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 +1,60 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: Qwen2.5-7B-Instruct_d1_science_all_large
+  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. -->
+
+# Qwen2.5-7B-Instruct_d1_science_all_large
+
+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/d1_science_all_large 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 0.20.0

added_tokens.json

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

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 3606870585507840.0,
+    "train_loss": 0.5023871626964835,
+    "train_runtime": 3261.3525,
+    "train_samples_per_second": 33.201,
+    "train_steps_per_second": 0.066
+}

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 sha256:5bc3345e3a1217d516a8dd5cddf3b5afc586f5eb2aa6ae8463e672b014fb07e0
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca327d07de324be9140098379f9d37a0cd64c7415465bc677e5f479725257434
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c940639eb569ae1720c6c19bd160bc8fdb325554ed9b8f56ea6374a22a98a13
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f08d3feaa25ceafc730d1863f88c51aa4a7424794adabe6a7edb9f3b1ed32299
+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": 5.0,
+    "total_flos": 3606870585507840.0,
+    "train_loss": 0.5023871626964835,
+    "train_runtime": 3261.3525,
+    "train_samples_per_second": 33.201,
+    "train_steps_per_second": 0.066
+}

trainer_log.jsonl

@@ -0,0 +1,216 @@
+{"current_steps": 1, "total_steps": 215, "loss": 0.9705, "lr": 3.6363636363636366e-06, "epoch": 0.023255813953488372, "percentage": 0.47, "elapsed_time": "0:00:42", "remaining_time": "2:31:20"}
+{"current_steps": 2, "total_steps": 215, "loss": 0.9693, "lr": 7.272727272727273e-06, "epoch": 0.046511627906976744, "percentage": 0.93, "elapsed_time": "0:00:55", "remaining_time": "1:37:57"}
+{"current_steps": 3, "total_steps": 215, "loss": 0.971, "lr": 1.0909090909090909e-05, "epoch": 0.06976744186046512, "percentage": 1.4, "elapsed_time": "0:01:07", "remaining_time": "1:19:42"}
+{"current_steps": 4, "total_steps": 215, "loss": 0.882, "lr": 1.4545454545454546e-05, "epoch": 0.09302325581395349, "percentage": 1.86, "elapsed_time": "0:01:20", "remaining_time": "1:10:57"}
+{"current_steps": 5, "total_steps": 215, "loss": 0.9089, "lr": 1.8181818181818182e-05, "epoch": 0.11627906976744186, "percentage": 2.33, "elapsed_time": "0:01:33", "remaining_time": "1:05:34"}
+{"current_steps": 6, "total_steps": 215, "loss": 0.9031, "lr": 2.1818181818181818e-05, "epoch": 0.13953488372093023, "percentage": 2.79, "elapsed_time": "0:01:47", "remaining_time": "1:02:14"}
+{"current_steps": 7, "total_steps": 215, "loss": 0.9058, "lr": 2.5454545454545457e-05, "epoch": 0.16279069767441862, "percentage": 3.26, "elapsed_time": "0:02:00", "remaining_time": "0:59:28"}
+{"current_steps": 8, "total_steps": 215, "loss": 0.8423, "lr": 2.9090909090909093e-05, "epoch": 0.18604651162790697, "percentage": 3.72, "elapsed_time": "0:02:13", "remaining_time": "0:57:24"}
+{"current_steps": 9, "total_steps": 215, "loss": 0.8043, "lr": 3.272727272727273e-05, "epoch": 0.20930232558139536, "percentage": 4.19, "elapsed_time": "0:02:25", "remaining_time": "0:55:35"}
+{"current_steps": 10, "total_steps": 215, "loss": 0.7799, "lr": 3.6363636363636364e-05, "epoch": 0.23255813953488372, "percentage": 4.65, "elapsed_time": "0:02:38", "remaining_time": "0:54:05"}
+{"current_steps": 11, "total_steps": 215, "loss": 0.7546, "lr": 4e-05, "epoch": 0.2558139534883721, "percentage": 5.12, "elapsed_time": "0:02:50", "remaining_time": "0:52:46"}
+{"current_steps": 12, "total_steps": 215, "loss": 0.7408, "lr": 4.3636363636363636e-05, "epoch": 0.27906976744186046, "percentage": 5.58, "elapsed_time": "0:03:03", "remaining_time": "0:51:46"}
+{"current_steps": 13, "total_steps": 215, "loss": 0.7216, "lr": 4.727272727272728e-05, "epoch": 0.3023255813953488, "percentage": 6.05, "elapsed_time": "0:03:16", "remaining_time": "0:50:48"}
+{"current_steps": 14, "total_steps": 215, "loss": 0.724, "lr": 5.0909090909090914e-05, "epoch": 0.32558139534883723, "percentage": 6.51, "elapsed_time": "0:03:28", "remaining_time": "0:49:58"}
+{"current_steps": 15, "total_steps": 215, "loss": 0.7084, "lr": 5.4545454545454546e-05, "epoch": 0.3488372093023256, "percentage": 6.98, "elapsed_time": "0:03:41", "remaining_time": "0:49:16"}
+{"current_steps": 16, "total_steps": 215, "loss": 0.6992, "lr": 5.8181818181818185e-05, "epoch": 0.37209302325581395, "percentage": 7.44, "elapsed_time": "0:03:54", "remaining_time": "0:48:37"}
+{"current_steps": 17, "total_steps": 215, "loss": 0.6969, "lr": 6.181818181818182e-05, "epoch": 0.3953488372093023, "percentage": 7.91, "elapsed_time": "0:04:07", "remaining_time": "0:48:05"}
+{"current_steps": 18, "total_steps": 215, "loss": 0.6819, "lr": 6.545454545454546e-05, "epoch": 0.4186046511627907, "percentage": 8.37, "elapsed_time": "0:04:20", "remaining_time": "0:47:32"}
+{"current_steps": 19, "total_steps": 215, "loss": 0.6986, "lr": 6.90909090909091e-05, "epoch": 0.4418604651162791, "percentage": 8.84, "elapsed_time": "0:04:33", "remaining_time": "0:47:01"}
+{"current_steps": 20, "total_steps": 215, "loss": 0.6801, "lr": 7.272727272727273e-05, "epoch": 0.46511627906976744, "percentage": 9.3, "elapsed_time": "0:04:46", "remaining_time": "0:46:32"}
+{"current_steps": 21, "total_steps": 215, "loss": 0.6751, "lr": 7.636363636363637e-05, "epoch": 0.4883720930232558, "percentage": 9.77, "elapsed_time": "0:04:59", "remaining_time": "0:46:06"}
+{"current_steps": 22, "total_steps": 215, "loss": 0.673, "lr": 8e-05, "epoch": 0.5116279069767442, "percentage": 10.23, "elapsed_time": "0:05:11", "remaining_time": "0:45:36"}
+{"current_steps": 23, "total_steps": 215, "loss": 0.6629, "lr": 7.999470085828896e-05, "epoch": 0.5348837209302325, "percentage": 10.7, "elapsed_time": "0:05:24", "remaining_time": "0:45:09"}
+{"current_steps": 24, "total_steps": 215, "loss": 0.6716, "lr": 7.997880483720098e-05, "epoch": 0.5581395348837209, "percentage": 11.16, "elapsed_time": "0:05:37", "remaining_time": "0:44:42"}
+{"current_steps": 25, "total_steps": 215, "loss": 0.671, "lr": 7.995231614849947e-05, "epoch": 0.5813953488372093, "percentage": 11.63, "elapsed_time": "0:05:50", "remaining_time": "0:44:20"}
+{"current_steps": 26, "total_steps": 215, "loss": 0.6608, "lr": 7.991524181055018e-05, "epoch": 0.6046511627906976, "percentage": 12.09, "elapsed_time": "0:06:02", "remaining_time": "0:43:54"}
+{"current_steps": 27, "total_steps": 215, "loss": 0.673, "lr": 7.986759164646167e-05, "epoch": 0.627906976744186, "percentage": 12.56, "elapsed_time": "0:06:15", "remaining_time": "0:43:32"}
+{"current_steps": 28, "total_steps": 215, "loss": 0.6916, "lr": 7.980937828148252e-05, "epoch": 0.6511627906976745, "percentage": 13.02, "elapsed_time": "0:06:27", "remaining_time": "0:43:11"}
+{"current_steps": 29, "total_steps": 215, "loss": 0.6487, "lr": 7.974061713965625e-05, "epoch": 0.6744186046511628, "percentage": 13.49, "elapsed_time": "0:06:41", "remaining_time": "0:42:52"}
+{"current_steps": 30, "total_steps": 215, "loss": 0.6429, "lr": 7.966132643973464e-05, "epoch": 0.6976744186046512, "percentage": 13.95, "elapsed_time": "0:06:53", "remaining_time": "0:42:31"}
+{"current_steps": 31, "total_steps": 215, "loss": 0.6398, "lr": 7.95715271903504e-05, "epoch": 0.7209302325581395, "percentage": 14.42, "elapsed_time": "0:07:06", "remaining_time": "0:42:11"}
+{"current_steps": 32, "total_steps": 215, "loss": 0.6398, "lr": 7.947124318445097e-05, "epoch": 0.7441860465116279, "percentage": 14.88, "elapsed_time": "0:07:36", "remaining_time": "0:43:29"}
+{"current_steps": 33, "total_steps": 215, "loss": 0.6243, "lr": 7.936050099299425e-05, "epoch": 0.7674418604651163, "percentage": 15.35, "elapsed_time": "0:07:49", "remaining_time": "0:43:08"}
+{"current_steps": 34, "total_steps": 215, "loss": 0.6335, "lr": 7.923932995790858e-05, "epoch": 0.7906976744186046, "percentage": 15.81, "elapsed_time": "0:08:01", "remaining_time": "0:42:44"}
+{"current_steps": 35, "total_steps": 215, "loss": 0.6224, "lr": 7.910776218431821e-05, "epoch": 0.813953488372093, "percentage": 16.28, "elapsed_time": "0:08:14", "remaining_time": "0:42:22"}
+{"current_steps": 36, "total_steps": 215, "loss": 0.6219, "lr": 7.896583253203703e-05, "epoch": 0.8372093023255814, "percentage": 16.74, "elapsed_time": "0:08:27", "remaining_time": "0:42:01"}
+{"current_steps": 37, "total_steps": 215, "loss": 0.6232, "lr": 7.881357860633204e-05, "epoch": 0.8604651162790697, "percentage": 17.21, "elapsed_time": "0:08:40", "remaining_time": "0:41:43"}
+{"current_steps": 38, "total_steps": 215, "loss": 0.5977, "lr": 7.865104074795966e-05, "epoch": 0.8837209302325582, "percentage": 17.67, "elapsed_time": "0:08:53", "remaining_time": "0:41:23"}
+{"current_steps": 39, "total_steps": 215, "loss": 0.6193, "lr": 7.847826202247715e-05, "epoch": 0.9069767441860465, "percentage": 18.14, "elapsed_time": "0:09:05", "remaining_time": "0:41:02"}
+{"current_steps": 40, "total_steps": 215, "loss": 0.604, "lr": 7.829528820883205e-05, "epoch": 0.9302325581395349, "percentage": 18.6, "elapsed_time": "0:09:18", "remaining_time": "0:40:41"}
+{"current_steps": 41, "total_steps": 215, "loss": 0.5909, "lr": 7.810216778723275e-05, "epoch": 0.9534883720930233, "percentage": 19.07, "elapsed_time": "0:09:31", "remaining_time": "0:40:24"}
+{"current_steps": 42, "total_steps": 215, "loss": 0.5927, "lr": 7.789895192630333e-05, "epoch": 0.9767441860465116, "percentage": 19.53, "elapsed_time": "0:09:44", "remaining_time": "0:40:06"}
+{"current_steps": 43, "total_steps": 215, "loss": 0.5843, "lr": 7.768569446952603e-05, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "0:12:50", "remaining_time": "0:51:22"}
+{"current_steps": 44, "total_steps": 215, "loss": 0.5722, "lr": 7.746245192097509e-05, "epoch": 1.0232558139534884, "percentage": 20.47, "elapsed_time": "0:13:45", "remaining_time": "0:53:26"}
+{"current_steps": 45, "total_steps": 215, "loss": 0.5773, "lr": 7.722928343034551e-05, "epoch": 1.0465116279069768, "percentage": 20.93, "elapsed_time": "0:13:58", "remaining_time": "0:52:46"}
+{"current_steps": 46, "total_steps": 215, "loss": 0.5672, "lr": 7.698625077728103e-05, "epoch": 1.069767441860465, "percentage": 21.4, "elapsed_time": "0:14:11", "remaining_time": "0:52:07"}
+{"current_steps": 47, "total_steps": 215, "loss": 0.5674, "lr": 7.67334183550051e-05, "epoch": 1.0930232558139534, "percentage": 21.86, "elapsed_time": "0:14:24", "remaining_time": "0:51:28"}
+{"current_steps": 48, "total_steps": 215, "loss": 0.5671, "lr": 7.647085315325946e-05, "epoch": 1.1162790697674418, "percentage": 22.33, "elapsed_time": "0:14:36", "remaining_time": "0:50:51"}
+{"current_steps": 49, "total_steps": 215, "loss": 0.5638, "lr": 7.619862474055472e-05, "epoch": 1.1395348837209303, "percentage": 22.79, "elapsed_time": "0:14:50", "remaining_time": "0:50:15"}
+{"current_steps": 50, "total_steps": 215, "loss": 0.5625, "lr": 7.591680524573773e-05, "epoch": 1.1627906976744187, "percentage": 23.26, "elapsed_time": "0:15:02", "remaining_time": "0:49:38"}
+{"current_steps": 51, "total_steps": 215, "loss": 0.5592, "lr": 7.56254693388805e-05, "epoch": 1.1860465116279069, "percentage": 23.72, "elapsed_time": "0:15:15", "remaining_time": "0:49:04"}
+{"current_steps": 52, "total_steps": 215, "loss": 0.5599, "lr": 7.532469421149578e-05, "epoch": 1.2093023255813953, "percentage": 24.19, "elapsed_time": "0:15:28", "remaining_time": "0:48:30"}
+{"current_steps": 53, "total_steps": 215, "loss": 0.5559, "lr": 7.501455955608479e-05, "epoch": 1.2325581395348837, "percentage": 24.65, "elapsed_time": "0:15:41", "remaining_time": "0:47:56"}
+{"current_steps": 54, "total_steps": 215, "loss": 0.5549, "lr": 7.469514754502191e-05, "epoch": 1.255813953488372, "percentage": 25.12, "elapsed_time": "0:15:54", "remaining_time": "0:47:24"}
+{"current_steps": 55, "total_steps": 215, "loss": 0.546, "lr": 7.436654280878269e-05, "epoch": 1.2790697674418605, "percentage": 25.58, "elapsed_time": "0:16:07", "remaining_time": "0:46:53"}
+{"current_steps": 56, "total_steps": 215, "loss": 0.5492, "lr": 7.402883241352037e-05, "epoch": 1.302325581395349, "percentage": 26.05, "elapsed_time": "0:16:20", "remaining_time": "0:46:22"}
+{"current_steps": 57, "total_steps": 215, "loss": 0.5481, "lr": 7.368210583799701e-05, "epoch": 1.3255813953488373, "percentage": 26.51, "elapsed_time": "0:16:32", "remaining_time": "0:45:52"}
+{"current_steps": 58, "total_steps": 215, "loss": 0.544, "lr": 7.332645494987555e-05, "epoch": 1.3488372093023255, "percentage": 26.98, "elapsed_time": "0:16:45", "remaining_time": "0:45:23"}
+{"current_steps": 59, "total_steps": 215, "loss": 0.5399, "lr": 7.296197398137878e-05, "epoch": 1.372093023255814, "percentage": 27.44, "elapsed_time": "0:16:59", "remaining_time": "0:44:54"}
+{"current_steps": 60, "total_steps": 215, "loss": 0.5457, "lr": 7.258875950432185e-05, "epoch": 1.3953488372093024, "percentage": 27.91, "elapsed_time": "0:17:11", "remaining_time": "0:44:25"}
+{"current_steps": 61, "total_steps": 215, "loss": 0.533, "lr": 7.220691040452491e-05, "epoch": 1.4186046511627908, "percentage": 28.37, "elapsed_time": "0:17:24", "remaining_time": "0:43:57"}
+{"current_steps": 62, "total_steps": 215, "loss": 0.5467, "lr": 7.181652785561254e-05, "epoch": 1.441860465116279, "percentage": 28.84, "elapsed_time": "0:17:37", "remaining_time": "0:43:29"}
+{"current_steps": 63, "total_steps": 215, "loss": 0.536, "lr": 7.141771529220716e-05, "epoch": 1.4651162790697674, "percentage": 29.3, "elapsed_time": "0:17:50", "remaining_time": "0:43:03"}
+{"current_steps": 64, "total_steps": 215, "loss": 0.5309, "lr": 7.101057838252324e-05, "epoch": 1.4883720930232558, "percentage": 29.77, "elapsed_time": "0:18:03", "remaining_time": "0:42:35"}
+{"current_steps": 65, "total_steps": 215, "loss": 0.535, "lr": 7.05952250003698e-05, "epoch": 1.5116279069767442, "percentage": 30.23, "elapsed_time": "0:18:15", "remaining_time": "0:42:08"}
+{"current_steps": 66, "total_steps": 215, "loss": 0.5378, "lr": 7.017176519656845e-05, "epoch": 1.5348837209302326, "percentage": 30.7, "elapsed_time": "0:18:28", "remaining_time": "0:41:42"}
+{"current_steps": 67, "total_steps": 215, "loss": 0.5407, "lr": 6.974031116979466e-05, "epoch": 1.558139534883721, "percentage": 31.16, "elapsed_time": "0:18:41", "remaining_time": "0:41:17"}
+{"current_steps": 68, "total_steps": 215, "loss": 0.5375, "lr": 6.93009772368499e-05, "epoch": 1.5813953488372094, "percentage": 31.63, "elapsed_time": "0:18:54", "remaining_time": "0:40:52"}
+{"current_steps": 69, "total_steps": 215, "loss": 0.5251, "lr": 6.885387980237262e-05, "epoch": 1.6046511627906976, "percentage": 32.09, "elapsed_time": "0:19:07", "remaining_time": "0:40:27"}
+{"current_steps": 70, "total_steps": 215, "loss": 0.5274, "lr": 6.839913732799604e-05, "epoch": 1.627906976744186, "percentage": 32.56, "elapsed_time": "0:19:20", "remaining_time": "0:40:03"}
+{"current_steps": 71, "total_steps": 215, "loss": 0.5295, "lr": 6.793687030096085e-05, "epoch": 1.6511627906976745, "percentage": 33.02, "elapsed_time": "0:19:32", "remaining_time": "0:39:39"}
+{"current_steps": 72, "total_steps": 215, "loss": 0.5421, "lr": 6.746720120219126e-05, "epoch": 1.6744186046511627, "percentage": 33.49, "elapsed_time": "0:19:45", "remaining_time": "0:39:15"}
+{"current_steps": 73, "total_steps": 215, "loss": 0.5312, "lr": 6.699025447384284e-05, "epoch": 1.697674418604651, "percentage": 33.95, "elapsed_time": "0:19:58", "remaining_time": "0:38:51"}
+{"current_steps": 74, "total_steps": 215, "loss": 0.5246, "lr": 6.650615648633075e-05, "epoch": 1.7209302325581395, "percentage": 34.42, "elapsed_time": "0:20:11", "remaining_time": "0:38:28"}
+{"current_steps": 75, "total_steps": 215, "loss": 0.5258, "lr": 6.601503550484684e-05, "epoch": 1.744186046511628, "percentage": 34.88, "elapsed_time": "0:20:24", "remaining_time": "0:38:05"}
+{"current_steps": 76, "total_steps": 215, "loss": 0.5271, "lr": 6.5517021655375e-05, "epoch": 1.7674418604651163, "percentage": 35.35, "elapsed_time": "0:20:37", "remaining_time": "0:37:42"}
+{"current_steps": 77, "total_steps": 215, "loss": 0.5185, "lr": 6.501224689021341e-05, "epoch": 1.7906976744186047, "percentage": 35.81, "elapsed_time": "0:20:49", "remaining_time": "0:37:19"}
+{"current_steps": 78, "total_steps": 215, "loss": 0.5169, "lr": 6.450084495301268e-05, "epoch": 1.8139534883720931, "percentage": 36.28, "elapsed_time": "0:21:02", "remaining_time": "0:36:57"}
+{"current_steps": 79, "total_steps": 215, "loss": 0.5197, "lr": 6.398295134333962e-05, "epoch": 1.8372093023255816, "percentage": 36.74, "elapsed_time": "0:21:15", "remaining_time": "0:36:35"}
+{"current_steps": 80, "total_steps": 215, "loss": 0.5189, "lr": 6.345870328077569e-05, "epoch": 1.8604651162790697, "percentage": 37.21, "elapsed_time": "0:21:28", "remaining_time": "0:36:14"}
+{"current_steps": 81, "total_steps": 215, "loss": 0.5184, "lr": 6.292823966855965e-05, "epoch": 1.8837209302325582, "percentage": 37.67, "elapsed_time": "0:21:41", "remaining_time": "0:35:52"}
+{"current_steps": 82, "total_steps": 215, "loss": 0.5151, "lr": 6.239170105678419e-05, "epoch": 1.9069767441860463, "percentage": 38.14, "elapsed_time": "0:21:53", "remaining_time": "0:35:31"}
+{"current_steps": 83, "total_steps": 215, "loss": 0.5088, "lr": 6.184922960515616e-05, "epoch": 1.9302325581395348, "percentage": 38.6, "elapsed_time": "0:22:07", "remaining_time": "0:35:10"}
+{"current_steps": 84, "total_steps": 215, "loss": 0.5212, "lr": 6.13009690453304e-05, "epoch": 1.9534883720930232, "percentage": 39.07, "elapsed_time": "0:22:20", "remaining_time": "0:34:50"}
+{"current_steps": 85, "total_steps": 215, "loss": 0.5081, "lr": 6.074706464282695e-05, "epoch": 1.9767441860465116, "percentage": 39.53, "elapsed_time": "0:22:33", "remaining_time": "0:34:29"}
+{"current_steps": 86, "total_steps": 215, "loss": 0.4843, "lr": 6.018766315854196e-05, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "0:22:45", "remaining_time": "0:34:08"}
+{"current_steps": 87, "total_steps": 215, "loss": 0.4787, "lr": 5.9622912809862384e-05, "epoch": 2.0232558139534884, "percentage": 40.47, "elapsed_time": "0:23:42", "remaining_time": "0:34:53"}
+{"current_steps": 88, "total_steps": 215, "loss": 0.4779, "lr": 5.905296323139467e-05, "epoch": 2.046511627906977, "percentage": 40.93, "elapsed_time": "0:23:56", "remaining_time": "0:34:33"}
+{"current_steps": 89, "total_steps": 215, "loss": 0.4708, "lr": 5.847796543531801e-05, "epoch": 2.0697674418604652, "percentage": 41.4, "elapsed_time": "0:24:09", "remaining_time": "0:34:12"}
+{"current_steps": 90, "total_steps": 215, "loss": 0.4747, "lr": 5.789807177137269e-05, "epoch": 2.0930232558139537, "percentage": 41.86, "elapsed_time": "0:24:22", "remaining_time": "0:33:51"}
+{"current_steps": 91, "total_steps": 215, "loss": 0.4707, "lr": 5.731343588649382e-05, "epoch": 2.116279069767442, "percentage": 42.33, "elapsed_time": "0:24:35", "remaining_time": "0:33:31"}
+{"current_steps": 92, "total_steps": 215, "loss": 0.4724, "lr": 5.6724212684101567e-05, "epoch": 2.13953488372093, "percentage": 42.79, "elapsed_time": "0:24:48", "remaining_time": "0:33:09"}
+{"current_steps": 93, "total_steps": 215, "loss": 0.4659, "lr": 5.613055828305838e-05, "epoch": 2.1627906976744184, "percentage": 43.26, "elapsed_time": "0:25:02", "remaining_time": "0:32:50"}
+{"current_steps": 94, "total_steps": 215, "loss": 0.4592, "lr": 5.553262997630419e-05, "epoch": 2.186046511627907, "percentage": 43.72, "elapsed_time": "0:25:14", "remaining_time": "0:32:29"}
+{"current_steps": 95, "total_steps": 215, "loss": 0.464, "lr": 5.493058618918051e-05, "epoch": 2.2093023255813953, "percentage": 44.19, "elapsed_time": "0:25:27", "remaining_time": "0:32:09"}
+{"current_steps": 96, "total_steps": 215, "loss": 0.4728, "lr": 5.432458643745456e-05, "epoch": 2.2325581395348837, "percentage": 44.65, "elapsed_time": "0:25:41", "remaining_time": "0:31:50"}
+{"current_steps": 97, "total_steps": 215, "loss": 0.4719, "lr": 5.37147912850544e-05, "epoch": 2.255813953488372, "percentage": 45.12, "elapsed_time": "0:25:54", "remaining_time": "0:31:31"}
+{"current_steps": 98, "total_steps": 215, "loss": 0.4635, "lr": 5.31013623015264e-05, "epoch": 2.2790697674418605, "percentage": 45.58, "elapsed_time": "0:26:07", "remaining_time": "0:31:11"}
+{"current_steps": 99, "total_steps": 215, "loss": 0.4636, "lr": 5.2484462019226216e-05, "epoch": 2.302325581395349, "percentage": 46.05, "elapsed_time": "0:26:19", "remaining_time": "0:30:51"}
+{"current_steps": 100, "total_steps": 215, "loss": 0.4669, "lr": 5.1864253890254744e-05, "epoch": 2.3255813953488373, "percentage": 46.51, "elapsed_time": "0:26:32", "remaining_time": "0:30:31"}
+{"current_steps": 101, "total_steps": 215, "loss": 0.4643, "lr": 5.1240902243150245e-05, "epoch": 2.3488372093023258, "percentage": 46.98, "elapsed_time": "0:26:46", "remaining_time": "0:30:12"}
+{"current_steps": 102, "total_steps": 215, "loss": 0.468, "lr": 5.0614572239348436e-05, "epoch": 2.3720930232558137, "percentage": 47.44, "elapsed_time": "0:26:58", "remaining_time": "0:29:53"}
+{"current_steps": 103, "total_steps": 215, "loss": 0.4646, "lr": 4.998542982942169e-05, "epoch": 2.395348837209302, "percentage": 47.91, "elapsed_time": "0:27:11", "remaining_time": "0:29:34"}
+{"current_steps": 104, "total_steps": 215, "loss": 0.466, "lr": 4.9353641709109366e-05, "epoch": 2.4186046511627906, "percentage": 48.37, "elapsed_time": "0:27:25", "remaining_time": "0:29:16"}
+{"current_steps": 105, "total_steps": 215, "loss": 0.4605, "lr": 4.87193752751505e-05, "epoch": 2.441860465116279, "percentage": 48.84, "elapsed_time": "0:27:38", "remaining_time": "0:28:57"}
+{"current_steps": 106, "total_steps": 215, "loss": 0.4633, "lr": 4.808279858093088e-05, "epoch": 2.4651162790697674, "percentage": 49.3, "elapsed_time": "0:27:51", "remaining_time": "0:28:38"}
+{"current_steps": 107, "total_steps": 215, "loss": 0.458, "lr": 4.744408029195616e-05, "epoch": 2.488372093023256, "percentage": 49.77, "elapsed_time": "0:28:04", "remaining_time": "0:28:19"}
+{"current_steps": 108, "total_steps": 215, "loss": 0.4694, "lr": 4.680338964116267e-05, "epoch": 2.511627906976744, "percentage": 50.23, "elapsed_time": "0:28:17", "remaining_time": "0:28:01"}
+{"current_steps": 109, "total_steps": 215, "loss": 0.4572, "lr": 4.616089638407798e-05, "epoch": 2.5348837209302326, "percentage": 50.7, "elapsed_time": "0:28:30", "remaining_time": "0:27:43"}
+{"current_steps": 110, "total_steps": 215, "loss": 0.4642, "lr": 4.551677075384296e-05, "epoch": 2.558139534883721, "percentage": 51.16, "elapsed_time": "0:28:44", "remaining_time": "0:27:25"}
+{"current_steps": 111, "total_steps": 215, "loss": 0.4558, "lr": 4.487118341610736e-05, "epoch": 2.5813953488372094, "percentage": 51.63, "elapsed_time": "0:28:56", "remaining_time": "0:27:07"}
+{"current_steps": 112, "total_steps": 215, "loss": 0.4646, "lr": 4.422430542381064e-05, "epoch": 2.604651162790698, "percentage": 52.09, "elapsed_time": "0:29:09", "remaining_time": "0:26:49"}
+{"current_steps": 113, "total_steps": 215, "loss": 0.4624, "lr": 4.3576308171860336e-05, "epoch": 2.6279069767441863, "percentage": 52.56, "elapsed_time": "0:29:22", "remaining_time": "0:26:31"}
+{"current_steps": 114, "total_steps": 215, "loss": 0.4566, "lr": 4.292736335171978e-05, "epoch": 2.6511627906976747, "percentage": 53.02, "elapsed_time": "0:29:35", "remaining_time": "0:26:13"}
+{"current_steps": 115, "total_steps": 215, "loss": 0.4566, "lr": 4.2277642905917205e-05, "epoch": 2.6744186046511627, "percentage": 53.49, "elapsed_time": "0:29:48", "remaining_time": "0:25:55"}
+{"current_steps": 116, "total_steps": 215, "loss": 0.4599, "lr": 4.162731898248834e-05, "epoch": 2.697674418604651, "percentage": 53.95, "elapsed_time": "0:30:01", "remaining_time": "0:25:37"}
+{"current_steps": 117, "total_steps": 215, "loss": 0.4623, "lr": 4.097656388936462e-05, "epoch": 2.7209302325581395, "percentage": 54.42, "elapsed_time": "0:30:14", "remaining_time": "0:25:20"}
+{"current_steps": 118, "total_steps": 215, "loss": 0.4587, "lr": 4.032555004871892e-05, "epoch": 2.744186046511628, "percentage": 54.88, "elapsed_time": "0:30:28", "remaining_time": "0:25:02"}
+{"current_steps": 119, "total_steps": 215, "loss": 0.4576, "lr": 3.9674449951281095e-05, "epoch": 2.7674418604651163, "percentage": 55.35, "elapsed_time": "0:30:40", "remaining_time": "0:24:45"}
+{"current_steps": 120, "total_steps": 215, "loss": 0.4556, "lr": 3.902343611063539e-05, "epoch": 2.7906976744186047, "percentage": 55.81, "elapsed_time": "0:30:53", "remaining_time": "0:24:27"}
+{"current_steps": 121, "total_steps": 215, "loss": 0.4558, "lr": 3.837268101751166e-05, "epoch": 2.813953488372093, "percentage": 56.28, "elapsed_time": "0:31:06", "remaining_time": "0:24:10"}
+{"current_steps": 122, "total_steps": 215, "loss": 0.4618, "lr": 3.7722357094082815e-05, "epoch": 2.8372093023255816, "percentage": 56.74, "elapsed_time": "0:31:19", "remaining_time": "0:23:53"}
+{"current_steps": 123, "total_steps": 215, "loss": 0.4591, "lr": 3.707263664828023e-05, "epoch": 2.8604651162790695, "percentage": 57.21, "elapsed_time": "0:31:32", "remaining_time": "0:23:35"}
+{"current_steps": 124, "total_steps": 215, "loss": 0.4524, "lr": 3.6423691828139685e-05, "epoch": 2.883720930232558, "percentage": 57.67, "elapsed_time": "0:31:45", "remaining_time": "0:23:18"}
+{"current_steps": 125, "total_steps": 215, "loss": 0.4606, "lr": 3.577569457618937e-05, "epoch": 2.9069767441860463, "percentage": 58.14, "elapsed_time": "0:31:59", "remaining_time": "0:23:01"}
+{"current_steps": 126, "total_steps": 215, "loss": 0.4578, "lr": 3.512881658389265e-05, "epoch": 2.9302325581395348, "percentage": 58.6, "elapsed_time": "0:32:13", "remaining_time": "0:22:45"}
+{"current_steps": 127, "total_steps": 215, "loss": 0.4544, "lr": 3.448322924615703e-05, "epoch": 2.953488372093023, "percentage": 59.07, "elapsed_time": "0:32:25", "remaining_time": "0:22:28"}
+{"current_steps": 128, "total_steps": 215, "loss": 0.458, "lr": 3.383910361592204e-05, "epoch": 2.9767441860465116, "percentage": 59.53, "elapsed_time": "0:32:38", "remaining_time": "0:22:11"}
+{"current_steps": 129, "total_steps": 215, "loss": 0.427, "lr": 3.319661035883734e-05, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "0:32:52", "remaining_time": "0:21:54"}
+{"current_steps": 130, "total_steps": 215, "loss": 0.4232, "lr": 3.2555919708043856e-05, "epoch": 3.0232558139534884, "percentage": 60.47, "elapsed_time": "0:33:51", "remaining_time": "0:22:07"}
+{"current_steps": 131, "total_steps": 215, "loss": 0.4149, "lr": 3.1917201419069126e-05, "epoch": 3.046511627906977, "percentage": 60.93, "elapsed_time": "0:34:03", "remaining_time": "0:21:50"}
+{"current_steps": 132, "total_steps": 215, "loss": 0.4193, "lr": 3.128062472484952e-05, "epoch": 3.0697674418604652, "percentage": 61.4, "elapsed_time": "0:34:16", "remaining_time": "0:21:33"}
+{"current_steps": 133, "total_steps": 215, "loss": 0.4113, "lr": 3.064635829089064e-05, "epoch": 3.0930232558139537, "percentage": 61.86, "elapsed_time": "0:34:30", "remaining_time": "0:21:16"}
+{"current_steps": 134, "total_steps": 215, "loss": 0.417, "lr": 3.0014570170578324e-05, "epoch": 3.116279069767442, "percentage": 62.33, "elapsed_time": "0:34:43", "remaining_time": "0:20:59"}
+{"current_steps": 135, "total_steps": 215, "loss": 0.4137, "lr": 2.938542776065158e-05, "epoch": 3.13953488372093, "percentage": 62.79, "elapsed_time": "0:34:56", "remaining_time": "0:20:42"}
+{"current_steps": 136, "total_steps": 215, "loss": 0.4211, "lr": 2.875909775684977e-05, "epoch": 3.1627906976744184, "percentage": 63.26, "elapsed_time": "0:35:09", "remaining_time": "0:20:25"}
+{"current_steps": 137, "total_steps": 215, "loss": 0.4138, "lr": 2.8135746109745273e-05, "epoch": 3.186046511627907, "percentage": 63.72, "elapsed_time": "0:35:22", "remaining_time": "0:20:08"}
+{"current_steps": 138, "total_steps": 215, "loss": 0.4153, "lr": 2.751553798077379e-05, "epoch": 3.2093023255813953, "percentage": 64.19, "elapsed_time": "0:35:36", "remaining_time": "0:19:52"}
+{"current_steps": 139, "total_steps": 215, "loss": 0.4135, "lr": 2.6898637698473605e-05, "epoch": 3.2325581395348837, "percentage": 64.65, "elapsed_time": "0:35:49", "remaining_time": "0:19:35"}
+{"current_steps": 140, "total_steps": 215, "loss": 0.407, "lr": 2.6285208714945615e-05, "epoch": 3.255813953488372, "percentage": 65.12, "elapsed_time": "0:36:01", "remaining_time": "0:19:18"}
+{"current_steps": 141, "total_steps": 215, "loss": 0.4044, "lr": 2.5675413562545453e-05, "epoch": 3.2790697674418605, "percentage": 65.58, "elapsed_time": "0:36:14", "remaining_time": "0:19:01"}
+{"current_steps": 142, "total_steps": 215, "loss": 0.4073, "lr": 2.5069413810819503e-05, "epoch": 3.302325581395349, "percentage": 66.05, "elapsed_time": "0:36:27", "remaining_time": "0:18:44"}
+{"current_steps": 143, "total_steps": 215, "loss": 0.4169, "lr": 2.446737002369582e-05, "epoch": 3.3255813953488373, "percentage": 66.51, "elapsed_time": "0:36:41", "remaining_time": "0:18:28"}
+{"current_steps": 144, "total_steps": 215, "loss": 0.4204, "lr": 2.3869441716941627e-05, "epoch": 3.3488372093023258, "percentage": 66.98, "elapsed_time": "0:36:54", "remaining_time": "0:18:11"}
+{"current_steps": 145, "total_steps": 215, "loss": 0.4065, "lr": 2.327578731589843e-05, "epoch": 3.3720930232558137, "percentage": 67.44, "elapsed_time": "0:37:08", "remaining_time": "0:17:55"}
+{"current_steps": 146, "total_steps": 215, "loss": 0.412, "lr": 2.2686564113506188e-05, "epoch": 3.395348837209302, "percentage": 67.91, "elapsed_time": "0:37:21", "remaining_time": "0:17:39"}
+{"current_steps": 147, "total_steps": 215, "loss": 0.4097, "lr": 2.210192822862733e-05, "epoch": 3.4186046511627906, "percentage": 68.37, "elapsed_time": "0:37:34", "remaining_time": "0:17:22"}
+{"current_steps": 148, "total_steps": 215, "loss": 0.4136, "lr": 2.1522034564681997e-05, "epoch": 3.441860465116279, "percentage": 68.84, "elapsed_time": "0:37:47", "remaining_time": "0:17:06"}
+{"current_steps": 149, "total_steps": 215, "loss": 0.4138, "lr": 2.0947036768605343e-05, "epoch": 3.4651162790697674, "percentage": 69.3, "elapsed_time": "0:38:00", "remaining_time": "0:16:49"}
+{"current_steps": 150, "total_steps": 215, "loss": 0.4121, "lr": 2.0377087190137615e-05, "epoch": 3.488372093023256, "percentage": 69.77, "elapsed_time": "0:38:13", "remaining_time": "0:16:33"}
+{"current_steps": 151, "total_steps": 215, "loss": 0.412, "lr": 1.9812336841458032e-05, "epoch": 3.511627906976744, "percentage": 70.23, "elapsed_time": "0:38:26", "remaining_time": "0:16:17"}
+{"current_steps": 152, "total_steps": 215, "loss": 0.4128, "lr": 1.925293535717306e-05, "epoch": 3.5348837209302326, "percentage": 70.7, "elapsed_time": "0:38:39", "remaining_time": "0:16:01"}
+{"current_steps": 153, "total_steps": 215, "loss": 0.4092, "lr": 1.869903095466962e-05, "epoch": 3.558139534883721, "percentage": 71.16, "elapsed_time": "0:38:52", "remaining_time": "0:15:45"}
+{"current_steps": 154, "total_steps": 215, "loss": 0.418, "lr": 1.815077039484385e-05, "epoch": 3.5813953488372094, "percentage": 71.63, "elapsed_time": "0:39:05", "remaining_time": "0:15:29"}
+{"current_steps": 155, "total_steps": 215, "loss": 0.4124, "lr": 1.760829894321582e-05, "epoch": 3.604651162790698, "percentage": 72.09, "elapsed_time": "0:39:18", "remaining_time": "0:15:13"}
+{"current_steps": 156, "total_steps": 215, "loss": 0.4134, "lr": 1.7071760331440352e-05, "epoch": 3.6279069767441863, "percentage": 72.56, "elapsed_time": "0:39:31", "remaining_time": "0:14:57"}
+{"current_steps": 157, "total_steps": 215, "loss": 0.4152, "lr": 1.6541296719224315e-05, "epoch": 3.6511627906976747, "percentage": 73.02, "elapsed_time": "0:39:44", "remaining_time": "0:14:41"}
+{"current_steps": 158, "total_steps": 215, "loss": 0.4127, "lr": 1.6017048656660392e-05, "epoch": 3.6744186046511627, "percentage": 73.49, "elapsed_time": "0:39:58", "remaining_time": "0:14:25"}
+{"current_steps": 159, "total_steps": 215, "loss": 0.4102, "lr": 1.5499155046987343e-05, "epoch": 3.697674418604651, "percentage": 73.95, "elapsed_time": "0:40:11", "remaining_time": "0:14:09"}
+{"current_steps": 160, "total_steps": 215, "loss": 0.412, "lr": 1.49877531097866e-05, "epoch": 3.7209302325581395, "percentage": 74.42, "elapsed_time": "0:40:24", "remaining_time": "0:13:53"}
+{"current_steps": 161, "total_steps": 215, "loss": 0.4112, "lr": 1.4482978344624999e-05, "epoch": 3.744186046511628, "percentage": 74.88, "elapsed_time": "0:40:36", "remaining_time": "0:13:37"}
+{"current_steps": 162, "total_steps": 215, "loss": 0.4107, "lr": 1.3984964495153178e-05, "epoch": 3.7674418604651163, "percentage": 75.35, "elapsed_time": "0:40:48", "remaining_time": "0:13:21"}
+{"current_steps": 163, "total_steps": 215, "loss": 0.4103, "lr": 1.349384351366926e-05, "epoch": 3.7906976744186047, "percentage": 75.81, "elapsed_time": "0:41:02", "remaining_time": "0:13:05"}
+{"current_steps": 164, "total_steps": 215, "loss": 0.4089, "lr": 1.3009745526157165e-05, "epoch": 3.813953488372093, "percentage": 76.28, "elapsed_time": "0:41:15", "remaining_time": "0:12:49"}
+{"current_steps": 165, "total_steps": 215, "loss": 0.4082, "lr": 1.2532798797808767e-05, "epoch": 3.8372093023255816, "percentage": 76.74, "elapsed_time": "0:41:28", "remaining_time": "0:12:34"}
+{"current_steps": 166, "total_steps": 215, "loss": 0.4072, "lr": 1.2063129699039169e-05, "epoch": 3.8604651162790695, "percentage": 77.21, "elapsed_time": "0:41:41", "remaining_time": "0:12:18"}
+{"current_steps": 167, "total_steps": 215, "loss": 0.408, "lr": 1.1600862672003964e-05, "epoch": 3.883720930232558, "percentage": 77.67, "elapsed_time": "0:41:54", "remaining_time": "0:12:02"}
+{"current_steps": 168, "total_steps": 215, "loss": 0.41, "lr": 1.1146120197627375e-05, "epoch": 3.9069767441860463, "percentage": 78.14, "elapsed_time": "0:42:08", "remaining_time": "0:11:47"}
+{"current_steps": 169, "total_steps": 215, "loss": 0.4115, "lr": 1.0699022763150104e-05, "epoch": 3.9302325581395348, "percentage": 78.6, "elapsed_time": "0:42:21", "remaining_time": "0:11:31"}
+{"current_steps": 170, "total_steps": 215, "loss": 0.4055, "lr": 1.0259688830205348e-05, "epoch": 3.953488372093023, "percentage": 79.07, "elapsed_time": "0:42:33", "remaining_time": "0:11:15"}
+{"current_steps": 171, "total_steps": 215, "loss": 0.411, "lr": 9.828234803431559e-06, "epoch": 3.9767441860465116, "percentage": 79.53, "elapsed_time": "0:42:46", "remaining_time": "0:11:00"}
+{"current_steps": 172, "total_steps": 215, "loss": 0.3931, "lr": 9.404774999630204e-06, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "0:43:00", "remaining_time": "0:10:45"}
+{"current_steps": 173, "total_steps": 215, "loss": 0.3903, "lr": 8.989421617476766e-06, "epoch": 4.023255813953488, "percentage": 80.47, "elapsed_time": "0:43:56", "remaining_time": "0:10:40"}
+{"current_steps": 174, "total_steps": 215, "loss": 0.387, "lr": 8.582284707792845e-06, "epoch": 4.046511627906977, "percentage": 80.93, "elapsed_time": "0:44:09", "remaining_time": "0:10:24"}
+{"current_steps": 175, "total_steps": 215, "loss": 0.3866, "lr": 8.183472144387456e-06, "epoch": 4.069767441860465, "percentage": 81.4, "elapsed_time": "0:44:22", "remaining_time": "0:10:08"}
+{"current_steps": 176, "total_steps": 215, "loss": 0.3913, "lr": 7.793089595475094e-06, "epoch": 4.093023255813954, "percentage": 81.86, "elapsed_time": "0:44:35", "remaining_time": "0:09:52"}
+{"current_steps": 177, "total_steps": 215, "loss": 0.3876, "lr": 7.411240495678158e-06, "epoch": 4.116279069767442, "percentage": 82.33, "elapsed_time": "0:44:50", "remaining_time": "0:09:37"}
+{"current_steps": 178, "total_steps": 215, "loss": 0.3839, "lr": 7.038026018621234e-06, "epoch": 4.1395348837209305, "percentage": 82.79, "elapsed_time": "0:45:03", "remaining_time": "0:09:21"}
+{"current_steps": 179, "total_steps": 215, "loss": 0.3894, "lr": 6.673545050124466e-06, "epoch": 4.162790697674419, "percentage": 83.26, "elapsed_time": "0:45:16", "remaining_time": "0:09:06"}
+{"current_steps": 180, "total_steps": 215, "loss": 0.3863, "lr": 6.317894162003004e-06, "epoch": 4.186046511627907, "percentage": 83.72, "elapsed_time": "0:45:29", "remaining_time": "0:08:50"}
+{"current_steps": 181, "total_steps": 215, "loss": 0.3878, "lr": 5.971167586479638e-06, "epoch": 4.209302325581396, "percentage": 84.19, "elapsed_time": "0:45:43", "remaining_time": "0:08:35"}
+{"current_steps": 182, "total_steps": 215, "loss": 0.3806, "lr": 5.633457191217311e-06, "epoch": 4.232558139534884, "percentage": 84.65, "elapsed_time": "0:45:55", "remaining_time": "0:08:19"}
+{"current_steps": 183, "total_steps": 215, "loss": 0.3833, "lr": 5.3048524549781066e-06, "epoch": 4.2558139534883725, "percentage": 85.12, "elapsed_time": "0:46:08", "remaining_time": "0:08:04"}
+{"current_steps": 184, "total_steps": 215, "loss": 0.3873, "lr": 4.985440443915223e-06, "epoch": 4.27906976744186, "percentage": 85.58, "elapsed_time": "0:46:21", "remaining_time": "0:07:48"}
+{"current_steps": 185, "total_steps": 215, "loss": 0.3827, "lr": 4.6753057885042186e-06, "epoch": 4.3023255813953485, "percentage": 86.05, "elapsed_time": "0:46:35", "remaining_time": "0:07:33"}
+{"current_steps": 186, "total_steps": 215, "loss": 0.3855, "lr": 4.374530661119512e-06, "epoch": 4.325581395348837, "percentage": 86.51, "elapsed_time": "0:46:48", "remaining_time": "0:07:17"}
+{"current_steps": 187, "total_steps": 215, "loss": 0.3855, "lr": 4.0831947542622655e-06, "epoch": 4.348837209302325, "percentage": 86.98, "elapsed_time": "0:47:01", "remaining_time": "0:07:02"}
+{"current_steps": 188, "total_steps": 215, "loss": 0.3862, "lr": 3.8013752594452834e-06, "epoch": 4.372093023255814, "percentage": 87.44, "elapsed_time": "0:47:14", "remaining_time": "0:06:47"}
+{"current_steps": 189, "total_steps": 215, "loss": 0.3853, "lr": 3.529146846740559e-06, "epoch": 4.395348837209302, "percentage": 87.91, "elapsed_time": "0:47:27", "remaining_time": "0:06:31"}
+{"current_steps": 190, "total_steps": 215, "loss": 0.3832, "lr": 3.266581644994915e-06, "epoch": 4.4186046511627906, "percentage": 88.37, "elapsed_time": "0:47:41", "remaining_time": "0:06:16"}
+{"current_steps": 191, "total_steps": 215, "loss": 0.3874, "lr": 3.0137492227189803e-06, "epoch": 4.441860465116279, "percentage": 88.84, "elapsed_time": "0:47:53", "remaining_time": "0:06:01"}
+{"current_steps": 192, "total_steps": 215, "loss": 0.3846, "lr": 2.7707165696545035e-06, "epoch": 4.465116279069767, "percentage": 89.3, "elapsed_time": "0:48:06", "remaining_time": "0:05:45"}
+{"current_steps": 193, "total_steps": 215, "loss": 0.3875, "lr": 2.537548079024923e-06, "epoch": 4.488372093023256, "percentage": 89.77, "elapsed_time": "0:48:20", "remaining_time": "0:05:30"}
+{"current_steps": 194, "total_steps": 215, "loss": 0.3878, "lr": 2.3143055304739725e-06, "epoch": 4.511627906976744, "percentage": 90.23, "elapsed_time": "0:48:33", "remaining_time": "0:05:15"}
+{"current_steps": 195, "total_steps": 215, "loss": 0.3844, "lr": 2.1010480736966788e-06, "epoch": 4.534883720930233, "percentage": 90.7, "elapsed_time": "0:48:46", "remaining_time": "0:05:00"}
+{"current_steps": 196, "total_steps": 215, "loss": 0.3864, "lr": 1.8978322127672522e-06, "epoch": 4.558139534883721, "percentage": 91.16, "elapsed_time": "0:48:59", "remaining_time": "0:04:44"}
+{"current_steps": 197, "total_steps": 215, "loss": 0.3764, "lr": 1.7047117911679567e-06, "epoch": 4.5813953488372094, "percentage": 91.63, "elapsed_time": "0:49:12", "remaining_time": "0:04:29"}
+{"current_steps": 198, "total_steps": 215, "loss": 0.3804, "lr": 1.5217379775228503e-06, "epoch": 4.604651162790698, "percentage": 92.09, "elapsed_time": "0:49:26", "remaining_time": "0:04:14"}
+{"current_steps": 199, "total_steps": 215, "loss": 0.3852, "lr": 1.3489592520403405e-06, "epoch": 4.627906976744186, "percentage": 92.56, "elapsed_time": "0:49:39", "remaining_time": "0:03:59"}
+{"current_steps": 200, "total_steps": 215, "loss": 0.3802, "lr": 1.186421393667967e-06, "epoch": 4.651162790697675, "percentage": 93.02, "elapsed_time": "0:49:52", "remaining_time": "0:03:44"}
+{"current_steps": 201, "total_steps": 215, "loss": 0.3867, "lr": 1.034167467962983e-06, "epoch": 4.674418604651163, "percentage": 93.49, "elapsed_time": "0:50:05", "remaining_time": "0:03:29"}
+{"current_steps": 202, "total_steps": 215, "loss": 0.3829, "lr": 8.922378156817957e-07, "epoch": 4.6976744186046515, "percentage": 93.95, "elapsed_time": "0:50:19", "remaining_time": "0:03:14"}
+{"current_steps": 203, "total_steps": 215, "loss": 0.3821, "lr": 7.606700420914381e-07, "epoch": 4.720930232558139, "percentage": 94.42, "elapsed_time": "0:50:32", "remaining_time": "0:02:59"}
+{"current_steps": 204, "total_steps": 215, "loss": 0.3903, "lr": 6.39499007005746e-07, "epoch": 4.7441860465116275, "percentage": 94.88, "elapsed_time": "0:50:45", "remaining_time": "0:02:44"}
+{"current_steps": 205, "total_steps": 215, "loss": 0.3885, "lr": 5.287568155490341e-07, "epoch": 4.767441860465116, "percentage": 95.35, "elapsed_time": "0:50:58", "remaining_time": "0:02:29"}
+{"current_steps": 206, "total_steps": 215, "loss": 0.3875, "lr": 4.284728096496027e-07, "epoch": 4.790697674418604, "percentage": 95.81, "elapsed_time": "0:51:11", "remaining_time": "0:02:14"}
+{"current_steps": 207, "total_steps": 215, "loss": 0.3855, "lr": 3.3867356026537457e-07, "epoch": 4.813953488372093, "percentage": 96.28, "elapsed_time": "0:51:24", "remaining_time": "0:01:59"}
+{"current_steps": 208, "total_steps": 215, "loss": 0.3846, "lr": 2.593828603437487e-07, "epoch": 4.837209302325581, "percentage": 96.74, "elapsed_time": "0:51:37", "remaining_time": "0:01:44"}
+{"current_steps": 209, "total_steps": 215, "loss": 0.3839, "lr": 1.906217185174919e-07, "epoch": 4.8604651162790695, "percentage": 97.21, "elapsed_time": "0:51:50", "remaining_time": "0:01:29"}
+{"current_steps": 210, "total_steps": 215, "loss": 0.3892, "lr": 1.3240835353834247e-07, "epoch": 4.883720930232558, "percentage": 97.67, "elapsed_time": "0:52:04", "remaining_time": "0:01:14"}
+{"current_steps": 211, "total_steps": 215, "loss": 0.3835, "lr": 8.475818944982728e-08, "epoch": 4.906976744186046, "percentage": 98.14, "elapsed_time": "0:52:16", "remaining_time": "0:00:59"}
+{"current_steps": 212, "total_steps": 215, "loss": 0.3788, "lr": 4.7683851500548437e-08, "epoch": 4.930232558139535, "percentage": 98.6, "elapsed_time": "0:52:29", "remaining_time": "0:00:44"}
+{"current_steps": 213, "total_steps": 215, "loss": 0.3903, "lr": 2.1195162799032554e-08, "epoch": 4.953488372093023, "percentage": 99.07, "elapsed_time": "0:52:42", "remaining_time": "0:00:29"}
+{"current_steps": 214, "total_steps": 215, "loss": 0.3865, "lr": 5.299141711043732e-09, "epoch": 4.976744186046512, "percentage": 99.53, "elapsed_time": "0:52:55", "remaining_time": "0:00:14"}
+{"current_steps": 215, "total_steps": 215, "loss": 0.379, "lr": 0.0, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:53:09", "remaining_time": "0:00:00"}
+{"current_steps": 215, "total_steps": 215, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:54:11", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1547 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 215,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.023255813953488372,
+      "grad_norm": 5.434192361984504,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 0.9705,
+      "step": 1
+    },
+    {
+      "epoch": 0.046511627906976744,
+      "grad_norm": 5.477136338528377,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 0.9693,
+      "step": 2
+    },
+    {
+      "epoch": 0.06976744186046512,
+      "grad_norm": 4.994172293091364,
+      "learning_rate": 1.0909090909090909e-05,
+      "loss": 0.971,
+      "step": 3
+    },
+    {
+      "epoch": 0.09302325581395349,
+      "grad_norm": 1.9715768923169905,
+      "learning_rate": 1.4545454545454546e-05,
+      "loss": 0.882,
+      "step": 4
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "grad_norm": 4.86558025165536,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 0.9089,
+      "step": 5
+    },
+    {
+      "epoch": 0.13953488372093023,
+      "grad_norm": 6.162689558609649,
+      "learning_rate": 2.1818181818181818e-05,
+      "loss": 0.9031,
+      "step": 6
+    },
+    {
+      "epoch": 0.16279069767441862,
+      "grad_norm": 5.545748731779107,
+      "learning_rate": 2.5454545454545457e-05,
+      "loss": 0.9058,
+      "step": 7
+    },
+    {
+      "epoch": 0.18604651162790697,
+      "grad_norm": 3.4785773417590877,
+      "learning_rate": 2.9090909090909093e-05,
+      "loss": 0.8423,
+      "step": 8
+    },
+    {
+      "epoch": 0.20930232558139536,
+      "grad_norm": 2.16515163827823,
+      "learning_rate": 3.272727272727273e-05,
+      "loss": 0.8043,
+      "step": 9
+    },
+    {
+      "epoch": 0.23255813953488372,
+      "grad_norm": 2.664754416131028,
+      "learning_rate": 3.6363636363636364e-05,
+      "loss": 0.7799,
+      "step": 10
+    },
+    {
+      "epoch": 0.2558139534883721,
+      "grad_norm": 1.4902721906661134,
+      "learning_rate": 4e-05,
+      "loss": 0.7546,
+      "step": 11
+    },
+    {
+      "epoch": 0.27906976744186046,
+      "grad_norm": 2.015625441498336,
+      "learning_rate": 4.3636363636363636e-05,
+      "loss": 0.7408,
+      "step": 12
+    },
+    {
+      "epoch": 0.3023255813953488,
+      "grad_norm": 1.1406136624119514,
+      "learning_rate": 4.727272727272728e-05,
+      "loss": 0.7216,
+      "step": 13
+    },
+    {
+      "epoch": 0.32558139534883723,
+      "grad_norm": 1.8195500867443861,
+      "learning_rate": 5.0909090909090914e-05,
+      "loss": 0.724,
+      "step": 14
+    },
+    {
+      "epoch": 0.3488372093023256,
+      "grad_norm": 1.595476578575812,
+      "learning_rate": 5.4545454545454546e-05,
+      "loss": 0.7084,
+      "step": 15
+    },
+    {
+      "epoch": 0.37209302325581395,
+      "grad_norm": 1.9850762532377662,
+      "learning_rate": 5.8181818181818185e-05,
+      "loss": 0.6992,
+      "step": 16
+    },
+    {
+      "epoch": 0.3953488372093023,
+      "grad_norm": 1.3156392269832544,
+      "learning_rate": 6.181818181818182e-05,
+      "loss": 0.6969,
+      "step": 17
+    },
+    {
+      "epoch": 0.4186046511627907,
+      "grad_norm": 2.165349958578573,
+      "learning_rate": 6.545454545454546e-05,
+      "loss": 0.6819,
+      "step": 18
+    },
+    {
+      "epoch": 0.4418604651162791,
+      "grad_norm": 1.860669140085515,
+      "learning_rate": 6.90909090909091e-05,
+      "loss": 0.6986,
+      "step": 19
+    },
+    {
+      "epoch": 0.46511627906976744,
+      "grad_norm": 1.7217756323779048,
+      "learning_rate": 7.272727272727273e-05,
+      "loss": 0.6801,
+      "step": 20
+    },
+    {
+      "epoch": 0.4883720930232558,
+      "grad_norm": 1.4025893684782413,
+      "learning_rate": 7.636363636363637e-05,
+      "loss": 0.6751,
+      "step": 21
+    },
+    {
+      "epoch": 0.5116279069767442,
+      "grad_norm": 1.7449603840187862,
+      "learning_rate": 8e-05,
+      "loss": 0.673,
+      "step": 22
+    },
+    {
+      "epoch": 0.5348837209302325,
+      "grad_norm": 2.482316452405395,
+      "learning_rate": 7.999470085828896e-05,
+      "loss": 0.6629,
+      "step": 23
+    },
+    {
+      "epoch": 0.5581395348837209,
+      "grad_norm": 1.2207804383595053,
+      "learning_rate": 7.997880483720098e-05,
+      "loss": 0.6716,
+      "step": 24
+    },
+    {
+      "epoch": 0.5813953488372093,
+      "grad_norm": 2.568593544907844,
+      "learning_rate": 7.995231614849947e-05,
+      "loss": 0.671,
+      "step": 25
+    },
+    {
+      "epoch": 0.6046511627906976,
+      "grad_norm": 1.502461502116564,
+      "learning_rate": 7.991524181055018e-05,
+      "loss": 0.6608,
+      "step": 26
+    },
+    {
+      "epoch": 0.627906976744186,
+      "grad_norm": 2.8212929800172915,
+      "learning_rate": 7.986759164646167e-05,
+      "loss": 0.673,
+      "step": 27
+    },
+    {
+      "epoch": 0.6511627906976745,
+      "grad_norm": 2.5422318457006825,
+      "learning_rate": 7.980937828148252e-05,
+      "loss": 0.6916,
+      "step": 28
+    },
+    {
+      "epoch": 0.6744186046511628,
+      "grad_norm": 1.6426727549059879,
+      "learning_rate": 7.974061713965625e-05,
+      "loss": 0.6487,
+      "step": 29
+    },
+    {
+      "epoch": 0.6976744186046512,
+      "grad_norm": 1.8002811870915256,
+      "learning_rate": 7.966132643973464e-05,
+      "loss": 0.6429,
+      "step": 30
+    },
+    {
+      "epoch": 0.7209302325581395,
+      "grad_norm": 1.4654311466330405,
+      "learning_rate": 7.95715271903504e-05,
+      "loss": 0.6398,
+      "step": 31
+    },
+    {
+      "epoch": 0.7441860465116279,
+      "grad_norm": 1.329866741625803,
+      "learning_rate": 7.947124318445097e-05,
+      "loss": 0.6398,
+      "step": 32
+    },
+    {
+      "epoch": 0.7674418604651163,
+      "grad_norm": 1.4731638464740446,
+      "learning_rate": 7.936050099299425e-05,
+      "loss": 0.6243,
+      "step": 33
+    },
+    {
+      "epoch": 0.7906976744186046,
+      "grad_norm": 1.4894523263564694,
+      "learning_rate": 7.923932995790858e-05,
+      "loss": 0.6335,
+      "step": 34
+    },
+    {
+      "epoch": 0.813953488372093,
+      "grad_norm": 1.173972016468102,
+      "learning_rate": 7.910776218431821e-05,
+      "loss": 0.6224,
+      "step": 35
+    },
+    {
+      "epoch": 0.8372093023255814,
+      "grad_norm": 1.6637513739112912,
+      "learning_rate": 7.896583253203703e-05,
+      "loss": 0.6219,
+      "step": 36
+    },
+    {
+      "epoch": 0.8604651162790697,
+      "grad_norm": 1.122406312089788,
+      "learning_rate": 7.881357860633204e-05,
+      "loss": 0.6232,
+      "step": 37
+    },
+    {
+      "epoch": 0.8837209302325582,
+      "grad_norm": 1.4388855947402022,
+      "learning_rate": 7.865104074795966e-05,
+      "loss": 0.5977,
+      "step": 38
+    },
+    {
+      "epoch": 0.9069767441860465,
+      "grad_norm": 1.4139997348656486,
+      "learning_rate": 7.847826202247715e-05,
+      "loss": 0.6193,
+      "step": 39
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 1.4041482845121371,
+      "learning_rate": 7.829528820883205e-05,
+      "loss": 0.604,
+      "step": 40
+    },
+    {
+      "epoch": 0.9534883720930233,
+      "grad_norm": 1.1795408353423182,
+      "learning_rate": 7.810216778723275e-05,
+      "loss": 0.5909,
+      "step": 41
+    },
+    {
+      "epoch": 0.9767441860465116,
+      "grad_norm": 1.0271878945240036,
+      "learning_rate": 7.789895192630333e-05,
+      "loss": 0.5927,
+      "step": 42
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.7552637527608157,
+      "learning_rate": 7.768569446952603e-05,
+      "loss": 0.5843,
+      "step": 43
+    },
+    {
+      "epoch": 1.0232558139534884,
+      "grad_norm": 0.9212131281614243,
+      "learning_rate": 7.746245192097509e-05,
+      "loss": 0.5722,
+      "step": 44
+    },
+    {
+      "epoch": 1.0465116279069768,
+      "grad_norm": 1.6756296752481579,
+      "learning_rate": 7.722928343034551e-05,
+      "loss": 0.5773,
+      "step": 45
+    },
+    {
+      "epoch": 1.069767441860465,
+      "grad_norm": 1.3543712007327793,
+      "learning_rate": 7.698625077728103e-05,
+      "loss": 0.5672,
+      "step": 46
+    },
+    {
+      "epoch": 1.0930232558139534,
+      "grad_norm": 1.7410081511463789,
+      "learning_rate": 7.67334183550051e-05,
+      "loss": 0.5674,
+      "step": 47
+    },
+    {
+      "epoch": 1.1162790697674418,
+      "grad_norm": 1.0733210547826335,
+      "learning_rate": 7.647085315325946e-05,
+      "loss": 0.5671,
+      "step": 48
+    },
+    {
+      "epoch": 1.1395348837209303,
+      "grad_norm": 2.252268000471556,
+      "learning_rate": 7.619862474055472e-05,
+      "loss": 0.5638,
+      "step": 49
+    },
+    {
+      "epoch": 1.1627906976744187,
+      "grad_norm": 1.6138509974039352,
+      "learning_rate": 7.591680524573773e-05,
+      "loss": 0.5625,
+      "step": 50
+    },
+    {
+      "epoch": 1.1860465116279069,
+      "grad_norm": 2.0237798746000193,
+      "learning_rate": 7.56254693388805e-05,
+      "loss": 0.5592,
+      "step": 51
+    },
+    {
+      "epoch": 1.2093023255813953,
+      "grad_norm": 1.4811712482469028,
+      "learning_rate": 7.532469421149578e-05,
+      "loss": 0.5599,
+      "step": 52
+    },
+    {
+      "epoch": 1.2325581395348837,
+      "grad_norm": 1.5279703879919382,
+      "learning_rate": 7.501455955608479e-05,
+      "loss": 0.5559,
+      "step": 53
+    },
+    {
+      "epoch": 1.255813953488372,
+      "grad_norm": 1.2468524365094296,
+      "learning_rate": 7.469514754502191e-05,
+      "loss": 0.5549,
+      "step": 54
+    },
+    {
+      "epoch": 1.2790697674418605,
+      "grad_norm": 1.2825998428965273,
+      "learning_rate": 7.436654280878269e-05,
+      "loss": 0.546,
+      "step": 55
+    },
+    {
+      "epoch": 1.302325581395349,
+      "grad_norm": 0.9710691709326068,
+      "learning_rate": 7.402883241352037e-05,
+      "loss": 0.5492,
+      "step": 56
+    },
+    {
+      "epoch": 1.3255813953488373,
+      "grad_norm": 1.4012298372305019,
+      "learning_rate": 7.368210583799701e-05,
+      "loss": 0.5481,
+      "step": 57
+    },
+    {
+      "epoch": 1.3488372093023255,
+      "grad_norm": 1.2045446990194086,
+      "learning_rate": 7.332645494987555e-05,
+      "loss": 0.544,
+      "step": 58
+    },
+    {
+      "epoch": 1.372093023255814,
+      "grad_norm": 1.5478512274120089,
+      "learning_rate": 7.296197398137878e-05,
+      "loss": 0.5399,
+      "step": 59
+    },
+    {
+      "epoch": 1.3953488372093024,
+      "grad_norm": 1.0482231123455121,
+      "learning_rate": 7.258875950432185e-05,
+      "loss": 0.5457,
+      "step": 60
+    },
+    {
+      "epoch": 1.4186046511627908,
+      "grad_norm": 1.350025832651234,
+      "learning_rate": 7.220691040452491e-05,
+      "loss": 0.533,
+      "step": 61
+    },
+    {
+      "epoch": 1.441860465116279,
+      "grad_norm": 1.6379778302822026,
+      "learning_rate": 7.181652785561254e-05,
+      "loss": 0.5467,
+      "step": 62
+    },
+    {
+      "epoch": 1.4651162790697674,
+      "grad_norm": 0.7697335505845303,
+      "learning_rate": 7.141771529220716e-05,
+      "loss": 0.536,
+      "step": 63
+    },
+    {
+      "epoch": 1.4883720930232558,
+      "grad_norm": 1.019518212307104,
+      "learning_rate": 7.101057838252324e-05,
+      "loss": 0.5309,
+      "step": 64
+    },
+    {
+      "epoch": 1.5116279069767442,
+      "grad_norm": 1.1970177274801466,
+      "learning_rate": 7.05952250003698e-05,
+      "loss": 0.535,
+      "step": 65
+    },
+    {
+      "epoch": 1.5348837209302326,
+      "grad_norm": 1.0203220373942377,
+      "learning_rate": 7.017176519656845e-05,
+      "loss": 0.5378,
+      "step": 66
+    },
+    {
+      "epoch": 1.558139534883721,
+      "grad_norm": 1.0958072090841686,
+      "learning_rate": 6.974031116979466e-05,
+      "loss": 0.5407,
+      "step": 67
+    },
+    {
+      "epoch": 1.5813953488372094,
+      "grad_norm": 1.3397310047597761,
+      "learning_rate": 6.93009772368499e-05,
+      "loss": 0.5375,
+      "step": 68
+    },
+    {
+      "epoch": 1.6046511627906976,
+      "grad_norm": 0.8782131687864965,
+      "learning_rate": 6.885387980237262e-05,
+      "loss": 0.5251,
+      "step": 69
+    },
+    {
+      "epoch": 1.627906976744186,
+      "grad_norm": 1.4357177318604477,
+      "learning_rate": 6.839913732799604e-05,
+      "loss": 0.5274,
+      "step": 70
+    },
+    {
+      "epoch": 1.6511627906976745,
+      "grad_norm": 1.215047188865305,
+      "learning_rate": 6.793687030096085e-05,
+      "loss": 0.5295,
+      "step": 71
+    },
+    {
+      "epoch": 1.6744186046511627,
+      "grad_norm": 1.2710521920417013,
+      "learning_rate": 6.746720120219126e-05,
+      "loss": 0.5421,
+      "step": 72
+    },
+    {
+      "epoch": 1.697674418604651,
+      "grad_norm": 0.7813066526911904,
+      "learning_rate": 6.699025447384284e-05,
+      "loss": 0.5312,
+      "step": 73
+    },
+    {
+      "epoch": 1.7209302325581395,
+      "grad_norm": 1.2496179982961972,
+      "learning_rate": 6.650615648633075e-05,
+      "loss": 0.5246,
+      "step": 74
+    },
+    {
+      "epoch": 1.744186046511628,
+      "grad_norm": 1.311820641764223,
+      "learning_rate": 6.601503550484684e-05,
+      "loss": 0.5258,
+      "step": 75
+    },
+    {
+      "epoch": 1.7674418604651163,
+      "grad_norm": 1.0893635673008315,
+      "learning_rate": 6.5517021655375e-05,
+      "loss": 0.5271,
+      "step": 76
+    },
+    {
+      "epoch": 1.7906976744186047,
+      "grad_norm": 0.7546199150125754,
+      "learning_rate": 6.501224689021341e-05,
+      "loss": 0.5185,
+      "step": 77
+    },
+    {
+      "epoch": 1.8139534883720931,
+      "grad_norm": 1.1638269494753801,
+      "learning_rate": 6.450084495301268e-05,
+      "loss": 0.5169,
+      "step": 78
+    },
+    {
+      "epoch": 1.8372093023255816,
+      "grad_norm": 1.1455758960103528,
+      "learning_rate": 6.398295134333962e-05,
+      "loss": 0.5197,
+      "step": 79
+    },
+    {
+      "epoch": 1.8604651162790697,
+      "grad_norm": 0.9787313133874568,
+      "learning_rate": 6.345870328077569e-05,
+      "loss": 0.5189,
+      "step": 80
+    },
+    {
+      "epoch": 1.8837209302325582,
+      "grad_norm": 1.2146657230893994,
+      "learning_rate": 6.292823966855965e-05,
+      "loss": 0.5184,
+      "step": 81
+    },
+    {
+      "epoch": 1.9069767441860463,
+      "grad_norm": 0.8315295395061865,
+      "learning_rate": 6.239170105678419e-05,
+      "loss": 0.5151,
+      "step": 82
+    },
+    {
+      "epoch": 1.9302325581395348,
+      "grad_norm": 0.43739239970652544,
+      "learning_rate": 6.184922960515616e-05,
+      "loss": 0.5088,
+      "step": 83
+    },
+    {
+      "epoch": 1.9534883720930232,
+      "grad_norm": 0.8529923746757689,
+      "learning_rate": 6.13009690453304e-05,
+      "loss": 0.5212,
+      "step": 84
+    },
+    {
+      "epoch": 1.9767441860465116,
+      "grad_norm": 0.7915534358179345,
+      "learning_rate": 6.074706464282695e-05,
+      "loss": 0.5081,
+      "step": 85
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.838942938146,
+      "learning_rate": 6.018766315854196e-05,
+      "loss": 0.4843,
+      "step": 86
+    },
+    {
+      "epoch": 2.0232558139534884,
+      "grad_norm": 1.0664271997362778,
+      "learning_rate": 5.9622912809862384e-05,
+      "loss": 0.4787,
+      "step": 87
+    },
+    {
+      "epoch": 2.046511627906977,
+      "grad_norm": 1.4645846831681002,
+      "learning_rate": 5.905296323139467e-05,
+      "loss": 0.4779,
+      "step": 88
+    },
+    {
+      "epoch": 2.0697674418604652,
+      "grad_norm": 1.0222504468766858,
+      "learning_rate": 5.847796543531801e-05,
+      "loss": 0.4708,
+      "step": 89
+    },
+    {
+      "epoch": 2.0930232558139537,
+      "grad_norm": 1.446291157107826,
+      "learning_rate": 5.789807177137269e-05,
+      "loss": 0.4747,
+      "step": 90
+    },
+    {
+      "epoch": 2.116279069767442,
+      "grad_norm": 0.894564054089064,
+      "learning_rate": 5.731343588649382e-05,
+      "loss": 0.4707,
+      "step": 91
+    },
+    {
+      "epoch": 2.13953488372093,
+      "grad_norm": 1.1812623112632408,
+      "learning_rate": 5.6724212684101567e-05,
+      "loss": 0.4724,
+      "step": 92
+    },
+    {
+      "epoch": 2.1627906976744184,
+      "grad_norm": 1.1141414953554294,
+      "learning_rate": 5.613055828305838e-05,
+      "loss": 0.4659,
+      "step": 93
+    },
+    {
+      "epoch": 2.186046511627907,
+      "grad_norm": 0.7770582052783432,
+      "learning_rate": 5.553262997630419e-05,
+      "loss": 0.4592,
+      "step": 94
+    },
+    {
+      "epoch": 2.2093023255813953,
+      "grad_norm": 1.0201596899389407,
+      "learning_rate": 5.493058618918051e-05,
+      "loss": 0.464,
+      "step": 95
+    },
+    {
+      "epoch": 2.2325581395348837,
+      "grad_norm": 0.99732039808284,
+      "learning_rate": 5.432458643745456e-05,
+      "loss": 0.4728,
+      "step": 96
+    },
+    {
+      "epoch": 2.255813953488372,
+      "grad_norm": 0.9946765474703833,
+      "learning_rate": 5.37147912850544e-05,
+      "loss": 0.4719,
+      "step": 97
+    },
+    {
+      "epoch": 2.2790697674418605,
+      "grad_norm": 0.67376712726853,
+      "learning_rate": 5.31013623015264e-05,
+      "loss": 0.4635,
+      "step": 98
+    },
+    {
+      "epoch": 2.302325581395349,
+      "grad_norm": 0.5331380825906256,
+      "learning_rate": 5.2484462019226216e-05,
+      "loss": 0.4636,
+      "step": 99
+    },
+    {
+      "epoch": 2.3255813953488373,
+      "grad_norm": 0.8114012150052442,
+      "learning_rate": 5.1864253890254744e-05,
+      "loss": 0.4669,
+      "step": 100
+    },
+    {
+      "epoch": 2.3488372093023258,
+      "grad_norm": 0.7817511193460437,
+      "learning_rate": 5.1240902243150245e-05,
+      "loss": 0.4643,
+      "step": 101
+    },
+    {
+      "epoch": 2.3720930232558137,
+      "grad_norm": 0.5742798063922762,
+      "learning_rate": 5.0614572239348436e-05,
+      "loss": 0.468,
+      "step": 102
+    },
+    {
+      "epoch": 2.395348837209302,
+      "grad_norm": 0.7545379109683643,
+      "learning_rate": 4.998542982942169e-05,
+      "loss": 0.4646,
+      "step": 103
+    },
+    {
+      "epoch": 2.4186046511627906,
+      "grad_norm": 0.6867300007616275,
+      "learning_rate": 4.9353641709109366e-05,
+      "loss": 0.466,
+      "step": 104
+    },
+    {
+      "epoch": 2.441860465116279,
+      "grad_norm": 0.5994645048448306,
+      "learning_rate": 4.87193752751505e-05,
+      "loss": 0.4605,
+      "step": 105
+    },
+    {
+      "epoch": 2.4651162790697674,
+      "grad_norm": 0.5648107826549134,
+      "learning_rate": 4.808279858093088e-05,
+      "loss": 0.4633,
+      "step": 106
+    },
+    {
+      "epoch": 2.488372093023256,
+      "grad_norm": 0.41656800662182036,
+      "learning_rate": 4.744408029195616e-05,
+      "loss": 0.458,
+      "step": 107
+    },
+    {
+      "epoch": 2.511627906976744,
+      "grad_norm": 0.560471313591134,
+      "learning_rate": 4.680338964116267e-05,
+      "loss": 0.4694,
+      "step": 108
+    },
+    {
+      "epoch": 2.5348837209302326,
+      "grad_norm": 0.3737750854348531,
+      "learning_rate": 4.616089638407798e-05,
+      "loss": 0.4572,
+      "step": 109
+    },
+    {
+      "epoch": 2.558139534883721,
+      "grad_norm": 0.4130815840573508,
+      "learning_rate": 4.551677075384296e-05,
+      "loss": 0.4642,
+      "step": 110
+    },
+    {
+      "epoch": 2.5813953488372094,
+      "grad_norm": 0.45613348607122495,
+      "learning_rate": 4.487118341610736e-05,
+      "loss": 0.4558,
+      "step": 111
+    },
+    {
+      "epoch": 2.604651162790698,
+      "grad_norm": 0.3913887000750076,
+      "learning_rate": 4.422430542381064e-05,
+      "loss": 0.4646,
+      "step": 112
+    },
+    {
+      "epoch": 2.6279069767441863,
+      "grad_norm": 0.30374911049832554,
+      "learning_rate": 4.3576308171860336e-05,
+      "loss": 0.4624,
+      "step": 113
+    },
+    {
+      "epoch": 2.6511627906976747,
+      "grad_norm": 0.3917025778134578,
+      "learning_rate": 4.292736335171978e-05,
+      "loss": 0.4566,
+      "step": 114
+    },
+    {
+      "epoch": 2.6744186046511627,
+      "grad_norm": 0.3717043272468876,
+      "learning_rate": 4.2277642905917205e-05,
+      "loss": 0.4566,
+      "step": 115
+    },
+    {
+      "epoch": 2.697674418604651,
+      "grad_norm": 0.30603425852066757,
+      "learning_rate": 4.162731898248834e-05,
+      "loss": 0.4599,
+      "step": 116
+    },
+    {
+      "epoch": 2.7209302325581395,
+      "grad_norm": 0.3251855900379686,
+      "learning_rate": 4.097656388936462e-05,
+      "loss": 0.4623,
+      "step": 117
+    },
+    {
+      "epoch": 2.744186046511628,
+      "grad_norm": 0.33442925355720576,
+      "learning_rate": 4.032555004871892e-05,
+      "loss": 0.4587,
+      "step": 118
+    },
+    {
+      "epoch": 2.7674418604651163,
+      "grad_norm": 0.33761110069481104,
+      "learning_rate": 3.9674449951281095e-05,
+      "loss": 0.4576,
+      "step": 119
+    },
+    {
+      "epoch": 2.7906976744186047,
+      "grad_norm": 0.26743941116764636,
+      "learning_rate": 3.902343611063539e-05,
+      "loss": 0.4556,
+      "step": 120
+    },
+    {
+      "epoch": 2.813953488372093,
+      "grad_norm": 0.2128179360983353,
+      "learning_rate": 3.837268101751166e-05,
+      "loss": 0.4558,
+      "step": 121
+    },
+    {
+      "epoch": 2.8372093023255816,
+      "grad_norm": 0.2896189154702043,
+      "learning_rate": 3.7722357094082815e-05,
+      "loss": 0.4618,
+      "step": 122
+    },
+    {
+      "epoch": 2.8604651162790695,
+      "grad_norm": 0.21296934932760417,
+      "learning_rate": 3.707263664828023e-05,
+      "loss": 0.4591,
+      "step": 123
+    },
+    {
+      "epoch": 2.883720930232558,
+      "grad_norm": 0.2791061519264039,
+      "learning_rate": 3.6423691828139685e-05,
+      "loss": 0.4524,
+      "step": 124
+    },
+    {
+      "epoch": 2.9069767441860463,
+      "grad_norm": 0.2631221143960164,
+      "learning_rate": 3.577569457618937e-05,
+      "loss": 0.4606,
+      "step": 125
+    },
+    {
+      "epoch": 2.9302325581395348,
+      "grad_norm": 0.20684807194617985,
+      "learning_rate": 3.512881658389265e-05,
+      "loss": 0.4578,
+      "step": 126
+    },
+    {
+      "epoch": 2.953488372093023,
+      "grad_norm": 0.2697328366910901,
+      "learning_rate": 3.448322924615703e-05,
+      "loss": 0.4544,
+      "step": 127
+    },
+    {
+      "epoch": 2.9767441860465116,
+      "grad_norm": 0.22910217651885814,
+      "learning_rate": 3.383910361592204e-05,
+      "loss": 0.458,
+      "step": 128
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.23244831316179806,
+      "learning_rate": 3.319661035883734e-05,
+      "loss": 0.427,
+      "step": 129
+    },
+    {
+      "epoch": 3.0232558139534884,
+      "grad_norm": 0.20986791210333858,
+      "learning_rate": 3.2555919708043856e-05,
+      "loss": 0.4232,
+      "step": 130
+    },
+    {
+      "epoch": 3.046511627906977,
+      "grad_norm": 0.2570519418980638,
+      "learning_rate": 3.1917201419069126e-05,
+      "loss": 0.4149,
+      "step": 131
+    },
+    {
+      "epoch": 3.0697674418604652,
+      "grad_norm": 0.24795179030963221,
+      "learning_rate": 3.128062472484952e-05,
+      "loss": 0.4193,
+      "step": 132
+    },
+    {
+      "epoch": 3.0930232558139537,
+      "grad_norm": 0.2576172200398066,
+      "learning_rate": 3.064635829089064e-05,
+      "loss": 0.4113,
+      "step": 133
+    },
+    {
+      "epoch": 3.116279069767442,
+      "grad_norm": 0.22687653576900754,
+      "learning_rate": 3.0014570170578324e-05,
+      "loss": 0.417,
+      "step": 134
+    },
+    {
+      "epoch": 3.13953488372093,
+      "grad_norm": 0.26047808565271,
+      "learning_rate": 2.938542776065158e-05,
+      "loss": 0.4137,
+      "step": 135
+    },
+    {
+      "epoch": 3.1627906976744184,
+      "grad_norm": 0.22319212273415287,
+      "learning_rate": 2.875909775684977e-05,
+      "loss": 0.4211,
+      "step": 136
+    },
+    {
+      "epoch": 3.186046511627907,
+      "grad_norm": 0.22428976031004036,
+      "learning_rate": 2.8135746109745273e-05,
+      "loss": 0.4138,
+      "step": 137
+    },
+    {
+      "epoch": 3.2093023255813953,
+      "grad_norm": 0.22247453156579614,
+      "learning_rate": 2.751553798077379e-05,
+      "loss": 0.4153,
+      "step": 138
+    },
+    {
+      "epoch": 3.2325581395348837,
+      "grad_norm": 0.20007992804768981,
+      "learning_rate": 2.6898637698473605e-05,
+      "loss": 0.4135,
+      "step": 139
+    },
+    {
+      "epoch": 3.255813953488372,
+      "grad_norm": 0.2451508001851349,
+      "learning_rate": 2.6285208714945615e-05,
+      "loss": 0.407,
+      "step": 140
+    },
+    {
+      "epoch": 3.2790697674418605,
+      "grad_norm": 0.18902377319628208,
+      "learning_rate": 2.5675413562545453e-05,
+      "loss": 0.4044,
+      "step": 141
+    },
+    {
+      "epoch": 3.302325581395349,
+      "grad_norm": 0.24194497338579668,
+      "learning_rate": 2.5069413810819503e-05,
+      "loss": 0.4073,
+      "step": 142
+    },
+    {
+      "epoch": 3.3255813953488373,
+      "grad_norm": 0.1989749287423866,
+      "learning_rate": 2.446737002369582e-05,
+      "loss": 0.4169,
+      "step": 143
+    },
+    {
+      "epoch": 3.3488372093023258,
+      "grad_norm": 0.2095582088688536,
+      "learning_rate": 2.3869441716941627e-05,
+      "loss": 0.4204,
+      "step": 144
+    },
+    {
+      "epoch": 3.3720930232558137,
+      "grad_norm": 0.162353572736833,
+      "learning_rate": 2.327578731589843e-05,
+      "loss": 0.4065,
+      "step": 145
+    },
+    {
+      "epoch": 3.395348837209302,
+      "grad_norm": 0.17279337899190159,
+      "learning_rate": 2.2686564113506188e-05,
+      "loss": 0.412,
+      "step": 146
+    },
+    {
+      "epoch": 3.4186046511627906,
+      "grad_norm": 0.16979965281268794,
+      "learning_rate": 2.210192822862733e-05,
+      "loss": 0.4097,
+      "step": 147
+    },
+    {
+      "epoch": 3.441860465116279,
+      "grad_norm": 0.1394513868982289,
+      "learning_rate": 2.1522034564681997e-05,
+      "loss": 0.4136,
+      "step": 148
+    },
+    {
+      "epoch": 3.4651162790697674,
+      "grad_norm": 0.15491336187962532,
+      "learning_rate": 2.0947036768605343e-05,
+      "loss": 0.4138,
+      "step": 149
+    },
+    {
+      "epoch": 3.488372093023256,
+      "grad_norm": 0.15331640718626022,
+      "learning_rate": 2.0377087190137615e-05,
+      "loss": 0.4121,
+      "step": 150
+    },
+    {
+      "epoch": 3.511627906976744,
+      "grad_norm": 0.14333365303471923,
+      "learning_rate": 1.9812336841458032e-05,
+      "loss": 0.412,
+      "step": 151
+    },
+    {
+      "epoch": 3.5348837209302326,
+      "grad_norm": 0.15342863178771485,
+      "learning_rate": 1.925293535717306e-05,
+      "loss": 0.4128,
+      "step": 152
+    },
+    {
+      "epoch": 3.558139534883721,
+      "grad_norm": 0.1515728462605629,
+      "learning_rate": 1.869903095466962e-05,
+      "loss": 0.4092,
+      "step": 153
+    },
+    {
+      "epoch": 3.5813953488372094,
+      "grad_norm": 0.16216900903578507,
+      "learning_rate": 1.815077039484385e-05,
+      "loss": 0.418,
+      "step": 154
+    },
+    {
+      "epoch": 3.604651162790698,
+      "grad_norm": 0.14923319773401145,
+      "learning_rate": 1.760829894321582e-05,
+      "loss": 0.4124,
+      "step": 155
+    },
+    {
+      "epoch": 3.6279069767441863,
+      "grad_norm": 0.1388357623921274,
+      "learning_rate": 1.7071760331440352e-05,
+      "loss": 0.4134,
+      "step": 156
+    },
+    {
+      "epoch": 3.6511627906976747,
+      "grad_norm": 0.14463436978493738,
+      "learning_rate": 1.6541296719224315e-05,
+      "loss": 0.4152,
+      "step": 157
+    },
+    {
+      "epoch": 3.6744186046511627,
+      "grad_norm": 0.13948667157444467,
+      "learning_rate": 1.6017048656660392e-05,
+      "loss": 0.4127,
+      "step": 158
+    },
+    {
+      "epoch": 3.697674418604651,
+      "grad_norm": 0.12962305417153203,
+      "learning_rate": 1.5499155046987343e-05,
+      "loss": 0.4102,
+      "step": 159
+    },
+    {
+      "epoch": 3.7209302325581395,
+      "grad_norm": 0.13488967836960994,
+      "learning_rate": 1.49877531097866e-05,
+      "loss": 0.412,
+      "step": 160
+    },
+    {
+      "epoch": 3.744186046511628,
+      "grad_norm": 0.14161978366263686,
+      "learning_rate": 1.4482978344624999e-05,
+      "loss": 0.4112,
+      "step": 161
+    },
+    {
+      "epoch": 3.7674418604651163,
+      "grad_norm": 0.12104463455571417,
+      "learning_rate": 1.3984964495153178e-05,
+      "loss": 0.4107,
+      "step": 162
+    },
+    {
+      "epoch": 3.7906976744186047,
+      "grad_norm": 0.14778280010357478,
+      "learning_rate": 1.349384351366926e-05,
+      "loss": 0.4103,
+      "step": 163
+    },
+    {
+      "epoch": 3.813953488372093,
+      "grad_norm": 0.13974610415305352,
+      "learning_rate": 1.3009745526157165e-05,
+      "loss": 0.4089,
+      "step": 164
+    },
+    {
+      "epoch": 3.8372093023255816,
+      "grad_norm": 0.12567459622985308,
+      "learning_rate": 1.2532798797808767e-05,
+      "loss": 0.4082,
+      "step": 165
+    },
+    {
+      "epoch": 3.8604651162790695,
+      "grad_norm": 0.13111313669138286,
+      "learning_rate": 1.2063129699039169e-05,
+      "loss": 0.4072,
+      "step": 166
+    },
+    {
+      "epoch": 3.883720930232558,
+      "grad_norm": 0.11859583351508307,
+      "learning_rate": 1.1600862672003964e-05,
+      "loss": 0.408,
+      "step": 167
+    },
+    {
+      "epoch": 3.9069767441860463,
+      "grad_norm": 0.12426128460062202,
+      "learning_rate": 1.1146120197627375e-05,
+      "loss": 0.41,
+      "step": 168
+    },
+    {
+      "epoch": 3.9302325581395348,
+      "grad_norm": 0.12183542106771499,
+      "learning_rate": 1.0699022763150104e-05,
+      "loss": 0.4115,
+      "step": 169
+    },
+    {
+      "epoch": 3.953488372093023,
+      "grad_norm": 0.1104533940594946,
+      "learning_rate": 1.0259688830205348e-05,
+      "loss": 0.4055,
+      "step": 170
+    },
+    {
+      "epoch": 3.9767441860465116,
+      "grad_norm": 0.11121249489433677,
+      "learning_rate": 9.828234803431559e-06,
+      "loss": 0.411,
+      "step": 171
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.15736411698947347,
+      "learning_rate": 9.404774999630204e-06,
+      "loss": 0.3931,
+      "step": 172
+    },
+    {
+      "epoch": 4.023255813953488,
+      "grad_norm": 0.14076644290125107,
+      "learning_rate": 8.989421617476766e-06,
+      "loss": 0.3903,
+      "step": 173
+    },
+    {
+      "epoch": 4.046511627906977,
+      "grad_norm": 0.11712681895575112,
+      "learning_rate": 8.582284707792845e-06,
+      "loss": 0.387,
+      "step": 174
+    },
+    {
+      "epoch": 4.069767441860465,
+      "grad_norm": 0.12595405435756382,
+      "learning_rate": 8.183472144387456e-06,
+      "loss": 0.3866,
+      "step": 175
+    },
+    {
+      "epoch": 4.093023255813954,
+      "grad_norm": 0.13565427155194576,
+      "learning_rate": 7.793089595475094e-06,
+      "loss": 0.3913,
+      "step": 176
+    },
+    {
+      "epoch": 4.116279069767442,
+      "grad_norm": 0.1412644950291927,
+      "learning_rate": 7.411240495678158e-06,
+      "loss": 0.3876,
+      "step": 177
+    },
+    {
+      "epoch": 4.1395348837209305,
+      "grad_norm": 0.13949397861852225,
+      "learning_rate": 7.038026018621234e-06,
+      "loss": 0.3839,
+      "step": 178
+    },
+    {
+      "epoch": 4.162790697674419,
+      "grad_norm": 0.12339126854002234,
+      "learning_rate": 6.673545050124466e-06,
+      "loss": 0.3894,
+      "step": 179
+    },
+    {
+      "epoch": 4.186046511627907,
+      "grad_norm": 0.12932008059607125,
+      "learning_rate": 6.317894162003004e-06,
+      "loss": 0.3863,
+      "step": 180
+    },
+    {
+      "epoch": 4.209302325581396,
+      "grad_norm": 0.12611084979552667,
+      "learning_rate": 5.971167586479638e-06,
+      "loss": 0.3878,
+      "step": 181
+    },
+    {
+      "epoch": 4.232558139534884,
+      "grad_norm": 0.12145402717998689,
+      "learning_rate": 5.633457191217311e-06,
+      "loss": 0.3806,
+      "step": 182
+    },
+    {
+      "epoch": 4.2558139534883725,
+      "grad_norm": 0.12362886923322695,
+      "learning_rate": 5.3048524549781066e-06,
+      "loss": 0.3833,
+      "step": 183
+    },
+    {
+      "epoch": 4.27906976744186,
+      "grad_norm": 0.1114983032825903,
+      "learning_rate": 4.985440443915223e-06,
+      "loss": 0.3873,
+      "step": 184
+    },
+    {
+      "epoch": 4.3023255813953485,
+      "grad_norm": 0.11722293815194844,
+      "learning_rate": 4.6753057885042186e-06,
+      "loss": 0.3827,
+      "step": 185
+    },
+    {
+      "epoch": 4.325581395348837,
+      "grad_norm": 0.1250948440370564,
+      "learning_rate": 4.374530661119512e-06,
+      "loss": 0.3855,
+      "step": 186
+    },
+    {
+      "epoch": 4.348837209302325,
+      "grad_norm": 0.1106181593146437,
+      "learning_rate": 4.0831947542622655e-06,
+      "loss": 0.3855,
+      "step": 187
+    },
+    {
+      "epoch": 4.372093023255814,
+      "grad_norm": 0.10428284018843,
+      "learning_rate": 3.8013752594452834e-06,
+      "loss": 0.3862,
+      "step": 188
+    },
+    {
+      "epoch": 4.395348837209302,
+      "grad_norm": 0.1049647850048849,
+      "learning_rate": 3.529146846740559e-06,
+      "loss": 0.3853,
+      "step": 189
+    },
+    {
+      "epoch": 4.4186046511627906,
+      "grad_norm": 0.10140234914167741,
+      "learning_rate": 3.266581644994915e-06,
+      "loss": 0.3832,
+      "step": 190
+    },
+    {
+      "epoch": 4.441860465116279,
+      "grad_norm": 0.1084178720824487,
+      "learning_rate": 3.0137492227189803e-06,
+      "loss": 0.3874,
+      "step": 191
+    },
+    {
+      "epoch": 4.465116279069767,
+      "grad_norm": 0.1035454061342504,
+      "learning_rate": 2.7707165696545035e-06,
+      "loss": 0.3846,
+      "step": 192
+    },
+    {
+      "epoch": 4.488372093023256,
+      "grad_norm": 0.10465143616293164,
+      "learning_rate": 2.537548079024923e-06,
+      "loss": 0.3875,
+      "step": 193
+    },
+    {
+      "epoch": 4.511627906976744,
+      "grad_norm": 0.10287343108965315,
+      "learning_rate": 2.3143055304739725e-06,
+      "loss": 0.3878,
+      "step": 194
+    },
+    {
+      "epoch": 4.534883720930233,
+      "grad_norm": 0.09899078580945446,
+      "learning_rate": 2.1010480736966788e-06,
+      "loss": 0.3844,
+      "step": 195
+    },
+    {
+      "epoch": 4.558139534883721,
+      "grad_norm": 0.0947795487504229,
+      "learning_rate": 1.8978322127672522e-06,
+      "loss": 0.3864,
+      "step": 196
+    },
+    {
+      "epoch": 4.5813953488372094,
+      "grad_norm": 0.09351592903837026,
+      "learning_rate": 1.7047117911679567e-06,
+      "loss": 0.3764,
+      "step": 197
+    },
+    {
+      "epoch": 4.604651162790698,
+      "grad_norm": 0.09075701229280372,
+      "learning_rate": 1.5217379775228503e-06,
+      "loss": 0.3804,
+      "step": 198
+    },
+    {
+      "epoch": 4.627906976744186,
+      "grad_norm": 0.09563361674368318,
+      "learning_rate": 1.3489592520403405e-06,
+      "loss": 0.3852,
+      "step": 199
+    },
+    {
+      "epoch": 4.651162790697675,
+      "grad_norm": 0.09593704632301235,
+      "learning_rate": 1.186421393667967e-06,
+      "loss": 0.3802,
+      "step": 200
+    },
+    {
+      "epoch": 4.674418604651163,
+      "grad_norm": 0.09257390445253719,
+      "learning_rate": 1.034167467962983e-06,
+      "loss": 0.3867,
+      "step": 201
+    },
+    {
+      "epoch": 4.6976744186046515,
+      "grad_norm": 0.09289347063379441,
+      "learning_rate": 8.922378156817957e-07,
+      "loss": 0.3829,
+      "step": 202
+    },
+    {
+      "epoch": 4.720930232558139,
+      "grad_norm": 0.09257169253912409,
+      "learning_rate": 7.606700420914381e-07,
+      "loss": 0.3821,
+      "step": 203
+    },
+    {
+      "epoch": 4.7441860465116275,
+      "grad_norm": 0.09310627098479367,
+      "learning_rate": 6.39499007005746e-07,
+      "loss": 0.3903,
+      "step": 204
+    },
+    {
+      "epoch": 4.767441860465116,
+      "grad_norm": 0.08944939258724487,
+      "learning_rate": 5.287568155490341e-07,
+      "loss": 0.3885,
+      "step": 205
+    },
+    {
+      "epoch": 4.790697674418604,
+      "grad_norm": 0.09592002472628403,
+      "learning_rate": 4.284728096496027e-07,
+      "loss": 0.3875,
+      "step": 206
+    },
+    {
+      "epoch": 4.813953488372093,
+      "grad_norm": 0.09180161205563094,
+      "learning_rate": 3.3867356026537457e-07,
+      "loss": 0.3855,
+      "step": 207
+    },
+    {
+      "epoch": 4.837209302325581,
+      "grad_norm": 0.08528621258416194,
+      "learning_rate": 2.593828603437487e-07,
+      "loss": 0.3846,
+      "step": 208
+    },
+    {
+      "epoch": 4.8604651162790695,
+      "grad_norm": 0.08815943836016799,
+      "learning_rate": 1.906217185174919e-07,
+      "loss": 0.3839,
+      "step": 209
+    },
+    {
+      "epoch": 4.883720930232558,
+      "grad_norm": 0.08604030139119473,
+      "learning_rate": 1.3240835353834247e-07,
+      "loss": 0.3892,
+      "step": 210
+    },
+    {
+      "epoch": 4.906976744186046,
+      "grad_norm": 0.0865890927390752,
+      "learning_rate": 8.475818944982728e-08,
+      "loss": 0.3835,
+      "step": 211
+    },
+    {
+      "epoch": 4.930232558139535,
+      "grad_norm": 0.09058754572938608,
+      "learning_rate": 4.7683851500548437e-08,
+      "loss": 0.3788,
+      "step": 212
+    },
+    {
+      "epoch": 4.953488372093023,
+      "grad_norm": 0.08787858276738178,
+      "learning_rate": 2.1195162799032554e-08,
+      "loss": 0.3903,
+      "step": 213
+    },
+    {
+      "epoch": 4.976744186046512,
+      "grad_norm": 0.08813542305445697,
+      "learning_rate": 5.299141711043732e-09,
+      "loss": 0.3865,
+      "step": 214
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.09709093222975328,
+      "learning_rate": 0.0,
+      "loss": 0.379,
+      "step": 215
+    },
+    {
+      "epoch": 5.0,
+      "step": 215,
+      "total_flos": 3606870585507840.0,
+      "train_loss": 0.5023871626964835,
+      "train_runtime": 3261.3525,
+      "train_samples_per_second": 33.201,
+      "train_steps_per_second": 0.066
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 215,
+  "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": 3606870585507840.0,
+  "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 sha256:144cc4444b0f9644053b112961ca1026fb28875f181e15f10c5e252f6a7821b3
+size 7416