Hugging Face's logo

AngoHF
/
EssayGPT

PEFT
Safetensors
lora
Generated from Trainer
Model card Files
xet
Community
AngoHF commited on
Commit
fbcb102
·
verified ·
1 Parent(s): f13764c

first commit

Browse files
Files changed (15) hide show
  1. README.md +55 -1
  2. adapter_config.json +26 -0
  3. adapter_model.safetensors +3 -0
  4. added_tokens.json +5 -0
  5. all_results.json +7 -0
  6. app.py +114 -0
  7. merges.txt +0 -0
  8. special_tokens_map.json +20 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +44 -0
  11. train_results.json +7 -0
  12. trainer_log.jsonl +197 -0
  13. trainer_state.json +1206 -0
  14. training_args.bin +3 -0
  15. vocab.json +0 -0
README.md CHANGED
@@ -1,3 +1,57 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: other
3
+ library_name: peft
4
+ tags:
5
+ - lora
6
+ - generated_from_trainer
7
+ base_model: Qwen1.5-1.8B-Chat
8
+ model-index:
9
+ - name: Qwen-1.8B
10
+ results: []
11
  ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # Qwen-1.8B
17
+
18
+ This model is a fine-tuned version of [Qwen1.5-1.8B-Chat](https://huggingface.co/models/Qwen1.5-1.8B-Chat) on the essay_dataset dataset.
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.0005
38
+ - train_batch_size: 2
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 8
42
+ - total_train_batch_size: 16
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: cosine
45
+ - num_epochs: 8.0
46
+
47
+ ### Training results
48
+
49
+
50
+
51
+ ### Framework versions
52
+
53
+ - PEFT 0.7.1
54
+ - Transformers 4.37.2
55
+ - Pytorch 1.13.1+cu116
56
+ - Datasets 2.14.7
57
+ - Tokenizers 0.15.1
adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/data/ango/models/Qwen1.5-1.8B-Chat",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 32.0,
13
+ "lora_dropout": 0.1,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 16,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "q_proj",
23
+ "v_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cf776c031b149eefe9c1c1bc060b13c6a62bf6824ebcd380a660e3be4b0feeb
3
+ size 6304288
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 8.0,
3
+ "train_loss": 1.1027992168251348,
4
+ "train_runtime": 31447.7257,
5
+ "train_samples_per_second": 0.997,
6
+ "train_steps_per_second": 0.062
7
+ }
app.py ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import gradio as gr
2
+
3
+
4
+ from transformers import (
5
+ AutoModelForCausalLM,
6
+ AutoTokenizer
7
+ )
8
+ from peft import PeftModel
9
+ import torch
10
+
11
+ model_path = "Qwen1.5-1.8B-Chat"
12
+ lora_path = "." #+ "/checkpoint-100"
13
+
14
+ if torch.cuda.is_available():
15
+ device = "cuda:0"
16
+ else:
17
+ device = "cpu"
18
+
19
+ tokenizer = AutoTokenizer.from_pretrained(
20
+ model_path,
21
+ )
22
+ config_kwargs = {"device_map": device}
23
+
24
+ model = AutoModelForCausalLM.from_pretrained(
25
+ model_path,
26
+ torch_dtype=torch.float16,
27
+ **config_kwargs
28
+ )
29
+
30
+ model = PeftModel.from_pretrained(model, lora_path)
31
+ model = model.merge_and_unload()
32
+ model.eval()
33
+
34
+ # model.config.use_cache = True
35
+ # model.to("cpu")
36
+ # model.save_pretrained("/data/ango/EssayGPT")
37
+
38
+ # tokenizer.save_pretrained("/data/ango/EssayGPT")
39
+
40
+
41
+ MAX_MATERIALS = 4
42
+
43
+
44
+ def call(related_materials, materials, question):
45
+ query_texts = [f"材料{i + 1}\n{material}" for i, material in enumerate(materials) if i in related_materials]
46
+ query_texts.append(f"问题:{question}")
47
+ query = "\n".join(query_texts)
48
+ messages = [
49
+ {"role": "system", "content": "请你根据以下提供的材料来回答问题"},
50
+ {"role": "user", "content": query}
51
+ ]
52
+ text = tokenizer.apply_chat_template(
53
+ messages,
54
+ tokenize=False,
55
+ add_generation_prompt=True
56
+ )
57
+ model_inputs = tokenizer([text], return_tensors="pt").to(device)
58
+ print(len(model_inputs.input_ids[0]))
59
+ generated_ids = model.generate(
60
+ model_inputs.input_ids,
61
+ max_length=8096
62
+ )
63
+ generated_ids = [
64
+ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
65
+ ]
66
+
67
+ response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
68
+ return response
69
+
70
+
71
+ def create_ui():
72
+ with gr.Blocks() as app:
73
+ gr.Markdown("""<center><font size=8>EssayGPT-申论大模型</center>""")
74
+ gr.Markdown(
75
+ """<center><font size=4>1.把材料填入对应位置 2.输入问题和要求 3.选择解答问题需要的相关材料 4.点击"提问!"</center>""")
76
+ with gr.Row():
77
+ with gr.Column():
78
+ materials = []
79
+
80
+ for i in range(MAX_MATERIALS):
81
+ with gr.Tab(f"材料{i + 1}"):
82
+ materials.append(gr.Textbox(label="材料内容"))
83
+ with gr.Column():
84
+ related_materials = gr.Dropdown(
85
+ choices=list(range(1, MAX_MATERIALS + 1)), multiselect=True,
86
+ label="问题所需相关材料")
87
+ question = gr.Textbox(label="问题")
88
+ submit = gr.Button("提问！")
89
+ answer = gr.Textbox(label="回答")
90
+ build_ui({"materials": materials, "related_materials": related_materials, "question": question,
91
+ "submit": submit, "answer": answer})
92
+ return app
93
+
94
+
95
+ def build_ui(components):
96
+ def func(related_materials, question, *materials):
97
+ if not related_materials:
98
+ return "请选择问题所需相关材料"
99
+ related_materials = [i - 1 for i in related_materials]
100
+ return call(related_materials, materials, question)
101
+
102
+ components["submit"].click(func,
103
+ [components["related_materials"], components["question"], *components["materials"]],
104
+ components["answer"])
105
+
106
+
107
+ def run():
108
+ app = create_ui()
109
+ app.queue()
110
+ app.launch(share=True)
111
+
112
+
113
+ if __name__ == '__main__':
114
+ run()
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|endoftext|>",
37
+ "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "padding_side": "right",
41
+ "split_special_tokens": false,
42
+ "tokenizer_class": "Qwen2Tokenizer",
43
+ "unk_token": null
44
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 8.0,
3
+ "train_loss": 1.1027992168251348,
4
+ "train_runtime": 31447.7257,
5
+ "train_samples_per_second": 0.997,
6
+ "train_steps_per_second": 0.062
7
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,197 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 1960, "loss": 1.9845, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004999678864499828, "epoch": 0.04, "percentage": 0.51, "elapsed_time": "0:03:07", "remaining_time": "10:09:35"}
2
+ {"current_steps": 20, "total_steps": 1960, "loss": 1.8444, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000499871554050172, "epoch": 0.08, "percentage": 1.02, "elapsed_time": "0:05:51", "remaining_time": "9:27:30"}
3
+ {"current_steps": 30, "total_steps": 1960, "loss": 1.721, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004997110275491702, "epoch": 0.12, "percentage": 1.53, "elapsed_time": "0:08:56", "remaining_time": "9:35:35"}
4
+ {"current_steps": 40, "total_steps": 1960, "loss": 1.6755, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004994863481875841, "epoch": 0.16, "percentage": 2.04, "elapsed_time": "0:11:14", "remaining_time": "8:59:37"}
5
+ {"current_steps": 50, "total_steps": 1960, "loss": 1.7248, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004991975736874289, "epoch": 0.2, "percentage": 2.55, "elapsed_time": "0:14:13", "remaining_time": "9:03:07"}
6
+ {"current_steps": 60, "total_steps": 1960, "loss": 1.6803, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004988447782372996, "epoch": 0.24, "percentage": 3.06, "elapsed_time": "0:16:41", "remaining_time": "8:48:47"}
7
+ {"current_steps": 70, "total_steps": 1960, "loss": 1.7063, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004984280524733107, "epoch": 0.29, "percentage": 3.57, "elapsed_time": "0:18:48", "remaining_time": "8:27:51"}
8
+ {"current_steps": 80, "total_steps": 1960, "loss": 1.6724, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004979475034558115, "epoch": 0.33, "percentage": 4.08, "elapsed_time": "0:21:21", "remaining_time": "8:21:58"}
9
+ {"current_steps": 90, "total_steps": 1960, "loss": 1.6933, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004974032546418815, "epoch": 0.37, "percentage": 4.59, "elapsed_time": "0:23:38", "remaining_time": "8:11:14"}
10
+ {"current_steps": 100, "total_steps": 1960, "loss": 1.6243, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004967954458536126, "epoch": 0.41, "percentage": 5.1, "elapsed_time": "0:27:15", "remaining_time": "8:27:03"}
11
+ {"current_steps": 110, "total_steps": 1960, "loss": 1.639, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004961242332421882, "epoch": 0.45, "percentage": 5.61, "elapsed_time": "0:29:46", "remaining_time": "8:20:48"}
12
+ {"current_steps": 120, "total_steps": 1960, "loss": 1.6545, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004953897892477664, "epoch": 0.49, "percentage": 6.12, "elapsed_time": "0:32:19", "remaining_time": "8:15:41"}
13
+ {"current_steps": 130, "total_steps": 1960, "loss": 1.6017, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004945923025551788, "epoch": 0.53, "percentage": 6.63, "elapsed_time": "0:35:07", "remaining_time": "8:14:28"}
14
+ {"current_steps": 140, "total_steps": 1960, "loss": 1.6522, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004937319780454559, "epoch": 0.57, "percentage": 7.14, "elapsed_time": "0:37:27", "remaining_time": "8:06:57"}
15
+ {"current_steps": 150, "total_steps": 1960, "loss": 1.5948, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000492809036743191, "epoch": 0.61, "percentage": 7.65, "elapsed_time": "0:39:48", "remaining_time": "8:00:15"}
16
+ {"current_steps": 160, "total_steps": 1960, "loss": 1.5385, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004918237157597574, "epoch": 0.65, "percentage": 8.16, "elapsed_time": "0:42:41", "remaining_time": "8:00:19"}
17
+ {"current_steps": 170, "total_steps": 1960, "loss": 1.6132, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004907762682323926, "epoch": 0.69, "percentage": 8.67, "elapsed_time": "0:44:50", "remaining_time": "7:52:05"}
18
+ {"current_steps": 180, "total_steps": 1960, "loss": 1.5396, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004896669632591652, "epoch": 0.73, "percentage": 9.18, "elapsed_time": "0:47:49", "remaining_time": "7:52:56"}
19
+ {"current_steps": 190, "total_steps": 1960, "loss": 1.5023, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000488496085829841, "epoch": 0.78, "percentage": 9.69, "elapsed_time": "0:50:34", "remaining_time": "7:51:12"}
20
+ {"current_steps": 200, "total_steps": 1960, "loss": 1.4937, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004872639367526672, "epoch": 0.82, "percentage": 10.2, "elapsed_time": "0:53:08", "remaining_time": "7:47:39"}
21
+ {"current_steps": 210, "total_steps": 1960, "loss": 1.4824, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004859708325770919, "epoch": 0.86, "percentage": 10.71, "elapsed_time": "0:55:49", "remaining_time": "7:45:14"}
22
+ {"current_steps": 220, "total_steps": 1960, "loss": 1.5506, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004846171055124401, "epoch": 0.9, "percentage": 11.22, "elapsed_time": "0:58:17", "remaining_time": "7:40:59"}
23
+ {"current_steps": 230, "total_steps": 1960, "loss": 1.5709, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00048320310334256625, "epoch": 0.94, "percentage": 11.73, "elapsed_time": "1:00:46", "remaining_time": "7:37:07"}
24
+ {"current_steps": 240, "total_steps": 1960, "loss": 1.5531, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004817291893365054, "epoch": 0.98, "percentage": 12.24, "elapsed_time": "1:03:30", "remaining_time": "7:35:08"}
25
+ {"current_steps": 250, "total_steps": 1960, "loss": 1.4546, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00048019574215514706, "epoch": 1.02, "percentage": 12.76, "elapsed_time": "1:06:27", "remaining_time": "7:34:35"}
26
+ {"current_steps": 260, "total_steps": 1960, "loss": 1.4281, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004786031557539531, "epoch": 1.06, "percentage": 13.27, "elapsed_time": "1:08:48", "remaining_time": "7:29:56"}
27
+ {"current_steps": 270, "total_steps": 1960, "loss": 1.4339, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00047695183928174803, "epoch": 1.1, "percentage": 13.78, "elapsed_time": "1:11:19", "remaining_time": "7:26:25"}
28
+ {"current_steps": 280, "total_steps": 1960, "loss": 1.3993, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00047524221697560476, "epoch": 1.14, "percentage": 14.29, "elapsed_time": "1:14:12", "remaining_time": "7:25:13"}
29
+ {"current_steps": 290, "total_steps": 1960, "loss": 1.3786, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004734747280518549, "epoch": 1.18, "percentage": 14.8, "elapsed_time": "1:16:40", "remaining_time": "7:21:34"}
30
+ {"current_steps": 300, "total_steps": 1960, "loss": 1.458, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00047164982659325005, "epoch": 1.22, "percentage": 15.31, "elapsed_time": "1:19:31", "remaining_time": "7:20:02"}
31
+ {"current_steps": 310, "total_steps": 1960, "loss": 1.3692, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004697679814323043, "epoch": 1.27, "percentage": 15.82, "elapsed_time": "1:22:11", "remaining_time": "7:17:28"}
32
+ {"current_steps": 320, "total_steps": 1960, "loss": 1.491, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00046782967603084736, "epoch": 1.31, "percentage": 16.33, "elapsed_time": "1:24:19", "remaining_time": "7:12:12"}
33
+ {"current_steps": 330, "total_steps": 1960, "loss": 1.3637, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00046583540835581883, "epoch": 1.35, "percentage": 16.84, "elapsed_time": "1:27:01", "remaining_time": "7:09:53"}
34
+ {"current_steps": 340, "total_steps": 1960, "loss": 1.4276, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004637856907513366, "epoch": 1.39, "percentage": 17.35, "elapsed_time": "1:29:42", "remaining_time": "7:07:26"}
35
+ {"current_steps": 350, "total_steps": 1960, "loss": 1.3943, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00046168104980707104, "epoch": 1.43, "percentage": 17.86, "elapsed_time": "1:32:50", "remaining_time": "7:07:05"}
36
+ {"current_steps": 360, "total_steps": 1960, "loss": 1.4274, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00045952202622296013, "epoch": 1.47, "percentage": 18.37, "elapsed_time": "1:35:49", "remaining_time": "7:05:53"}
37
+ {"current_steps": 370, "total_steps": 1960, "loss": 1.4829, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00045730917467029877, "epoch": 1.51, "percentage": 18.88, "elapsed_time": "1:38:47", "remaining_time": "7:04:33"}
38
+ {"current_steps": 380, "total_steps": 1960, "loss": 1.3585, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00045504306364923896, "epoch": 1.55, "percentage": 19.39, "elapsed_time": "1:41:32", "remaining_time": "7:02:11"}
39
+ {"current_steps": 390, "total_steps": 1960, "loss": 1.4194, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00045272427534273776, "epoch": 1.59, "percentage": 19.9, "elapsed_time": "1:43:53", "remaining_time": "6:58:15"}
40
+ {"current_steps": 400, "total_steps": 1960, "loss": 1.3924, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00045035340546698916, "epoch": 1.63, "percentage": 20.41, "elapsed_time": "1:46:26", "remaining_time": "6:55:08"}
41
+ {"current_steps": 410, "total_steps": 1960, "loss": 1.4117, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004479310631183799, "epoch": 1.67, "percentage": 20.92, "elapsed_time": "1:48:55", "remaining_time": "6:51:47"}
42
+ {"current_steps": 420, "total_steps": 1960, "loss": 1.3849, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004454578706170075, "epoch": 1.71, "percentage": 21.43, "elapsed_time": "1:51:59", "remaining_time": "6:50:39"}
43
+ {"current_steps": 430, "total_steps": 1960, "loss": 1.3857, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004429344633468004, "epoch": 1.76, "percentage": 21.94, "elapsed_time": "1:55:10", "remaining_time": "6:49:49"}
44
+ {"current_steps": 440, "total_steps": 1960, "loss": 1.4772, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004403614895922836, "epoch": 1.8, "percentage": 22.45, "elapsed_time": "1:57:55", "remaining_time": "6:47:22"}
45
+ {"current_steps": 450, "total_steps": 1960, "loss": 1.4021, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004377396103720278, "epoch": 1.84, "percentage": 22.96, "elapsed_time": "2:00:54", "remaining_time": "6:45:41"}
46
+ {"current_steps": 460, "total_steps": 1960, "loss": 1.3589, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00043506949926882887, "epoch": 1.88, "percentage": 23.47, "elapsed_time": "2:03:50", "remaining_time": "6:43:50"}
47
+ {"current_steps": 470, "total_steps": 1960, "loss": 1.45, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004323518422566586, "epoch": 1.92, "percentage": 23.98, "elapsed_time": "2:06:09", "remaining_time": "6:39:57"}
48
+ {"current_steps": 480, "total_steps": 1960, "loss": 1.2784, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004295873375244319, "epoch": 1.96, "percentage": 24.49, "elapsed_time": "2:08:40", "remaining_time": "6:36:46"}
49
+ {"current_steps": 490, "total_steps": 1960, "loss": 1.4127, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00042677669529663686, "epoch": 2.0, "percentage": 25.0, "elapsed_time": "2:10:43", "remaining_time": "6:32:11"}
50
+ {"current_steps": 500, "total_steps": 1960, "loss": 1.2777, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004239206376508716, "epoch": 2.04, "percentage": 25.51, "elapsed_time": "2:12:54", "remaining_time": "6:28:04"}
51
+ {"current_steps": 510, "total_steps": 1960, "loss": 1.1873, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00042101989833233654, "epoch": 2.08, "percentage": 26.02, "elapsed_time": "2:15:54", "remaining_time": "6:26:23"}
52
+ {"current_steps": 520, "total_steps": 1960, "loss": 1.2746, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004180752225653292, "epoch": 2.12, "percentage": 26.53, "elapsed_time": "2:18:42", "remaining_time": "6:24:05"}
53
+ {"current_steps": 530, "total_steps": 1960, "loss": 1.308, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004150873668617898, "epoch": 2.16, "percentage": 27.04, "elapsed_time": "2:21:41", "remaining_time": "6:22:18"}
54
+ {"current_steps": 540, "total_steps": 1960, "loss": 1.2431, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00041205709882694713, "epoch": 2.2, "percentage": 27.55, "elapsed_time": "2:23:41", "remaining_time": "6:17:50"}
55
+ {"current_steps": 550, "total_steps": 1960, "loss": 1.3411, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004089851969621138, "epoch": 2.24, "percentage": 28.06, "elapsed_time": "2:26:14", "remaining_time": "6:14:55"}
56
+ {"current_steps": 560, "total_steps": 1960, "loss": 1.2369, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004058724504646834, "epoch": 2.29, "percentage": 28.57, "elapsed_time": "2:29:01", "remaining_time": "6:12:33"}
57
+ {"current_steps": 570, "total_steps": 1960, "loss": 1.303, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004027196590253786, "epoch": 2.33, "percentage": 29.08, "elapsed_time": "2:32:00", "remaining_time": "6:10:42"}
58
+ {"current_steps": 580, "total_steps": 1960, "loss": 1.2011, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000399527632622804, "epoch": 2.37, "percentage": 29.59, "elapsed_time": "2:34:36", "remaining_time": "6:07:52"}
59
+ {"current_steps": 590, "total_steps": 1960, "loss": 1.2239, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003962971913153559, "epoch": 2.41, "percentage": 30.1, "elapsed_time": "2:38:15", "remaining_time": "6:07:27"}
60
+ {"current_steps": 600, "total_steps": 1960, "loss": 1.2133, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00039302916503054243, "epoch": 2.45, "percentage": 30.61, "elapsed_time": "2:41:10", "remaining_time": "6:05:19"}
61
+ {"current_steps": 610, "total_steps": 1960, "loss": 1.2108, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003897243933517679, "epoch": 2.49, "percentage": 31.12, "elapsed_time": "2:44:28", "remaining_time": "6:03:59"}
62
+ {"current_steps": 620, "total_steps": 1960, "loss": 1.3095, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00038638372530263714, "epoch": 2.53, "percentage": 31.63, "elapsed_time": "2:46:56", "remaining_time": "6:00:49"}
63
+ {"current_steps": 630, "total_steps": 1960, "loss": 1.2392, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00038300801912883415, "epoch": 2.57, "percentage": 32.14, "elapsed_time": "2:49:45", "remaining_time": "5:58:22"}
64
+ {"current_steps": 640, "total_steps": 1960, "loss": 1.1789, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003795981420776313, "epoch": 2.61, "percentage": 32.65, "elapsed_time": "2:51:38", "remaining_time": "5:54:00"}
65
+ {"current_steps": 650, "total_steps": 1960, "loss": 1.2285, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003761549701750865, "epoch": 2.65, "percentage": 33.16, "elapsed_time": "2:53:37", "remaining_time": "5:49:56"}
66
+ {"current_steps": 660, "total_steps": 1960, "loss": 1.2101, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003726793880009845, "epoch": 2.69, "percentage": 33.67, "elapsed_time": "2:56:15", "remaining_time": "5:47:09"}
67
+ {"current_steps": 670, "total_steps": 1960, "loss": 1.1973, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00036917228846158136, "epoch": 2.73, "percentage": 34.18, "elapsed_time": "2:58:53", "remaining_time": "5:44:25"}
68
+ {"current_steps": 680, "total_steps": 1960, "loss": 1.2238, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00036563457256020887, "epoch": 2.78, "percentage": 34.69, "elapsed_time": "3:02:05", "remaining_time": "5:42:44"}
69
+ {"current_steps": 690, "total_steps": 1960, "loss": 1.2249, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003620671491657992, "epoch": 2.82, "percentage": 35.2, "elapsed_time": "3:04:08", "remaining_time": "5:38:54"}
70
+ {"current_steps": 700, "total_steps": 1960, "loss": 1.2314, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00035847093477938953, "epoch": 2.86, "percentage": 35.71, "elapsed_time": "3:06:19", "remaining_time": "5:35:22"}
71
+ {"current_steps": 710, "total_steps": 1960, "loss": 1.2987, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00035484685329866423, "epoch": 2.9, "percentage": 36.22, "elapsed_time": "3:09:18", "remaining_time": "5:33:18"}
72
+ {"current_steps": 720, "total_steps": 1960, "loss": 1.2416, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00035119583578059843, "epoch": 2.94, "percentage": 36.73, "elapsed_time": "3:11:24", "remaining_time": "5:29:38"}
73
+ {"current_steps": 730, "total_steps": 1960, "loss": 1.175, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00034751882020226174, "epoch": 2.98, "percentage": 37.24, "elapsed_time": "3:14:56", "remaining_time": "5:28:27"}
74
+ {"current_steps": 740, "total_steps": 1960, "loss": 1.2123, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003438167512198436, "epoch": 3.02, "percentage": 37.76, "elapsed_time": "3:17:04", "remaining_time": "5:24:54"}
75
+ {"current_steps": 750, "total_steps": 1960, "loss": 1.0257, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00034009057992596335, "epoch": 3.06, "percentage": 38.27, "elapsed_time": "3:19:46", "remaining_time": "5:22:18"}
76
+ {"current_steps": 760, "total_steps": 1960, "loss": 1.118, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003363412636053269, "epoch": 3.1, "percentage": 38.78, "elapsed_time": "3:23:00", "remaining_time": "5:20:31"}
77
+ {"current_steps": 770, "total_steps": 1960, "loss": 1.1586, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00033256976548879183, "epoch": 3.14, "percentage": 39.29, "elapsed_time": "3:25:08", "remaining_time": "5:17:02"}
78
+ {"current_steps": 780, "total_steps": 1960, "loss": 1.0559, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003287770545059052, "epoch": 3.18, "percentage": 39.8, "elapsed_time": "3:27:39", "remaining_time": "5:14:08"}
79
+ {"current_steps": 790, "total_steps": 1960, "loss": 1.0775, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003249641050359779, "epoch": 3.22, "percentage": 40.31, "elapsed_time": "3:30:22", "remaining_time": "5:11:34"}
80
+ {"current_steps": 800, "total_steps": 1960, "loss": 1.0905, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003211318966577581, "epoch": 3.27, "percentage": 40.82, "elapsed_time": "3:33:04", "remaining_time": "5:08:57"}
81
+ {"current_steps": 810, "total_steps": 1960, "loss": 1.088, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00031728141389776923, "epoch": 3.31, "percentage": 41.33, "elapsed_time": "3:35:41", "remaining_time": "5:06:13"}
82
+ {"current_steps": 820, "total_steps": 1960, "loss": 1.0395, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003134136459773768, "epoch": 3.35, "percentage": 41.84, "elapsed_time": "3:38:12", "remaining_time": "5:03:21"}
83
+ {"current_steps": 830, "total_steps": 1960, "loss": 1.1064, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00030952958655864954, "epoch": 3.39, "percentage": 42.35, "elapsed_time": "3:41:15", "remaining_time": "5:01:14"}
84
+ {"current_steps": 840, "total_steps": 1960, "loss": 1.0662, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003056302334890786, "epoch": 3.43, "percentage": 42.86, "elapsed_time": "3:44:14", "remaining_time": "4:58:58"}
85
+ {"current_steps": 850, "total_steps": 1960, "loss": 1.0627, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003017165885452227, "epoch": 3.47, "percentage": 43.37, "elapsed_time": "3:46:30", "remaining_time": "4:55:47"}
86
+ {"current_steps": 860, "total_steps": 1960, "loss": 0.9968, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00029778965717534313, "epoch": 3.51, "percentage": 43.88, "elapsed_time": "3:49:07", "remaining_time": "4:53:03"}
87
+ {"current_steps": 870, "total_steps": 1960, "loss": 1.1237, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002938504482410954, "epoch": 3.55, "percentage": 44.39, "elapsed_time": "3:51:33", "remaining_time": "4:50:06"}
88
+ {"current_steps": 880, "total_steps": 1960, "loss": 1.0432, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00028989997375834483, "epoch": 3.59, "percentage": 44.9, "elapsed_time": "3:54:03", "remaining_time": "4:47:15"}
89
+ {"current_steps": 890, "total_steps": 1960, "loss": 1.1197, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00028593924863717045, "epoch": 3.63, "percentage": 45.41, "elapsed_time": "3:56:28", "remaining_time": "4:44:17"}
90
+ {"current_steps": 900, "total_steps": 1960, "loss": 1.0016, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002819692904211265, "epoch": 3.67, "percentage": 45.92, "elapsed_time": "3:58:59", "remaining_time": "4:41:28"}
91
+ {"current_steps": 910, "total_steps": 1960, "loss": 1.0956, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00027799111902582696, "epoch": 3.71, "percentage": 46.43, "elapsed_time": "4:01:37", "remaining_time": "4:38:47"}
92
+ {"current_steps": 920, "total_steps": 1960, "loss": 1.0878, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00027400575647692046, "epoch": 3.76, "percentage": 46.94, "elapsed_time": "4:04:02", "remaining_time": "4:35:52"}
93
+ {"current_steps": 930, "total_steps": 1960, "loss": 1.0838, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00027001422664752335, "epoch": 3.8, "percentage": 47.45, "elapsed_time": "4:06:50", "remaining_time": "4:33:22"}
94
+ {"current_steps": 940, "total_steps": 1960, "loss": 1.0587, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00026601755499517824, "epoch": 3.84, "percentage": 47.96, "elapsed_time": "4:09:48", "remaining_time": "4:31:04"}
95
+ {"current_steps": 950, "total_steps": 1960, "loss": 1.0857, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002620167682984052, "epoch": 3.88, "percentage": 48.47, "elapsed_time": "4:11:48", "remaining_time": "4:27:42"}
96
+ {"current_steps": 960, "total_steps": 1960, "loss": 1.0107, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00025801289439291385, "epoch": 3.92, "percentage": 48.98, "elapsed_time": "4:14:38", "remaining_time": "4:25:14"}
97
+ {"current_steps": 970, "total_steps": 1960, "loss": 1.1491, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00025400696190754345, "epoch": 3.96, "percentage": 49.49, "elapsed_time": "4:18:04", "remaining_time": "4:23:23"}
98
+ {"current_steps": 980, "total_steps": 1960, "loss": 1.0726, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00025, "epoch": 4.0, "percentage": 50.0, "elapsed_time": "4:20:54", "remaining_time": "4:20:54"}
99
+ {"current_steps": 990, "total_steps": 1960, "loss": 0.9856, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002459930380924566, "epoch": 4.04, "percentage": 50.51, "elapsed_time": "4:24:27", "remaining_time": "4:19:06"}
100
+ {"current_steps": 1000, "total_steps": 1960, "loss": 0.9726, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002419871056070862, "epoch": 4.08, "percentage": 51.02, "elapsed_time": "4:27:24", "remaining_time": "4:16:43"}
101
+ {"current_steps": 1010, "total_steps": 1960, "loss": 0.9675, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00023798323170159486, "epoch": 4.12, "percentage": 51.53, "elapsed_time": "4:29:54", "remaining_time": "4:13:52"}
102
+ {"current_steps": 1020, "total_steps": 1960, "loss": 0.9831, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002339824450048218, "epoch": 4.16, "percentage": 52.04, "elapsed_time": "4:31:58", "remaining_time": "4:10:38"}
103
+ {"current_steps": 1030, "total_steps": 1960, "loss": 0.9082, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002299857733524767, "epoch": 4.2, "percentage": 52.55, "elapsed_time": "4:34:36", "remaining_time": "4:07:56"}
104
+ {"current_steps": 1040, "total_steps": 1960, "loss": 1.04, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00022599424352307955, "epoch": 4.24, "percentage": 53.06, "elapsed_time": "4:36:46", "remaining_time": "4:04:50"}
105
+ {"current_steps": 1050, "total_steps": 1960, "loss": 0.9608, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00022200888097417305, "epoch": 4.29, "percentage": 53.57, "elapsed_time": "4:38:49", "remaining_time": "4:01:38"}
106
+ {"current_steps": 1060, "total_steps": 1960, "loss": 1.0405, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00021803070957887347, "epoch": 4.33, "percentage": 54.08, "elapsed_time": "4:41:14", "remaining_time": "3:58:47"}
107
+ {"current_steps": 1070, "total_steps": 1960, "loss": 0.9635, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002140607513628296, "epoch": 4.37, "percentage": 54.59, "elapsed_time": "4:45:08", "remaining_time": "3:57:10"}
108
+ {"current_steps": 1080, "total_steps": 1960, "loss": 0.8787, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00021010002624165526, "epoch": 4.41, "percentage": 55.1, "elapsed_time": "4:47:48", "remaining_time": "3:54:30"}
109
+ {"current_steps": 1090, "total_steps": 1960, "loss": 0.9367, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00020614955175890463, "epoch": 4.45, "percentage": 55.61, "elapsed_time": "4:51:01", "remaining_time": "3:52:17"}
110
+ {"current_steps": 1100, "total_steps": 1960, "loss": 1.0206, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00020221034282465699, "epoch": 4.49, "percentage": 56.12, "elapsed_time": "4:53:20", "remaining_time": "3:49:20"}
111
+ {"current_steps": 1110, "total_steps": 1960, "loss": 0.962, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019828341145477728, "epoch": 4.53, "percentage": 56.63, "elapsed_time": "4:55:41", "remaining_time": "3:46:25"}
112
+ {"current_steps": 1120, "total_steps": 1960, "loss": 0.8907, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019436976651092142, "epoch": 4.57, "percentage": 57.14, "elapsed_time": "4:58:58", "remaining_time": "3:44:13"}
113
+ {"current_steps": 1130, "total_steps": 1960, "loss": 0.932, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019047041344135045, "epoch": 4.61, "percentage": 57.65, "elapsed_time": "5:01:15", "remaining_time": "3:41:16"}
114
+ {"current_steps": 1140, "total_steps": 1960, "loss": 0.957, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001865863540226232, "epoch": 4.65, "percentage": 58.16, "elapsed_time": "5:04:07", "remaining_time": "3:38:45"}
115
+ {"current_steps": 1150, "total_steps": 1960, "loss": 0.9121, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001827185861022308, "epoch": 4.69, "percentage": 58.67, "elapsed_time": "5:06:22", "remaining_time": "3:35:47"}
116
+ {"current_steps": 1160, "total_steps": 1960, "loss": 0.9817, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001788681033422419, "epoch": 4.73, "percentage": 59.18, "elapsed_time": "5:09:48", "remaining_time": "3:33:39"}
117
+ {"current_steps": 1170, "total_steps": 1960, "loss": 0.9116, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001750358949640221, "epoch": 4.78, "percentage": 59.69, "elapsed_time": "5:12:21", "remaining_time": "3:30:54"}
118
+ {"current_steps": 1180, "total_steps": 1960, "loss": 0.8627, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00017122294549409484, "epoch": 4.82, "percentage": 60.2, "elapsed_time": "5:14:29", "remaining_time": "3:27:53"}
119
+ {"current_steps": 1190, "total_steps": 1960, "loss": 0.8922, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016743023451120832, "epoch": 4.86, "percentage": 60.71, "elapsed_time": "5:17:08", "remaining_time": "3:25:12"}
120
+ {"current_steps": 1200, "total_steps": 1960, "loss": 0.9926, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016365873639467314, "epoch": 4.9, "percentage": 61.22, "elapsed_time": "5:20:09", "remaining_time": "3:22:46"}
121
+ {"current_steps": 1210, "total_steps": 1960, "loss": 1.0046, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001599094200740367, "epoch": 4.94, "percentage": 61.73, "elapsed_time": "5:22:41", "remaining_time": "3:20:00"}
122
+ {"current_steps": 1220, "total_steps": 1960, "loss": 0.927, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001561832487801565, "epoch": 4.98, "percentage": 62.24, "elapsed_time": "5:25:27", "remaining_time": "3:17:24"}
123
+ {"current_steps": 1230, "total_steps": 1960, "loss": 0.8946, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001524811797977383, "epoch": 5.02, "percentage": 62.76, "elapsed_time": "5:28:46", "remaining_time": "3:15:07"}
124
+ {"current_steps": 1240, "total_steps": 1960, "loss": 0.9484, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00014880416421940155, "epoch": 5.06, "percentage": 63.27, "elapsed_time": "5:31:35", "remaining_time": "3:12:32"}
125
+ {"current_steps": 1250, "total_steps": 1960, "loss": 0.7806, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001451531467013358, "epoch": 5.1, "percentage": 63.78, "elapsed_time": "5:34:18", "remaining_time": "3:09:53"}
126
+ {"current_steps": 1260, "total_steps": 1960, "loss": 0.8487, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00014152906522061048, "epoch": 5.14, "percentage": 64.29, "elapsed_time": "5:36:58", "remaining_time": "3:07:12"}
127
+ {"current_steps": 1270, "total_steps": 1960, "loss": 0.7939, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00013793285083420076, "epoch": 5.18, "percentage": 64.8, "elapsed_time": "5:38:25", "remaining_time": "3:03:51"}
128
+ {"current_steps": 1280, "total_steps": 1960, "loss": 0.9054, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00013436542743979125, "epoch": 5.22, "percentage": 65.31, "elapsed_time": "5:41:18", "remaining_time": "3:01:19"}
129
+ {"current_steps": 1290, "total_steps": 1960, "loss": 0.8808, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001308277115384187, "epoch": 5.27, "percentage": 65.82, "elapsed_time": "5:43:59", "remaining_time": "2:58:39"}
130
+ {"current_steps": 1300, "total_steps": 1960, "loss": 0.8748, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012732061199901561, "epoch": 5.31, "percentage": 66.33, "elapsed_time": "5:47:22", "remaining_time": "2:56:21"}
131
+ {"current_steps": 1310, "total_steps": 1960, "loss": 0.9054, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012384502982491357, "epoch": 5.35, "percentage": 66.84, "elapsed_time": "5:49:21", "remaining_time": "2:53:20"}
132
+ {"current_steps": 1320, "total_steps": 1960, "loss": 0.8023, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012040185792236874, "epoch": 5.39, "percentage": 67.35, "elapsed_time": "5:51:27", "remaining_time": "2:50:24"}
133
+ {"current_steps": 1330, "total_steps": 1960, "loss": 0.9195, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00011699198087116588, "epoch": 5.43, "percentage": 67.86, "elapsed_time": "5:53:43", "remaining_time": "2:47:33"}
134
+ {"current_steps": 1340, "total_steps": 1960, "loss": 0.8406, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00011361627469736286, "epoch": 5.47, "percentage": 68.37, "elapsed_time": "5:55:55", "remaining_time": "2:44:40"}
135
+ {"current_steps": 1350, "total_steps": 1960, "loss": 0.8873, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00011027560664823208, "epoch": 5.51, "percentage": 68.88, "elapsed_time": "5:58:36", "remaining_time": "2:42:02"}
136
+ {"current_steps": 1360, "total_steps": 1960, "loss": 0.8811, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00010697083496945764, "epoch": 5.55, "percentage": 69.39, "elapsed_time": "6:01:22", "remaining_time": "2:39:25"}
137
+ {"current_steps": 1370, "total_steps": 1960, "loss": 0.9164, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00010370280868464405, "epoch": 5.59, "percentage": 69.9, "elapsed_time": "6:04:56", "remaining_time": "2:37:09"}
138
+ {"current_steps": 1380, "total_steps": 1960, "loss": 0.9604, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000100472367377196, "epoch": 5.63, "percentage": 70.41, "elapsed_time": "6:07:29", "remaining_time": "2:34:27"}
139
+ {"current_steps": 1390, "total_steps": 1960, "loss": 0.9027, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.728034097462144e-05, "epoch": 5.67, "percentage": 70.92, "elapsed_time": "6:10:24", "remaining_time": "2:31:53"}
140
+ {"current_steps": 1400, "total_steps": 1960, "loss": 0.857, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.412754953531663e-05, "epoch": 5.71, "percentage": 71.43, "elapsed_time": "6:14:00", "remaining_time": "2:29:36"}
141
+ {"current_steps": 1410, "total_steps": 1960, "loss": 0.8198, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.101480303788623e-05, "epoch": 5.76, "percentage": 71.94, "elapsed_time": "6:16:16", "remaining_time": "2:26:46"}
142
+ {"current_steps": 1420, "total_steps": 1960, "loss": 0.866, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.794290117305295e-05, "epoch": 5.8, "percentage": 72.45, "elapsed_time": "6:19:11", "remaining_time": "2:24:12"}
143
+ {"current_steps": 1430, "total_steps": 1960, "loss": 0.8422, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.491263313821021e-05, "epoch": 5.84, "percentage": 72.96, "elapsed_time": "6:21:52", "remaining_time": "2:21:32"}
144
+ {"current_steps": 1440, "total_steps": 1960, "loss": 0.8921, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.192477743467078e-05, "epoch": 5.88, "percentage": 73.47, "elapsed_time": "6:24:22", "remaining_time": "2:18:48"}
145
+ {"current_steps": 1450, "total_steps": 1960, "loss": 0.8429, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.898010166766348e-05, "epoch": 5.92, "percentage": 73.98, "elapsed_time": "6:27:17", "remaining_time": "2:16:13"}
146
+ {"current_steps": 1460, "total_steps": 1960, "loss": 0.8728, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.60793623491284e-05, "epoch": 5.96, "percentage": 74.49, "elapsed_time": "6:30:32", "remaining_time": "2:13:44"}
147
+ {"current_steps": 1470, "total_steps": 1960, "loss": 0.8335, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.322330470336314e-05, "epoch": 6.0, "percentage": 75.0, "elapsed_time": "6:33:06", "remaining_time": "2:11:02"}
148
+ {"current_steps": 1480, "total_steps": 1960, "loss": 0.8213, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.041266247556813e-05, "epoch": 6.04, "percentage": 75.51, "elapsed_time": "6:36:12", "remaining_time": "2:08:30"}
149
+ {"current_steps": 1490, "total_steps": 1960, "loss": 0.8509, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.764815774334149e-05, "epoch": 6.08, "percentage": 76.02, "elapsed_time": "6:39:04", "remaining_time": "2:05:52"}
150
+ {"current_steps": 1500, "total_steps": 1960, "loss": 0.7348, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.493050073117116e-05, "epoch": 6.12, "percentage": 76.53, "elapsed_time": "6:41:36", "remaining_time": "2:03:09"}
151
+ {"current_steps": 1510, "total_steps": 1960, "loss": 0.8422, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.226038962797217e-05, "epoch": 6.16, "percentage": 77.04, "elapsed_time": "6:44:44", "remaining_time": "2:00:36"}
152
+ {"current_steps": 1520, "total_steps": 1960, "loss": 0.896, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.96385104077164e-05, "epoch": 6.2, "percentage": 77.55, "elapsed_time": "6:47:45", "remaining_time": "1:58:02"}
153
+ {"current_steps": 1530, "total_steps": 1960, "loss": 0.7791, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.706553665319955e-05, "epoch": 6.24, "percentage": 78.06, "elapsed_time": "6:50:05", "remaining_time": "1:55:15"}
154
+ {"current_steps": 1540, "total_steps": 1960, "loss": 0.8045, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.454212938299255e-05, "epoch": 6.29, "percentage": 78.57, "elapsed_time": "6:52:27", "remaining_time": "1:52:29"}
155
+ {"current_steps": 1550, "total_steps": 1960, "loss": 0.8531, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.206893688162009e-05, "epoch": 6.33, "percentage": 79.08, "elapsed_time": "6:55:02", "remaining_time": "1:49:47"}
156
+ {"current_steps": 1560, "total_steps": 1960, "loss": 0.8444, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9646594533010875e-05, "epoch": 6.37, "percentage": 79.59, "elapsed_time": "6:58:12", "remaining_time": "1:47:13"}
157
+ {"current_steps": 1570, "total_steps": 1960, "loss": 0.7966, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7275724657262294e-05, "epoch": 6.41, "percentage": 80.1, "elapsed_time": "7:00:26", "remaining_time": "1:44:26"}
158
+ {"current_steps": 1580, "total_steps": 1960, "loss": 0.7895, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.495693635076101e-05, "epoch": 6.45, "percentage": 80.61, "elapsed_time": "7:02:39", "remaining_time": "1:41:39"}
159
+ {"current_steps": 1590, "total_steps": 1960, "loss": 0.7409, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.269082532970131e-05, "epoch": 6.49, "percentage": 81.12, "elapsed_time": "7:05:02", "remaining_time": "1:38:54"}
160
+ {"current_steps": 1600, "total_steps": 1960, "loss": 0.875, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.047797377703985e-05, "epoch": 6.53, "percentage": 81.63, "elapsed_time": "7:07:25", "remaining_time": "1:36:10"}
161
+ {"current_steps": 1610, "total_steps": 1960, "loss": 0.8869, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.831895019292897e-05, "epoch": 6.57, "percentage": 82.14, "elapsed_time": "7:10:53", "remaining_time": "1:33:40"}
162
+ {"current_steps": 1620, "total_steps": 1960, "loss": 0.8159, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.621430924866348e-05, "epoch": 6.61, "percentage": 82.65, "elapsed_time": "7:13:33", "remaining_time": "1:30:59"}
163
+ {"current_steps": 1630, "total_steps": 1960, "loss": 0.7707, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.416459164418123e-05, "epoch": 6.65, "percentage": 83.16, "elapsed_time": "7:15:48", "remaining_time": "1:28:13"}
164
+ {"current_steps": 1640, "total_steps": 1960, "loss": 0.8724, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.217032396915265e-05, "epoch": 6.69, "percentage": 83.67, "elapsed_time": "7:18:55", "remaining_time": "1:25:38"}
165
+ {"current_steps": 1650, "total_steps": 1960, "loss": 0.7733, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0232018567695695e-05, "epoch": 6.73, "percentage": 84.18, "elapsed_time": "7:21:13", "remaining_time": "1:22:53"}
166
+ {"current_steps": 1660, "total_steps": 1960, "loss": 0.8311, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8350173406749973e-05, "epoch": 6.78, "percentage": 84.69, "elapsed_time": "7:24:11", "remaining_time": "1:20:16"}
167
+ {"current_steps": 1670, "total_steps": 1960, "loss": 0.8356, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.652527194814511e-05, "epoch": 6.82, "percentage": 85.2, "elapsed_time": "7:26:58", "remaining_time": "1:17:37"}
168
+ {"current_steps": 1680, "total_steps": 1960, "loss": 0.8144, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4757783024395242e-05, "epoch": 6.86, "percentage": 85.71, "elapsed_time": "7:29:56", "remaining_time": "1:14:59"}
169
+ {"current_steps": 1690, "total_steps": 1960, "loss": 0.7767, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3048160718251997e-05, "epoch": 6.9, "percentage": 86.22, "elapsed_time": "7:32:20", "remaining_time": "1:12:16"}
170
+ {"current_steps": 1700, "total_steps": 1960, "loss": 0.8402, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1396844246046905e-05, "epoch": 6.94, "percentage": 86.73, "elapsed_time": "7:35:35", "remaining_time": "1:09:40"}
171
+ {"current_steps": 1710, "total_steps": 1960, "loss": 0.8576, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.980425784485293e-05, "epoch": 6.98, "percentage": 87.24, "elapsed_time": "7:37:59", "remaining_time": "1:06:57"}
172
+ {"current_steps": 1720, "total_steps": 1960, "loss": 0.7797, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.827081066349459e-05, "epoch": 7.02, "percentage": 87.76, "elapsed_time": "7:40:34", "remaining_time": "1:04:15"}
173
+ {"current_steps": 1730, "total_steps": 1960, "loss": 0.8409, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6796896657433808e-05, "epoch": 7.06, "percentage": 88.27, "elapsed_time": "7:42:27", "remaining_time": "1:01:28"}
174
+ {"current_steps": 1740, "total_steps": 1960, "loss": 0.7642, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.538289448755989e-05, "epoch": 7.1, "percentage": 88.78, "elapsed_time": "7:45:04", "remaining_time": "0:58:48"}
175
+ {"current_steps": 1750, "total_steps": 1960, "loss": 0.8464, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4029167422908107e-05, "epoch": 7.14, "percentage": 89.29, "elapsed_time": "7:47:31", "remaining_time": "0:56:06"}
176
+ {"current_steps": 1760, "total_steps": 1960, "loss": 0.7975, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.273606324733284e-05, "epoch": 7.18, "percentage": 89.8, "elapsed_time": "7:50:53", "remaining_time": "0:53:30"}
177
+ {"current_steps": 1770, "total_steps": 1960, "loss": 0.7577, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1503914170159058e-05, "epoch": 7.22, "percentage": 90.31, "elapsed_time": "7:53:52", "remaining_time": "0:50:52"}
178
+ {"current_steps": 1780, "total_steps": 1960, "loss": 0.8085, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0333036740834856e-05, "epoch": 7.27, "percentage": 90.82, "elapsed_time": "7:57:00", "remaining_time": "0:48:14"}
179
+ {"current_steps": 1790, "total_steps": 1960, "loss": 0.7511, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.223731767607434e-06, "epoch": 7.31, "percentage": 91.33, "elapsed_time": "7:59:11", "remaining_time": "0:45:30"}
180
+ {"current_steps": 1800, "total_steps": 1960, "loss": 0.845, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.176284240242638e-06, "epoch": 7.35, "percentage": 91.84, "elapsed_time": "8:02:10", "remaining_time": "0:42:51"}
181
+ {"current_steps": 1810, "total_steps": 1960, "loss": 0.865, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.190963256809069e-06, "epoch": 7.39, "percentage": 92.35, "elapsed_time": "8:04:43", "remaining_time": "0:40:10"}
182
+ {"current_steps": 1820, "total_steps": 1960, "loss": 0.8486, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.268021954544096e-06, "epoch": 7.43, "percentage": 92.86, "elapsed_time": "8:07:08", "remaining_time": "0:37:28"}
183
+ {"current_steps": 1830, "total_steps": 1960, "loss": 0.7099, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.407697444821169e-06, "epoch": 7.47, "percentage": 93.37, "elapsed_time": "8:09:47", "remaining_time": "0:34:47"}
184
+ {"current_steps": 1840, "total_steps": 1960, "loss": 0.8223, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.61021075223364e-06, "epoch": 7.51, "percentage": 93.88, "elapsed_time": "8:12:23", "remaining_time": "0:32:06"}
185
+ {"current_steps": 1850, "total_steps": 1960, "loss": 0.8753, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.8757667578118995e-06, "epoch": 7.55, "percentage": 94.39, "elapsed_time": "8:15:25", "remaining_time": "0:29:27"}
186
+ {"current_steps": 1860, "total_steps": 1960, "loss": 0.8835, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.2045541463874563e-06, "epoch": 7.59, "percentage": 94.9, "elapsed_time": "8:18:18", "remaining_time": "0:26:47"}
187
+ {"current_steps": 1870, "total_steps": 1960, "loss": 0.7877, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5967453581185186e-06, "epoch": 7.63, "percentage": 95.41, "elapsed_time": "8:20:56", "remaining_time": "0:24:06"}
188
+ {"current_steps": 1880, "total_steps": 1960, "loss": 0.8828, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.052496544188487e-06, "epoch": 7.67, "percentage": 95.92, "elapsed_time": "8:23:25", "remaining_time": "0:21:25"}
189
+ {"current_steps": 1890, "total_steps": 1960, "loss": 0.7658, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.571947526689349e-06, "epoch": 7.71, "percentage": 96.43, "elapsed_time": "8:26:19", "remaining_time": "0:18:45"}
190
+ {"current_steps": 1900, "total_steps": 1960, "loss": 0.8952, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1552217627004424e-06, "epoch": 7.76, "percentage": 96.94, "elapsed_time": "8:29:21", "remaining_time": "0:16:05"}
191
+ {"current_steps": 1910, "total_steps": 1960, "loss": 0.8118, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.024263125710751e-07, "epoch": 7.8, "percentage": 97.45, "elapsed_time": "8:32:23", "remaining_time": "0:13:24"}
192
+ {"current_steps": 1920, "total_steps": 1960, "loss": 0.8503, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.136518124159162e-07, "epoch": 7.84, "percentage": 97.96, "elapsed_time": "8:34:53", "remaining_time": "0:10:43"}
193
+ {"current_steps": 1930, "total_steps": 1960, "loss": 0.8248, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8897245082978865e-07, "epoch": 7.88, "percentage": 98.47, "elapsed_time": "8:37:02", "remaining_time": "0:08:02"}
194
+ {"current_steps": 1940, "total_steps": 1960, "loss": 0.8515, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.284459498280266e-07, "epoch": 7.92, "percentage": 98.98, "elapsed_time": "8:39:03", "remaining_time": "0:05:21"}
195
+ {"current_steps": 1950, "total_steps": 1960, "loss": 0.8274, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.2113550017198734e-08, "epoch": 7.96, "percentage": 99.49, "elapsed_time": "8:41:44", "remaining_time": "0:02:40"}
196
+ {"current_steps": 1960, "total_steps": 1960, "loss": 0.7359, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 8.0, "percentage": 100.0, "elapsed_time": "8:44:07", "remaining_time": "0:00:00"}
197
+ {"current_steps": 1960, "total_steps": 1960, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 8.0, "percentage": 100.0, "elapsed_time": "8:44:07", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,1206 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1960,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04,
13
+ "learning_rate": 0.0004999678864499828,
14
+ "loss": 1.9845,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.08,
19
+ "learning_rate": 0.000499871554050172,
20
+ "loss": 1.8444,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.12,
25
+ "learning_rate": 0.0004997110275491702,
26
+ "loss": 1.721,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.16,
31
+ "learning_rate": 0.0004994863481875841,
32
+ "loss": 1.6755,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.2,
37
+ "learning_rate": 0.0004991975736874289,
38
+ "loss": 1.7248,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.24,
43
+ "learning_rate": 0.0004988447782372996,
44
+ "loss": 1.6803,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.29,
49
+ "learning_rate": 0.0004984280524733107,
50
+ "loss": 1.7063,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.33,
55
+ "learning_rate": 0.0004979475034558115,
56
+ "loss": 1.6724,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.37,
61
+ "learning_rate": 0.0004974032546418815,
62
+ "loss": 1.6933,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.41,
67
+ "learning_rate": 0.0004967954458536126,
68
+ "loss": 1.6243,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.45,
73
+ "learning_rate": 0.0004961242332421882,
74
+ "loss": 1.639,
75
+ "step": 110
76
+ },
77
+ {
78
+ "epoch": 0.49,
79
+ "learning_rate": 0.0004953897892477664,
80
+ "loss": 1.6545,
81
+ "step": 120
82
+ },
83
+ {
84
+ "epoch": 0.53,
85
+ "learning_rate": 0.0004945923025551788,
86
+ "loss": 1.6017,
87
+ "step": 130
88
+ },
89
+ {
90
+ "epoch": 0.57,
91
+ "learning_rate": 0.0004937319780454559,
92
+ "loss": 1.6522,
93
+ "step": 140
94
+ },
95
+ {
96
+ "epoch": 0.61,
97
+ "learning_rate": 0.000492809036743191,
98
+ "loss": 1.5948,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 0.65,
103
+ "learning_rate": 0.0004918237157597574,
104
+ "loss": 1.5385,
105
+ "step": 160
106
+ },
107
+ {
108
+ "epoch": 0.69,
109
+ "learning_rate": 0.0004907762682323926,
110
+ "loss": 1.6132,
111
+ "step": 170
112
+ },
113
+ {
114
+ "epoch": 0.73,
115
+ "learning_rate": 0.0004896669632591652,
116
+ "loss": 1.5396,
117
+ "step": 180
118
+ },
119
+ {
120
+ "epoch": 0.78,
121
+ "learning_rate": 0.000488496085829841,
122
+ "loss": 1.5023,
123
+ "step": 190
124
+ },
125
+ {
126
+ "epoch": 0.82,
127
+ "learning_rate": 0.0004872639367526672,
128
+ "loss": 1.4937,
129
+ "step": 200
130
+ },
131
+ {
132
+ "epoch": 0.86,
133
+ "learning_rate": 0.0004859708325770919,
134
+ "loss": 1.4824,
135
+ "step": 210
136
+ },
137
+ {
138
+ "epoch": 0.9,
139
+ "learning_rate": 0.0004846171055124401,
140
+ "loss": 1.5506,
141
+ "step": 220
142
+ },
143
+ {
144
+ "epoch": 0.94,
145
+ "learning_rate": 0.00048320310334256625,
146
+ "loss": 1.5709,
147
+ "step": 230
148
+ },
149
+ {
150
+ "epoch": 0.98,
151
+ "learning_rate": 0.0004817291893365054,
152
+ "loss": 1.5531,
153
+ "step": 240
154
+ },
155
+ {
156
+ "epoch": 1.02,
157
+ "learning_rate": 0.00048019574215514706,
158
+ "loss": 1.4546,
159
+ "step": 250
160
+ },
161
+ {
162
+ "epoch": 1.06,
163
+ "learning_rate": 0.0004786031557539531,
164
+ "loss": 1.4281,
165
+ "step": 260
166
+ },
167
+ {
168
+ "epoch": 1.1,
169
+ "learning_rate": 0.00047695183928174803,
170
+ "loss": 1.4339,
171
+ "step": 270
172
+ },
173
+ {
174
+ "epoch": 1.14,
175
+ "learning_rate": 0.00047524221697560476,
176
+ "loss": 1.3993,
177
+ "step": 280
178
+ },
179
+ {
180
+ "epoch": 1.18,
181
+ "learning_rate": 0.0004734747280518549,
182
+ "loss": 1.3786,
183
+ "step": 290
184
+ },
185
+ {
186
+ "epoch": 1.22,
187
+ "learning_rate": 0.00047164982659325005,
188
+ "loss": 1.458,
189
+ "step": 300
190
+ },
191
+ {
192
+ "epoch": 1.27,
193
+ "learning_rate": 0.0004697679814323043,
194
+ "loss": 1.3692,
195
+ "step": 310
196
+ },
197
+ {
198
+ "epoch": 1.31,
199
+ "learning_rate": 0.00046782967603084736,
200
+ "loss": 1.491,
201
+ "step": 320
202
+ },
203
+ {
204
+ "epoch": 1.35,
205
+ "learning_rate": 0.00046583540835581883,
206
+ "loss": 1.3637,
207
+ "step": 330
208
+ },
209
+ {
210
+ "epoch": 1.39,
211
+ "learning_rate": 0.0004637856907513366,
212
+ "loss": 1.4276,
213
+ "step": 340
214
+ },
215
+ {
216
+ "epoch": 1.43,
217
+ "learning_rate": 0.00046168104980707104,
218
+ "loss": 1.3943,
219
+ "step": 350
220
+ },
221
+ {
222
+ "epoch": 1.47,
223
+ "learning_rate": 0.00045952202622296013,
224
+ "loss": 1.4274,
225
+ "step": 360
226
+ },
227
+ {
228
+ "epoch": 1.51,
229
+ "learning_rate": 0.00045730917467029877,
230
+ "loss": 1.4829,
231
+ "step": 370
232
+ },
233
+ {
234
+ "epoch": 1.55,
235
+ "learning_rate": 0.00045504306364923896,
236
+ "loss": 1.3585,
237
+ "step": 380
238
+ },
239
+ {
240
+ "epoch": 1.59,
241
+ "learning_rate": 0.00045272427534273776,
242
+ "loss": 1.4194,
243
+ "step": 390
244
+ },
245
+ {
246
+ "epoch": 1.63,
247
+ "learning_rate": 0.00045035340546698916,
248
+ "loss": 1.3924,
249
+ "step": 400
250
+ },
251
+ {
252
+ "epoch": 1.67,
253
+ "learning_rate": 0.0004479310631183799,
254
+ "loss": 1.4117,
255
+ "step": 410
256
+ },
257
+ {
258
+ "epoch": 1.71,
259
+ "learning_rate": 0.0004454578706170075,
260
+ "loss": 1.3849,
261
+ "step": 420
262
+ },
263
+ {
264
+ "epoch": 1.76,
265
+ "learning_rate": 0.0004429344633468004,
266
+ "loss": 1.3857,
267
+ "step": 430
268
+ },
269
+ {
270
+ "epoch": 1.8,
271
+ "learning_rate": 0.0004403614895922836,
272
+ "loss": 1.4772,
273
+ "step": 440
274
+ },
275
+ {
276
+ "epoch": 1.84,
277
+ "learning_rate": 0.0004377396103720278,
278
+ "loss": 1.4021,
279
+ "step": 450
280
+ },
281
+ {
282
+ "epoch": 1.88,
283
+ "learning_rate": 0.00043506949926882887,
284
+ "loss": 1.3589,
285
+ "step": 460
286
+ },
287
+ {
288
+ "epoch": 1.92,
289
+ "learning_rate": 0.0004323518422566586,
290
+ "loss": 1.45,
291
+ "step": 470
292
+ },
293
+ {
294
+ "epoch": 1.96,
295
+ "learning_rate": 0.0004295873375244319,
296
+ "loss": 1.2784,
297
+ "step": 480
298
+ },
299
+ {
300
+ "epoch": 2.0,
301
+ "learning_rate": 0.00042677669529663686,
302
+ "loss": 1.4127,
303
+ "step": 490
304
+ },
305
+ {
306
+ "epoch": 2.04,
307
+ "learning_rate": 0.0004239206376508716,
308
+ "loss": 1.2777,
309
+ "step": 500
310
+ },
311
+ {
312
+ "epoch": 2.08,
313
+ "learning_rate": 0.00042101989833233654,
314
+ "loss": 1.1873,
315
+ "step": 510
316
+ },
317
+ {
318
+ "epoch": 2.12,
319
+ "learning_rate": 0.0004180752225653292,
320
+ "loss": 1.2746,
321
+ "step": 520
322
+ },
323
+ {
324
+ "epoch": 2.16,
325
+ "learning_rate": 0.0004150873668617898,
326
+ "loss": 1.308,
327
+ "step": 530
328
+ },
329
+ {
330
+ "epoch": 2.2,
331
+ "learning_rate": 0.00041205709882694713,
332
+ "loss": 1.2431,
333
+ "step": 540
334
+ },
335
+ {
336
+ "epoch": 2.24,
337
+ "learning_rate": 0.0004089851969621138,
338
+ "loss": 1.3411,
339
+ "step": 550
340
+ },
341
+ {
342
+ "epoch": 2.29,
343
+ "learning_rate": 0.0004058724504646834,
344
+ "loss": 1.2369,
345
+ "step": 560
346
+ },
347
+ {
348
+ "epoch": 2.33,
349
+ "learning_rate": 0.0004027196590253786,
350
+ "loss": 1.303,
351
+ "step": 570
352
+ },
353
+ {
354
+ "epoch": 2.37,
355
+ "learning_rate": 0.000399527632622804,
356
+ "loss": 1.2011,
357
+ "step": 580
358
+ },
359
+ {
360
+ "epoch": 2.41,
361
+ "learning_rate": 0.0003962971913153559,
362
+ "loss": 1.2239,
363
+ "step": 590
364
+ },
365
+ {
366
+ "epoch": 2.45,
367
+ "learning_rate": 0.00039302916503054243,
368
+ "loss": 1.2133,
369
+ "step": 600
370
+ },
371
+ {
372
+ "epoch": 2.49,
373
+ "learning_rate": 0.0003897243933517679,
374
+ "loss": 1.2108,
375
+ "step": 610
376
+ },
377
+ {
378
+ "epoch": 2.53,
379
+ "learning_rate": 0.00038638372530263714,
380
+ "loss": 1.3095,
381
+ "step": 620
382
+ },
383
+ {
384
+ "epoch": 2.57,
385
+ "learning_rate": 0.00038300801912883415,
386
+ "loss": 1.2392,
387
+ "step": 630
388
+ },
389
+ {
390
+ "epoch": 2.61,
391
+ "learning_rate": 0.0003795981420776313,
392
+ "loss": 1.1789,
393
+ "step": 640
394
+ },
395
+ {
396
+ "epoch": 2.65,
397
+ "learning_rate": 0.0003761549701750865,
398
+ "loss": 1.2285,
399
+ "step": 650
400
+ },
401
+ {
402
+ "epoch": 2.69,
403
+ "learning_rate": 0.0003726793880009845,
404
+ "loss": 1.2101,
405
+ "step": 660
406
+ },
407
+ {
408
+ "epoch": 2.73,
409
+ "learning_rate": 0.00036917228846158136,
410
+ "loss": 1.1973,
411
+ "step": 670
412
+ },
413
+ {
414
+ "epoch": 2.78,
415
+ "learning_rate": 0.00036563457256020887,
416
+ "loss": 1.2238,
417
+ "step": 680
418
+ },
419
+ {
420
+ "epoch": 2.82,
421
+ "learning_rate": 0.0003620671491657992,
422
+ "loss": 1.2249,
423
+ "step": 690
424
+ },
425
+ {
426
+ "epoch": 2.86,
427
+ "learning_rate": 0.00035847093477938953,
428
+ "loss": 1.2314,
429
+ "step": 700
430
+ },
431
+ {
432
+ "epoch": 2.9,
433
+ "learning_rate": 0.00035484685329866423,
434
+ "loss": 1.2987,
435
+ "step": 710
436
+ },
437
+ {
438
+ "epoch": 2.94,
439
+ "learning_rate": 0.00035119583578059843,
440
+ "loss": 1.2416,
441
+ "step": 720
442
+ },
443
+ {
444
+ "epoch": 2.98,
445
+ "learning_rate": 0.00034751882020226174,
446
+ "loss": 1.175,
447
+ "step": 730
448
+ },
449
+ {
450
+ "epoch": 3.02,
451
+ "learning_rate": 0.0003438167512198436,
452
+ "loss": 1.2123,
453
+ "step": 740
454
+ },
455
+ {
456
+ "epoch": 3.06,
457
+ "learning_rate": 0.00034009057992596335,
458
+ "loss": 1.0257,
459
+ "step": 750
460
+ },
461
+ {
462
+ "epoch": 3.1,
463
+ "learning_rate": 0.0003363412636053269,
464
+ "loss": 1.118,
465
+ "step": 760
466
+ },
467
+ {
468
+ "epoch": 3.14,
469
+ "learning_rate": 0.00033256976548879183,
470
+ "loss": 1.1586,
471
+ "step": 770
472
+ },
473
+ {
474
+ "epoch": 3.18,
475
+ "learning_rate": 0.0003287770545059052,
476
+ "loss": 1.0559,
477
+ "step": 780
478
+ },
479
+ {
480
+ "epoch": 3.22,
481
+ "learning_rate": 0.0003249641050359779,
482
+ "loss": 1.0775,
483
+ "step": 790
484
+ },
485
+ {
486
+ "epoch": 3.27,
487
+ "learning_rate": 0.0003211318966577581,
488
+ "loss": 1.0905,
489
+ "step": 800
490
+ },
491
+ {
492
+ "epoch": 3.31,
493
+ "learning_rate": 0.00031728141389776923,
494
+ "loss": 1.088,
495
+ "step": 810
496
+ },
497
+ {
498
+ "epoch": 3.35,
499
+ "learning_rate": 0.0003134136459773768,
500
+ "loss": 1.0395,
501
+ "step": 820
502
+ },
503
+ {
504
+ "epoch": 3.39,
505
+ "learning_rate": 0.00030952958655864954,
506
+ "loss": 1.1064,
507
+ "step": 830
508
+ },
509
+ {
510
+ "epoch": 3.43,
511
+ "learning_rate": 0.0003056302334890786,
512
+ "loss": 1.0662,
513
+ "step": 840
514
+ },
515
+ {
516
+ "epoch": 3.47,
517
+ "learning_rate": 0.0003017165885452227,
518
+ "loss": 1.0627,
519
+ "step": 850
520
+ },
521
+ {
522
+ "epoch": 3.51,
523
+ "learning_rate": 0.00029778965717534313,
524
+ "loss": 0.9968,
525
+ "step": 860
526
+ },
527
+ {
528
+ "epoch": 3.55,
529
+ "learning_rate": 0.0002938504482410954,
530
+ "loss": 1.1237,
531
+ "step": 870
532
+ },
533
+ {
534
+ "epoch": 3.59,
535
+ "learning_rate": 0.00028989997375834483,
536
+ "loss": 1.0432,
537
+ "step": 880
538
+ },
539
+ {
540
+ "epoch": 3.63,
541
+ "learning_rate": 0.00028593924863717045,
542
+ "loss": 1.1197,
543
+ "step": 890
544
+ },
545
+ {
546
+ "epoch": 3.67,
547
+ "learning_rate": 0.0002819692904211265,
548
+ "loss": 1.0016,
549
+ "step": 900
550
+ },
551
+ {
552
+ "epoch": 3.71,
553
+ "learning_rate": 0.00027799111902582696,
554
+ "loss": 1.0956,
555
+ "step": 910
556
+ },
557
+ {
558
+ "epoch": 3.76,
559
+ "learning_rate": 0.00027400575647692046,
560
+ "loss": 1.0878,
561
+ "step": 920
562
+ },
563
+ {
564
+ "epoch": 3.8,
565
+ "learning_rate": 0.00027001422664752335,
566
+ "loss": 1.0838,
567
+ "step": 930
568
+ },
569
+ {
570
+ "epoch": 3.84,
571
+ "learning_rate": 0.00026601755499517824,
572
+ "loss": 1.0587,
573
+ "step": 940
574
+ },
575
+ {
576
+ "epoch": 3.88,
577
+ "learning_rate": 0.0002620167682984052,
578
+ "loss": 1.0857,
579
+ "step": 950
580
+ },
581
+ {
582
+ "epoch": 3.92,
583
+ "learning_rate": 0.00025801289439291385,
584
+ "loss": 1.0107,
585
+ "step": 960
586
+ },
587
+ {
588
+ "epoch": 3.96,
589
+ "learning_rate": 0.00025400696190754345,
590
+ "loss": 1.1491,
591
+ "step": 970
592
+ },
593
+ {
594
+ "epoch": 4.0,
595
+ "learning_rate": 0.00025,
596
+ "loss": 1.0726,
597
+ "step": 980
598
+ },
599
+ {
600
+ "epoch": 4.04,
601
+ "learning_rate": 0.0002459930380924566,
602
+ "loss": 0.9856,
603
+ "step": 990
604
+ },
605
+ {
606
+ "epoch": 4.08,
607
+ "learning_rate": 0.0002419871056070862,
608
+ "loss": 0.9726,
609
+ "step": 1000
610
+ },
611
+ {
612
+ "epoch": 4.12,
613
+ "learning_rate": 0.00023798323170159486,
614
+ "loss": 0.9675,
615
+ "step": 1010
616
+ },
617
+ {
618
+ "epoch": 4.16,
619
+ "learning_rate": 0.0002339824450048218,
620
+ "loss": 0.9831,
621
+ "step": 1020
622
+ },
623
+ {
624
+ "epoch": 4.2,
625
+ "learning_rate": 0.0002299857733524767,
626
+ "loss": 0.9082,
627
+ "step": 1030
628
+ },
629
+ {
630
+ "epoch": 4.24,
631
+ "learning_rate": 0.00022599424352307955,
632
+ "loss": 1.04,
633
+ "step": 1040
634
+ },
635
+ {
636
+ "epoch": 4.29,
637
+ "learning_rate": 0.00022200888097417305,
638
+ "loss": 0.9608,
639
+ "step": 1050
640
+ },
641
+ {
642
+ "epoch": 4.33,
643
+ "learning_rate": 0.00021803070957887347,
644
+ "loss": 1.0405,
645
+ "step": 1060
646
+ },
647
+ {
648
+ "epoch": 4.37,
649
+ "learning_rate": 0.0002140607513628296,
650
+ "loss": 0.9635,
651
+ "step": 1070
652
+ },
653
+ {
654
+ "epoch": 4.41,
655
+ "learning_rate": 0.00021010002624165526,
656
+ "loss": 0.8787,
657
+ "step": 1080
658
+ },
659
+ {
660
+ "epoch": 4.45,
661
+ "learning_rate": 0.00020614955175890463,
662
+ "loss": 0.9367,
663
+ "step": 1090
664
+ },
665
+ {
666
+ "epoch": 4.49,
667
+ "learning_rate": 0.00020221034282465699,
668
+ "loss": 1.0206,
669
+ "step": 1100
670
+ },
671
+ {
672
+ "epoch": 4.53,
673
+ "learning_rate": 0.00019828341145477728,
674
+ "loss": 0.962,
675
+ "step": 1110
676
+ },
677
+ {
678
+ "epoch": 4.57,
679
+ "learning_rate": 0.00019436976651092142,
680
+ "loss": 0.8907,
681
+ "step": 1120
682
+ },
683
+ {
684
+ "epoch": 4.61,
685
+ "learning_rate": 0.00019047041344135045,
686
+ "loss": 0.932,
687
+ "step": 1130
688
+ },
689
+ {
690
+ "epoch": 4.65,
691
+ "learning_rate": 0.0001865863540226232,
692
+ "loss": 0.957,
693
+ "step": 1140
694
+ },
695
+ {
696
+ "epoch": 4.69,
697
+ "learning_rate": 0.0001827185861022308,
698
+ "loss": 0.9121,
699
+ "step": 1150
700
+ },
701
+ {
702
+ "epoch": 4.73,
703
+ "learning_rate": 0.0001788681033422419,
704
+ "loss": 0.9817,
705
+ "step": 1160
706
+ },
707
+ {
708
+ "epoch": 4.78,
709
+ "learning_rate": 0.0001750358949640221,
710
+ "loss": 0.9116,
711
+ "step": 1170
712
+ },
713
+ {
714
+ "epoch": 4.82,
715
+ "learning_rate": 0.00017122294549409484,
716
+ "loss": 0.8627,
717
+ "step": 1180
718
+ },
719
+ {
720
+ "epoch": 4.86,
721
+ "learning_rate": 0.00016743023451120832,
722
+ "loss": 0.8922,
723
+ "step": 1190
724
+ },
725
+ {
726
+ "epoch": 4.9,
727
+ "learning_rate": 0.00016365873639467314,
728
+ "loss": 0.9926,
729
+ "step": 1200
730
+ },
731
+ {
732
+ "epoch": 4.94,
733
+ "learning_rate": 0.0001599094200740367,
734
+ "loss": 1.0046,
735
+ "step": 1210
736
+ },
737
+ {
738
+ "epoch": 4.98,
739
+ "learning_rate": 0.0001561832487801565,
740
+ "loss": 0.927,
741
+ "step": 1220
742
+ },
743
+ {
744
+ "epoch": 5.02,
745
+ "learning_rate": 0.0001524811797977383,
746
+ "loss": 0.8946,
747
+ "step": 1230
748
+ },
749
+ {
750
+ "epoch": 5.06,
751
+ "learning_rate": 0.00014880416421940155,
752
+ "loss": 0.9484,
753
+ "step": 1240
754
+ },
755
+ {
756
+ "epoch": 5.1,
757
+ "learning_rate": 0.0001451531467013358,
758
+ "loss": 0.7806,
759
+ "step": 1250
760
+ },
761
+ {
762
+ "epoch": 5.14,
763
+ "learning_rate": 0.00014152906522061048,
764
+ "loss": 0.8487,
765
+ "step": 1260
766
+ },
767
+ {
768
+ "epoch": 5.18,
769
+ "learning_rate": 0.00013793285083420076,
770
+ "loss": 0.7939,
771
+ "step": 1270
772
+ },
773
+ {
774
+ "epoch": 5.22,
775
+ "learning_rate": 0.00013436542743979125,
776
+ "loss": 0.9054,
777
+ "step": 1280
778
+ },
779
+ {
780
+ "epoch": 5.27,
781
+ "learning_rate": 0.0001308277115384187,
782
+ "loss": 0.8808,
783
+ "step": 1290
784
+ },
785
+ {
786
+ "epoch": 5.31,
787
+ "learning_rate": 0.00012732061199901561,
788
+ "loss": 0.8748,
789
+ "step": 1300
790
+ },
791
+ {
792
+ "epoch": 5.35,
793
+ "learning_rate": 0.00012384502982491357,
794
+ "loss": 0.9054,
795
+ "step": 1310
796
+ },
797
+ {
798
+ "epoch": 5.39,
799
+ "learning_rate": 0.00012040185792236874,
800
+ "loss": 0.8023,
801
+ "step": 1320
802
+ },
803
+ {
804
+ "epoch": 5.43,
805
+ "learning_rate": 0.00011699198087116588,
806
+ "loss": 0.9195,
807
+ "step": 1330
808
+ },
809
+ {
810
+ "epoch": 5.47,
811
+ "learning_rate": 0.00011361627469736286,
812
+ "loss": 0.8406,
813
+ "step": 1340
814
+ },
815
+ {
816
+ "epoch": 5.51,
817
+ "learning_rate": 0.00011027560664823208,
818
+ "loss": 0.8873,
819
+ "step": 1350
820
+ },
821
+ {
822
+ "epoch": 5.55,
823
+ "learning_rate": 0.00010697083496945764,
824
+ "loss": 0.8811,
825
+ "step": 1360
826
+ },
827
+ {
828
+ "epoch": 5.59,
829
+ "learning_rate": 0.00010370280868464405,
830
+ "loss": 0.9164,
831
+ "step": 1370
832
+ },
833
+ {
834
+ "epoch": 5.63,
835
+ "learning_rate": 0.000100472367377196,
836
+ "loss": 0.9604,
837
+ "step": 1380
838
+ },
839
+ {
840
+ "epoch": 5.67,
841
+ "learning_rate": 9.728034097462144e-05,
842
+ "loss": 0.9027,
843
+ "step": 1390
844
+ },
845
+ {
846
+ "epoch": 5.71,
847
+ "learning_rate": 9.412754953531663e-05,
848
+ "loss": 0.857,
849
+ "step": 1400
850
+ },
851
+ {
852
+ "epoch": 5.76,
853
+ "learning_rate": 9.101480303788623e-05,
854
+ "loss": 0.8198,
855
+ "step": 1410
856
+ },
857
+ {
858
+ "epoch": 5.8,
859
+ "learning_rate": 8.794290117305295e-05,
860
+ "loss": 0.866,
861
+ "step": 1420
862
+ },
863
+ {
864
+ "epoch": 5.84,
865
+ "learning_rate": 8.491263313821021e-05,
866
+ "loss": 0.8422,
867
+ "step": 1430
868
+ },
869
+ {
870
+ "epoch": 5.88,
871
+ "learning_rate": 8.192477743467078e-05,
872
+ "loss": 0.8921,
873
+ "step": 1440
874
+ },
875
+ {
876
+ "epoch": 5.92,
877
+ "learning_rate": 7.898010166766348e-05,
878
+ "loss": 0.8429,
879
+ "step": 1450
880
+ },
881
+ {
882
+ "epoch": 5.96,
883
+ "learning_rate": 7.60793623491284e-05,
884
+ "loss": 0.8728,
885
+ "step": 1460
886
+ },
887
+ {
888
+ "epoch": 6.0,
889
+ "learning_rate": 7.322330470336314e-05,
890
+ "loss": 0.8335,
891
+ "step": 1470
892
+ },
893
+ {
894
+ "epoch": 6.04,
895
+ "learning_rate": 7.041266247556813e-05,
896
+ "loss": 0.8213,
897
+ "step": 1480
898
+ },
899
+ {
900
+ "epoch": 6.08,
901
+ "learning_rate": 6.764815774334149e-05,
902
+ "loss": 0.8509,
903
+ "step": 1490
904
+ },
905
+ {
906
+ "epoch": 6.12,
907
+ "learning_rate": 6.493050073117116e-05,
908
+ "loss": 0.7348,
909
+ "step": 1500
910
+ },
911
+ {
912
+ "epoch": 6.16,
913
+ "learning_rate": 6.226038962797217e-05,
914
+ "loss": 0.8422,
915
+ "step": 1510
916
+ },
917
+ {
918
+ "epoch": 6.2,
919
+ "learning_rate": 5.96385104077164e-05,
920
+ "loss": 0.896,
921
+ "step": 1520
922
+ },
923
+ {
924
+ "epoch": 6.24,
925
+ "learning_rate": 5.706553665319955e-05,
926
+ "loss": 0.7791,
927
+ "step": 1530
928
+ },
929
+ {
930
+ "epoch": 6.29,
931
+ "learning_rate": 5.454212938299255e-05,
932
+ "loss": 0.8045,
933
+ "step": 1540
934
+ },
935
+ {
936
+ "epoch": 6.33,
937
+ "learning_rate": 5.206893688162009e-05,
938
+ "loss": 0.8531,
939
+ "step": 1550
940
+ },
941
+ {
942
+ "epoch": 6.37,
943
+ "learning_rate": 4.9646594533010875e-05,
944
+ "loss": 0.8444,
945
+ "step": 1560
946
+ },
947
+ {
948
+ "epoch": 6.41,
949
+ "learning_rate": 4.7275724657262294e-05,
950
+ "loss": 0.7966,
951
+ "step": 1570
952
+ },
953
+ {
954
+ "epoch": 6.45,
955
+ "learning_rate": 4.495693635076101e-05,
956
+ "loss": 0.7895,
957
+ "step": 1580
958
+ },
959
+ {
960
+ "epoch": 6.49,
961
+ "learning_rate": 4.269082532970131e-05,
962
+ "loss": 0.7409,
963
+ "step": 1590
964
+ },
965
+ {
966
+ "epoch": 6.53,
967
+ "learning_rate": 4.047797377703985e-05,
968
+ "loss": 0.875,
969
+ "step": 1600
970
+ },
971
+ {
972
+ "epoch": 6.57,
973
+ "learning_rate": 3.831895019292897e-05,
974
+ "loss": 0.8869,
975
+ "step": 1610
976
+ },
977
+ {
978
+ "epoch": 6.61,
979
+ "learning_rate": 3.621430924866348e-05,
980
+ "loss": 0.8159,
981
+ "step": 1620
982
+ },
983
+ {
984
+ "epoch": 6.65,
985
+ "learning_rate": 3.416459164418123e-05,
986
+ "loss": 0.7707,
987
+ "step": 1630
988
+ },
989
+ {
990
+ "epoch": 6.69,
991
+ "learning_rate": 3.217032396915265e-05,
992
+ "loss": 0.8724,
993
+ "step": 1640
994
+ },
995
+ {
996
+ "epoch": 6.73,
997
+ "learning_rate": 3.0232018567695695e-05,
998
+ "loss": 0.7733,
999
+ "step": 1650
1000
+ },
1001
+ {
1002
+ "epoch": 6.78,
1003
+ "learning_rate": 2.8350173406749973e-05,
1004
+ "loss": 0.8311,
1005
+ "step": 1660
1006
+ },
1007
+ {
1008
+ "epoch": 6.82,
1009
+ "learning_rate": 2.652527194814511e-05,
1010
+ "loss": 0.8356,
1011
+ "step": 1670
1012
+ },
1013
+ {
1014
+ "epoch": 6.86,
1015
+ "learning_rate": 2.4757783024395242e-05,
1016
+ "loss": 0.8144,
1017
+ "step": 1680
1018
+ },
1019
+ {
1020
+ "epoch": 6.9,
1021
+ "learning_rate": 2.3048160718251997e-05,
1022
+ "loss": 0.7767,
1023
+ "step": 1690
1024
+ },
1025
+ {
1026
+ "epoch": 6.94,
1027
+ "learning_rate": 2.1396844246046905e-05,
1028
+ "loss": 0.8402,
1029
+ "step": 1700
1030
+ },
1031
+ {
1032
+ "epoch": 6.98,
1033
+ "learning_rate": 1.980425784485293e-05,
1034
+ "loss": 0.8576,
1035
+ "step": 1710
1036
+ },
1037
+ {
1038
+ "epoch": 7.02,
1039
+ "learning_rate": 1.827081066349459e-05,
1040
+ "loss": 0.7797,
1041
+ "step": 1720
1042
+ },
1043
+ {
1044
+ "epoch": 7.06,
1045
+ "learning_rate": 1.6796896657433808e-05,
1046
+ "loss": 0.8409,
1047
+ "step": 1730
1048
+ },
1049
+ {
1050
+ "epoch": 7.1,
1051
+ "learning_rate": 1.538289448755989e-05,
1052
+ "loss": 0.7642,
1053
+ "step": 1740
1054
+ },
1055
+ {
1056
+ "epoch": 7.14,
1057
+ "learning_rate": 1.4029167422908107e-05,
1058
+ "loss": 0.8464,
1059
+ "step": 1750
1060
+ },
1061
+ {
1062
+ "epoch": 7.18,
1063
+ "learning_rate": 1.273606324733284e-05,
1064
+ "loss": 0.7975,
1065
+ "step": 1760
1066
+ },
1067
+ {
1068
+ "epoch": 7.22,
1069
+ "learning_rate": 1.1503914170159058e-05,
1070
+ "loss": 0.7577,
1071
+ "step": 1770
1072
+ },
1073
+ {
1074
+ "epoch": 7.27,
1075
+ "learning_rate": 1.0333036740834856e-05,
1076
+ "loss": 0.8085,
1077
+ "step": 1780
1078
+ },
1079
+ {
1080
+ "epoch": 7.31,
1081
+ "learning_rate": 9.223731767607434e-06,
1082
+ "loss": 0.7511,
1083
+ "step": 1790
1084
+ },
1085
+ {
1086
+ "epoch": 7.35,
1087
+ "learning_rate": 8.176284240242638e-06,
1088
+ "loss": 0.845,
1089
+ "step": 1800
1090
+ },
1091
+ {
1092
+ "epoch": 7.39,
1093
+ "learning_rate": 7.190963256809069e-06,
1094
+ "loss": 0.865,
1095
+ "step": 1810
1096
+ },
1097
+ {
1098
+ "epoch": 7.43,
1099
+ "learning_rate": 6.268021954544096e-06,
1100
+ "loss": 0.8486,
1101
+ "step": 1820
1102
+ },
1103
+ {
1104
+ "epoch": 7.47,
1105
+ "learning_rate": 5.407697444821169e-06,
1106
+ "loss": 0.7099,
1107
+ "step": 1830
1108
+ },
1109
+ {
1110
+ "epoch": 7.51,
1111
+ "learning_rate": 4.61021075223364e-06,
1112
+ "loss": 0.8223,
1113
+ "step": 1840
1114
+ },
1115
+ {
1116
+ "epoch": 7.55,
1117
+ "learning_rate": 3.8757667578118995e-06,
1118
+ "loss": 0.8753,
1119
+ "step": 1850
1120
+ },
1121
+ {
1122
+ "epoch": 7.59,
1123
+ "learning_rate": 3.2045541463874563e-06,
1124
+ "loss": 0.8835,
1125
+ "step": 1860
1126
+ },
1127
+ {
1128
+ "epoch": 7.63,
1129
+ "learning_rate": 2.5967453581185186e-06,
1130
+ "loss": 0.7877,
1131
+ "step": 1870
1132
+ },
1133
+ {
1134
+ "epoch": 7.67,
1135
+ "learning_rate": 2.052496544188487e-06,
1136
+ "loss": 0.8828,
1137
+ "step": 1880
1138
+ },
1139
+ {
1140
+ "epoch": 7.71,
1141
+ "learning_rate": 1.571947526689349e-06,
1142
+ "loss": 0.7658,
1143
+ "step": 1890
1144
+ },
1145
+ {
1146
+ "epoch": 7.76,
1147
+ "learning_rate": 1.1552217627004424e-06,
1148
+ "loss": 0.8952,
1149
+ "step": 1900
1150
+ },
1151
+ {
1152
+ "epoch": 7.8,
1153
+ "learning_rate": 8.024263125710751e-07,
1154
+ "loss": 0.8118,
1155
+ "step": 1910
1156
+ },
1157
+ {
1158
+ "epoch": 7.84,
1159
+ "learning_rate": 5.136518124159162e-07,
1160
+ "loss": 0.8503,
1161
+ "step": 1920
1162
+ },
1163
+ {
1164
+ "epoch": 7.88,
1165
+ "learning_rate": 2.8897245082978865e-07,
1166
+ "loss": 0.8248,
1167
+ "step": 1930
1168
+ },
1169
+ {
1170
+ "epoch": 7.92,
1171
+ "learning_rate": 1.284459498280266e-07,
1172
+ "loss": 0.8515,
1173
+ "step": 1940
1174
+ },
1175
+ {
1176
+ "epoch": 7.96,
1177
+ "learning_rate": 3.2113550017198734e-08,
1178
+ "loss": 0.8274,
1179
+ "step": 1950
1180
+ },
1181
+ {
1182
+ "epoch": 8.0,
1183
+ "learning_rate": 0.0,
1184
+ "loss": 0.7359,
1185
+ "step": 1960
1186
+ },
1187
+ {
1188
+ "epoch": 8.0,
1189
+ "step": 1960,
1190
+ "total_flos": 7.457847416862474e+17,
1191
+ "train_loss": 1.1027992168251348,
1192
+ "train_runtime": 31447.7257,
1193
+ "train_samples_per_second": 0.997,
1194
+ "train_steps_per_second": 0.062
1195
+ }
1196
+ ],
1197
+ "logging_steps": 10,
1198
+ "max_steps": 1960,
1199
+ "num_input_tokens_seen": 0,
1200
+ "num_train_epochs": 8,
1201
+ "save_steps": 100,
1202
+ "total_flos": 7.457847416862474e+17,
1203
+ "train_batch_size": 2,
1204
+ "trial_name": null,
1205
+ "trial_params": null
1206
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97e7cd0a00536d695f867e388e99cfec0e1802f7a71fa7d4d504b937faa46f08
3
+ size 4475
vocab.json ADDED
The diff for this file is too large to render. See raw diff