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: original
+  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. -->
+
+# original
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the Sky-T1 dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 12
+- total_train_batch_size: 96
+- total_eval_batch_size: 64
+- 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: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.4.0a0+f70bd71a48.nv24.06
+- 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": 1.991111111111111,
+    "total_flos": 185195202609152.0,
+    "train_loss": 0.65867241738098,
+    "train_runtime": 12992.6194,
+    "train_samples_per_second": 0.83,
+    "train_steps_per_second": 0.009
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "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:b5bdd81d38d526fd624ec5b539329080d16aef574d2d8d7a8183fbdc6fafa676
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aca3caccfc231cb4656f779878787c8f8629d69bdc83ec5ddb8b5317a76774ec
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3db292aa538da52c792b82583d7c8028d32bb8f22dcae1b446112ad7256a4b0
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bca2036175c18ed020961b3d089a5e5aa512b4161b40df905ff7d071bb25bd6d
+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": 1.991111111111111,
+    "total_flos": 185195202609152.0,
+    "train_loss": 0.65867241738098,
+    "train_runtime": 12992.6194,
+    "train_samples_per_second": 0.83,
+    "train_steps_per_second": 0.009
+}

trainer_log.jsonl

@@ -0,0 +1,113 @@
+{"current_steps": 1, "total_steps": 112, "loss": 0.9993, "lr": 1.6666666666666667e-06, "epoch": 0.017777777777777778, "percentage": 0.89, "elapsed_time": "0:02:05", "remaining_time": "3:52:28"}
+{"current_steps": 2, "total_steps": 112, "loss": 1.0111, "lr": 3.3333333333333333e-06, "epoch": 0.035555555555555556, "percentage": 1.79, "elapsed_time": "0:04:08", "remaining_time": "3:47:30"}
+{"current_steps": 3, "total_steps": 112, "loss": 0.9858, "lr": 5e-06, "epoch": 0.05333333333333334, "percentage": 2.68, "elapsed_time": "0:05:54", "remaining_time": "3:34:27"}
+{"current_steps": 4, "total_steps": 112, "loss": 0.9484, "lr": 6.666666666666667e-06, "epoch": 0.07111111111111111, "percentage": 3.57, "elapsed_time": "0:08:01", "remaining_time": "3:36:28"}
+{"current_steps": 5, "total_steps": 112, "loss": 0.9376, "lr": 8.333333333333334e-06, "epoch": 0.08888888888888889, "percentage": 4.46, "elapsed_time": "0:09:54", "remaining_time": "3:31:57"}
+{"current_steps": 6, "total_steps": 112, "loss": 0.9214, "lr": 1e-05, "epoch": 0.10666666666666667, "percentage": 5.36, "elapsed_time": "0:11:36", "remaining_time": "3:25:07"}
+{"current_steps": 7, "total_steps": 112, "loss": 0.9122, "lr": 1.1666666666666668e-05, "epoch": 0.12444444444444444, "percentage": 6.25, "elapsed_time": "0:13:27", "remaining_time": "3:21:57"}
+{"current_steps": 8, "total_steps": 112, "loss": 0.8665, "lr": 1.3333333333333333e-05, "epoch": 0.14222222222222222, "percentage": 7.14, "elapsed_time": "0:15:25", "remaining_time": "3:20:29"}
+{"current_steps": 9, "total_steps": 112, "loss": 0.8395, "lr": 1.5000000000000002e-05, "epoch": 0.16, "percentage": 8.04, "elapsed_time": "0:17:14", "remaining_time": "3:17:22"}
+{"current_steps": 10, "total_steps": 112, "loss": 0.8198, "lr": 1.6666666666666667e-05, "epoch": 0.17777777777777778, "percentage": 8.93, "elapsed_time": "0:19:15", "remaining_time": "3:16:25"}
+{"current_steps": 11, "total_steps": 112, "loss": 0.7984, "lr": 1.8333333333333333e-05, "epoch": 0.19555555555555557, "percentage": 9.82, "elapsed_time": "0:21:11", "remaining_time": "3:14:32"}
+{"current_steps": 12, "total_steps": 112, "loss": 0.794, "lr": 2e-05, "epoch": 0.21333333333333335, "percentage": 10.71, "elapsed_time": "0:23:21", "remaining_time": "3:14:35"}
+{"current_steps": 13, "total_steps": 112, "loss": 0.783, "lr": 1.9995065603657317e-05, "epoch": 0.2311111111111111, "percentage": 11.61, "elapsed_time": "0:25:25", "remaining_time": "3:13:40"}
+{"current_steps": 14, "total_steps": 112, "loss": 0.7379, "lr": 1.9980267284282718e-05, "epoch": 0.24888888888888888, "percentage": 12.5, "elapsed_time": "0:27:25", "remaining_time": "3:11:58"}
+{"current_steps": 15, "total_steps": 112, "loss": 0.7524, "lr": 1.99556196460308e-05, "epoch": 0.26666666666666666, "percentage": 13.39, "elapsed_time": "0:29:08", "remaining_time": "3:08:29"}
+{"current_steps": 16, "total_steps": 112, "loss": 0.754, "lr": 1.9921147013144782e-05, "epoch": 0.28444444444444444, "percentage": 14.29, "elapsed_time": "0:30:51", "remaining_time": "3:05:07"}
+{"current_steps": 17, "total_steps": 112, "loss": 0.7073, "lr": 1.9876883405951378e-05, "epoch": 0.3022222222222222, "percentage": 15.18, "elapsed_time": "0:32:35", "remaining_time": "3:02:05"}
+{"current_steps": 18, "total_steps": 112, "loss": 0.7159, "lr": 1.982287250728689e-05, "epoch": 0.32, "percentage": 16.07, "elapsed_time": "0:34:36", "remaining_time": "3:00:42"}
+{"current_steps": 19, "total_steps": 112, "loss": 0.7114, "lr": 1.9759167619387474e-05, "epoch": 0.3377777777777778, "percentage": 16.96, "elapsed_time": "0:36:33", "remaining_time": "2:58:58"}
+{"current_steps": 20, "total_steps": 112, "loss": 0.7012, "lr": 1.9685831611286312e-05, "epoch": 0.35555555555555557, "percentage": 17.86, "elapsed_time": "0:38:17", "remaining_time": "2:56:07"}
+{"current_steps": 21, "total_steps": 112, "loss": 0.6948, "lr": 1.9602936856769432e-05, "epoch": 0.37333333333333335, "percentage": 18.75, "elapsed_time": "0:40:00", "remaining_time": "2:53:21"}
+{"current_steps": 22, "total_steps": 112, "loss": 0.7046, "lr": 1.9510565162951538e-05, "epoch": 0.39111111111111113, "percentage": 19.64, "elapsed_time": "0:42:05", "remaining_time": "2:52:12"}
+{"current_steps": 23, "total_steps": 112, "loss": 0.7076, "lr": 1.9408807689542257e-05, "epoch": 0.4088888888888889, "percentage": 20.54, "elapsed_time": "0:44:00", "remaining_time": "2:50:16"}
+{"current_steps": 24, "total_steps": 112, "loss": 0.6983, "lr": 1.9297764858882516e-05, "epoch": 0.4266666666666667, "percentage": 21.43, "elapsed_time": "0:45:52", "remaining_time": "2:48:13"}
+{"current_steps": 25, "total_steps": 112, "loss": 0.6839, "lr": 1.9177546256839814e-05, "epoch": 0.4444444444444444, "percentage": 22.32, "elapsed_time": "0:47:44", "remaining_time": "2:46:06"}
+{"current_steps": 26, "total_steps": 112, "loss": 0.6768, "lr": 1.9048270524660197e-05, "epoch": 0.4622222222222222, "percentage": 23.21, "elapsed_time": "0:49:47", "remaining_time": "2:44:40"}
+{"current_steps": 27, "total_steps": 112, "loss": 0.6773, "lr": 1.891006524188368e-05, "epoch": 0.48, "percentage": 24.11, "elapsed_time": "0:51:44", "remaining_time": "2:42:54"}
+{"current_steps": 28, "total_steps": 112, "loss": 0.6852, "lr": 1.8763066800438638e-05, "epoch": 0.49777777777777776, "percentage": 25.0, "elapsed_time": "0:53:44", "remaining_time": "2:41:14"}
+{"current_steps": 29, "total_steps": 112, "loss": 0.6882, "lr": 1.860742027003944e-05, "epoch": 0.5155555555555555, "percentage": 25.89, "elapsed_time": "0:55:40", "remaining_time": "2:39:21"}
+{"current_steps": 30, "total_steps": 112, "loss": 0.6677, "lr": 1.8443279255020153e-05, "epoch": 0.5333333333333333, "percentage": 26.79, "elapsed_time": "0:57:37", "remaining_time": "2:37:31"}
+{"current_steps": 31, "total_steps": 112, "loss": 0.6696, "lr": 1.827080574274562e-05, "epoch": 0.5511111111111111, "percentage": 27.68, "elapsed_time": "0:59:44", "remaining_time": "2:36:05"}
+{"current_steps": 32, "total_steps": 112, "loss": 0.6484, "lr": 1.8090169943749477e-05, "epoch": 0.5688888888888889, "percentage": 28.57, "elapsed_time": "1:01:48", "remaining_time": "2:34:32"}
+{"current_steps": 33, "total_steps": 112, "loss": 0.6859, "lr": 1.7901550123756906e-05, "epoch": 0.5866666666666667, "percentage": 29.46, "elapsed_time": "1:03:34", "remaining_time": "2:32:12"}
+{"current_steps": 34, "total_steps": 112, "loss": 0.6557, "lr": 1.7705132427757895e-05, "epoch": 0.6044444444444445, "percentage": 30.36, "elapsed_time": "1:05:24", "remaining_time": "2:30:02"}
+{"current_steps": 35, "total_steps": 112, "loss": 0.6511, "lr": 1.7501110696304598e-05, "epoch": 0.6222222222222222, "percentage": 31.25, "elapsed_time": "1:07:17", "remaining_time": "2:28:01"}
+{"current_steps": 36, "total_steps": 112, "loss": 0.6603, "lr": 1.7289686274214116e-05, "epoch": 0.64, "percentage": 32.14, "elapsed_time": "1:09:05", "remaining_time": "2:25:51"}
+{"current_steps": 37, "total_steps": 112, "loss": 0.6674, "lr": 1.7071067811865477e-05, "epoch": 0.6577777777777778, "percentage": 33.04, "elapsed_time": "1:11:01", "remaining_time": "2:23:57"}
+{"current_steps": 38, "total_steps": 112, "loss": 0.6624, "lr": 1.684547105928689e-05, "epoch": 0.6755555555555556, "percentage": 33.93, "elapsed_time": "1:12:51", "remaining_time": "2:21:53"}
+{"current_steps": 39, "total_steps": 112, "loss": 0.659, "lr": 1.661311865323652e-05, "epoch": 0.6933333333333334, "percentage": 34.82, "elapsed_time": "1:14:54", "remaining_time": "2:20:12"}
+{"current_steps": 40, "total_steps": 112, "loss": 0.6403, "lr": 1.63742398974869e-05, "epoch": 0.7111111111111111, "percentage": 35.71, "elapsed_time": "1:16:42", "remaining_time": "2:18:03"}
+{"current_steps": 41, "total_steps": 112, "loss": 0.6649, "lr": 1.6129070536529767e-05, "epoch": 0.7288888888888889, "percentage": 36.61, "elapsed_time": "1:18:39", "remaining_time": "2:16:13"}
+{"current_steps": 42, "total_steps": 112, "loss": 0.6636, "lr": 1.5877852522924733e-05, "epoch": 0.7466666666666667, "percentage": 37.5, "elapsed_time": "1:20:30", "remaining_time": "2:14:10"}
+{"current_steps": 43, "total_steps": 112, "loss": 0.6464, "lr": 1.5620833778521306e-05, "epoch": 0.7644444444444445, "percentage": 38.39, "elapsed_time": "1:22:22", "remaining_time": "2:12:10"}
+{"current_steps": 44, "total_steps": 112, "loss": 0.6513, "lr": 1.5358267949789968e-05, "epoch": 0.7822222222222223, "percentage": 39.29, "elapsed_time": "1:24:26", "remaining_time": "2:10:30"}
+{"current_steps": 45, "total_steps": 112, "loss": 0.6625, "lr": 1.5090414157503715e-05, "epoch": 0.8, "percentage": 40.18, "elapsed_time": "1:26:14", "remaining_time": "2:08:24"}
+{"current_steps": 46, "total_steps": 112, "loss": 0.6471, "lr": 1.4817536741017153e-05, "epoch": 0.8177777777777778, "percentage": 41.07, "elapsed_time": "1:28:10", "remaining_time": "2:06:31"}
+{"current_steps": 47, "total_steps": 112, "loss": 0.6625, "lr": 1.4539904997395468e-05, "epoch": 0.8355555555555556, "percentage": 41.96, "elapsed_time": "1:30:13", "remaining_time": "2:04:46"}
+{"current_steps": 48, "total_steps": 112, "loss": 0.6374, "lr": 1.4257792915650728e-05, "epoch": 0.8533333333333334, "percentage": 42.86, "elapsed_time": "1:32:06", "remaining_time": "2:02:48"}
+{"current_steps": 49, "total_steps": 112, "loss": 0.6431, "lr": 1.3971478906347806e-05, "epoch": 0.8711111111111111, "percentage": 43.75, "elapsed_time": "1:33:50", "remaining_time": "2:00:39"}
+{"current_steps": 50, "total_steps": 112, "loss": 0.6381, "lr": 1.3681245526846782e-05, "epoch": 0.8888888888888888, "percentage": 44.64, "elapsed_time": "1:35:49", "remaining_time": "1:58:48"}
+{"current_steps": 51, "total_steps": 112, "loss": 0.6338, "lr": 1.3387379202452917e-05, "epoch": 0.9066666666666666, "percentage": 45.54, "elapsed_time": "1:37:38", "remaining_time": "1:56:47"}
+{"current_steps": 52, "total_steps": 112, "loss": 0.6502, "lr": 1.3090169943749475e-05, "epoch": 0.9244444444444444, "percentage": 46.43, "elapsed_time": "1:39:43", "remaining_time": "1:55:04"}
+{"current_steps": 53, "total_steps": 112, "loss": 0.6449, "lr": 1.2789911060392295e-05, "epoch": 0.9422222222222222, "percentage": 47.32, "elapsed_time": "1:41:46", "remaining_time": "1:53:18"}
+{"current_steps": 54, "total_steps": 112, "loss": 0.6511, "lr": 1.2486898871648552e-05, "epoch": 0.96, "percentage": 48.21, "elapsed_time": "1:43:36", "remaining_time": "1:51:17"}
+{"current_steps": 55, "total_steps": 112, "loss": 0.6367, "lr": 1.2181432413965428e-05, "epoch": 0.9777777777777777, "percentage": 49.11, "elapsed_time": "1:45:27", "remaining_time": "1:49:17"}
+{"current_steps": 56, "total_steps": 112, "loss": 0.6532, "lr": 1.187381314585725e-05, "epoch": 0.9955555555555555, "percentage": 50.0, "elapsed_time": "1:47:18", "remaining_time": "1:47:18"}
+{"current_steps": 57, "total_steps": 112, "loss": 1.0796, "lr": 1.156434465040231e-05, "epoch": 1.0133333333333334, "percentage": 50.89, "elapsed_time": "1:49:09", "remaining_time": "1:45:19"}
+{"current_steps": 58, "total_steps": 112, "loss": 0.634, "lr": 1.1253332335643043e-05, "epoch": 1.031111111111111, "percentage": 51.79, "elapsed_time": "1:51:06", "remaining_time": "1:43:27"}
+{"current_steps": 59, "total_steps": 112, "loss": 0.6002, "lr": 1.0941083133185146e-05, "epoch": 1.048888888888889, "percentage": 52.68, "elapsed_time": "1:53:14", "remaining_time": "1:41:43"}
+{"current_steps": 60, "total_steps": 112, "loss": 0.5628, "lr": 1.0627905195293135e-05, "epoch": 1.0666666666666667, "percentage": 53.57, "elapsed_time": "1:55:07", "remaining_time": "1:39:46"}
+{"current_steps": 61, "total_steps": 112, "loss": 0.6532, "lr": 1.0314107590781284e-05, "epoch": 1.0844444444444445, "percentage": 54.46, "elapsed_time": "1:56:57", "remaining_time": "1:37:46"}
+{"current_steps": 62, "total_steps": 112, "loss": 0.5744, "lr": 1e-05, "epoch": 1.1022222222222222, "percentage": 55.36, "elapsed_time": "1:59:02", "remaining_time": "1:35:59"}
+{"current_steps": 63, "total_steps": 112, "loss": 0.5798, "lr": 9.685892409218718e-06, "epoch": 1.12, "percentage": 56.25, "elapsed_time": "2:00:52", "remaining_time": "1:34:00"}
+{"current_steps": 64, "total_steps": 112, "loss": 0.567, "lr": 9.372094804706867e-06, "epoch": 1.1377777777777778, "percentage": 57.14, "elapsed_time": "2:02:53", "remaining_time": "1:32:10"}
+{"current_steps": 65, "total_steps": 112, "loss": 0.6152, "lr": 9.058916866814857e-06, "epoch": 1.1555555555555554, "percentage": 58.04, "elapsed_time": "2:04:58", "remaining_time": "1:30:22"}
+{"current_steps": 66, "total_steps": 112, "loss": 0.6099, "lr": 8.746667664356957e-06, "epoch": 1.1733333333333333, "percentage": 58.93, "elapsed_time": "2:06:55", "remaining_time": "1:28:27"}
+{"current_steps": 67, "total_steps": 112, "loss": 0.5508, "lr": 8.43565534959769e-06, "epoch": 1.1911111111111112, "percentage": 59.82, "elapsed_time": "2:08:40", "remaining_time": "1:26:25"}
+{"current_steps": 68, "total_steps": 112, "loss": 0.625, "lr": 8.126186854142752e-06, "epoch": 1.208888888888889, "percentage": 60.71, "elapsed_time": "2:10:45", "remaining_time": "1:24:36"}
+{"current_steps": 69, "total_steps": 112, "loss": 0.5666, "lr": 7.818567586034578e-06, "epoch": 1.2266666666666666, "percentage": 61.61, "elapsed_time": "2:12:40", "remaining_time": "1:22:41"}
+{"current_steps": 70, "total_steps": 112, "loss": 0.6, "lr": 7.513101128351454e-06, "epoch": 1.2444444444444445, "percentage": 62.5, "elapsed_time": "2:14:28", "remaining_time": "1:20:41"}
+{"current_steps": 71, "total_steps": 112, "loss": 0.5466, "lr": 7.210088939607709e-06, "epoch": 1.2622222222222224, "percentage": 63.39, "elapsed_time": "2:16:26", "remaining_time": "1:18:47"}
+{"current_steps": 72, "total_steps": 112, "loss": 0.6297, "lr": 6.909830056250527e-06, "epoch": 1.28, "percentage": 64.29, "elapsed_time": "2:18:22", "remaining_time": "1:16:52"}
+{"current_steps": 73, "total_steps": 112, "loss": 0.5333, "lr": 6.612620797547087e-06, "epoch": 1.2977777777777777, "percentage": 65.18, "elapsed_time": "2:20:11", "remaining_time": "1:14:53"}
+{"current_steps": 74, "total_steps": 112, "loss": 0.6132, "lr": 6.318754473153221e-06, "epoch": 1.3155555555555556, "percentage": 66.07, "elapsed_time": "2:22:20", "remaining_time": "1:13:05"}
+{"current_steps": 75, "total_steps": 112, "loss": 0.5587, "lr": 6.028521093652195e-06, "epoch": 1.3333333333333333, "percentage": 66.96, "elapsed_time": "2:24:15", "remaining_time": "1:11:10"}
+{"current_steps": 76, "total_steps": 112, "loss": 0.6111, "lr": 5.742207084349274e-06, "epoch": 1.3511111111111112, "percentage": 67.86, "elapsed_time": "2:26:23", "remaining_time": "1:09:20"}
+{"current_steps": 77, "total_steps": 112, "loss": 0.5848, "lr": 5.460095002604533e-06, "epoch": 1.3688888888888888, "percentage": 68.75, "elapsed_time": "2:28:19", "remaining_time": "1:07:25"}
+{"current_steps": 78, "total_steps": 112, "loss": 0.6158, "lr": 5.1824632589828465e-06, "epoch": 1.3866666666666667, "percentage": 69.64, "elapsed_time": "2:30:17", "remaining_time": "1:05:30"}
+{"current_steps": 79, "total_steps": 112, "loss": 0.5424, "lr": 4.909585842496287e-06, "epoch": 1.4044444444444444, "percentage": 70.54, "elapsed_time": "2:32:12", "remaining_time": "1:03:34"}
+{"current_steps": 80, "total_steps": 112, "loss": 0.5793, "lr": 4.641732050210032e-06, "epoch": 1.4222222222222223, "percentage": 71.43, "elapsed_time": "2:34:06", "remaining_time": "1:01:38"}
+{"current_steps": 81, "total_steps": 112, "loss": 0.5984, "lr": 4.379166221478697e-06, "epoch": 1.44, "percentage": 72.32, "elapsed_time": "2:35:58", "remaining_time": "0:59:41"}
+{"current_steps": 82, "total_steps": 112, "loss": 0.621, "lr": 4.12214747707527e-06, "epoch": 1.4577777777777778, "percentage": 73.21, "elapsed_time": "2:37:56", "remaining_time": "0:57:46"}
+{"current_steps": 83, "total_steps": 112, "loss": 0.5242, "lr": 3.8709294634702374e-06, "epoch": 1.4755555555555555, "percentage": 74.11, "elapsed_time": "2:39:42", "remaining_time": "0:55:48"}
+{"current_steps": 84, "total_steps": 112, "loss": 0.563, "lr": 3.625760102513103e-06, "epoch": 1.4933333333333334, "percentage": 75.0, "elapsed_time": "2:41:28", "remaining_time": "0:53:49"}
+{"current_steps": 85, "total_steps": 112, "loss": 0.6099, "lr": 3.3868813467634833e-06, "epoch": 1.511111111111111, "percentage": 75.89, "elapsed_time": "2:43:20", "remaining_time": "0:51:53"}
+{"current_steps": 86, "total_steps": 112, "loss": 0.5765, "lr": 3.1545289407131128e-06, "epoch": 1.528888888888889, "percentage": 76.79, "elapsed_time": "2:45:06", "remaining_time": "0:49:55"}
+{"current_steps": 87, "total_steps": 112, "loss": 0.5988, "lr": 2.9289321881345257e-06, "epoch": 1.5466666666666666, "percentage": 77.68, "elapsed_time": "2:46:56", "remaining_time": "0:47:58"}
+{"current_steps": 88, "total_steps": 112, "loss": 0.5901, "lr": 2.7103137257858867e-06, "epoch": 1.5644444444444443, "percentage": 78.57, "elapsed_time": "2:48:42", "remaining_time": "0:46:00"}
+{"current_steps": 89, "total_steps": 112, "loss": 0.5578, "lr": 2.4988893036954045e-06, "epoch": 1.5822222222222222, "percentage": 79.46, "elapsed_time": "2:50:35", "remaining_time": "0:44:05"}
+{"current_steps": 90, "total_steps": 112, "loss": 0.5952, "lr": 2.2948675722421086e-06, "epoch": 1.6, "percentage": 80.36, "elapsed_time": "2:52:22", "remaining_time": "0:42:08"}
+{"current_steps": 91, "total_steps": 112, "loss": 0.5729, "lr": 2.098449876243096e-06, "epoch": 1.6177777777777778, "percentage": 81.25, "elapsed_time": "2:54:29", "remaining_time": "0:40:16"}
+{"current_steps": 92, "total_steps": 112, "loss": 0.6167, "lr": 1.9098300562505266e-06, "epoch": 1.6355555555555554, "percentage": 82.14, "elapsed_time": "2:56:37", "remaining_time": "0:38:23"}
+{"current_steps": 93, "total_steps": 112, "loss": 0.558, "lr": 1.7291942572543806e-06, "epoch": 1.6533333333333333, "percentage": 83.04, "elapsed_time": "2:58:23", "remaining_time": "0:36:26"}
+{"current_steps": 94, "total_steps": 112, "loss": 0.5948, "lr": 1.5567207449798517e-06, "epoch": 1.6711111111111112, "percentage": 83.93, "elapsed_time": "3:00:25", "remaining_time": "0:34:32"}
+{"current_steps": 95, "total_steps": 112, "loss": 0.5715, "lr": 1.3925797299605649e-06, "epoch": 1.6888888888888889, "percentage": 84.82, "elapsed_time": "3:02:16", "remaining_time": "0:32:36"}
+{"current_steps": 96, "total_steps": 112, "loss": 0.5936, "lr": 1.2369331995613664e-06, "epoch": 1.7066666666666666, "percentage": 85.71, "elapsed_time": "3:04:05", "remaining_time": "0:30:40"}
+{"current_steps": 97, "total_steps": 112, "loss": 0.5924, "lr": 1.0899347581163222e-06, "epoch": 1.7244444444444444, "percentage": 86.61, "elapsed_time": "3:06:09", "remaining_time": "0:28:47"}
+{"current_steps": 98, "total_steps": 112, "loss": 0.575, "lr": 9.517294753398066e-07, "epoch": 1.7422222222222223, "percentage": 87.5, "elapsed_time": "3:08:11", "remaining_time": "0:26:53"}
+{"current_steps": 99, "total_steps": 112, "loss": 0.5367, "lr": 8.224537431601886e-07, "epoch": 1.76, "percentage": 88.39, "elapsed_time": "3:10:04", "remaining_time": "0:24:57"}
+{"current_steps": 100, "total_steps": 112, "loss": 0.5957, "lr": 7.022351411174866e-07, "epoch": 1.7777777777777777, "percentage": 89.29, "elapsed_time": "3:11:55", "remaining_time": "0:23:01"}
+{"current_steps": 101, "total_steps": 112, "loss": 0.5824, "lr": 5.911923104577455e-07, "epoch": 1.7955555555555556, "percentage": 90.18, "elapsed_time": "3:14:59", "remaining_time": "0:21:14"}
+{"current_steps": 102, "total_steps": 112, "loss": 0.561, "lr": 4.894348370484648e-07, "epoch": 1.8133333333333335, "percentage": 91.07, "elapsed_time": "3:16:57", "remaining_time": "0:19:18"}
+{"current_steps": 103, "total_steps": 112, "loss": 0.5761, "lr": 3.9706314323056936e-07, "epoch": 1.8311111111111111, "percentage": 91.96, "elapsed_time": "3:18:45", "remaining_time": "0:17:22"}
+{"current_steps": 104, "total_steps": 112, "loss": 0.5536, "lr": 3.1416838871368925e-07, "epoch": 1.8488888888888888, "percentage": 92.86, "elapsed_time": "3:20:15", "remaining_time": "0:15:24"}
+{"current_steps": 105, "total_steps": 112, "loss": 0.6234, "lr": 2.4083238061252565e-07, "epoch": 1.8666666666666667, "percentage": 93.75, "elapsed_time": "3:22:02", "remaining_time": "0:13:28"}
+{"current_steps": 106, "total_steps": 112, "loss": 0.5415, "lr": 1.7712749271311392e-07, "epoch": 1.8844444444444446, "percentage": 94.64, "elapsed_time": "3:23:46", "remaining_time": "0:11:32"}
+{"current_steps": 107, "total_steps": 112, "loss": 0.5611, "lr": 1.231165940486234e-07, "epoch": 1.9022222222222223, "percentage": 95.54, "elapsed_time": "3:25:45", "remaining_time": "0:09:36"}
+{"current_steps": 108, "total_steps": 112, "loss": 0.5628, "lr": 7.885298685522235e-08, "epoch": 1.92, "percentage": 96.43, "elapsed_time": "3:27:25", "remaining_time": "0:07:40"}
+{"current_steps": 109, "total_steps": 112, "loss": 0.5907, "lr": 4.438035396920004e-08, "epoch": 1.9377777777777778, "percentage": 97.32, "elapsed_time": "3:29:17", "remaining_time": "0:05:45"}
+{"current_steps": 110, "total_steps": 112, "loss": 0.6009, "lr": 1.973271571728441e-08, "epoch": 1.9555555555555557, "percentage": 98.21, "elapsed_time": "3:31:29", "remaining_time": "0:03:50"}
+{"current_steps": 111, "total_steps": 112, "loss": 0.5773, "lr": 4.9343963426840006e-09, "epoch": 1.9733333333333334, "percentage": 99.11, "elapsed_time": "3:33:37", "remaining_time": "0:01:55"}
+{"current_steps": 112, "total_steps": 112, "loss": 0.5963, "lr": 0.0, "epoch": 1.991111111111111, "percentage": 100.0, "elapsed_time": "3:35:29", "remaining_time": "0:00:00"}
+{"current_steps": 112, "total_steps": 112, "epoch": 1.991111111111111, "percentage": 100.0, "elapsed_time": "3:36:31", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,826 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.991111111111111,
+  "eval_steps": 500,
+  "global_step": 112,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 6.02266263961792,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.9993,
+      "step": 1
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 6.143394947052002,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.0111,
+      "step": 2
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 5.803601264953613,
+      "learning_rate": 5e-06,
+      "loss": 0.9858,
+      "step": 3
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 4.266067028045654,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.9484,
+      "step": 4
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 2.9427103996276855,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.9376,
+      "step": 5
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 4.489638805389404,
+      "learning_rate": 1e-05,
+      "loss": 0.9214,
+      "step": 6
+    },
+    {
+      "epoch": 0.12444444444444444,
+      "grad_norm": 4.621401786804199,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 0.9122,
+      "step": 7
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 3.9608113765716553,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.8665,
+      "step": 8
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.7279064655303955,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.8395,
+      "step": 9
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 2.407290458679199,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.8198,
+      "step": 10
+    },
+    {
+      "epoch": 0.19555555555555557,
+      "grad_norm": 2.280531644821167,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 0.7984,
+      "step": 11
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 2.6176528930664062,
+      "learning_rate": 2e-05,
+      "loss": 0.794,
+      "step": 12
+    },
+    {
+      "epoch": 0.2311111111111111,
+      "grad_norm": 1.707384467124939,
+      "learning_rate": 1.9995065603657317e-05,
+      "loss": 0.783,
+      "step": 13
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 1.9082920551300049,
+      "learning_rate": 1.9980267284282718e-05,
+      "loss": 0.7379,
+      "step": 14
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 1.7811676263809204,
+      "learning_rate": 1.99556196460308e-05,
+      "loss": 0.7524,
+      "step": 15
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 1.3555017709732056,
+      "learning_rate": 1.9921147013144782e-05,
+      "loss": 0.754,
+      "step": 16
+    },
+    {
+      "epoch": 0.3022222222222222,
+      "grad_norm": 1.3673418760299683,
+      "learning_rate": 1.9876883405951378e-05,
+      "loss": 0.7073,
+      "step": 17
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.4924910068511963,
+      "learning_rate": 1.982287250728689e-05,
+      "loss": 0.7159,
+      "step": 18
+    },
+    {
+      "epoch": 0.3377777777777778,
+      "grad_norm": 1.6850374937057495,
+      "learning_rate": 1.9759167619387474e-05,
+      "loss": 0.7114,
+      "step": 19
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 1.511631727218628,
+      "learning_rate": 1.9685831611286312e-05,
+      "loss": 0.7012,
+      "step": 20
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 1.2830287218093872,
+      "learning_rate": 1.9602936856769432e-05,
+      "loss": 0.6948,
+      "step": 21
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 1.2557350397109985,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 0.7046,
+      "step": 22
+    },
+    {
+      "epoch": 0.4088888888888889,
+      "grad_norm": 0.9395996928215027,
+      "learning_rate": 1.9408807689542257e-05,
+      "loss": 0.7076,
+      "step": 23
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 1.0723974704742432,
+      "learning_rate": 1.9297764858882516e-05,
+      "loss": 0.6983,
+      "step": 24
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.0539971590042114,
+      "learning_rate": 1.9177546256839814e-05,
+      "loss": 0.6839,
+      "step": 25
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 0.9047765135765076,
+      "learning_rate": 1.9048270524660197e-05,
+      "loss": 0.6768,
+      "step": 26
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.9144095182418823,
+      "learning_rate": 1.891006524188368e-05,
+      "loss": 0.6773,
+      "step": 27
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 0.8761118054389954,
+      "learning_rate": 1.8763066800438638e-05,
+      "loss": 0.6852,
+      "step": 28
+    },
+    {
+      "epoch": 0.5155555555555555,
+      "grad_norm": 0.9473320841789246,
+      "learning_rate": 1.860742027003944e-05,
+      "loss": 0.6882,
+      "step": 29
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 1.0702017545700073,
+      "learning_rate": 1.8443279255020153e-05,
+      "loss": 0.6677,
+      "step": 30
+    },
+    {
+      "epoch": 0.5511111111111111,
+      "grad_norm": 0.7134117484092712,
+      "learning_rate": 1.827080574274562e-05,
+      "loss": 0.6696,
+      "step": 31
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 0.8997704386711121,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.6484,
+      "step": 32
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.7318180203437805,
+      "learning_rate": 1.7901550123756906e-05,
+      "loss": 0.6859,
+      "step": 33
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 0.8574209213256836,
+      "learning_rate": 1.7705132427757895e-05,
+      "loss": 0.6557,
+      "step": 34
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.7167562246322632,
+      "learning_rate": 1.7501110696304598e-05,
+      "loss": 0.6511,
+      "step": 35
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.701689600944519,
+      "learning_rate": 1.7289686274214116e-05,
+      "loss": 0.6603,
+      "step": 36
+    },
+    {
+      "epoch": 0.6577777777777778,
+      "grad_norm": 0.6708585023880005,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.6674,
+      "step": 37
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 0.7055069208145142,
+      "learning_rate": 1.684547105928689e-05,
+      "loss": 0.6624,
+      "step": 38
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 0.6366652250289917,
+      "learning_rate": 1.661311865323652e-05,
+      "loss": 0.659,
+      "step": 39
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.7192656397819519,
+      "learning_rate": 1.63742398974869e-05,
+      "loss": 0.6403,
+      "step": 40
+    },
+    {
+      "epoch": 0.7288888888888889,
+      "grad_norm": 0.7419708967208862,
+      "learning_rate": 1.6129070536529767e-05,
+      "loss": 0.6649,
+      "step": 41
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.6875132918357849,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 0.6636,
+      "step": 42
+    },
+    {
+      "epoch": 0.7644444444444445,
+      "grad_norm": 0.7200429439544678,
+      "learning_rate": 1.5620833778521306e-05,
+      "loss": 0.6464,
+      "step": 43
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 0.6726692318916321,
+      "learning_rate": 1.5358267949789968e-05,
+      "loss": 0.6513,
+      "step": 44
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.6832252740859985,
+      "learning_rate": 1.5090414157503715e-05,
+      "loss": 0.6625,
+      "step": 45
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 0.7112930417060852,
+      "learning_rate": 1.4817536741017153e-05,
+      "loss": 0.6471,
+      "step": 46
+    },
+    {
+      "epoch": 0.8355555555555556,
+      "grad_norm": 0.671824038028717,
+      "learning_rate": 1.4539904997395468e-05,
+      "loss": 0.6625,
+      "step": 47
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.6902845501899719,
+      "learning_rate": 1.4257792915650728e-05,
+      "loss": 0.6374,
+      "step": 48
+    },
+    {
+      "epoch": 0.8711111111111111,
+      "grad_norm": 0.5699530243873596,
+      "learning_rate": 1.3971478906347806e-05,
+      "loss": 0.6431,
+      "step": 49
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.6002618670463562,
+      "learning_rate": 1.3681245526846782e-05,
+      "loss": 0.6381,
+      "step": 50
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 0.576767086982727,
+      "learning_rate": 1.3387379202452917e-05,
+      "loss": 0.6338,
+      "step": 51
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 0.6442639231681824,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.6502,
+      "step": 52
+    },
+    {
+      "epoch": 0.9422222222222222,
+      "grad_norm": 0.651739776134491,
+      "learning_rate": 1.2789911060392295e-05,
+      "loss": 0.6449,
+      "step": 53
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.8692764043807983,
+      "learning_rate": 1.2486898871648552e-05,
+      "loss": 0.6511,
+      "step": 54
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.6121811270713806,
+      "learning_rate": 1.2181432413965428e-05,
+      "loss": 0.6367,
+      "step": 55
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 0.8803330659866333,
+      "learning_rate": 1.187381314585725e-05,
+      "loss": 0.6532,
+      "step": 56
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 1.236048698425293,
+      "learning_rate": 1.156434465040231e-05,
+      "loss": 1.0796,
+      "step": 57
+    },
+    {
+      "epoch": 1.031111111111111,
+      "grad_norm": 0.899872362613678,
+      "learning_rate": 1.1253332335643043e-05,
+      "loss": 0.634,
+      "step": 58
+    },
+    {
+      "epoch": 1.048888888888889,
+      "grad_norm": 0.5719662308692932,
+      "learning_rate": 1.0941083133185146e-05,
+      "loss": 0.6002,
+      "step": 59
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.788408100605011,
+      "learning_rate": 1.0627905195293135e-05,
+      "loss": 0.5628,
+      "step": 60
+    },
+    {
+      "epoch": 1.0844444444444445,
+      "grad_norm": 0.7448046207427979,
+      "learning_rate": 1.0314107590781284e-05,
+      "loss": 0.6532,
+      "step": 61
+    },
+    {
+      "epoch": 1.1022222222222222,
+      "grad_norm": 0.8060784935951233,
+      "learning_rate": 1e-05,
+      "loss": 0.5744,
+      "step": 62
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.7961754202842712,
+      "learning_rate": 9.685892409218718e-06,
+      "loss": 0.5798,
+      "step": 63
+    },
+    {
+      "epoch": 1.1377777777777778,
+      "grad_norm": 0.6215574145317078,
+      "learning_rate": 9.372094804706867e-06,
+      "loss": 0.567,
+      "step": 64
+    },
+    {
+      "epoch": 1.1555555555555554,
+      "grad_norm": 0.7157091498374939,
+      "learning_rate": 9.058916866814857e-06,
+      "loss": 0.6152,
+      "step": 65
+    },
+    {
+      "epoch": 1.1733333333333333,
+      "grad_norm": 0.6254159212112427,
+      "learning_rate": 8.746667664356957e-06,
+      "loss": 0.6099,
+      "step": 66
+    },
+    {
+      "epoch": 1.1911111111111112,
+      "grad_norm": 0.5155752897262573,
+      "learning_rate": 8.43565534959769e-06,
+      "loss": 0.5508,
+      "step": 67
+    },
+    {
+      "epoch": 1.208888888888889,
+      "grad_norm": 0.5491471886634827,
+      "learning_rate": 8.126186854142752e-06,
+      "loss": 0.625,
+      "step": 68
+    },
+    {
+      "epoch": 1.2266666666666666,
+      "grad_norm": 0.5200133919715881,
+      "learning_rate": 7.818567586034578e-06,
+      "loss": 0.5666,
+      "step": 69
+    },
+    {
+      "epoch": 1.2444444444444445,
+      "grad_norm": 0.5425897240638733,
+      "learning_rate": 7.513101128351454e-06,
+      "loss": 0.6,
+      "step": 70
+    },
+    {
+      "epoch": 1.2622222222222224,
+      "grad_norm": 0.420964777469635,
+      "learning_rate": 7.210088939607709e-06,
+      "loss": 0.5466,
+      "step": 71
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.5204867124557495,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.6297,
+      "step": 72
+    },
+    {
+      "epoch": 1.2977777777777777,
+      "grad_norm": 0.491071879863739,
+      "learning_rate": 6.612620797547087e-06,
+      "loss": 0.5333,
+      "step": 73
+    },
+    {
+      "epoch": 1.3155555555555556,
+      "grad_norm": 0.4720323979854584,
+      "learning_rate": 6.318754473153221e-06,
+      "loss": 0.6132,
+      "step": 74
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.430493026971817,
+      "learning_rate": 6.028521093652195e-06,
+      "loss": 0.5587,
+      "step": 75
+    },
+    {
+      "epoch": 1.3511111111111112,
+      "grad_norm": 0.583470344543457,
+      "learning_rate": 5.742207084349274e-06,
+      "loss": 0.6111,
+      "step": 76
+    },
+    {
+      "epoch": 1.3688888888888888,
+      "grad_norm": 0.5109282732009888,
+      "learning_rate": 5.460095002604533e-06,
+      "loss": 0.5848,
+      "step": 77
+    },
+    {
+      "epoch": 1.3866666666666667,
+      "grad_norm": 0.5880340933799744,
+      "learning_rate": 5.1824632589828465e-06,
+      "loss": 0.6158,
+      "step": 78
+    },
+    {
+      "epoch": 1.4044444444444444,
+      "grad_norm": 0.5229690670967102,
+      "learning_rate": 4.909585842496287e-06,
+      "loss": 0.5424,
+      "step": 79
+    },
+    {
+      "epoch": 1.4222222222222223,
+      "grad_norm": 0.5499680638313293,
+      "learning_rate": 4.641732050210032e-06,
+      "loss": 0.5793,
+      "step": 80
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.42541825771331787,
+      "learning_rate": 4.379166221478697e-06,
+      "loss": 0.5984,
+      "step": 81
+    },
+    {
+      "epoch": 1.4577777777777778,
+      "grad_norm": 0.46670961380004883,
+      "learning_rate": 4.12214747707527e-06,
+      "loss": 0.621,
+      "step": 82
+    },
+    {
+      "epoch": 1.4755555555555555,
+      "grad_norm": 0.4210701286792755,
+      "learning_rate": 3.8709294634702374e-06,
+      "loss": 0.5242,
+      "step": 83
+    },
+    {
+      "epoch": 1.4933333333333334,
+      "grad_norm": 0.4062272310256958,
+      "learning_rate": 3.625760102513103e-06,
+      "loss": 0.563,
+      "step": 84
+    },
+    {
+      "epoch": 1.511111111111111,
+      "grad_norm": 0.42036882042884827,
+      "learning_rate": 3.3868813467634833e-06,
+      "loss": 0.6099,
+      "step": 85
+    },
+    {
+      "epoch": 1.528888888888889,
+      "grad_norm": 0.413107693195343,
+      "learning_rate": 3.1545289407131128e-06,
+      "loss": 0.5765,
+      "step": 86
+    },
+    {
+      "epoch": 1.5466666666666666,
+      "grad_norm": 0.4331943392753601,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 0.5988,
+      "step": 87
+    },
+    {
+      "epoch": 1.5644444444444443,
+      "grad_norm": 0.4215940535068512,
+      "learning_rate": 2.7103137257858867e-06,
+      "loss": 0.5901,
+      "step": 88
+    },
+    {
+      "epoch": 1.5822222222222222,
+      "grad_norm": 0.3558850586414337,
+      "learning_rate": 2.4988893036954045e-06,
+      "loss": 0.5578,
+      "step": 89
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.35593435168266296,
+      "learning_rate": 2.2948675722421086e-06,
+      "loss": 0.5952,
+      "step": 90
+    },
+    {
+      "epoch": 1.6177777777777778,
+      "grad_norm": 0.35841694474220276,
+      "learning_rate": 2.098449876243096e-06,
+      "loss": 0.5729,
+      "step": 91
+    },
+    {
+      "epoch": 1.6355555555555554,
+      "grad_norm": 0.36976689100265503,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.6167,
+      "step": 92
+    },
+    {
+      "epoch": 1.6533333333333333,
+      "grad_norm": 0.34893473982810974,
+      "learning_rate": 1.7291942572543806e-06,
+      "loss": 0.558,
+      "step": 93
+    },
+    {
+      "epoch": 1.6711111111111112,
+      "grad_norm": 0.3704639673233032,
+      "learning_rate": 1.5567207449798517e-06,
+      "loss": 0.5948,
+      "step": 94
+    },
+    {
+      "epoch": 1.6888888888888889,
+      "grad_norm": 0.3578838109970093,
+      "learning_rate": 1.3925797299605649e-06,
+      "loss": 0.5715,
+      "step": 95
+    },
+    {
+      "epoch": 1.7066666666666666,
+      "grad_norm": 0.35762616991996765,
+      "learning_rate": 1.2369331995613664e-06,
+      "loss": 0.5936,
+      "step": 96
+    },
+    {
+      "epoch": 1.7244444444444444,
+      "grad_norm": 0.3288617730140686,
+      "learning_rate": 1.0899347581163222e-06,
+      "loss": 0.5924,
+      "step": 97
+    },
+    {
+      "epoch": 1.7422222222222223,
+      "grad_norm": 0.35121095180511475,
+      "learning_rate": 9.517294753398066e-07,
+      "loss": 0.575,
+      "step": 98
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.32291051745414734,
+      "learning_rate": 8.224537431601886e-07,
+      "loss": 0.5367,
+      "step": 99
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.37526610493659973,
+      "learning_rate": 7.022351411174866e-07,
+      "loss": 0.5957,
+      "step": 100
+    },
+    {
+      "epoch": 1.7955555555555556,
+      "grad_norm": 0.34747347235679626,
+      "learning_rate": 5.911923104577455e-07,
+      "loss": 0.5824,
+      "step": 101
+    },
+    {
+      "epoch": 1.8133333333333335,
+      "grad_norm": 0.3201601803302765,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 0.561,
+      "step": 102
+    },
+    {
+      "epoch": 1.8311111111111111,
+      "grad_norm": 0.36945855617523193,
+      "learning_rate": 3.9706314323056936e-07,
+      "loss": 0.5761,
+      "step": 103
+    },
+    {
+      "epoch": 1.8488888888888888,
+      "grad_norm": 0.3337363600730896,
+      "learning_rate": 3.1416838871368925e-07,
+      "loss": 0.5536,
+      "step": 104
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.35673728585243225,
+      "learning_rate": 2.4083238061252565e-07,
+      "loss": 0.6234,
+      "step": 105
+    },
+    {
+      "epoch": 1.8844444444444446,
+      "grad_norm": 0.3251909613609314,
+      "learning_rate": 1.7712749271311392e-07,
+      "loss": 0.5415,
+      "step": 106
+    },
+    {
+      "epoch": 1.9022222222222223,
+      "grad_norm": 0.35213449597358704,
+      "learning_rate": 1.231165940486234e-07,
+      "loss": 0.5611,
+      "step": 107
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.34044721722602844,
+      "learning_rate": 7.885298685522235e-08,
+      "loss": 0.5628,
+      "step": 108
+    },
+    {
+      "epoch": 1.9377777777777778,
+      "grad_norm": 0.34606897830963135,
+      "learning_rate": 4.438035396920004e-08,
+      "loss": 0.5907,
+      "step": 109
+    },
+    {
+      "epoch": 1.9555555555555557,
+      "grad_norm": 0.3360365629196167,
+      "learning_rate": 1.973271571728441e-08,
+      "loss": 0.6009,
+      "step": 110
+    },
+    {
+      "epoch": 1.9733333333333334,
+      "grad_norm": 0.3323586583137512,
+      "learning_rate": 4.9343963426840006e-09,
+      "loss": 0.5773,
+      "step": 111
+    },
+    {
+      "epoch": 1.991111111111111,
+      "grad_norm": 0.3478974997997284,
+      "learning_rate": 0.0,
+      "loss": 0.5963,
+      "step": 112
+    },
+    {
+      "epoch": 1.991111111111111,
+      "step": 112,
+      "total_flos": 185195202609152.0,
+      "train_loss": 0.65867241738098,
+      "train_runtime": 12992.6194,
+      "train_samples_per_second": 0.83,
+      "train_steps_per_second": 0.009
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 112,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 185195202609152.0,
+  "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 sha256:6add66dd5d153f621aa86f217739a1b5097adfcd09ff4887b181d9a284c89ba7
+size 7416