Hugging Face's logo

LoneStriker
/
TIGERScore-13B-6.0bpw-h6-exl2

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Inference Endpoints
Model card Files Community
LoneStriker commited on
Commit
4188d5a
•
1 Parent(s): b7e3328

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. README.md +118 -0
  2. added_tokens.json +3 -0
  3. config.json +27 -0
  4. generation_config.json +10 -0
  5. model.safetensors.index.json +370 -0
  6. output-00001-of-00002.safetensors +3 -0
  7. output-00002-of-00002.safetensors +3 -0
  8. special_tokens_map.json +30 -0
  9. tokenizer.model +3 -0
  10. tokenizer_config.json +50 -0
  11. trainer_state.json +2011 -0
  12. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ ---
4
+
5
+
6
+ ## TIGERScore
7
+
8
+ [Project Page](https://tiger-ai-lab.github.io/TIGERScore/) | [Paper](https://arxiv.org/abs/2310.00752) | [Code](https://github.com/TIGER-AI-Lab/TIGERScore) | [🤗Demo](https://huggingface.co/spaces/TIGER-Lab/TIGERScore) |
9
+ [🤗TIGERScore-7B](https://huggingface.co/TIGER-Lab/TIGERScore-7B-V1.2) | [🤗TIGERScore-13B](https://huggingface.co/TIGER-Lab/TIGERScore-13B-V1.2)
10
+
11
+ ## Introduction
12
+
13
+ We present TIGERScore, a **T**rained metric that follows **I**nstruction **G**uidance to perform **E**xplainable, and **R**eference-free evaluation over a wide spectrum of text generation tasks. TIGERScore is guided by natural language instruction to provide error analysis to pinpoint the mistakes in the generated text. Our metric is based on LLaMA-2, trained on our meticulously curated instruction-tuning dataset MetricInstruct which covers 6 text generation tasks and 23 text generation datasets. As a reference-free metric, its correlation can even surpass the best existing reference-based metrics. To further qualitatively assess the rationale generated by our metric, we conduct human evaluation on the generated explanations and found that the explanations are 70.8% accurate. Through these experimental results, we believe TIGERScore demonstrates the possibility of building universal explainable metrics to evaluate any text generation task.
14
+
15
+ ## Training Data
16
+
17
+ The models are trained on the 🤗 [MetricInstruct Dataset](https://huggingface.co/datasets/TIGER-Lab/MetricInstruct), which covers 6 text generation tasks and 22 text generation datasets. Check out the dataset card for more details.
18
+
19
+ ## Training Procedure
20
+
21
+ The models are fine-tuned with the MetricInstruct dataset using the original Llama-2 model as base models. The training procedure varies for different models based on their sizes. Check out our paper for more details.
22
+
23
+ ## Evaluation
24
+
25
+ TIGERScore significantly surpasses traditional metrics, i.e. BLUE, ROUGE, BARTScore, and BLEURT, and emerging LLM-based metrics as reference-free metrics. Though our dataset was originally sourced from ChatGPT, our distilled model actually outperforms ChatGPT itself, which proves the effectiveness of our filtering strategy. On the unseen task of story generation, TIGERScore also demonstrates reasonable generalization capability.
26
+
27
+ | Tasks→ | Summarization | Translation | Data2Text | Long-form QA | MathQA | Instruction Following | Story-Gen | Average |
28
+ |-------------------------------------------|----------------|----------------|----------------|-----------------|----------------|----------------|----------------|----------------|
29
+ | GPT-3.5-turbo (few-shot) | **38.50** | 40.53 | 40.20 | 29.33 | **66.46** | 23.20 | 4.77 | 34.71 |
30
+ | GPT-4 (zero-shot) | 36.46 | **43.87** | **44.04** | **48.95** | 51.71 | **58.53** | **32.48** | **45.15** |
31
+ | BLEU | 11.98 | 19.73 | 33.29 | 11.38 | 21.12 | **46.61** | -1.17 | 20.42 |
32
+ | ROUGE-2f | 14.53 | 17.83 | 35.49 | 16.83 | 22.12 | 44.56 | 2.34 | 21.96 |
33
+ | InstructScore | 26.33 | 47.30 | 43.93 | 21.62 | -4.15 | 16.19 | 16.13 | 23.91 |
34
+ | GPTScore-ref | 14.73 | 24.95 | 39.42 | 31.60 | 18.20 | 33.14 | 18.24 | 25.75 |
35
+ | BARTScore-cnn(hypo-ref) | 13.64 | 28.53 | 36.12 | 29.57 | **23.35** | 32.49 | 26.64 | 27.19 |
36
+ | BARTScore-para (hypo-ref) | 17.18 | 33.72 | 40.79 | 28.94 | 17.27 | 34.47 | 17.43 | 27.11 |
37
+ | BERTScore | 23.67 | 42.41 | 43.75 | 25.60 | 11.53 | 45.77 | 2.88 | 27.95 |
38
+ | BLEURT | 17.30 | 48.41 | **48.76** | 33.26 | 3.53 | 36.46 | 27.52 | 30.75 |
39
+ | UniEval(summ) | **47.52** | 21.90 | 38.38 | **41.83** | 19.78 | 16.02 | **44.46** | 32.84 |
40
+ | COMET-22 | 33.75 | **56.35** | 33.92 | 35.28 | -5.53 | 46.13 | 39.20 | **34.16** |
41
+ | BARTScore-para (src-hypo) | **38.68** | 9.60 | 32.26 | 26.86 | -2.70 | 5.92 | 20.55 | 18.74 |
42
+ | BARTScore-cnn (src-hypo) | 35.50 | 12.83 | 34.33 | 40.96 | 1.50 | 25.43 | 33.48 | 26.29 |
43
+ | Llama-2-13b-chat-0-shot | 28.53 | 14.38 | 29.24 | 19.91 | 1.08 | 21.37 | 26.78 | 20.18 |
44
+ | COMETKiwi | 16.27 | **48.48** | 27.90 | 18.05 | -11.48 | 34.86 | 18.47 | 21.79 |
45
+ | GPTScore-src | 37.41 | 8.90 | 28.82 | 39.48 | 14.25 | 26.46 | 23.91 | 25.61 |
46
+ | TIGERScore-7B (ours) | 35.11 | 41.50 | 42.39 | **47.11** | 21.23 | 43.57 | 39.26 | 38.60 |
47
+ | TIGERScore-13B (ours) | 36.81 | 44.99 | **45.88** | 46.22 | **23.32** | **47.03** | **46.36** | **41.52** |
48
+ | Δ (ours - best reference-free) | -2 | -3 | +12 | +5 | +9 | +14 | +13 | +16 |
49
+
50
+ ## Formatting
51
+
52
+
53
+ To format the data fields into a single prompt for finetuning or testing, We provide the following code for users to refer:
54
+ ```python
55
+ FINETUNE_INST = "You are evaluating errors in a model-generated output for a given instruction."
56
+ FINETUNE_INPUT = """\
57
+ Instruction: ${generation_instruction}
58
+ ${input_context}
59
+
60
+
61
+ Model-generated Output:
62
+ ${hypothesis_output}
63
+
64
+
65
+ For each error you give in the response, please also elaborate the following information:
66
+ - error location (the words that are wrong in the output)
67
+ - error aspect it belongs to.
68
+ - explanation why it's an error, and the correction suggestions.
69
+ - severity of the error ("Major" or "Minor").
70
+ - reduction of score (between 0.5 and 5 given the severity of the error)
71
+
72
+ Your evaluation output:
73
+ """
74
+ inst_part = Template(FINETUNE_INST)
75
+ inst_part = inst_part.substitute(task=task)
76
+ input_part = Template(FINETUNE_INPUT)
77
+ input_part = input_part.substitute(
78
+ generation_instruction=instruction,
79
+ input_context=input_context,
80
+ hypothesis_output=hypo_output
81
+ )
82
+ prompt = (inst_part + "\n" + input_part).strip("\n ") + "\n"
83
+ encodings = tigerscore_tokenizer(prompt, return_tensors="pt")
84
+ input_ids = encodings["input_ids"].to(tigerscore_model.device)
85
+ attention_mask = encodings["attention_mask"].to(tigerscore_model.device)
86
+ ```
87
+
88
+ Example of formatted prompt:
89
+ ```txt
90
+ You are evaluating errors in a model-generated output for a given instruction.
91
+ Instruction: Translate the following text from German to English.
92
+ Der künftige EM-Cheforganisator Philipp Lahm soll laut Grindel im DFB-Präsidium mitarbeiten.
93
+
94
+
95
+ Model-generated Output:
96
+ According to Grindel, the future head of the European Championships, Philipp Lahm, is to participate in the DFB Presidency.
97
+
98
+
99
+ For each error you give in the response, please also elaborate the following information:
100
+ - error location (the words that are wrong in the output)
101
+ - error aspect it belongs to.
102
+ - explanation why it's an error, and the correction suggestions.
103
+ - severity of the error ("Major" or "Minor").
104
+ - reduction of score (between 0.5 and 5 given the severity of the error)
105
+
106
+ Your evaluation output:
107
+ ```
108
+
109
+ ## Citation
110
+
111
+ ```
112
+ @article{jiang2023TIGERScore,
113
+ title={TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks},
114
+ author={Dongfu Jiang, Yishan Li, Ge Zhang, Wenhao Huang, Bill Yuchen Lin, Wenhu Chen},
115
+ journal={arXiv preprint arXiv:2310.00752},
116
+ year={2023}
117
+ }
118
+ ```
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 32000
3
+ }
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/ML-A100/models/Llama-2-13b-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 13824,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 40,
16
+ "num_hidden_layers": 40,
17
+ "num_key_value_heads": 40,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "rope_theta": 10000.0,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.35.1",
25
+ "use_cache": true,
26
+ "vocab_size": 32001
27
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.6,
8
+ "top_p": 0.9,
9
+ "transformers_version": "4.35.1"
10
+ }
model.safetensors.index.json ADDED
@@ -0,0 +1,370 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26031749120
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00006-of-00006.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
242
+ "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
243
+ "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
244
+ "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
245
+ "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
246
+ "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
247
+ "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
248
+ "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
249
+ "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
250
+ "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
251
+ "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
252
+ "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
253
+ "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
254
+ "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
255
+ "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
256
+ "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
257
+ "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
258
+ "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
259
+ "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
260
+ "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
261
+ "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
262
+ "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
263
+ "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
264
+ "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
265
+ "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
266
+ "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
267
+ "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
268
+ "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
269
+ "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
270
+ "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
271
+ "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
272
+ "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
273
+ "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
274
+ "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
275
+ "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
276
+ "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
277
+ "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
278
+ "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
279
+ "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
280
+ "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
281
+ "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
282
+ "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
283
+ "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
284
+ "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
285
+ "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
286
+ "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
287
+ "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
288
+ "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
289
+ "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
290
+ "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
291
+ "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
292
+ "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
293
+ "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
294
+ "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
295
+ "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
296
+ "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
297
+ "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
298
+ "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
299
+ "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
300
+ "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
301
+ "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
302
+ "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
303
+ "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
304
+ "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
305
+ "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
306
+ "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
307
+ "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
308
+ "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
309
+ "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
310
+ "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
311
+ "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
312
+ "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
313
+ "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
314
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
316
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
317
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
318
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
319
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
320
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
321
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
322
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
323
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
324
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
325
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
326
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
327
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
328
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
329
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
330
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
331
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
332
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00006.safetensors",
333
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
334
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
335
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
336
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
337
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
338
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
339
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
340
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
341
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
342
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
343
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
344
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
345
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
346
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
347
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
348
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
349
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
350
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
351
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
352
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
353
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
354
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
355
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
356
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
357
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
358
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
359
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
360
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
361
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
362
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
363
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
364
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
365
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
366
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
367
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
368
+ "model.norm.weight": "model-00006-of-00006.safetensors"
369
+ }
370
+ }
output-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96239550445b171da691a58a758d004aa48935fe9b10b242f16f77d47ce8a316
3
+ size 8583446952
output-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c0f43eb45dc4ae9b33299286455bea2018d5aaf10435a58285c32c48c013fe0
3
+ size 1400681632
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "[PAD]",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "bos_token": "<s>",
39
+ "clean_up_tokenization_spaces": false,
40
+ "eos_token": "</s>",
41
+ "legacy": false,
42
+ "model_max_length": 1024,
43
+ "pad_token": "[PAD]",
44
+ "padding_side": "right",
45
+ "sp_model_kwargs": {},
46
+ "spaces_between_special_tokens": false,
47
+ "tokenizer_class": "LlamaTokenizer",
48
+ "unk_token": "<unk>",
49
+ "use_default_system_prompt": false
50
+ }
trainer_state.json ADDED
@@ -0,0 +1,2011 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 664,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 1.3082402064781276e-06,
14
+ "loss": 0.7935,
15
+ "step": 2
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 2.6164804129562553e-06,
20
+ "loss": 0.7,
21
+ "step": 4
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "learning_rate": 3.381751875681663e-06,
26
+ "loss": 0.6316,
27
+ "step": 6
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 3.924720619434383e-06,
32
+ "loss": 0.5405,
33
+ "step": 8
34
+ },
35
+ {
36
+ "epoch": 0.03,
37
+ "learning_rate": 4.345879896760937e-06,
38
+ "loss": 0.522,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.04,
43
+ "learning_rate": 4.689992082159791e-06,
44
+ "loss": 0.4827,
45
+ "step": 12
46
+ },
47
+ {
48
+ "epoch": 0.04,
49
+ "learning_rate": 4.980934789368156e-06,
50
+ "loss": 0.4555,
51
+ "step": 14
52
+ },
53
+ {
54
+ "epoch": 0.05,
55
+ "learning_rate": 5.2329608259125105e-06,
56
+ "loss": 0.45,
57
+ "step": 16
58
+ },
59
+ {
60
+ "epoch": 0.05,
61
+ "learning_rate": 5.4552635448851985e-06,
62
+ "loss": 0.4315,
63
+ "step": 18
64
+ },
65
+ {
66
+ "epoch": 0.06,
67
+ "learning_rate": 5.6541201032390644e-06,
68
+ "loss": 0.4153,
69
+ "step": 20
70
+ },
71
+ {
72
+ "epoch": 0.07,
73
+ "learning_rate": 5.83400774154115e-06,
74
+ "loss": 0.4374,
75
+ "step": 22
76
+ },
77
+ {
78
+ "epoch": 0.07,
79
+ "learning_rate": 5.99823228863792e-06,
80
+ "loss": 0.4171,
81
+ "step": 24
82
+ },
83
+ {
84
+ "epoch": 0.08,
85
+ "learning_rate": 6.149304227398896e-06,
86
+ "loss": 0.41,
87
+ "step": 26
88
+ },
89
+ {
90
+ "epoch": 0.08,
91
+ "learning_rate": 6.289174995846284e-06,
92
+ "loss": 0.4101,
93
+ "step": 28
94
+ },
95
+ {
96
+ "epoch": 0.09,
97
+ "learning_rate": 6.419391565964472e-06,
98
+ "loss": 0.4075,
99
+ "step": 30
100
+ },
101
+ {
102
+ "epoch": 0.1,
103
+ "learning_rate": 6.541201032390639e-06,
104
+ "loss": 0.395,
105
+ "step": 32
106
+ },
107
+ {
108
+ "epoch": 0.1,
109
+ "learning_rate": 6.655623437887147e-06,
110
+ "loss": 0.3873,
111
+ "step": 34
112
+ },
113
+ {
114
+ "epoch": 0.11,
115
+ "learning_rate": 6.763503751363326e-06,
116
+ "loss": 0.4005,
117
+ "step": 36
118
+ },
119
+ {
120
+ "epoch": 0.11,
121
+ "learning_rate": 6.865549773769684e-06,
122
+ "loss": 0.3754,
123
+ "step": 38
124
+ },
125
+ {
126
+ "epoch": 0.12,
127
+ "learning_rate": 6.9623603097171925e-06,
128
+ "loss": 0.3733,
129
+ "step": 40
130
+ },
131
+ {
132
+ "epoch": 0.13,
133
+ "learning_rate": 7.054446458571692e-06,
134
+ "loss": 0.3622,
135
+ "step": 42
136
+ },
137
+ {
138
+ "epoch": 0.13,
139
+ "learning_rate": 7.1422479480192775e-06,
140
+ "loss": 0.369,
141
+ "step": 44
142
+ },
143
+ {
144
+ "epoch": 0.14,
145
+ "learning_rate": 7.226145833886759e-06,
146
+ "loss": 0.3745,
147
+ "step": 46
148
+ },
149
+ {
150
+ "epoch": 0.14,
151
+ "learning_rate": 7.306472495116047e-06,
152
+ "loss": 0.3775,
153
+ "step": 48
154
+ },
155
+ {
156
+ "epoch": 0.15,
157
+ "learning_rate": 7.3835195870437456e-06,
158
+ "loss": 0.3652,
159
+ "step": 50
160
+ },
161
+ {
162
+ "epoch": 0.16,
163
+ "learning_rate": 7.457544433877025e-06,
164
+ "loss": 0.3645,
165
+ "step": 52
166
+ },
167
+ {
168
+ "epoch": 0.16,
169
+ "learning_rate": 7.528775214088733e-06,
170
+ "loss": 0.3554,
171
+ "step": 54
172
+ },
173
+ {
174
+ "epoch": 0.17,
175
+ "learning_rate": 7.597415202324413e-06,
176
+ "loss": 0.3591,
177
+ "step": 56
178
+ },
179
+ {
180
+ "epoch": 0.17,
181
+ "learning_rate": 7.663646266610644e-06,
182
+ "loss": 0.3797,
183
+ "step": 58
184
+ },
185
+ {
186
+ "epoch": 0.18,
187
+ "learning_rate": 7.7276317724426e-06,
188
+ "loss": 0.363,
189
+ "step": 60
190
+ },
191
+ {
192
+ "epoch": 0.19,
193
+ "learning_rate": 7.789519010511834e-06,
194
+ "loss": 0.367,
195
+ "step": 62
196
+ },
197
+ {
198
+ "epoch": 0.19,
199
+ "learning_rate": 7.849441238868767e-06,
200
+ "loss": 0.367,
201
+ "step": 64
202
+ },
203
+ {
204
+ "epoch": 0.2,
205
+ "learning_rate": 7.907519410744684e-06,
206
+ "loss": 0.3696,
207
+ "step": 66
208
+ },
209
+ {
210
+ "epoch": 0.2,
211
+ "learning_rate": 7.963863644365277e-06,
212
+ "loss": 0.3627,
213
+ "step": 68
214
+ },
215
+ {
216
+ "epoch": 0.21,
217
+ "learning_rate": 8.018574479650967e-06,
218
+ "loss": 0.3689,
219
+ "step": 70
220
+ },
221
+ {
222
+ "epoch": 0.22,
223
+ "learning_rate": 8.071743957841455e-06,
224
+ "loss": 0.344,
225
+ "step": 72
226
+ },
227
+ {
228
+ "epoch": 0.22,
229
+ "learning_rate": 8.123456553166724e-06,
230
+ "loss": 0.3412,
231
+ "step": 74
232
+ },
233
+ {
234
+ "epoch": 0.23,
235
+ "learning_rate": 8.173789980247812e-06,
236
+ "loss": 0.3574,
237
+ "step": 76
238
+ },
239
+ {
240
+ "epoch": 0.23,
241
+ "learning_rate": 8.222815896602431e-06,
242
+ "loss": 0.339,
243
+ "step": 78
244
+ },
245
+ {
246
+ "epoch": 0.24,
247
+ "learning_rate": 8.270600516195319e-06,
248
+ "loss": 0.3547,
249
+ "step": 80
250
+ },
251
+ {
252
+ "epoch": 0.25,
253
+ "learning_rate": 8.317205147216999e-06,
254
+ "loss": 0.358,
255
+ "step": 82
256
+ },
257
+ {
258
+ "epoch": 0.25,
259
+ "learning_rate": 8.36268666504982e-06,
260
+ "loss": 0.3475,
261
+ "step": 84
262
+ },
263
+ {
264
+ "epoch": 0.26,
265
+ "learning_rate": 8.407097929574588e-06,
266
+ "loss": 0.3554,
267
+ "step": 86
268
+ },
269
+ {
270
+ "epoch": 0.27,
271
+ "learning_rate": 8.450488154497406e-06,
272
+ "loss": 0.3406,
273
+ "step": 88
274
+ },
275
+ {
276
+ "epoch": 0.27,
277
+ "learning_rate": 8.492903235168008e-06,
278
+ "loss": 0.3267,
279
+ "step": 90
280
+ },
281
+ {
282
+ "epoch": 0.28,
283
+ "learning_rate": 8.534386040364887e-06,
284
+ "loss": 0.341,
285
+ "step": 92
286
+ },
287
+ {
288
+ "epoch": 0.28,
289
+ "learning_rate": 8.574976672697987e-06,
290
+ "loss": 0.3524,
291
+ "step": 94
292
+ },
293
+ {
294
+ "epoch": 0.29,
295
+ "learning_rate": 8.614712701594175e-06,
296
+ "loss": 0.3584,
297
+ "step": 96
298
+ },
299
+ {
300
+ "epoch": 0.3,
301
+ "learning_rate": 8.653629372258186e-06,
302
+ "loss": 0.3351,
303
+ "step": 98
304
+ },
305
+ {
306
+ "epoch": 0.3,
307
+ "learning_rate": 8.691759793521874e-06,
308
+ "loss": 0.3522,
309
+ "step": 100
310
+ },
311
+ {
312
+ "epoch": 0.31,
313
+ "learning_rate": 8.729135107090682e-06,
314
+ "loss": 0.3544,
315
+ "step": 102
316
+ },
317
+ {
318
+ "epoch": 0.31,
319
+ "learning_rate": 8.765784640355151e-06,
320
+ "loss": 0.3408,
321
+ "step": 104
322
+ },
323
+ {
324
+ "epoch": 0.32,
325
+ "learning_rate": 8.80173604464618e-06,
326
+ "loss": 0.3519,
327
+ "step": 106
328
+ },
329
+ {
330
+ "epoch": 0.33,
331
+ "learning_rate": 8.837015420566862e-06,
332
+ "loss": 0.3417,
333
+ "step": 108
334
+ },
335
+ {
336
+ "epoch": 0.33,
337
+ "learning_rate": 8.87164743182396e-06,
338
+ "loss": 0.3555,
339
+ "step": 110
340
+ },
341
+ {
342
+ "epoch": 0.34,
343
+ "learning_rate": 8.90565540880254e-06,
344
+ "loss": 0.3477,
345
+ "step": 112
346
+ },
347
+ {
348
+ "epoch": 0.34,
349
+ "learning_rate": 8.93906144297322e-06,
350
+ "loss": 0.3298,
351
+ "step": 114
352
+ },
353
+ {
354
+ "epoch": 0.35,
355
+ "learning_rate": 8.971886473088772e-06,
356
+ "loss": 0.3431,
357
+ "step": 116
358
+ },
359
+ {
360
+ "epoch": 0.36,
361
+ "learning_rate": 9.004150364012388e-06,
362
+ "loss": 0.3504,
363
+ "step": 118
364
+ },
365
+ {
366
+ "epoch": 0.36,
367
+ "learning_rate": 9.035871978920727e-06,
368
+ "loss": 0.3327,
369
+ "step": 120
370
+ },
371
+ {
372
+ "epoch": 0.37,
373
+ "learning_rate": 9.067069245538941e-06,
374
+ "loss": 0.3284,
375
+ "step": 122
376
+ },
377
+ {
378
+ "epoch": 0.37,
379
+ "learning_rate": 9.09775921698996e-06,
380
+ "loss": 0.3345,
381
+ "step": 124
382
+ },
383
+ {
384
+ "epoch": 0.38,
385
+ "learning_rate": 9.127958127775227e-06,
386
+ "loss": 0.3464,
387
+ "step": 126
388
+ },
389
+ {
390
+ "epoch": 0.39,
391
+ "learning_rate": 9.157681445346895e-06,
392
+ "loss": 0.336,
393
+ "step": 128
394
+ },
395
+ {
396
+ "epoch": 0.39,
397
+ "learning_rate": 9.186943917681705e-06,
398
+ "loss": 0.3546,
399
+ "step": 130
400
+ },
401
+ {
402
+ "epoch": 0.4,
403
+ "learning_rate": 9.215759617222812e-06,
404
+ "loss": 0.3194,
405
+ "step": 132
406
+ },
407
+ {
408
+ "epoch": 0.4,
409
+ "learning_rate": 9.244141981517345e-06,
410
+ "loss": 0.3296,
411
+ "step": 134
412
+ },
413
+ {
414
+ "epoch": 0.41,
415
+ "learning_rate": 9.272103850843403e-06,
416
+ "loss": 0.3331,
417
+ "step": 136
418
+ },
419
+ {
420
+ "epoch": 0.42,
421
+ "learning_rate": 9.299657503090295e-06,
422
+ "loss": 0.3362,
423
+ "step": 138
424
+ },
425
+ {
426
+ "epoch": 0.42,
427
+ "learning_rate": 9.326814686129093e-06,
428
+ "loss": 0.3414,
429
+ "step": 140
430
+ },
431
+ {
432
+ "epoch": 0.43,
433
+ "learning_rate": 9.353586647887207e-06,
434
+ "loss": 0.3249,
435
+ "step": 142
436
+ },
437
+ {
438
+ "epoch": 0.43,
439
+ "learning_rate": 9.379984164319582e-06,
440
+ "loss": 0.3334,
441
+ "step": 144
442
+ },
443
+ {
444
+ "epoch": 0.44,
445
+ "learning_rate": 9.406017565450707e-06,
446
+ "loss": 0.3294,
447
+ "step": 146
448
+ },
449
+ {
450
+ "epoch": 0.45,
451
+ "learning_rate": 9.43169675964485e-06,
452
+ "loss": 0.3436,
453
+ "step": 148
454
+ },
455
+ {
456
+ "epoch": 0.45,
457
+ "learning_rate": 9.457031256247281e-06,
458
+ "loss": 0.3216,
459
+ "step": 150
460
+ },
461
+ {
462
+ "epoch": 0.46,
463
+ "learning_rate": 9.48203018672594e-06,
464
+ "loss": 0.3509,
465
+ "step": 152
466
+ },
467
+ {
468
+ "epoch": 0.46,
469
+ "learning_rate": 9.50670232443118e-06,
470
+ "loss": 0.326,
471
+ "step": 154
472
+ },
473
+ {
474
+ "epoch": 0.47,
475
+ "learning_rate": 9.53105610308056e-06,
476
+ "loss": 0.3391,
477
+ "step": 156
478
+ },
479
+ {
480
+ "epoch": 0.48,
481
+ "learning_rate": 9.555099634066188e-06,
482
+ "loss": 0.3264,
483
+ "step": 158
484
+ },
485
+ {
486
+ "epoch": 0.48,
487
+ "learning_rate": 9.578840722673449e-06,
488
+ "loss": 0.3245,
489
+ "step": 160
490
+ },
491
+ {
492
+ "epoch": 0.49,
493
+ "learning_rate": 9.602286883292267e-06,
494
+ "loss": 0.333,
495
+ "step": 162
496
+ },
497
+ {
498
+ "epoch": 0.49,
499
+ "learning_rate": 9.625445353695127e-06,
500
+ "loss": 0.3491,
501
+ "step": 164
502
+ },
503
+ {
504
+ "epoch": 0.5,
505
+ "learning_rate": 9.648323108449636e-06,
506
+ "loss": 0.34,
507
+ "step": 166
508
+ },
509
+ {
510
+ "epoch": 0.51,
511
+ "learning_rate": 9.670926871527948e-06,
512
+ "loss": 0.3343,
513
+ "step": 168
514
+ },
515
+ {
516
+ "epoch": 0.51,
517
+ "learning_rate": 9.693263128169957e-06,
518
+ "loss": 0.3311,
519
+ "step": 170
520
+ },
521
+ {
522
+ "epoch": 0.52,
523
+ "learning_rate": 9.715338136052716e-06,
524
+ "loss": 0.333,
525
+ "step": 172
526
+ },
527
+ {
528
+ "epoch": 0.52,
529
+ "learning_rate": 9.73715793581418e-06,
530
+ "loss": 0.3002,
531
+ "step": 174
532
+ },
533
+ {
534
+ "epoch": 0.53,
535
+ "learning_rate": 9.758728360975532e-06,
536
+ "loss": 0.3271,
537
+ "step": 176
538
+ },
539
+ {
540
+ "epoch": 0.54,
541
+ "learning_rate": 9.780055047302923e-06,
542
+ "loss": 0.323,
543
+ "step": 178
544
+ },
545
+ {
546
+ "epoch": 0.54,
547
+ "learning_rate": 9.801143441646136e-06,
548
+ "loss": 0.3562,
549
+ "step": 180
550
+ },
551
+ {
552
+ "epoch": 0.55,
553
+ "learning_rate": 9.821998810288924e-06,
554
+ "loss": 0.3228,
555
+ "step": 182
556
+ },
557
+ {
558
+ "epoch": 0.55,
559
+ "learning_rate": 9.842626246843015e-06,
560
+ "loss": 0.3422,
561
+ "step": 184
562
+ },
563
+ {
564
+ "epoch": 0.56,
565
+ "learning_rate": 9.863030679715369e-06,
566
+ "loss": 0.3296,
567
+ "step": 186
568
+ },
569
+ {
570
+ "epoch": 0.57,
571
+ "learning_rate": 9.883216879176116e-06,
572
+ "loss": 0.3176,
573
+ "step": 188
574
+ },
575
+ {
576
+ "epoch": 0.57,
577
+ "learning_rate": 9.903189464052494e-06,
578
+ "loss": 0.3297,
579
+ "step": 190
580
+ },
581
+ {
582
+ "epoch": 0.58,
583
+ "learning_rate": 9.922952908072303e-06,
584
+ "loss": 0.3246,
585
+ "step": 192
586
+ },
587
+ {
588
+ "epoch": 0.58,
589
+ "learning_rate": 9.942511545878664e-06,
590
+ "loss": 0.3261,
591
+ "step": 194
592
+ },
593
+ {
594
+ "epoch": 0.59,
595
+ "learning_rate": 9.961869578736312e-06,
596
+ "loss": 0.3258,
597
+ "step": 196
598
+ },
599
+ {
600
+ "epoch": 0.6,
601
+ "learning_rate": 9.98103107994822e-06,
602
+ "loss": 0.3269,
603
+ "step": 198
604
+ },
605
+ {
606
+ "epoch": 0.6,
607
+ "learning_rate": 1e-05,
608
+ "loss": 0.324,
609
+ "step": 200
610
+ },
611
+ {
612
+ "epoch": 0.61,
613
+ "learning_rate": 1e-05,
614
+ "loss": 0.3106,
615
+ "step": 202
616
+ },
617
+ {
618
+ "epoch": 0.61,
619
+ "learning_rate": 1e-05,
620
+ "loss": 0.3086,
621
+ "step": 204
622
+ },
623
+ {
624
+ "epoch": 0.62,
625
+ "learning_rate": 1e-05,
626
+ "loss": 0.3269,
627
+ "step": 206
628
+ },
629
+ {
630
+ "epoch": 0.63,
631
+ "learning_rate": 1e-05,
632
+ "loss": 0.3396,
633
+ "step": 208
634
+ },
635
+ {
636
+ "epoch": 0.63,
637
+ "learning_rate": 1e-05,
638
+ "loss": 0.3249,
639
+ "step": 210
640
+ },
641
+ {
642
+ "epoch": 0.64,
643
+ "learning_rate": 1e-05,
644
+ "loss": 0.3294,
645
+ "step": 212
646
+ },
647
+ {
648
+ "epoch": 0.64,
649
+ "learning_rate": 1e-05,
650
+ "loss": 0.3502,
651
+ "step": 214
652
+ },
653
+ {
654
+ "epoch": 0.65,
655
+ "learning_rate": 1e-05,
656
+ "loss": 0.3329,
657
+ "step": 216
658
+ },
659
+ {
660
+ "epoch": 0.66,
661
+ "learning_rate": 1e-05,
662
+ "loss": 0.3501,
663
+ "step": 218
664
+ },
665
+ {
666
+ "epoch": 0.66,
667
+ "learning_rate": 1e-05,
668
+ "loss": 0.3375,
669
+ "step": 220
670
+ },
671
+ {
672
+ "epoch": 0.67,
673
+ "learning_rate": 1e-05,
674
+ "loss": 0.3326,
675
+ "step": 222
676
+ },
677
+ {
678
+ "epoch": 0.67,
679
+ "learning_rate": 1e-05,
680
+ "loss": 0.3312,
681
+ "step": 224
682
+ },
683
+ {
684
+ "epoch": 0.68,
685
+ "learning_rate": 1e-05,
686
+ "loss": 0.3246,
687
+ "step": 226
688
+ },
689
+ {
690
+ "epoch": 0.69,
691
+ "learning_rate": 1e-05,
692
+ "loss": 0.3142,
693
+ "step": 228
694
+ },
695
+ {
696
+ "epoch": 0.69,
697
+ "learning_rate": 1e-05,
698
+ "loss": 0.3246,
699
+ "step": 230
700
+ },
701
+ {
702
+ "epoch": 0.7,
703
+ "learning_rate": 1e-05,
704
+ "loss": 0.329,
705
+ "step": 232
706
+ },
707
+ {
708
+ "epoch": 0.7,
709
+ "learning_rate": 1e-05,
710
+ "loss": 0.3446,
711
+ "step": 234
712
+ },
713
+ {
714
+ "epoch": 0.71,
715
+ "learning_rate": 1e-05,
716
+ "loss": 0.3205,
717
+ "step": 236
718
+ },
719
+ {
720
+ "epoch": 0.72,
721
+ "learning_rate": 1e-05,
722
+ "loss": 0.3066,
723
+ "step": 238
724
+ },
725
+ {
726
+ "epoch": 0.72,
727
+ "learning_rate": 1e-05,
728
+ "loss": 0.3267,
729
+ "step": 240
730
+ },
731
+ {
732
+ "epoch": 0.73,
733
+ "learning_rate": 1e-05,
734
+ "loss": 0.3169,
735
+ "step": 242
736
+ },
737
+ {
738
+ "epoch": 0.73,
739
+ "learning_rate": 1e-05,
740
+ "loss": 0.333,
741
+ "step": 244
742
+ },
743
+ {
744
+ "epoch": 0.74,
745
+ "learning_rate": 1e-05,
746
+ "loss": 0.3155,
747
+ "step": 246
748
+ },
749
+ {
750
+ "epoch": 0.75,
751
+ "learning_rate": 1e-05,
752
+ "loss": 0.3263,
753
+ "step": 248
754
+ },
755
+ {
756
+ "epoch": 0.75,
757
+ "learning_rate": 1e-05,
758
+ "loss": 0.3154,
759
+ "step": 250
760
+ },
761
+ {
762
+ "epoch": 0.76,
763
+ "learning_rate": 1e-05,
764
+ "loss": 0.3303,
765
+ "step": 252
766
+ },
767
+ {
768
+ "epoch": 0.77,
769
+ "learning_rate": 1e-05,
770
+ "loss": 0.3298,
771
+ "step": 254
772
+ },
773
+ {
774
+ "epoch": 0.77,
775
+ "learning_rate": 1e-05,
776
+ "loss": 0.3319,
777
+ "step": 256
778
+ },
779
+ {
780
+ "epoch": 0.78,
781
+ "learning_rate": 1e-05,
782
+ "loss": 0.3178,
783
+ "step": 258
784
+ },
785
+ {
786
+ "epoch": 0.78,
787
+ "learning_rate": 1e-05,
788
+ "loss": 0.3178,
789
+ "step": 260
790
+ },
791
+ {
792
+ "epoch": 0.79,
793
+ "learning_rate": 1e-05,
794
+ "loss": 0.3163,
795
+ "step": 262
796
+ },
797
+ {
798
+ "epoch": 0.8,
799
+ "learning_rate": 1e-05,
800
+ "loss": 0.2977,
801
+ "step": 264
802
+ },
803
+ {
804
+ "epoch": 0.8,
805
+ "learning_rate": 1e-05,
806
+ "loss": 0.3184,
807
+ "step": 266
808
+ },
809
+ {
810
+ "epoch": 0.81,
811
+ "learning_rate": 1e-05,
812
+ "loss": 0.3359,
813
+ "step": 268
814
+ },
815
+ {
816
+ "epoch": 0.81,
817
+ "learning_rate": 1e-05,
818
+ "loss": 0.321,
819
+ "step": 270
820
+ },
821
+ {
822
+ "epoch": 0.82,
823
+ "learning_rate": 1e-05,
824
+ "loss": 0.3275,
825
+ "step": 272
826
+ },
827
+ {
828
+ "epoch": 0.83,
829
+ "learning_rate": 1e-05,
830
+ "loss": 0.3198,
831
+ "step": 274
832
+ },
833
+ {
834
+ "epoch": 0.83,
835
+ "learning_rate": 1e-05,
836
+ "loss": 0.3352,
837
+ "step": 276
838
+ },
839
+ {
840
+ "epoch": 0.84,
841
+ "learning_rate": 1e-05,
842
+ "loss": 0.3387,
843
+ "step": 278
844
+ },
845
+ {
846
+ "epoch": 0.84,
847
+ "learning_rate": 1e-05,
848
+ "loss": 0.3176,
849
+ "step": 280
850
+ },
851
+ {
852
+ "epoch": 0.85,
853
+ "learning_rate": 1e-05,
854
+ "loss": 0.3278,
855
+ "step": 282
856
+ },
857
+ {
858
+ "epoch": 0.86,
859
+ "learning_rate": 1e-05,
860
+ "loss": 0.2959,
861
+ "step": 284
862
+ },
863
+ {
864
+ "epoch": 0.86,
865
+ "learning_rate": 1e-05,
866
+ "loss": 0.3213,
867
+ "step": 286
868
+ },
869
+ {
870
+ "epoch": 0.87,
871
+ "learning_rate": 1e-05,
872
+ "loss": 0.3154,
873
+ "step": 288
874
+ },
875
+ {
876
+ "epoch": 0.87,
877
+ "learning_rate": 1e-05,
878
+ "loss": 0.3158,
879
+ "step": 290
880
+ },
881
+ {
882
+ "epoch": 0.88,
883
+ "learning_rate": 1e-05,
884
+ "loss": 0.3068,
885
+ "step": 292
886
+ },
887
+ {
888
+ "epoch": 0.89,
889
+ "learning_rate": 1e-05,
890
+ "loss": 0.3178,
891
+ "step": 294
892
+ },
893
+ {
894
+ "epoch": 0.89,
895
+ "learning_rate": 1e-05,
896
+ "loss": 0.3241,
897
+ "step": 296
898
+ },
899
+ {
900
+ "epoch": 0.9,
901
+ "learning_rate": 1e-05,
902
+ "loss": 0.3192,
903
+ "step": 298
904
+ },
905
+ {
906
+ "epoch": 0.9,
907
+ "learning_rate": 1e-05,
908
+ "loss": 0.3238,
909
+ "step": 300
910
+ },
911
+ {
912
+ "epoch": 0.91,
913
+ "learning_rate": 1e-05,
914
+ "loss": 0.3259,
915
+ "step": 302
916
+ },
917
+ {
918
+ "epoch": 0.92,
919
+ "learning_rate": 1e-05,
920
+ "loss": 0.2884,
921
+ "step": 304
922
+ },
923
+ {
924
+ "epoch": 0.92,
925
+ "learning_rate": 1e-05,
926
+ "loss": 0.3148,
927
+ "step": 306
928
+ },
929
+ {
930
+ "epoch": 0.93,
931
+ "learning_rate": 1e-05,
932
+ "loss": 0.3133,
933
+ "step": 308
934
+ },
935
+ {
936
+ "epoch": 0.93,
937
+ "learning_rate": 1e-05,
938
+ "loss": 0.3141,
939
+ "step": 310
940
+ },
941
+ {
942
+ "epoch": 0.94,
943
+ "learning_rate": 1e-05,
944
+ "loss": 0.3187,
945
+ "step": 312
946
+ },
947
+ {
948
+ "epoch": 0.95,
949
+ "learning_rate": 1e-05,
950
+ "loss": 0.3211,
951
+ "step": 314
952
+ },
953
+ {
954
+ "epoch": 0.95,
955
+ "learning_rate": 1e-05,
956
+ "loss": 0.3198,
957
+ "step": 316
958
+ },
959
+ {
960
+ "epoch": 0.96,
961
+ "learning_rate": 1e-05,
962
+ "loss": 0.316,
963
+ "step": 318
964
+ },
965
+ {
966
+ "epoch": 0.96,
967
+ "learning_rate": 1e-05,
968
+ "loss": 0.329,
969
+ "step": 320
970
+ },
971
+ {
972
+ "epoch": 0.97,
973
+ "learning_rate": 1e-05,
974
+ "loss": 0.3008,
975
+ "step": 322
976
+ },
977
+ {
978
+ "epoch": 0.98,
979
+ "learning_rate": 1e-05,
980
+ "loss": 0.3184,
981
+ "step": 324
982
+ },
983
+ {
984
+ "epoch": 0.98,
985
+ "learning_rate": 1e-05,
986
+ "loss": 0.3329,
987
+ "step": 326
988
+ },
989
+ {
990
+ "epoch": 0.99,
991
+ "learning_rate": 1e-05,
992
+ "loss": 0.3106,
993
+ "step": 328
994
+ },
995
+ {
996
+ "epoch": 0.99,
997
+ "learning_rate": 1e-05,
998
+ "loss": 0.3133,
999
+ "step": 330
1000
+ },
1001
+ {
1002
+ "epoch": 1.0,
1003
+ "learning_rate": 1e-05,
1004
+ "loss": 0.3238,
1005
+ "step": 332
1006
+ },
1007
+ {
1008
+ "epoch": 1.01,
1009
+ "learning_rate": 1e-05,
1010
+ "loss": 0.3145,
1011
+ "step": 334
1012
+ },
1013
+ {
1014
+ "epoch": 1.01,
1015
+ "learning_rate": 1e-05,
1016
+ "loss": 0.3053,
1017
+ "step": 336
1018
+ },
1019
+ {
1020
+ "epoch": 1.02,
1021
+ "learning_rate": 1e-05,
1022
+ "loss": 0.3025,
1023
+ "step": 338
1024
+ },
1025
+ {
1026
+ "epoch": 1.02,
1027
+ "learning_rate": 1e-05,
1028
+ "loss": 0.2953,
1029
+ "step": 340
1030
+ },
1031
+ {
1032
+ "epoch": 1.03,
1033
+ "learning_rate": 1e-05,
1034
+ "loss": 0.302,
1035
+ "step": 342
1036
+ },
1037
+ {
1038
+ "epoch": 1.04,
1039
+ "learning_rate": 1e-05,
1040
+ "loss": 0.2956,
1041
+ "step": 344
1042
+ },
1043
+ {
1044
+ "epoch": 1.04,
1045
+ "learning_rate": 1e-05,
1046
+ "loss": 0.2763,
1047
+ "step": 346
1048
+ },
1049
+ {
1050
+ "epoch": 1.05,
1051
+ "learning_rate": 1e-05,
1052
+ "loss": 0.2848,
1053
+ "step": 348
1054
+ },
1055
+ {
1056
+ "epoch": 1.05,
1057
+ "learning_rate": 1e-05,
1058
+ "loss": 0.2664,
1059
+ "step": 350
1060
+ },
1061
+ {
1062
+ "epoch": 1.06,
1063
+ "learning_rate": 1e-05,
1064
+ "loss": 0.2641,
1065
+ "step": 352
1066
+ },
1067
+ {
1068
+ "epoch": 1.07,
1069
+ "learning_rate": 1e-05,
1070
+ "loss": 0.2783,
1071
+ "step": 354
1072
+ },
1073
+ {
1074
+ "epoch": 1.07,
1075
+ "learning_rate": 1e-05,
1076
+ "loss": 0.2757,
1077
+ "step": 356
1078
+ },
1079
+ {
1080
+ "epoch": 1.08,
1081
+ "learning_rate": 1e-05,
1082
+ "loss": 0.2647,
1083
+ "step": 358
1084
+ },
1085
+ {
1086
+ "epoch": 1.08,
1087
+ "learning_rate": 1e-05,
1088
+ "loss": 0.2725,
1089
+ "step": 360
1090
+ },
1091
+ {
1092
+ "epoch": 1.09,
1093
+ "learning_rate": 1e-05,
1094
+ "loss": 0.277,
1095
+ "step": 362
1096
+ },
1097
+ {
1098
+ "epoch": 1.1,
1099
+ "learning_rate": 1e-05,
1100
+ "loss": 0.2648,
1101
+ "step": 364
1102
+ },
1103
+ {
1104
+ "epoch": 1.1,
1105
+ "learning_rate": 1e-05,
1106
+ "loss": 0.2593,
1107
+ "step": 366
1108
+ },
1109
+ {
1110
+ "epoch": 1.11,
1111
+ "learning_rate": 1e-05,
1112
+ "loss": 0.2654,
1113
+ "step": 368
1114
+ },
1115
+ {
1116
+ "epoch": 1.11,
1117
+ "learning_rate": 1e-05,
1118
+ "loss": 0.2574,
1119
+ "step": 370
1120
+ },
1121
+ {
1122
+ "epoch": 1.12,
1123
+ "learning_rate": 1e-05,
1124
+ "loss": 0.2528,
1125
+ "step": 372
1126
+ },
1127
+ {
1128
+ "epoch": 1.13,
1129
+ "learning_rate": 1e-05,
1130
+ "loss": 0.2415,
1131
+ "step": 374
1132
+ },
1133
+ {
1134
+ "epoch": 1.13,
1135
+ "learning_rate": 1e-05,
1136
+ "loss": 0.2493,
1137
+ "step": 376
1138
+ },
1139
+ {
1140
+ "epoch": 1.14,
1141
+ "learning_rate": 1e-05,
1142
+ "loss": 0.2543,
1143
+ "step": 378
1144
+ },
1145
+ {
1146
+ "epoch": 1.14,
1147
+ "learning_rate": 1e-05,
1148
+ "loss": 0.259,
1149
+ "step": 380
1150
+ },
1151
+ {
1152
+ "epoch": 1.15,
1153
+ "learning_rate": 1e-05,
1154
+ "loss": 0.2445,
1155
+ "step": 382
1156
+ },
1157
+ {
1158
+ "epoch": 1.16,
1159
+ "learning_rate": 1e-05,
1160
+ "loss": 0.2476,
1161
+ "step": 384
1162
+ },
1163
+ {
1164
+ "epoch": 1.16,
1165
+ "learning_rate": 1e-05,
1166
+ "loss": 0.2388,
1167
+ "step": 386
1168
+ },
1169
+ {
1170
+ "epoch": 1.17,
1171
+ "learning_rate": 1e-05,
1172
+ "loss": 0.2398,
1173
+ "step": 388
1174
+ },
1175
+ {
1176
+ "epoch": 1.17,
1177
+ "learning_rate": 1e-05,
1178
+ "loss": 0.2559,
1179
+ "step": 390
1180
+ },
1181
+ {
1182
+ "epoch": 1.18,
1183
+ "learning_rate": 1e-05,
1184
+ "loss": 0.2398,
1185
+ "step": 392
1186
+ },
1187
+ {
1188
+ "epoch": 1.19,
1189
+ "learning_rate": 1e-05,
1190
+ "loss": 0.245,
1191
+ "step": 394
1192
+ },
1193
+ {
1194
+ "epoch": 1.19,
1195
+ "learning_rate": 1e-05,
1196
+ "loss": 0.2502,
1197
+ "step": 396
1198
+ },
1199
+ {
1200
+ "epoch": 1.2,
1201
+ "learning_rate": 1e-05,
1202
+ "loss": 0.2541,
1203
+ "step": 398
1204
+ },
1205
+ {
1206
+ "epoch": 1.2,
1207
+ "learning_rate": 1e-05,
1208
+ "loss": 0.2433,
1209
+ "step": 400
1210
+ },
1211
+ {
1212
+ "epoch": 1.21,
1213
+ "learning_rate": 1e-05,
1214
+ "loss": 0.2486,
1215
+ "step": 402
1216
+ },
1217
+ {
1218
+ "epoch": 1.22,
1219
+ "learning_rate": 1e-05,
1220
+ "loss": 0.2297,
1221
+ "step": 404
1222
+ },
1223
+ {
1224
+ "epoch": 1.22,
1225
+ "learning_rate": 1e-05,
1226
+ "loss": 0.2286,
1227
+ "step": 406
1228
+ },
1229
+ {
1230
+ "epoch": 1.23,
1231
+ "learning_rate": 1e-05,
1232
+ "loss": 0.2425,
1233
+ "step": 408
1234
+ },
1235
+ {
1236
+ "epoch": 1.23,
1237
+ "learning_rate": 1e-05,
1238
+ "loss": 0.2271,
1239
+ "step": 410
1240
+ },
1241
+ {
1242
+ "epoch": 1.24,
1243
+ "learning_rate": 1e-05,
1244
+ "loss": 0.2394,
1245
+ "step": 412
1246
+ },
1247
+ {
1248
+ "epoch": 1.25,
1249
+ "learning_rate": 1e-05,
1250
+ "loss": 0.2446,
1251
+ "step": 414
1252
+ },
1253
+ {
1254
+ "epoch": 1.25,
1255
+ "learning_rate": 1e-05,
1256
+ "loss": 0.2342,
1257
+ "step": 416
1258
+ },
1259
+ {
1260
+ "epoch": 1.26,
1261
+ "learning_rate": 1e-05,
1262
+ "loss": 0.2423,
1263
+ "step": 418
1264
+ },
1265
+ {
1266
+ "epoch": 1.27,
1267
+ "learning_rate": 1e-05,
1268
+ "loss": 0.2334,
1269
+ "step": 420
1270
+ },
1271
+ {
1272
+ "epoch": 1.27,
1273
+ "learning_rate": 1e-05,
1274
+ "loss": 0.2213,
1275
+ "step": 422
1276
+ },
1277
+ {
1278
+ "epoch": 1.28,
1279
+ "learning_rate": 1e-05,
1280
+ "loss": 0.2254,
1281
+ "step": 424
1282
+ },
1283
+ {
1284
+ "epoch": 1.28,
1285
+ "learning_rate": 1e-05,
1286
+ "loss": 0.2385,
1287
+ "step": 426
1288
+ },
1289
+ {
1290
+ "epoch": 1.29,
1291
+ "learning_rate": 1e-05,
1292
+ "loss": 0.2439,
1293
+ "step": 428
1294
+ },
1295
+ {
1296
+ "epoch": 1.3,
1297
+ "learning_rate": 1e-05,
1298
+ "loss": 0.2314,
1299
+ "step": 430
1300
+ },
1301
+ {
1302
+ "epoch": 1.3,
1303
+ "learning_rate": 1e-05,
1304
+ "loss": 0.2423,
1305
+ "step": 432
1306
+ },
1307
+ {
1308
+ "epoch": 1.31,
1309
+ "learning_rate": 1e-05,
1310
+ "loss": 0.2387,
1311
+ "step": 434
1312
+ },
1313
+ {
1314
+ "epoch": 1.31,
1315
+ "learning_rate": 1e-05,
1316
+ "loss": 0.2283,
1317
+ "step": 436
1318
+ },
1319
+ {
1320
+ "epoch": 1.32,
1321
+ "learning_rate": 1e-05,
1322
+ "loss": 0.2358,
1323
+ "step": 438
1324
+ },
1325
+ {
1326
+ "epoch": 1.33,
1327
+ "learning_rate": 1e-05,
1328
+ "loss": 0.2271,
1329
+ "step": 440
1330
+ },
1331
+ {
1332
+ "epoch": 1.33,
1333
+ "learning_rate": 1e-05,
1334
+ "loss": 0.2403,
1335
+ "step": 442
1336
+ },
1337
+ {
1338
+ "epoch": 1.34,
1339
+ "learning_rate": 1e-05,
1340
+ "loss": 0.2365,
1341
+ "step": 444
1342
+ },
1343
+ {
1344
+ "epoch": 1.34,
1345
+ "learning_rate": 1e-05,
1346
+ "loss": 0.2206,
1347
+ "step": 446
1348
+ },
1349
+ {
1350
+ "epoch": 1.35,
1351
+ "learning_rate": 1e-05,
1352
+ "loss": 0.2329,
1353
+ "step": 448
1354
+ },
1355
+ {
1356
+ "epoch": 1.36,
1357
+ "learning_rate": 1e-05,
1358
+ "loss": 0.23,
1359
+ "step": 450
1360
+ },
1361
+ {
1362
+ "epoch": 1.36,
1363
+ "learning_rate": 1e-05,
1364
+ "loss": 0.2177,
1365
+ "step": 452
1366
+ },
1367
+ {
1368
+ "epoch": 1.37,
1369
+ "learning_rate": 1e-05,
1370
+ "loss": 0.219,
1371
+ "step": 454
1372
+ },
1373
+ {
1374
+ "epoch": 1.37,
1375
+ "learning_rate": 1e-05,
1376
+ "loss": 0.226,
1377
+ "step": 456
1378
+ },
1379
+ {
1380
+ "epoch": 1.38,
1381
+ "learning_rate": 1e-05,
1382
+ "loss": 0.2267,
1383
+ "step": 458
1384
+ },
1385
+ {
1386
+ "epoch": 1.39,
1387
+ "learning_rate": 1e-05,
1388
+ "loss": 0.2249,
1389
+ "step": 460
1390
+ },
1391
+ {
1392
+ "epoch": 1.39,
1393
+ "learning_rate": 1e-05,
1394
+ "loss": 0.2368,
1395
+ "step": 462
1396
+ },
1397
+ {
1398
+ "epoch": 1.4,
1399
+ "learning_rate": 1e-05,
1400
+ "loss": 0.2146,
1401
+ "step": 464
1402
+ },
1403
+ {
1404
+ "epoch": 1.4,
1405
+ "learning_rate": 1e-05,
1406
+ "loss": 0.218,
1407
+ "step": 466
1408
+ },
1409
+ {
1410
+ "epoch": 1.41,
1411
+ "learning_rate": 1e-05,
1412
+ "loss": 0.2304,
1413
+ "step": 468
1414
+ },
1415
+ {
1416
+ "epoch": 1.42,
1417
+ "learning_rate": 1e-05,
1418
+ "loss": 0.2314,
1419
+ "step": 470
1420
+ },
1421
+ {
1422
+ "epoch": 1.42,
1423
+ "learning_rate": 1e-05,
1424
+ "loss": 0.2295,
1425
+ "step": 472
1426
+ },
1427
+ {
1428
+ "epoch": 1.43,
1429
+ "learning_rate": 1e-05,
1430
+ "loss": 0.22,
1431
+ "step": 474
1432
+ },
1433
+ {
1434
+ "epoch": 1.43,
1435
+ "learning_rate": 1e-05,
1436
+ "loss": 0.2172,
1437
+ "step": 476
1438
+ },
1439
+ {
1440
+ "epoch": 1.44,
1441
+ "learning_rate": 1e-05,
1442
+ "loss": 0.2244,
1443
+ "step": 478
1444
+ },
1445
+ {
1446
+ "epoch": 1.45,
1447
+ "learning_rate": 1e-05,
1448
+ "loss": 0.2301,
1449
+ "step": 480
1450
+ },
1451
+ {
1452
+ "epoch": 1.45,
1453
+ "learning_rate": 1e-05,
1454
+ "loss": 0.2069,
1455
+ "step": 482
1456
+ },
1457
+ {
1458
+ "epoch": 1.46,
1459
+ "learning_rate": 1e-05,
1460
+ "loss": 0.2342,
1461
+ "step": 484
1462
+ },
1463
+ {
1464
+ "epoch": 1.46,
1465
+ "learning_rate": 1e-05,
1466
+ "loss": 0.2162,
1467
+ "step": 486
1468
+ },
1469
+ {
1470
+ "epoch": 1.47,
1471
+ "learning_rate": 1e-05,
1472
+ "loss": 0.2184,
1473
+ "step": 488
1474
+ },
1475
+ {
1476
+ "epoch": 1.48,
1477
+ "learning_rate": 1e-05,
1478
+ "loss": 0.2369,
1479
+ "step": 490
1480
+ },
1481
+ {
1482
+ "epoch": 1.48,
1483
+ "learning_rate": 1e-05,
1484
+ "loss": 0.2053,
1485
+ "step": 492
1486
+ },
1487
+ {
1488
+ "epoch": 1.49,
1489
+ "learning_rate": 1e-05,
1490
+ "loss": 0.2148,
1491
+ "step": 494
1492
+ },
1493
+ {
1494
+ "epoch": 1.49,
1495
+ "learning_rate": 1e-05,
1496
+ "loss": 0.227,
1497
+ "step": 496
1498
+ },
1499
+ {
1500
+ "epoch": 1.5,
1501
+ "learning_rate": 1e-05,
1502
+ "loss": 0.2252,
1503
+ "step": 498
1504
+ },
1505
+ {
1506
+ "epoch": 1.51,
1507
+ "learning_rate": 1e-05,
1508
+ "loss": 0.2183,
1509
+ "step": 500
1510
+ },
1511
+ {
1512
+ "epoch": 1.51,
1513
+ "learning_rate": 1e-05,
1514
+ "loss": 0.2222,
1515
+ "step": 502
1516
+ },
1517
+ {
1518
+ "epoch": 1.52,
1519
+ "learning_rate": 1e-05,
1520
+ "loss": 0.2158,
1521
+ "step": 504
1522
+ },
1523
+ {
1524
+ "epoch": 1.52,
1525
+ "learning_rate": 1e-05,
1526
+ "loss": 0.1991,
1527
+ "step": 506
1528
+ },
1529
+ {
1530
+ "epoch": 1.53,
1531
+ "learning_rate": 1e-05,
1532
+ "loss": 0.2093,
1533
+ "step": 508
1534
+ },
1535
+ {
1536
+ "epoch": 1.54,
1537
+ "learning_rate": 1e-05,
1538
+ "loss": 0.2021,
1539
+ "step": 510
1540
+ },
1541
+ {
1542
+ "epoch": 1.54,
1543
+ "learning_rate": 1e-05,
1544
+ "loss": 0.2392,
1545
+ "step": 512
1546
+ },
1547
+ {
1548
+ "epoch": 1.55,
1549
+ "learning_rate": 1e-05,
1550
+ "loss": 0.2119,
1551
+ "step": 514
1552
+ },
1553
+ {
1554
+ "epoch": 1.55,
1555
+ "learning_rate": 1e-05,
1556
+ "loss": 0.2261,
1557
+ "step": 516
1558
+ },
1559
+ {
1560
+ "epoch": 1.56,
1561
+ "learning_rate": 1e-05,
1562
+ "loss": 0.2138,
1563
+ "step": 518
1564
+ },
1565
+ {
1566
+ "epoch": 1.57,
1567
+ "learning_rate": 1e-05,
1568
+ "loss": 0.2029,
1569
+ "step": 520
1570
+ },
1571
+ {
1572
+ "epoch": 1.57,
1573
+ "learning_rate": 1e-05,
1574
+ "loss": 0.2107,
1575
+ "step": 522
1576
+ },
1577
+ {
1578
+ "epoch": 1.58,
1579
+ "learning_rate": 1e-05,
1580
+ "loss": 0.2078,
1581
+ "step": 524
1582
+ },
1583
+ {
1584
+ "epoch": 1.58,
1585
+ "learning_rate": 1e-05,
1586
+ "loss": 0.2187,
1587
+ "step": 526
1588
+ },
1589
+ {
1590
+ "epoch": 1.59,
1591
+ "learning_rate": 1e-05,
1592
+ "loss": 0.2174,
1593
+ "step": 528
1594
+ },
1595
+ {
1596
+ "epoch": 1.6,
1597
+ "learning_rate": 1e-05,
1598
+ "loss": 0.2165,
1599
+ "step": 530
1600
+ },
1601
+ {
1602
+ "epoch": 1.6,
1603
+ "learning_rate": 1e-05,
1604
+ "loss": 0.2098,
1605
+ "step": 532
1606
+ },
1607
+ {
1608
+ "epoch": 1.61,
1609
+ "learning_rate": 1e-05,
1610
+ "loss": 0.199,
1611
+ "step": 534
1612
+ },
1613
+ {
1614
+ "epoch": 1.61,
1615
+ "learning_rate": 1e-05,
1616
+ "loss": 0.2002,
1617
+ "step": 536
1618
+ },
1619
+ {
1620
+ "epoch": 1.62,
1621
+ "learning_rate": 1e-05,
1622
+ "loss": 0.2137,
1623
+ "step": 538
1624
+ },
1625
+ {
1626
+ "epoch": 1.63,
1627
+ "learning_rate": 1e-05,
1628
+ "loss": 0.2176,
1629
+ "step": 540
1630
+ },
1631
+ {
1632
+ "epoch": 1.63,
1633
+ "learning_rate": 1e-05,
1634
+ "loss": 0.2153,
1635
+ "step": 542
1636
+ },
1637
+ {
1638
+ "epoch": 1.64,
1639
+ "learning_rate": 1e-05,
1640
+ "loss": 0.2164,
1641
+ "step": 544
1642
+ },
1643
+ {
1644
+ "epoch": 1.64,
1645
+ "learning_rate": 1e-05,
1646
+ "loss": 0.2305,
1647
+ "step": 546
1648
+ },
1649
+ {
1650
+ "epoch": 1.65,
1651
+ "learning_rate": 1e-05,
1652
+ "loss": 0.2182,
1653
+ "step": 548
1654
+ },
1655
+ {
1656
+ "epoch": 1.66,
1657
+ "learning_rate": 1e-05,
1658
+ "loss": 0.2228,
1659
+ "step": 550
1660
+ },
1661
+ {
1662
+ "epoch": 1.66,
1663
+ "learning_rate": 1e-05,
1664
+ "loss": 0.2207,
1665
+ "step": 552
1666
+ },
1667
+ {
1668
+ "epoch": 1.67,
1669
+ "learning_rate": 1e-05,
1670
+ "loss": 0.224,
1671
+ "step": 554
1672
+ },
1673
+ {
1674
+ "epoch": 1.67,
1675
+ "learning_rate": 1e-05,
1676
+ "loss": 0.2201,
1677
+ "step": 556
1678
+ },
1679
+ {
1680
+ "epoch": 1.68,
1681
+ "learning_rate": 1e-05,
1682
+ "loss": 0.2137,
1683
+ "step": 558
1684
+ },
1685
+ {
1686
+ "epoch": 1.69,
1687
+ "learning_rate": 1e-05,
1688
+ "loss": 0.2097,
1689
+ "step": 560
1690
+ },
1691
+ {
1692
+ "epoch": 1.69,
1693
+ "learning_rate": 1e-05,
1694
+ "loss": 0.2155,
1695
+ "step": 562
1696
+ },
1697
+ {
1698
+ "epoch": 1.7,
1699
+ "learning_rate": 1e-05,
1700
+ "loss": 0.2166,
1701
+ "step": 564
1702
+ },
1703
+ {
1704
+ "epoch": 1.7,
1705
+ "learning_rate": 1e-05,
1706
+ "loss": 0.2302,
1707
+ "step": 566
1708
+ },
1709
+ {
1710
+ "epoch": 1.71,
1711
+ "learning_rate": 1e-05,
1712
+ "loss": 0.2078,
1713
+ "step": 568
1714
+ },
1715
+ {
1716
+ "epoch": 1.72,
1717
+ "learning_rate": 1e-05,
1718
+ "loss": 0.1972,
1719
+ "step": 570
1720
+ },
1721
+ {
1722
+ "epoch": 1.72,
1723
+ "learning_rate": 1e-05,
1724
+ "loss": 0.2198,
1725
+ "step": 572
1726
+ },
1727
+ {
1728
+ "epoch": 1.73,
1729
+ "learning_rate": 1e-05,
1730
+ "loss": 0.213,
1731
+ "step": 574
1732
+ },
1733
+ {
1734
+ "epoch": 1.73,
1735
+ "learning_rate": 1e-05,
1736
+ "loss": 0.2183,
1737
+ "step": 576
1738
+ },
1739
+ {
1740
+ "epoch": 1.74,
1741
+ "learning_rate": 1e-05,
1742
+ "loss": 0.2044,
1743
+ "step": 578
1744
+ },
1745
+ {
1746
+ "epoch": 1.75,
1747
+ "learning_rate": 1e-05,
1748
+ "loss": 0.2163,
1749
+ "step": 580
1750
+ },
1751
+ {
1752
+ "epoch": 1.75,
1753
+ "learning_rate": 1e-05,
1754
+ "loss": 0.2031,
1755
+ "step": 582
1756
+ },
1757
+ {
1758
+ "epoch": 1.76,
1759
+ "learning_rate": 1e-05,
1760
+ "loss": 0.2228,
1761
+ "step": 584
1762
+ },
1763
+ {
1764
+ "epoch": 1.77,
1765
+ "learning_rate": 1e-05,
1766
+ "loss": 0.2271,
1767
+ "step": 586
1768
+ },
1769
+ {
1770
+ "epoch": 1.77,
1771
+ "learning_rate": 1e-05,
1772
+ "loss": 0.2196,
1773
+ "step": 588
1774
+ },
1775
+ {
1776
+ "epoch": 1.78,
1777
+ "learning_rate": 1e-05,
1778
+ "loss": 0.2134,
1779
+ "step": 590
1780
+ },
1781
+ {
1782
+ "epoch": 1.78,
1783
+ "learning_rate": 1e-05,
1784
+ "loss": 0.2019,
1785
+ "step": 592
1786
+ },
1787
+ {
1788
+ "epoch": 1.79,
1789
+ "learning_rate": 1e-05,
1790
+ "loss": 0.1986,
1791
+ "step": 594
1792
+ },
1793
+ {
1794
+ "epoch": 1.8,
1795
+ "learning_rate": 1e-05,
1796
+ "loss": 0.1943,
1797
+ "step": 596
1798
+ },
1799
+ {
1800
+ "epoch": 1.8,
1801
+ "learning_rate": 1e-05,
1802
+ "loss": 0.206,
1803
+ "step": 598
1804
+ },
1805
+ {
1806
+ "epoch": 1.81,
1807
+ "learning_rate": 1e-05,
1808
+ "loss": 0.2154,
1809
+ "step": 600
1810
+ },
1811
+ {
1812
+ "epoch": 1.81,
1813
+ "learning_rate": 1e-05,
1814
+ "loss": 0.2103,
1815
+ "step": 602
1816
+ },
1817
+ {
1818
+ "epoch": 1.82,
1819
+ "learning_rate": 1e-05,
1820
+ "loss": 0.2167,
1821
+ "step": 604
1822
+ },
1823
+ {
1824
+ "epoch": 1.83,
1825
+ "learning_rate": 1e-05,
1826
+ "loss": 0.209,
1827
+ "step": 606
1828
+ },
1829
+ {
1830
+ "epoch": 1.83,
1831
+ "learning_rate": 1e-05,
1832
+ "loss": 0.2208,
1833
+ "step": 608
1834
+ },
1835
+ {
1836
+ "epoch": 1.84,
1837
+ "learning_rate": 1e-05,
1838
+ "loss": 0.2252,
1839
+ "step": 610
1840
+ },
1841
+ {
1842
+ "epoch": 1.84,
1843
+ "learning_rate": 1e-05,
1844
+ "loss": 0.2092,
1845
+ "step": 612
1846
+ },
1847
+ {
1848
+ "epoch": 1.85,
1849
+ "learning_rate": 1e-05,
1850
+ "loss": 0.2099,
1851
+ "step": 614
1852
+ },
1853
+ {
1854
+ "epoch": 1.86,
1855
+ "learning_rate": 1e-05,
1856
+ "loss": 0.1955,
1857
+ "step": 616
1858
+ },
1859
+ {
1860
+ "epoch": 1.86,
1861
+ "learning_rate": 1e-05,
1862
+ "loss": 0.2176,
1863
+ "step": 618
1864
+ },
1865
+ {
1866
+ "epoch": 1.87,
1867
+ "learning_rate": 1e-05,
1868
+ "loss": 0.2053,
1869
+ "step": 620
1870
+ },
1871
+ {
1872
+ "epoch": 1.87,
1873
+ "learning_rate": 1e-05,
1874
+ "loss": 0.2119,
1875
+ "step": 622
1876
+ },
1877
+ {
1878
+ "epoch": 1.88,
1879
+ "learning_rate": 1e-05,
1880
+ "loss": 0.1986,
1881
+ "step": 624
1882
+ },
1883
+ {
1884
+ "epoch": 1.89,
1885
+ "learning_rate": 1e-05,
1886
+ "loss": 0.2136,
1887
+ "step": 626
1888
+ },
1889
+ {
1890
+ "epoch": 1.89,
1891
+ "learning_rate": 1e-05,
1892
+ "loss": 0.2154,
1893
+ "step": 628
1894
+ },
1895
+ {
1896
+ "epoch": 1.9,
1897
+ "learning_rate": 1e-05,
1898
+ "loss": 0.2091,
1899
+ "step": 630
1900
+ },
1901
+ {
1902
+ "epoch": 1.9,
1903
+ "learning_rate": 1e-05,
1904
+ "loss": 0.2161,
1905
+ "step": 632
1906
+ },
1907
+ {
1908
+ "epoch": 1.91,
1909
+ "learning_rate": 1e-05,
1910
+ "loss": 0.2107,
1911
+ "step": 634
1912
+ },
1913
+ {
1914
+ "epoch": 1.92,
1915
+ "learning_rate": 1e-05,
1916
+ "loss": 0.1814,
1917
+ "step": 636
1918
+ },
1919
+ {
1920
+ "epoch": 1.92,
1921
+ "learning_rate": 1e-05,
1922
+ "loss": 0.2097,
1923
+ "step": 638
1924
+ },
1925
+ {
1926
+ "epoch": 1.93,
1927
+ "learning_rate": 1e-05,
1928
+ "loss": 0.2078,
1929
+ "step": 640
1930
+ },
1931
+ {
1932
+ "epoch": 1.93,
1933
+ "learning_rate": 1e-05,
1934
+ "loss": 0.1985,
1935
+ "step": 642
1936
+ },
1937
+ {
1938
+ "epoch": 1.94,
1939
+ "learning_rate": 1e-05,
1940
+ "loss": 0.2115,
1941
+ "step": 644
1942
+ },
1943
+ {
1944
+ "epoch": 1.95,
1945
+ "learning_rate": 1e-05,
1946
+ "loss": 0.2128,
1947
+ "step": 646
1948
+ },
1949
+ {
1950
+ "epoch": 1.95,
1951
+ "learning_rate": 1e-05,
1952
+ "loss": 0.2133,
1953
+ "step": 648
1954
+ },
1955
+ {
1956
+ "epoch": 1.96,
1957
+ "learning_rate": 1e-05,
1958
+ "loss": 0.2109,
1959
+ "step": 650
1960
+ },
1961
+ {
1962
+ "epoch": 1.96,
1963
+ "learning_rate": 1e-05,
1964
+ "loss": 0.2133,
1965
+ "step": 652
1966
+ },
1967
+ {
1968
+ "epoch": 1.97,
1969
+ "learning_rate": 1e-05,
1970
+ "loss": 0.198,
1971
+ "step": 654
1972
+ },
1973
+ {
1974
+ "epoch": 1.98,
1975
+ "learning_rate": 1e-05,
1976
+ "loss": 0.2068,
1977
+ "step": 656
1978
+ },
1979
+ {
1980
+ "epoch": 1.98,
1981
+ "learning_rate": 1e-05,
1982
+ "loss": 0.2222,
1983
+ "step": 658
1984
+ },
1985
+ {
1986
+ "epoch": 1.99,
1987
+ "learning_rate": 1e-05,
1988
+ "loss": 0.2035,
1989
+ "step": 660
1990
+ },
1991
+ {
1992
+ "epoch": 1.99,
1993
+ "learning_rate": 1e-05,
1994
+ "loss": 0.2067,
1995
+ "step": 662
1996
+ },
1997
+ {
1998
+ "epoch": 2.0,
1999
+ "learning_rate": 1e-05,
2000
+ "loss": 0.207,
2001
+ "step": 664
2002
+ }
2003
+ ],
2004
+ "logging_steps": 2,
2005
+ "max_steps": 1992,
2006
+ "num_train_epochs": 6,
2007
+ "save_steps": 64.0,
2008
+ "total_flos": 148901009686528.0,
2009
+ "trial_name": null,
2010
+ "trial_params": null
2011
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6da0167127a217efe26c78d229b99ad905ad18eecd77581e01cd9a087834755f
3
+ size 6456