.5384615384615383, "percentage": 50.77, "elapsed_time": "1:17:20", "remaining_time": "1:14:59"}
+{"current_steps": 67, "total_steps": 130, "loss": 0.4404, "lr": 4.4821467210212924e-05, "epoch": 2.5769230769230766, "percentage": 51.54, "elapsed_time": "1:17:39", "remaining_time": "1:13:00"}
+{"current_steps": 68, "total_steps": 130, "loss": 0.4561, "lr": 4.375363957612717e-05, "epoch": 2.6153846153846154, "percentage": 52.31, "elapsed_time": "1:17:54", "remaining_time": "1:11:02"}
+{"current_steps": 69, "total_steps": 130, "loss": 0.4504, "lr": 4.2683105775640096e-05, "epoch": 2.6538461538461537, "percentage": 53.08, "elapsed_time": "1:18:13", "remaining_time": "1:09:09"}
+{"current_steps": 70, "total_steps": 130, "loss": 0.4469, "lr": 4.1610637604376614e-05, "epoch": 2.6923076923076925, "percentage": 53.85, "elapsed_time": "1:18:30", "remaining_time": "1:07:17"}
+{"current_steps": 71, "total_steps": 130, "loss": 0.4515, "lr": 4.0537008252535904e-05, "epoch": 2.730769230769231, "percentage": 54.62, "elapsed_time": "1:18:46", "remaining_time": "1:05:27"}
+{"current_steps": 72, "total_steps": 130, "loss": 0.4461, "lr": 3.946299174746411e-05, "epoch": 2.769230769230769, "percentage": 55.38, "elapsed_time": "1:19:04", "remaining_time": "1:03:42"}
+{"current_steps": 73, "total_steps": 130, "loss": 0.4519, "lr": 3.8389362395623406e-05, "epoch": 2.8076923076923075, "percentage": 56.15, "elapsed_time": "1:19:21", "remaining_time": "1:01:58"}
+{"current_steps": 74, "total_steps": 130, "loss": 0.4496, "lr": 3.7316894224359904e-05, "epoch": 2.8461538461538463, "percentage": 56.92, "elapsed_time": "1:19:37", "remaining_time": "1:00:15"}
+{"current_steps": 75, "total_steps": 130, "loss": 0.461, "lr": 3.6246360423872834e-05, "epoch": 2.8846153846153846, "percentage": 57.69, "elapsed_time": "1:19:54", "remaining_time": "0:58:36"}
+{"current_steps": 76, "total_steps": 130, "loss": 0.4465, "lr": 3.517853278978708e-05, "epoch": 2.9230769230769234, "percentage": 58.46, "elapsed_time": "1:20:11", "remaining_time": "0:56:59"}
+{"current_steps": 77, "total_steps": 130, "loss": 0.4502, "lr": 3.4114181166731355e-05, "epoch": 2.9615384615384617, "percentage": 59.23, "elapsed_time": "1:20:29", "remaining_time": "0:55:23"}
+{"current_steps": 78, "total_steps": 130, "loss": 0.4325, "lr": 3.305407289332279e-05, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "1:20:44", "remaining_time": "0:53:49"}
+{"current_steps": 79, "total_steps": 130, "loss": 0.4271, "lr": 3.199897224895823e-05, "epoch": 3.0384615384615383, "percentage": 60.77, "elapsed_time": "1:21:49", "remaining_time": "0:52:49"}
+{"current_steps": 80, "total_steps": 130, "loss": 0.4124, "lr": 3.094963990281112e-05, "epoch": 3.076923076923077, "percentage": 61.54, "elapsed_time": "1:22:03", "remaining_time": "0:51:17"}
+{"current_steps": 81, "total_steps": 130, "loss": 0.3998, "lr": 2.9906832365431132e-05, "epoch": 3.1153846153846154, "percentage": 62.31, "elapsed_time": "1:22:17", "remaining_time": "0:49:46"}
+{"current_steps": 82, "total_steps": 130, "loss": 0.4, "lr": 2.88713014433419e-05, "epoch": 3.1538461538461537, "percentage": 63.08, "elapsed_time": "1:22:31", "remaining_time": "0:48:18"}
+{"current_steps": 83, "total_steps": 130, "loss": 0.4031, "lr": 2.7843793697030128e-05, "epoch": 3.1923076923076925, "percentage": 63.85, "elapsed_time": "1:22:45", "remaining_time": "0:46:51"}
+{"current_steps": 84, "total_steps": 130, "loss": 0.4138, "lr": 2.682504990271682e-05, "epoch": 3.230769230769231, "percentage": 64.62, "elapsed_time": "1:22:59", "remaining_time": "0:45:26"}
+{"current_steps": 85, "total_steps": 130, "loss": 0.415, "lr": 2.5815804518298575e-05, "epoch": 3.269230769230769, "percentage": 65.38, "elapsed_time": "1:23:13", "remaining_time": "0:44:03"}
+{"current_steps": 86, "total_steps": 130, "loss": 0.4029, "lr": 2.481678515384415e-05, "epoch": 3.3076923076923075, "percentage": 66.15, "elapsed_time": "1:23:27", "remaining_time": "0:42:42"}
+{"current_steps": 87, "total_steps": 130, "loss": 0.4137, "lr": 2.382871204702781e-05, "epoch": 3.3461538461538463, "percentage": 66.92, "elapsed_time": "1:23:41", "remaining_time": "0:41:21"}
+{"current_steps": 88, "total_steps": 130, "loss": 0.3986, "lr": 2.285229754387783e-05, "epoch": 3.3846153846153846, "percentage": 67.69, "elapsed_time": "1:23:56", "remaining_time": "0:40:03"}
+{"current_steps": 89, "total_steps": 130, "loss": 0.417, "lr": 2.188824558521452e-05, "epoch": 3.423076923076923, "percentage": 68.46, "elapsed_time": "1:24:10", "remaining_time": "0:38:46"}
+{"current_steps": 90, "total_steps": 130, "loss": 0.3993, "lr": 2.0937251199147684e-05, "epoch": 3.4615384615384617, "percentage": 69.23, "elapsed_time": "1:24:24", "remaining_time": "0:37:30"}
+{"current_steps": 91, "total_steps": 130, "loss": 0.4128, "lr": 2.0000000000000012e-05, "epoch": 3.5, "percentage": 70.0, "elapsed_time": "1:24:38", "remaining_time": "0:36:16"}
+{"current_steps": 92, "total_steps": 130, "loss": 0.4085, "lr": 1.9077167694016903e-05, "epoch": 3.5384615384615383, "percentage": 70.77, "elapsed_time": "1:24:54", "remaining_time": "0:35:04"}
+{"current_steps": 93, "total_steps": 130, "loss": 0.4021, "lr": 1.8169419592219813e-05, "epoch": 3.5769230769230766, "percentage": 71.54, "elapsed_time": "1:25:12", "remaining_time": "0:33:54"}
+{"current_steps": 94, "total_steps": 130, "loss": 0.4043, "lr": 1.7277410130753775e-05, "epoch": 3.6153846153846154, "percentage": 72.31, "elapsed_time": "1:25:28", "remaining_time": "0:32:44"}
+{"current_steps": 95, "total_steps": 130, "loss": 0.3965, "lr": 1.6401782399075098e-05, "epoch": 3.6538461538461537, "percentage": 73.08, "elapsed_time": "1:25:46", "remaining_time": "0:31:36"}
+{"current_steps": 96, "total_steps": 130, "loss": 0.4071, "lr": 1.554316767631951e-05, "epoch": 3.6923076923076925, "percentage": 73.85, "elapsed_time": "1:26:01", "remaining_time": "0:30:28"}
+{"current_steps": 97, "total_steps": 130, "loss": 0.4041, "lr": 1.4702184976184915e-05, "epoch": 3.730769230769231, "percentage": 74.62, "elapsed_time": "1:26:19", "remaining_time": "0:29:22"}
+{"current_steps": 98, "total_steps": 130, "loss": 0.4135, "lr": 1.3879440600656607e-05, "epoch": 3.769230769230769, "percentage": 75.38, "elapsed_time": "1:26:35", "remaining_time": "0:28:16"}
+{"current_steps": 99, "total_steps": 130, "loss": 0.3931, "lr": 1.3075527702897185e-05, "epoch": 3.8076923076923075, "percentage": 76.15, "elapsed_time": "1:26:53", "remaining_time": "0:27:12"}
+{"current_steps": 100, "total_steps": 130, "loss": 0.4109, "lr": 1.2291025859616026e-05, "epoch": 3.8461538461538463, "percentage": 76.92, "elapsed_time": "1:27:07", "remaining_time": "0:26:08"}
+{"current_steps": 101, "total_steps": 130, "loss": 0.402, "lr": 1.1526500653226385e-05, "epoch": 3.8846153846153846, "percentage": 77.69, "elapsed_time": "1:27:25", "remaining_time": "0:25:06"}
+{"current_steps": 102, "total_steps": 130, "loss": 0.3985, "lr": 1.078250326409188e-05, "epoch": 3.9230769230769234, "percentage": 78.46, "elapsed_time": "1:27:42", "remaining_time": "0:24:04"}
+{"current_steps": 103, "total_steps": 130, "loss": 0.4119, "lr": 1.0059570073155953e-05, "epoch": 3.9615384615384617, "percentage": 79.23, "elapsed_time": "1:27:59", "remaining_time": "0:23:04"}
+{"current_steps": 104, "total_steps": 130, "loss": 0.4036, "lr": 9.358222275240884e-06, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "1:28:18", "remaining_time": "0:22:04"}
+{"current_steps": 105, "total_steps": 130, "loss": 0.3828, "lr": 8.678965503295114e-06, "epoch": 4.038461538461538, "percentage": 80.77, "elapsed_time": "1:29:26", "remaining_time": "0:21:17"}
+{"current_steps": 106, "total_steps": 130, "loss": 0.3832, "lr": 8.022289463859963e-06, "epoch": 4.076923076923077, "percentage": 81.54, "elapsed_time": "1:29:43", "remaining_time": "0:20:18"}
+{"current_steps": 107, "total_steps": 130, "loss": 0.3859, "lr": 7.38866758401823e-06, "epoch": 4.115384615384615, "percentage": 82.31, "elapsed_time": "1:30:00", "remaining_time": "0:19:20"}
+{"current_steps": 108, "total_steps": 130, "loss": 0.4004, "lr": 6.778556670079535e-06, "epoch": 4.153846153846154, "percentage": 83.08, "elapsed_time": "1:30:16", "remaining_time": "0:18:23"}
+{"current_steps": 109, "total_steps": 130, "loss": 0.3864, "lr": 6.1923965782482165e-06, "epoch": 4.1923076923076925, "percentage": 83.85, "elapsed_time": "1:30:32", "remaining_time": "0:17:26"}
+{"current_steps": 110, "total_steps": 130, "loss": 0.3876, "lr": 5.630609897511328e-06, "epoch": 4.230769230769231, "percentage": 84.62, "elapsed_time": "1:30:49", "remaining_time": "0:16:30"}
+{"current_steps": 111, "total_steps": 130, "loss": 0.3821, "lr": 5.093601644975428e-06, "epoch": 4.269230769230769, "percentage": 85.38, "elapsed_time": "1:31:06", "remaining_time": "0:15:35"}
+{"current_steps": 112, "total_steps": 130, "loss": 0.3843, "lr": 4.581758973871609e-06, "epoch": 4.3076923076923075, "percentage": 86.15, "elapsed_time": "1:31:23", "remaining_time": "0:14:41"}
+{"current_steps": 113, "total_steps": 130, "loss": 0.3714, "lr": 4.0954508944394474e-06, "epoch": 4.346153846153846, "percentage": 86.92, "elapsed_time": "1:31:38", "remaining_time": "0:13:47"}
+{"current_steps": 114, "total_steps": 130, "loss": 0.391, "lr": 3.635028007891048e-06, "epoch": 4.384615384615385, "percentage": 87.69, "elapsed_time": "1:31:52", "remaining_time": "0:12:53"}
+{"current_steps": 115, "total_steps": 130, "loss": 0.389, "lr": 3.200822253647031e-06, "epoch": 4.423076923076923, "percentage": 88.46, "elapsed_time": "1:32:06", "remaining_time": "0:12:00"}
+{"current_steps": 116, "total_steps": 130, "loss": 0.3855, "lr": 2.793146670026472e-06, "epoch": 4.461538461538462, "percentage": 89.23, "elapsed_time": "1:32:20", "remaining_time": "0:11:08"}
+{"current_steps": 117, "total_steps": 130, "loss": 0.3733, "lr": 2.4122951685636674e-06, "epoch": 4.5, "percentage": 90.0, "elapsed_time": "1:33:20", "remaining_time": "0:10:22"}
+{"current_steps": 118, "total_steps": 130, "loss": 0.3821, "lr": 2.0585423221141807e-06, "epoch": 4.538461538461538, "percentage": 90.77, "elapsed_time": "1:33:34", "remaining_time": "0:09:30"}
+{"current_steps": 119, "total_steps": 130, "loss": 0.381, "lr": 1.7321431669029953e-06, "epoch": 4.576923076923077, "percentage": 91.54, "elapsed_time": "1:33:49", "remaining_time": "0:08:40"}
+{"current_steps": 120, "total_steps": 130, "loss": 0.3904, "lr": 1.4333330186575079e-06, "epoch": 4.615384615384615, "percentage": 92.31, "elapsed_time": "1:34:03", "remaining_time": "0:07:50"}
+{"current_steps": 121, "total_steps": 130, "loss": 0.3792, "lr": 1.1623273029579195e-06, "epoch": 4.653846153846154, "percentage": 93.08, "elapsed_time": "1:34:16", "remaining_time": "0:07:00"}
+{"current_steps": 122, "total_steps": 130, "loss": 0.3797, "lr": 9.193213999273199e-07, "epoch": 4.6923076923076925, "percentage": 93.85, "elapsed_time": "1:34:32", "remaining_time": "0:06:11"}
+{"current_steps": 123, "total_steps": 130, "loss": 0.377, "lr": 7.044905033734096e-07, "epoch": 4.730769230769231, "percentage": 94.62, "elapsed_time": "1:34:47", "remaining_time": "0:05:23"}
+{"current_steps": 124, "total_steps": 130, "loss": 0.383, "lr": 5.179894944834863e-07, "epoch": 4.769230769230769, "percentage": 95.38, "elapsed_time": "1:35:04", "remaining_time": "0:04:36"}
+{"current_steps": 125, "total_steps": 130, "loss": 0.3897, "lr": 3.599528301636612e-07, "epoch": 4.8076923076923075, "percentage": 96.15, "elapsed_time": "1:35:21", "remaining_time": "0:03:48"}
+{"current_steps": 126, "total_steps": 130, "loss": 0.378, "lr": 2.3049444610288462e-07, "epoch": 4.846153846153846, "percentage": 96.92, "elapsed_time": "1:35:40", "remaining_time": "0:03:02"}
+{"current_steps": 127, "total_steps": 130, "loss": 0.3866, "lr": 1.2970767463160284e-07, "epoch": 4.884615384615385, "percentage": 97.69, "elapsed_time": "1:35:55", "remaining_time": "0:02:15"}
+{"current_steps": 128, "total_steps": 130, "loss": 0.3876, "lr": 5.766517743432953e-08, "epoch": 4.923076923076923, "percentage": 98.46, "elapsed_time": "1:36:13", "remaining_time": "0:01:30"}
+{"current_steps": 129, "total_steps": 130, "loss": 0.3813, "lr": 1.4418893164585002e-08, "epoch": 4.961538461538462, "percentage": 99.23, "elapsed_time": "1:36:29", "remaining_time": "0:00:44"}
+{"current_steps": 130, "total_steps": 130, "loss": 0.3787, "lr": 0.0, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:36:46", "remaining_time": "0:00:00"}
+{"current_steps": 130, "total_steps": 130, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:37:58", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,952 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 130,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.038461538461538464,
+      "grad_norm": 4.763484488171998,
+      "learning_rate": 6.153846153846155e-06,
+      "loss": 0.8846,
+      "step": 1
+    },
+    {
+      "epoch": 0.07692307692307693,
+      "grad_norm": 4.8435158376792495,
+      "learning_rate": 1.230769230769231e-05,
+      "loss": 0.9166,
+      "step": 2
+    },
+    {
+      "epoch": 0.11538461538461539,
+      "grad_norm": 3.4157492863415784,
+      "learning_rate": 1.8461538461538465e-05,
+      "loss": 0.8465,
+      "step": 3
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 3.558732918782158,
+      "learning_rate": 2.461538461538462e-05,
+      "loss": 0.822,
+      "step": 4
+    },
+    {
+      "epoch": 0.19230769230769232,
+      "grad_norm": 4.108731132280649,
+      "learning_rate": 3.0769230769230774e-05,
+      "loss": 0.815,
+      "step": 5
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 3.052794049198824,
+      "learning_rate": 3.692307692307693e-05,
+      "loss": 0.7895,
+      "step": 6
+    },
+    {
+      "epoch": 0.2692307692307692,
+      "grad_norm": 2.709016644304453,
+      "learning_rate": 4.307692307692308e-05,
+      "loss": 0.7446,
+      "step": 7
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 1.6799311029831894,
+      "learning_rate": 4.923076923076924e-05,
+      "loss": 0.7037,
+      "step": 8
+    },
+    {
+      "epoch": 0.34615384615384615,
+      "grad_norm": 1.7624659211089349,
+      "learning_rate": 5.538461538461539e-05,
+      "loss": 0.6895,
+      "step": 9
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 2.342839042004691,
+      "learning_rate": 6.153846153846155e-05,
+      "loss": 0.6774,
+      "step": 10
+    },
+    {
+      "epoch": 0.4230769230769231,
+      "grad_norm": 2.086123624512103,
+      "learning_rate": 6.76923076923077e-05,
+      "loss": 0.6652,
+      "step": 11
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 1.847042821202323,
+      "learning_rate": 7.384615384615386e-05,
+      "loss": 0.6615,
+      "step": 12
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.104958536006521,
+      "learning_rate": 8e-05,
+      "loss": 0.6622,
+      "step": 13
+    },
+    {
+      "epoch": 0.5384615384615384,
+      "grad_norm": 1.5248735737766572,
+      "learning_rate": 7.998558110683542e-05,
+      "loss": 0.639,
+      "step": 14
+    },
+    {
+      "epoch": 0.5769230769230769,
+      "grad_norm": 2.943708656023143,
+      "learning_rate": 7.994233482256567e-05,
+      "loss": 0.6532,
+      "step": 15
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 1.2635799952200861,
+      "learning_rate": 7.987029232536841e-05,
+      "loss": 0.6315,
+      "step": 16
+    },
+    {
+      "epoch": 0.6538461538461539,
+      "grad_norm": 2.9152980345772903,
+      "learning_rate": 7.976950555389713e-05,
+      "loss": 0.6489,
+      "step": 17
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 2.140419699121764,
+      "learning_rate": 7.964004716983635e-05,
+      "loss": 0.6411,
+      "step": 18
+    },
+    {
+      "epoch": 0.7307692307692307,
+      "grad_norm": 1.5682849671276975,
+      "learning_rate": 7.948201050551651e-05,
+      "loss": 0.6203,
+      "step": 19
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 1.5855580445688784,
+      "learning_rate": 7.929550949662659e-05,
+      "loss": 0.6131,
+      "step": 20
+    },
+    {
+      "epoch": 0.8076923076923077,
+      "grad_norm": 1.000443112434742,
+      "learning_rate": 7.908067860007268e-05,
+      "loss": 0.6114,
+      "step": 21
+    },
+    {
+      "epoch": 0.8461538461538461,
+      "grad_norm": 13.631506116696286,
+      "learning_rate": 7.883767269704209e-05,
+      "loss": 0.6072,
+      "step": 22
+    },
+    {
+      "epoch": 0.8846153846153846,
+      "grad_norm": 13.714155639363888,
+      "learning_rate": 7.85666669813425e-05,
+      "loss": 0.6592,
+      "step": 23
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 3.979135644942687,
+      "learning_rate": 7.826785683309702e-05,
+      "loss": 0.7024,
+      "step": 24
+    },
+    {
+      "epoch": 0.9615384615384616,
+      "grad_norm": 2.0633513641937187,
+      "learning_rate": 7.794145767788582e-05,
+      "loss": 0.6472,
+      "step": 25
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.8225149755833943,
+      "learning_rate": 7.758770483143634e-05,
+      "loss": 0.6101,
+      "step": 26
+    },
+    {
+      "epoch": 1.0384615384615385,
+      "grad_norm": 1.7988394249374877,
+      "learning_rate": 7.720685332997354e-05,
+      "loss": 0.5858,
+      "step": 27
+    },
+    {
+      "epoch": 1.0769230769230769,
+      "grad_norm": 1.5643014796670933,
+      "learning_rate": 7.679917774635298e-05,
+      "loss": 0.5946,
+      "step": 28
+    },
+    {
+      "epoch": 1.1153846153846154,
+      "grad_norm": 1.0131017385245997,
+      "learning_rate": 7.636497199210895e-05,
+      "loss": 0.5729,
+      "step": 29
+    },
+    {
+      "epoch": 1.1538461538461537,
+      "grad_norm": 1.2706708396558766,
+      "learning_rate": 7.590454910556058e-05,
+      "loss": 0.5639,
+      "step": 30
+    },
+    {
+      "epoch": 1.1923076923076923,
+      "grad_norm": 0.9344751141249785,
+      "learning_rate": 7.541824102612839e-05,
+      "loss": 0.5644,
+      "step": 31
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 1.1292309903446889,
+      "learning_rate": 7.490639835502458e-05,
+      "loss": 0.5588,
+      "step": 32
+    },
+    {
+      "epoch": 1.2692307692307692,
+      "grad_norm": 1.0080539632871013,
+      "learning_rate": 7.436939010248868e-05,
+      "loss": 0.5441,
+      "step": 33
+    },
+    {
+      "epoch": 1.3076923076923077,
+      "grad_norm": 0.8921599040108631,
+      "learning_rate": 7.38076034217518e-05,
+      "loss": 0.5531,
+      "step": 34
+    },
+    {
+      "epoch": 1.3461538461538463,
+      "grad_norm": 0.6527572740720818,
+      "learning_rate": 7.322144332992047e-05,
+      "loss": 0.5536,
+      "step": 35
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "grad_norm": 0.8904469326541663,
+      "learning_rate": 7.261133241598177e-05,
+      "loss": 0.5593,
+      "step": 36
+    },
+    {
+      "epoch": 1.4230769230769231,
+      "grad_norm": 0.7190879119297497,
+      "learning_rate": 7.197771053614006e-05,
+      "loss": 0.5499,
+      "step": 37
+    },
+    {
+      "epoch": 1.4615384615384617,
+      "grad_norm": 0.7097954745187864,
+      "learning_rate": 7.13210344967049e-05,
+      "loss": 0.5419,
+      "step": 38
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.50303827795115,
+      "learning_rate": 7.064177772475912e-05,
+      "loss": 0.5339,
+      "step": 39
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.524223892671044,
+      "learning_rate": 6.994042992684406e-05,
+      "loss": 0.527,
+      "step": 40
+    },
+    {
+      "epoch": 1.5769230769230769,
+      "grad_norm": 0.4715949007356978,
+      "learning_rate": 6.921749673590813e-05,
+      "loss": 0.5261,
+      "step": 41
+    },
+    {
+      "epoch": 1.6153846153846154,
+      "grad_norm": 0.5358013583744001,
+      "learning_rate": 6.847349934677363e-05,
+      "loss": 0.5374,
+      "step": 42
+    },
+    {
+      "epoch": 1.6538461538461537,
+      "grad_norm": 0.5453928782785091,
+      "learning_rate": 6.770897414038398e-05,
+      "loss": 0.5247,
+      "step": 43
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 0.5728091140043043,
+      "learning_rate": 6.69244722971028e-05,
+      "loss": 0.521,
+      "step": 44
+    },
+    {
+      "epoch": 1.7307692307692308,
+      "grad_norm": 0.5792721942324168,
+      "learning_rate": 6.61205593993434e-05,
+      "loss": 0.5124,
+      "step": 45
+    },
+    {
+      "epoch": 1.7692307692307692,
+      "grad_norm": 0.5357551189503096,
+      "learning_rate": 6.529781502381509e-05,
+      "loss": 0.5237,
+      "step": 46
+    },
+    {
+      "epoch": 1.8076923076923077,
+      "grad_norm": 0.5766821661657299,
+      "learning_rate": 6.44568323236805e-05,
+      "loss": 0.5083,
+      "step": 47
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": 0.6080691171347822,
+      "learning_rate": 6.359821760092493e-05,
+      "loss": 0.5125,
+      "step": 48
+    },
+    {
+      "epoch": 1.8846153846153846,
+      "grad_norm": 0.49261123530624706,
+      "learning_rate": 6.272258986924624e-05,
+      "loss": 0.5228,
+      "step": 49
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 0.5117773679166865,
+      "learning_rate": 6.183058040778018e-05,
+      "loss": 0.5133,
+      "step": 50
+    },
+    {
+      "epoch": 1.9615384615384617,
+      "grad_norm": 0.5182532089317814,
+      "learning_rate": 6.092283230598311e-05,
+      "loss": 0.5203,
+      "step": 51
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.4104089099359907,
+      "learning_rate": 6.000000000000001e-05,
+      "loss": 0.4988,
+      "step": 52
+    },
+    {
+      "epoch": 2.0384615384615383,
+      "grad_norm": 0.36716205391958984,
+      "learning_rate": 5.9062748800852315e-05,
+      "loss": 0.4568,
+      "step": 53
+    },
+    {
+      "epoch": 2.076923076923077,
+      "grad_norm": 0.40645730304962985,
+      "learning_rate": 5.8111754414785504e-05,
+      "loss": 0.4675,
+      "step": 54
+    },
+    {
+      "epoch": 2.1153846153846154,
+      "grad_norm": 0.5208276735992378,
+      "learning_rate": 5.714770245612217e-05,
+      "loss": 0.4636,
+      "step": 55
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "grad_norm": 0.5211346046426674,
+      "learning_rate": 5.61712879529722e-05,
+      "loss": 0.467,
+      "step": 56
+    },
+    {
+      "epoch": 2.1923076923076925,
+      "grad_norm": 0.555536669586776,
+      "learning_rate": 5.5183214846155864e-05,
+      "loss": 0.4668,
+      "step": 57
+    },
+    {
+      "epoch": 2.230769230769231,
+      "grad_norm": 0.5617973814123592,
+      "learning_rate": 5.4184195481701425e-05,
+      "loss": 0.4574,
+      "step": 58
+    },
+    {
+      "epoch": 2.269230769230769,
+      "grad_norm": 0.6489292445301046,
+      "learning_rate": 5.317495009728319e-05,
+      "loss": 0.4591,
+      "step": 59
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 0.6669569389695914,
+      "learning_rate": 5.215620630296988e-05,
+      "loss": 0.4739,
+      "step": 60
+    },
+    {
+      "epoch": 2.3461538461538463,
+      "grad_norm": 0.6349730041530024,
+      "learning_rate": 5.112869855665811e-05,
+      "loss": 0.4548,
+      "step": 61
+    },
+    {
+      "epoch": 2.3846153846153846,
+      "grad_norm": 0.6122734889559123,
+      "learning_rate": 5.0093167634568874e-05,
+      "loss": 0.4584,
+      "step": 62
+    },
+    {
+      "epoch": 2.423076923076923,
+      "grad_norm": 0.5990842720598878,
+      "learning_rate": 4.9050360097188904e-05,
+      "loss": 0.4633,
+      "step": 63
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 0.4894794587514671,
+      "learning_rate": 4.8001027751041784e-05,
+      "loss": 0.4624,
+      "step": 64
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.4004026819563169,
+      "learning_rate": 4.694592710667723e-05,
+      "loss": 0.4492,
+      "step": 65
+    },
+    {
+      "epoch": 2.5384615384615383,
+      "grad_norm": 0.40373539943523723,
+      "learning_rate": 4.588581883326865e-05,
+      "loss": 0.4573,
+      "step": 66
+    },
+    {
+      "epoch": 2.5769230769230766,
+      "grad_norm": 0.4753306906880666,
+      "learning_rate": 4.4821467210212924e-05,
+      "loss": 0.4404,
+      "step": 67
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "grad_norm": 0.38136081842860303,
+      "learning_rate": 4.375363957612717e-05,
+      "loss": 0.4561,
+      "step": 68
+    },
+    {
+      "epoch": 2.6538461538461537,
+      "grad_norm": 0.3504398395164611,
+      "learning_rate": 4.2683105775640096e-05,
+      "loss": 0.4504,
+      "step": 69
+    },
+    {
+      "epoch": 2.6923076923076925,
+      "grad_norm": 0.4675814499308422,
+      "learning_rate": 4.1610637604376614e-05,
+      "loss": 0.4469,
+      "step": 70
+    },
+    {
+      "epoch": 2.730769230769231,
+      "grad_norm": 0.22700859367565587,
+      "learning_rate": 4.0537008252535904e-05,
+      "loss": 0.4515,
+      "step": 71
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": 0.35153717244738086,
+      "learning_rate": 3.946299174746411e-05,
+      "loss": 0.4461,
+      "step": 72
+    },
+    {
+      "epoch": 2.8076923076923075,
+      "grad_norm": 0.2769787497861352,
+      "learning_rate": 3.8389362395623406e-05,
+      "loss": 0.4519,
+      "step": 73
+    },
+    {
+      "epoch": 2.8461538461538463,
+      "grad_norm": 0.2229413340258103,
+      "learning_rate": 3.7316894224359904e-05,
+      "loss": 0.4496,
+      "step": 74
+    },
+    {
+      "epoch": 2.8846153846153846,
+      "grad_norm": 0.23278729614567556,
+      "learning_rate": 3.6246360423872834e-05,
+      "loss": 0.461,
+      "step": 75
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "grad_norm": 0.20966293912301187,
+      "learning_rate": 3.517853278978708e-05,
+      "loss": 0.4465,
+      "step": 76
+    },
+    {
+      "epoch": 2.9615384615384617,
+      "grad_norm": 0.1919927380706883,
+      "learning_rate": 3.4114181166731355e-05,
+      "loss": 0.4502,
+      "step": 77
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.24286589371168532,
+      "learning_rate": 3.305407289332279e-05,
+      "loss": 0.4325,
+      "step": 78
+    },
+    {
+      "epoch": 3.0384615384615383,
+      "grad_norm": 0.2094178623780362,
+      "learning_rate": 3.199897224895823e-05,
+      "loss": 0.4271,
+      "step": 79
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 0.2794273710494021,
+      "learning_rate": 3.094963990281112e-05,
+      "loss": 0.4124,
+      "step": 80
+    },
+    {
+      "epoch": 3.1153846153846154,
+      "grad_norm": 0.21602981852769582,
+      "learning_rate": 2.9906832365431132e-05,
+      "loss": 0.3998,
+      "step": 81
+    },
+    {
+      "epoch": 3.1538461538461537,
+      "grad_norm": 0.24039019458655728,
+      "learning_rate": 2.88713014433419e-05,
+      "loss": 0.4,
+      "step": 82
+    },
+    {
+      "epoch": 3.1923076923076925,
+      "grad_norm": 0.2403665602673451,
+      "learning_rate": 2.7843793697030128e-05,
+      "loss": 0.4031,
+      "step": 83
+    },
+    {
+      "epoch": 3.230769230769231,
+      "grad_norm": 0.23621192360927643,
+      "learning_rate": 2.682504990271682e-05,
+      "loss": 0.4138,
+      "step": 84
+    },
+    {
+      "epoch": 3.269230769230769,
+      "grad_norm": 0.25868164599747834,
+      "learning_rate": 2.5815804518298575e-05,
+      "loss": 0.415,
+      "step": 85
+    },
+    {
+      "epoch": 3.3076923076923075,
+      "grad_norm": 0.2095050670894767,
+      "learning_rate": 2.481678515384415e-05,
+      "loss": 0.4029,
+      "step": 86
+    },
+    {
+      "epoch": 3.3461538461538463,
+      "grad_norm": 0.23474723733922512,
+      "learning_rate": 2.382871204702781e-05,
+      "loss": 0.4137,
+      "step": 87
+    },
+    {
+      "epoch": 3.3846153846153846,
+      "grad_norm": 0.1852579729847356,
+      "learning_rate": 2.285229754387783e-05,
+      "loss": 0.3986,
+      "step": 88
+    },
+    {
+      "epoch": 3.423076923076923,
+      "grad_norm": 0.1954725736746499,
+      "learning_rate": 2.188824558521452e-05,
+      "loss": 0.417,
+      "step": 89
+    },
+    {
+      "epoch": 3.4615384615384617,
+      "grad_norm": 0.1677648709227486,
+      "learning_rate": 2.0937251199147684e-05,
+      "loss": 0.3993,
+      "step": 90
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.19583525703848234,
+      "learning_rate": 2.0000000000000012e-05,
+      "loss": 0.4128,
+      "step": 91
+    },
+    {
+      "epoch": 3.5384615384615383,
+      "grad_norm": 0.1702570689803967,
+      "learning_rate": 1.9077167694016903e-05,
+      "loss": 0.4085,
+      "step": 92
+    },
+    {
+      "epoch": 3.5769230769230766,
+      "grad_norm": 0.1599862202464209,
+      "learning_rate": 1.8169419592219813e-05,
+      "loss": 0.4021,
+      "step": 93
+    },
+    {
+      "epoch": 3.6153846153846154,
+      "grad_norm": 0.16364191922767002,
+      "learning_rate": 1.7277410130753775e-05,
+      "loss": 0.4043,
+      "step": 94
+    },
+    {
+      "epoch": 3.6538461538461537,
+      "grad_norm": 0.1432532332081394,
+      "learning_rate": 1.6401782399075098e-05,
+      "loss": 0.3965,
+      "step": 95
+    },
+    {
+      "epoch": 3.6923076923076925,
+      "grad_norm": 0.1366520068799443,
+      "learning_rate": 1.554316767631951e-05,
+      "loss": 0.4071,
+      "step": 96
+    },
+    {
+      "epoch": 3.730769230769231,
+      "grad_norm": 0.14353291419636313,
+      "learning_rate": 1.4702184976184915e-05,
+      "loss": 0.4041,
+      "step": 97
+    },
+    {
+      "epoch": 3.769230769230769,
+      "grad_norm": 0.13669395103425974,
+      "learning_rate": 1.3879440600656607e-05,
+      "loss": 0.4135,
+      "step": 98
+    },
+    {
+      "epoch": 3.8076923076923075,
+      "grad_norm": 0.13702870002296721,
+      "learning_rate": 1.3075527702897185e-05,
+      "loss": 0.3931,
+      "step": 99
+    },
+    {
+      "epoch": 3.8461538461538463,
+      "grad_norm": 0.14656112080057185,
+      "learning_rate": 1.2291025859616026e-05,
+      "loss": 0.4109,
+      "step": 100
+    },
+    {
+      "epoch": 3.8846153846153846,
+      "grad_norm": 0.14660537017051012,
+      "learning_rate": 1.1526500653226385e-05,
+      "loss": 0.402,
+      "step": 101
+    },
+    {
+      "epoch": 3.9230769230769234,
+      "grad_norm": 0.13980471666575722,
+      "learning_rate": 1.078250326409188e-05,
+      "loss": 0.3985,
+      "step": 102
+    },
+    {
+      "epoch": 3.9615384615384617,
+      "grad_norm": 0.135199205720943,
+      "learning_rate": 1.0059570073155953e-05,
+      "loss": 0.4119,
+      "step": 103
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.13828597758520242,
+      "learning_rate": 9.358222275240884e-06,
+      "loss": 0.4036,
+      "step": 104
+    },
+    {
+      "epoch": 4.038461538461538,
+      "grad_norm": 0.15288235481932816,
+      "learning_rate": 8.678965503295114e-06,
+      "loss": 0.3828,
+      "step": 105
+    },
+    {
+      "epoch": 4.076923076923077,
+      "grad_norm": 0.1641026415674448,
+      "learning_rate": 8.022289463859963e-06,
+      "loss": 0.3832,
+      "step": 106
+    },
+    {
+      "epoch": 4.115384615384615,
+      "grad_norm": 0.1130738484582326,
+      "learning_rate": 7.38866758401823e-06,
+      "loss": 0.3859,
+      "step": 107
+    },
+    {
+      "epoch": 4.153846153846154,
+      "grad_norm": 0.13149937470761827,
+      "learning_rate": 6.778556670079535e-06,
+      "loss": 0.4004,
+      "step": 108
+    },
+    {
+      "epoch": 4.1923076923076925,
+      "grad_norm": 0.1300541574495771,
+      "learning_rate": 6.1923965782482165e-06,
+      "loss": 0.3864,
+      "step": 109
+    },
+    {
+      "epoch": 4.230769230769231,
+      "grad_norm": 0.13443144947894425,
+      "learning_rate": 5.630609897511328e-06,
+      "loss": 0.3876,
+      "step": 110
+    },
+    {
+      "epoch": 4.269230769230769,
+      "grad_norm": 0.11513726688946264,
+      "learning_rate": 5.093601644975428e-06,
+      "loss": 0.3821,
+      "step": 111
+    },
+    {
+      "epoch": 4.3076923076923075,
+      "grad_norm": 0.11550093213095762,
+      "learning_rate": 4.581758973871609e-06,
+      "loss": 0.3843,
+      "step": 112
+    },
+    {
+      "epoch": 4.346153846153846,
+      "grad_norm": 0.11161429488960148,
+      "learning_rate": 4.0954508944394474e-06,
+      "loss": 0.3714,
+      "step": 113
+    },
+    {
+      "epoch": 4.384615384615385,
+      "grad_norm": 0.10707288286973188,
+      "learning_rate": 3.635028007891048e-06,
+      "loss": 0.391,
+      "step": 114
+    },
+    {
+      "epoch": 4.423076923076923,
+      "grad_norm": 0.09997591763637227,
+      "learning_rate": 3.200822253647031e-06,
+      "loss": 0.389,
+      "step": 115
+    },
+    {
+      "epoch": 4.461538461538462,
+      "grad_norm": 0.25150206260506447,
+      "learning_rate": 2.793146670026472e-06,
+      "loss": 0.3855,
+      "step": 116
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.11822371641036339,
+      "learning_rate": 2.4122951685636674e-06,
+      "loss": 0.3733,
+      "step": 117
+    },
+    {
+      "epoch": 4.538461538461538,
+      "grad_norm": 0.12032866909774866,
+      "learning_rate": 2.0585423221141807e-06,
+      "loss": 0.3821,
+      "step": 118
+    },
+    {
+      "epoch": 4.576923076923077,
+      "grad_norm": 0.09821080934350153,
+      "learning_rate": 1.7321431669029953e-06,
+      "loss": 0.381,
+      "step": 119
+    },
+    {
+      "epoch": 4.615384615384615,
+      "grad_norm": 0.09426960244907097,
+      "learning_rate": 1.4333330186575079e-06,
+      "loss": 0.3904,
+      "step": 120
+    },
+    {
+      "epoch": 4.653846153846154,
+      "grad_norm": 0.09467913192838641,
+      "learning_rate": 1.1623273029579195e-06,
+      "loss": 0.3792,
+      "step": 121
+    },
+    {
+      "epoch": 4.6923076923076925,
+      "grad_norm": 0.0933501903517312,
+      "learning_rate": 9.193213999273199e-07,
+      "loss": 0.3797,
+      "step": 122
+    },
+    {
+      "epoch": 4.730769230769231,
+      "grad_norm": 0.11007696887793282,
+      "learning_rate": 7.044905033734096e-07,
+      "loss": 0.377,
+      "step": 123
+    },
+    {
+      "epoch": 4.769230769230769,
+      "grad_norm": 0.08944249101042777,
+      "learning_rate": 5.179894944834863e-07,
+      "loss": 0.383,
+      "step": 124
+    },
+    {
+      "epoch": 4.8076923076923075,
+      "grad_norm": 0.09091769880374838,
+      "learning_rate": 3.599528301636612e-07,
+      "loss": 0.3897,
+      "step": 125
+    },
+    {
+      "epoch": 4.846153846153846,
+      "grad_norm": 0.08847911686943111,
+      "learning_rate": 2.3049444610288462e-07,
+      "loss": 0.378,
+      "step": 126
+    },
+    {
+      "epoch": 4.884615384615385,
+      "grad_norm": 0.08727876430729421,
+      "learning_rate": 1.2970767463160284e-07,
+      "loss": 0.3866,
+      "step": 127
+    },
+    {
+      "epoch": 4.923076923076923,
+      "grad_norm": 0.08870602324673937,
+      "learning_rate": 5.766517743432953e-08,
+      "loss": 0.3876,
+      "step": 128
+    },
+    {
+      "epoch": 4.961538461538462,
+      "grad_norm": 0.08693947349353748,
+      "learning_rate": 1.4418893164585002e-08,
+      "loss": 0.3813,
+      "step": 129
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.08921334939628389,
+      "learning_rate": 0.0,
+      "loss": 0.3787,
+      "step": 130
+    },
+    {
+      "epoch": 5.0,
+      "step": 130,
+      "total_flos": 2180898493562880.0,
+      "train_loss": 0.4967416850420145,
+      "train_runtime": 5886.6032,
+      "train_samples_per_second": 11.151,
+      "train_steps_per_second": 0.022
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 130,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2180898493562880.0,
+  "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 sha256:85345ed92f05c2e615a96478c429c20b43a0523c906a05ee31c6f23e38dd852d
+size 7416