Upload 17 files
Browse files- README.md +69 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +5 -0
- all_results.json +20 -0
- eval_results.json +15 -0
- merges.txt +0 -0
- special_tokens_map.json +20 -0
- tokenizer.json +0 -0
- tokenizer_config.json +44 -0
- train_results.json +8 -0
- trainer_log.jsonl +205 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
- training_loss.png +0 -0
- training_rewards_accuracies.png +0 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- llama-factory
|
6 |
+
- lora
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: Qwen2/Qwen2-7B-Instruct
|
9 |
+
model-index:
|
10 |
+
- name: dpo_0621
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# dpo_0621
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [/root/LLM_Data_Engineer/LLaMA-Factory/models/Qwen2-7B-Instruct-lora-06072000](https://huggingface.co//root/LLM_Data_Engineer/LLaMA-Factory/models/Qwen2-7B-Instruct-lora-06072000) on the dpo_data_5370_0621 dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.1241
|
22 |
+
- Rewards/chosen: -1.0706
|
23 |
+
- Rewards/rejected: -5.6170
|
24 |
+
- Rewards/accuracies: 0.9778
|
25 |
+
- Rewards/margins: 4.5464
|
26 |
+
- Logps/rejected: -238.9563
|
27 |
+
- Logps/chosen: -277.6737
|
28 |
+
- Logits/rejected: -1.3396
|
29 |
+
- Logits/chosen: -0.1357
|
30 |
+
|
31 |
+
## Model description
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Intended uses & limitations
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training and evaluation data
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Training procedure
|
44 |
+
|
45 |
+
### Training hyperparameters
|
46 |
+
|
47 |
+
The following hyperparameters were used during training:
|
48 |
+
- learning_rate: 5e-06
|
49 |
+
- train_batch_size: 4
|
50 |
+
- eval_batch_size: 1
|
51 |
+
- seed: 42
|
52 |
+
- gradient_accumulation_steps: 8
|
53 |
+
- total_train_batch_size: 32
|
54 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
55 |
+
- lr_scheduler_type: cosine
|
56 |
+
- lr_scheduler_warmup_ratio: 0.1
|
57 |
+
- num_epochs: 3.0
|
58 |
+
|
59 |
+
### Training results
|
60 |
+
|
61 |
+
|
62 |
+
|
63 |
+
### Framework versions
|
64 |
+
|
65 |
+
- PEFT 0.11.1
|
66 |
+
- Transformers 4.41.2
|
67 |
+
- Pytorch 2.1.2
|
68 |
+
- Datasets 2.19.2
|
69 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen2/Qwen2-7B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0.0,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"q_proj",
|
25 |
+
"up_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"k_proj",
|
28 |
+
"o_proj",
|
29 |
+
"down_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b9e7814005e9e8e4fab439e01068f696d5668110e9748d0597fe68690418716
|
3 |
+
size 80792096
|
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 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.994495412844037,
|
3 |
+
"eval_logits/chosen": -0.13572698831558228,
|
4 |
+
"eval_logits/rejected": -1.339600920677185,
|
5 |
+
"eval_logps/chosen": -277.6737060546875,
|
6 |
+
"eval_logps/rejected": -238.95631408691406,
|
7 |
+
"eval_loss": 0.12411908805370331,
|
8 |
+
"eval_rewards/accuracies": 0.9777777791023254,
|
9 |
+
"eval_rewards/chosen": -1.0706360340118408,
|
10 |
+
"eval_rewards/margins": 4.546375274658203,
|
11 |
+
"eval_rewards/rejected": -5.617011070251465,
|
12 |
+
"eval_runtime": 9.0092,
|
13 |
+
"eval_samples_per_second": 4.995,
|
14 |
+
"eval_steps_per_second": 4.995,
|
15 |
+
"total_flos": 7.837376281021809e+17,
|
16 |
+
"train_loss": 0.23205441671113172,
|
17 |
+
"train_runtime": 8090.8922,
|
18 |
+
"train_samples_per_second": 1.616,
|
19 |
+
"train_steps_per_second": 0.05
|
20 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.994495412844037,
|
3 |
+
"eval_logits/chosen": -0.13572698831558228,
|
4 |
+
"eval_logits/rejected": -1.339600920677185,
|
5 |
+
"eval_logps/chosen": -277.6737060546875,
|
6 |
+
"eval_logps/rejected": -238.95631408691406,
|
7 |
+
"eval_loss": 0.12411908805370331,
|
8 |
+
"eval_rewards/accuracies": 0.9777777791023254,
|
9 |
+
"eval_rewards/chosen": -1.0706360340118408,
|
10 |
+
"eval_rewards/margins": 4.546375274658203,
|
11 |
+
"eval_rewards/rejected": -5.617011070251465,
|
12 |
+
"eval_runtime": 9.0092,
|
13 |
+
"eval_samples_per_second": 4.995,
|
14 |
+
"eval_steps_per_second": 4.995
|
15 |
+
}
|
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": "<|im_end|>",
|
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": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
|
35 |
+
"clean_up_tokenization_spaces": false,
|
36 |
+
"eos_token": "<|im_end|>",
|
37 |
+
"errors": "replace",
|
38 |
+
"model_max_length": 131072,
|
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 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.994495412844037,
|
3 |
+
"total_flos": 7.837376281021809e+17,
|
4 |
+
"train_loss": 0.23205441671113172,
|
5 |
+
"train_runtime": 8090.8922,
|
6 |
+
"train_samples_per_second": 1.616,
|
7 |
+
"train_steps_per_second": 0.05
|
8 |
+
}
|
trainer_log.jsonl
ADDED
@@ -0,0 +1,205 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"current_steps": 2, "total_steps": 408, "loss": 0.6931, "accuracy": 0.0, "learning_rate": 2.439024390243903e-07, "epoch": 0.014678899082568808, "percentage": 0.49, "elapsed_time": "0:00:31", "remaining_time": "1:47:56", "throughput": "0.00", "total_tokens": 0}
|
2 |
+
{"current_steps": 4, "total_steps": 408, "loss": 0.6907, "accuracy": 0.53125, "learning_rate": 4.878048780487805e-07, "epoch": 0.029357798165137616, "percentage": 0.98, "elapsed_time": "0:01:20", "remaining_time": "2:16:14", "throughput": "0.00", "total_tokens": 0}
|
3 |
+
{"current_steps": 6, "total_steps": 408, "loss": 0.6967, "accuracy": 0.53125, "learning_rate": 7.317073170731707e-07, "epoch": 0.044036697247706424, "percentage": 1.47, "elapsed_time": "0:02:07", "remaining_time": "2:22:42", "throughput": "0.00", "total_tokens": 0}
|
4 |
+
{"current_steps": 8, "total_steps": 408, "loss": 0.6966, "accuracy": 0.453125, "learning_rate": 9.75609756097561e-07, "epoch": 0.05871559633027523, "percentage": 1.96, "elapsed_time": "0:02:40", "remaining_time": "2:13:32", "throughput": "0.00", "total_tokens": 0}
|
5 |
+
{"current_steps": 10, "total_steps": 408, "loss": 0.6939, "accuracy": 0.453125, "learning_rate": 1.2195121951219514e-06, "epoch": 0.07339449541284404, "percentage": 2.45, "elapsed_time": "0:03:22", "remaining_time": "2:14:08", "throughput": "0.00", "total_tokens": 0}
|
6 |
+
{"current_steps": 12, "total_steps": 408, "loss": 0.6939, "accuracy": 0.53125, "learning_rate": 1.4634146341463414e-06, "epoch": 0.08807339449541285, "percentage": 2.94, "elapsed_time": "0:03:57", "remaining_time": "2:10:40", "throughput": "0.00", "total_tokens": 0}
|
7 |
+
{"current_steps": 14, "total_steps": 408, "loss": 0.6917, "accuracy": 0.5625, "learning_rate": 1.707317073170732e-06, "epoch": 0.10275229357798166, "percentage": 3.43, "elapsed_time": "0:04:30", "remaining_time": "2:06:43", "throughput": "0.00", "total_tokens": 0}
|
8 |
+
{"current_steps": 16, "total_steps": 408, "loss": 0.6971, "accuracy": 0.46875, "learning_rate": 1.951219512195122e-06, "epoch": 0.11743119266055047, "percentage": 3.92, "elapsed_time": "0:05:06", "remaining_time": "2:05:14", "throughput": "0.00", "total_tokens": 0}
|
9 |
+
{"current_steps": 18, "total_steps": 408, "loss": 0.6959, "accuracy": 0.5, "learning_rate": 2.1951219512195125e-06, "epoch": 0.13211009174311927, "percentage": 4.41, "elapsed_time": "0:05:44", "remaining_time": "2:04:14", "throughput": "0.00", "total_tokens": 0}
|
10 |
+
{"current_steps": 20, "total_steps": 408, "loss": 0.6933, "accuracy": 0.53125, "learning_rate": 2.4390243902439027e-06, "epoch": 0.14678899082568808, "percentage": 4.9, "elapsed_time": "0:06:26", "remaining_time": "2:04:56", "throughput": "0.00", "total_tokens": 0}
|
11 |
+
{"current_steps": 22, "total_steps": 408, "loss": 0.6847, "accuracy": 0.53125, "learning_rate": 2.682926829268293e-06, "epoch": 0.1614678899082569, "percentage": 5.39, "elapsed_time": "0:07:15", "remaining_time": "2:07:13", "throughput": "0.00", "total_tokens": 0}
|
12 |
+
{"current_steps": 24, "total_steps": 408, "loss": 0.6828, "accuracy": 0.609375, "learning_rate": 2.926829268292683e-06, "epoch": 0.1761467889908257, "percentage": 5.88, "elapsed_time": "0:07:48", "remaining_time": "2:04:56", "throughput": "0.00", "total_tokens": 0}
|
13 |
+
{"current_steps": 26, "total_steps": 408, "loss": 0.6865, "accuracy": 0.59375, "learning_rate": 3.1707317073170736e-06, "epoch": 0.1908256880733945, "percentage": 6.37, "elapsed_time": "0:08:25", "remaining_time": "2:03:46", "throughput": "0.00", "total_tokens": 0}
|
14 |
+
{"current_steps": 28, "total_steps": 408, "loss": 0.6886, "accuracy": 0.578125, "learning_rate": 3.414634146341464e-06, "epoch": 0.20550458715596331, "percentage": 6.86, "elapsed_time": "0:09:04", "remaining_time": "2:03:03", "throughput": "0.00", "total_tokens": 0}
|
15 |
+
{"current_steps": 30, "total_steps": 408, "loss": 0.6955, "accuracy": 0.46875, "learning_rate": 3.6585365853658537e-06, "epoch": 0.22018348623853212, "percentage": 7.35, "elapsed_time": "0:09:41", "remaining_time": "2:02:06", "throughput": "0.00", "total_tokens": 0}
|
16 |
+
{"current_steps": 32, "total_steps": 408, "loss": 0.6909, "accuracy": 0.53125, "learning_rate": 3.902439024390244e-06, "epoch": 0.23486238532110093, "percentage": 7.84, "elapsed_time": "0:10:30", "remaining_time": "2:03:30", "throughput": "0.00", "total_tokens": 0}
|
17 |
+
{"current_steps": 34, "total_steps": 408, "loss": 0.6841, "accuracy": 0.578125, "learning_rate": 4.146341463414634e-06, "epoch": 0.24954128440366974, "percentage": 8.33, "elapsed_time": "0:11:17", "remaining_time": "2:04:16", "throughput": "0.00", "total_tokens": 0}
|
18 |
+
{"current_steps": 36, "total_steps": 408, "loss": 0.68, "accuracy": 0.578125, "learning_rate": 4.390243902439025e-06, "epoch": 0.26422018348623855, "percentage": 8.82, "elapsed_time": "0:12:06", "remaining_time": "2:05:10", "throughput": "0.00", "total_tokens": 0}
|
19 |
+
{"current_steps": 38, "total_steps": 408, "loss": 0.6859, "accuracy": 0.546875, "learning_rate": 4.634146341463416e-06, "epoch": 0.27889908256880735, "percentage": 9.31, "elapsed_time": "0:12:46", "remaining_time": "2:04:25", "throughput": "0.00", "total_tokens": 0}
|
20 |
+
{"current_steps": 40, "total_steps": 408, "loss": 0.6883, "accuracy": 0.5, "learning_rate": 4.8780487804878055e-06, "epoch": 0.29357798165137616, "percentage": 9.8, "elapsed_time": "0:13:22", "remaining_time": "2:03:04", "throughput": "0.00", "total_tokens": 0}
|
21 |
+
{"current_steps": 42, "total_steps": 408, "loss": 0.6796, "accuracy": 0.71875, "learning_rate": 4.999908404322799e-06, "epoch": 0.30825688073394497, "percentage": 10.29, "elapsed_time": "0:13:59", "remaining_time": "2:01:53", "throughput": "0.00", "total_tokens": 0}
|
22 |
+
{"current_steps": 44, "total_steps": 408, "loss": 0.673, "accuracy": 0.703125, "learning_rate": 4.999175679175577e-06, "epoch": 0.3229357798165138, "percentage": 10.78, "elapsed_time": "0:14:37", "remaining_time": "2:01:00", "throughput": "0.00", "total_tokens": 0}
|
23 |
+
{"current_steps": 46, "total_steps": 408, "loss": 0.6842, "accuracy": 0.59375, "learning_rate": 4.997710443643461e-06, "epoch": 0.3376146788990826, "percentage": 11.27, "elapsed_time": "0:15:34", "remaining_time": "2:02:36", "throughput": "0.00", "total_tokens": 0}
|
24 |
+
{"current_steps": 48, "total_steps": 408, "loss": 0.6615, "accuracy": 0.828125, "learning_rate": 4.995513127188151e-06, "epoch": 0.3522935779816514, "percentage": 11.76, "elapsed_time": "0:16:22", "remaining_time": "2:02:47", "throughput": "0.00", "total_tokens": 0}
|
25 |
+
{"current_steps": 50, "total_steps": 408, "loss": 0.6693, "accuracy": 0.734375, "learning_rate": 4.992584373844853e-06, "epoch": 0.3669724770642202, "percentage": 12.25, "elapsed_time": "0:17:02", "remaining_time": "2:02:01", "throughput": "0.00", "total_tokens": 0}
|
26 |
+
{"current_steps": 52, "total_steps": 408, "loss": 0.6679, "accuracy": 0.828125, "learning_rate": 4.98892504203351e-06, "epoch": 0.381651376146789, "percentage": 12.75, "elapsed_time": "0:17:39", "remaining_time": "2:00:50", "throughput": "0.00", "total_tokens": 0}
|
27 |
+
{"current_steps": 54, "total_steps": 408, "loss": 0.6581, "accuracy": 0.796875, "learning_rate": 4.9845362043071925e-06, "epoch": 0.3963302752293578, "percentage": 13.24, "elapsed_time": "0:18:12", "remaining_time": "1:59:19", "throughput": "0.00", "total_tokens": 0}
|
28 |
+
{"current_steps": 56, "total_steps": 408, "loss": 0.6426, "accuracy": 0.921875, "learning_rate": 4.97941914703774e-06, "epoch": 0.41100917431192663, "percentage": 13.73, "elapsed_time": "0:19:01", "remaining_time": "1:59:34", "throughput": "0.00", "total_tokens": 0}
|
29 |
+
{"current_steps": 58, "total_steps": 408, "loss": 0.6367, "accuracy": 0.90625, "learning_rate": 4.973575370038718e-06, "epoch": 0.42568807339449544, "percentage": 14.22, "elapsed_time": "0:19:44", "remaining_time": "1:59:08", "throughput": "0.00", "total_tokens": 0}
|
30 |
+
{"current_steps": 60, "total_steps": 408, "loss": 0.6195, "accuracy": 0.921875, "learning_rate": 4.967006586125827e-06, "epoch": 0.44036697247706424, "percentage": 14.71, "elapsed_time": "0:20:23", "remaining_time": "1:58:14", "throughput": "0.00", "total_tokens": 0}
|
31 |
+
{"current_steps": 62, "total_steps": 408, "loss": 0.6116, "accuracy": 0.953125, "learning_rate": 4.959714720614871e-06, "epoch": 0.45504587155963305, "percentage": 15.2, "elapsed_time": "0:21:12", "remaining_time": "1:58:23", "throughput": "0.00", "total_tokens": 0}
|
32 |
+
{"current_steps": 64, "total_steps": 408, "loss": 0.6071, "accuracy": 0.90625, "learning_rate": 4.951701910757446e-06, "epoch": 0.46972477064220186, "percentage": 15.69, "elapsed_time": "0:21:52", "remaining_time": "1:57:36", "throughput": "0.00", "total_tokens": 0}
|
33 |
+
{"current_steps": 66, "total_steps": 408, "loss": 0.5823, "accuracy": 0.96875, "learning_rate": 4.942970505114514e-06, "epoch": 0.48440366972477067, "percentage": 16.18, "elapsed_time": "0:22:26", "remaining_time": "1:56:18", "throughput": "0.00", "total_tokens": 0}
|
34 |
+
{"current_steps": 68, "total_steps": 408, "loss": 0.5955, "accuracy": 0.921875, "learning_rate": 4.933523062868033e-06, "epoch": 0.4990825688073395, "percentage": 16.67, "elapsed_time": "0:23:00", "remaining_time": "1:55:00", "throughput": "0.00", "total_tokens": 0}
|
35 |
+
{"current_steps": 70, "total_steps": 408, "loss": 0.5739, "accuracy": 0.984375, "learning_rate": 4.923362353070859e-06, "epoch": 0.5137614678899083, "percentage": 17.16, "elapsed_time": "0:23:37", "remaining_time": "1:54:06", "throughput": "0.00", "total_tokens": 0}
|
36 |
+
{"current_steps": 72, "total_steps": 408, "loss": 0.5615, "accuracy": 0.953125, "learning_rate": 4.912491353835138e-06, "epoch": 0.5284403669724771, "percentage": 17.65, "elapsed_time": "0:24:26", "remaining_time": "1:54:05", "throughput": "0.00", "total_tokens": 0}
|
37 |
+
{"current_steps": 74, "total_steps": 408, "loss": 0.5552, "accuracy": 0.953125, "learning_rate": 4.900913251459418e-06, "epoch": 0.5431192660550459, "percentage": 18.14, "elapsed_time": "0:25:01", "remaining_time": "1:52:56", "throughput": "0.00", "total_tokens": 0}
|
38 |
+
{"current_steps": 76, "total_steps": 408, "loss": 0.5215, "accuracy": 1.0, "learning_rate": 4.8886314394947396e-06, "epoch": 0.5577981651376147, "percentage": 18.63, "elapsed_time": "0:25:34", "remaining_time": "1:51:41", "throughput": "0.00", "total_tokens": 0}
|
39 |
+
{"current_steps": 78, "total_steps": 408, "loss": 0.5145, "accuracy": 0.96875, "learning_rate": 4.875649517749985e-06, "epoch": 0.5724770642201835, "percentage": 19.12, "elapsed_time": "0:26:06", "remaining_time": "1:50:27", "throughput": "0.00", "total_tokens": 0}
|
40 |
+
{"current_steps": 80, "total_steps": 408, "loss": 0.53, "accuracy": 0.890625, "learning_rate": 4.861971291236772e-06, "epoch": 0.5871559633027523, "percentage": 19.61, "elapsed_time": "0:26:43", "remaining_time": "1:49:34", "throughput": "0.00", "total_tokens": 0}
|
41 |
+
{"current_steps": 82, "total_steps": 408, "loss": 0.5022, "accuracy": 0.984375, "learning_rate": 4.847600769054201e-06, "epoch": 0.6018348623853211, "percentage": 20.1, "elapsed_time": "0:27:28", "remaining_time": "1:49:12", "throughput": "0.00", "total_tokens": 0}
|
42 |
+
{"current_steps": 84, "total_steps": 408, "loss": 0.4934, "accuracy": 0.96875, "learning_rate": 4.832542163213787e-06, "epoch": 0.6165137614678899, "percentage": 20.59, "elapsed_time": "0:28:01", "remaining_time": "1:48:07", "throughput": "0.00", "total_tokens": 0}
|
43 |
+
{"current_steps": 86, "total_steps": 408, "loss": 0.4836, "accuracy": 0.96875, "learning_rate": 4.816799887404911e-06, "epoch": 0.6311926605504588, "percentage": 21.08, "elapsed_time": "0:28:47", "remaining_time": "1:47:48", "throughput": "0.00", "total_tokens": 0}
|
44 |
+
{"current_steps": 88, "total_steps": 408, "loss": 0.4407, "accuracy": 0.9375, "learning_rate": 4.800378555701168e-06, "epoch": 0.6458715596330276, "percentage": 21.57, "elapsed_time": "0:29:26", "remaining_time": "1:47:03", "throughput": "0.00", "total_tokens": 0}
|
45 |
+
{"current_steps": 90, "total_steps": 408, "loss": 0.4509, "accuracy": 0.96875, "learning_rate": 4.783282981207979e-06, "epoch": 0.6605504587155964, "percentage": 22.06, "elapsed_time": "0:30:05", "remaining_time": "1:46:19", "throughput": "0.00", "total_tokens": 0}
|
46 |
+
{"current_steps": 92, "total_steps": 408, "loss": 0.4227, "accuracy": 0.984375, "learning_rate": 4.765518174651864e-06, "epoch": 0.6752293577981652, "percentage": 22.55, "elapsed_time": "0:30:40", "remaining_time": "1:45:20", "throughput": "0.00", "total_tokens": 0}
|
47 |
+
{"current_steps": 94, "total_steps": 408, "loss": 0.421, "accuracy": 0.984375, "learning_rate": 4.747089342911793e-06, "epoch": 0.689908256880734, "percentage": 23.04, "elapsed_time": "0:31:25", "remaining_time": "1:44:57", "throughput": "0.00", "total_tokens": 0}
|
48 |
+
{"current_steps": 96, "total_steps": 408, "loss": 0.4037, "accuracy": 1.0, "learning_rate": 4.728001887493048e-06, "epoch": 0.7045871559633028, "percentage": 23.53, "elapsed_time": "0:31:59", "remaining_time": "1:43:57", "throughput": "0.00", "total_tokens": 0}
|
49 |
+
{"current_steps": 98, "total_steps": 408, "loss": 0.3953, "accuracy": 0.953125, "learning_rate": 4.708261402944036e-06, "epoch": 0.7192660550458716, "percentage": 24.02, "elapsed_time": "0:32:40", "remaining_time": "1:43:22", "throughput": "0.00", "total_tokens": 0}
|
50 |
+
{"current_steps": 100, "total_steps": 408, "loss": 0.3808, "accuracy": 0.984375, "learning_rate": 4.687873675216522e-06, "epoch": 0.7339449541284404, "percentage": 24.51, "elapsed_time": "0:33:25", "remaining_time": "1:42:56", "throughput": "0.00", "total_tokens": 0}
|
51 |
+
{"current_steps": 102, "total_steps": 408, "loss": 0.3233, "accuracy": 1.0, "learning_rate": 4.666844679969765e-06, "epoch": 0.7486238532110092, "percentage": 25.0, "elapsed_time": "0:34:20", "remaining_time": "1:43:02", "throughput": "0.00", "total_tokens": 0}
|
52 |
+
{"current_steps": 104, "total_steps": 408, "loss": 0.3502, "accuracy": 0.984375, "learning_rate": 4.6451805808190464e-06, "epoch": 0.763302752293578, "percentage": 25.49, "elapsed_time": "0:34:55", "remaining_time": "1:42:04", "throughput": "0.00", "total_tokens": 0}
|
53 |
+
{"current_steps": 106, "total_steps": 408, "loss": 0.3127, "accuracy": 0.953125, "learning_rate": 4.622887727529104e-06, "epoch": 0.7779816513761468, "percentage": 25.98, "elapsed_time": "0:35:35", "remaining_time": "1:41:22", "throughput": "0.00", "total_tokens": 0}
|
54 |
+
{"current_steps": 108, "total_steps": 408, "loss": 0.303, "accuracy": 1.0, "learning_rate": 4.599972654153018e-06, "epoch": 0.7926605504587156, "percentage": 26.47, "elapsed_time": "0:36:06", "remaining_time": "1:40:17", "throughput": "0.00", "total_tokens": 0}
|
55 |
+
{"current_steps": 110, "total_steps": 408, "loss": 0.317, "accuracy": 0.96875, "learning_rate": 4.5764420771170735e-06, "epoch": 0.8073394495412844, "percentage": 26.96, "elapsed_time": "0:36:36", "remaining_time": "1:39:10", "throughput": "0.00", "total_tokens": 0}
|
56 |
+
{"current_steps": 112, "total_steps": 408, "loss": 0.2781, "accuracy": 1.0, "learning_rate": 4.552302893252166e-06, "epoch": 0.8220183486238533, "percentage": 27.45, "elapsed_time": "0:37:23", "remaining_time": "1:38:48", "throughput": "0.00", "total_tokens": 0}
|
57 |
+
{"current_steps": 114, "total_steps": 408, "loss": 0.3122, "accuracy": 0.984375, "learning_rate": 4.52756217777234e-06, "epoch": 0.8366972477064221, "percentage": 27.94, "elapsed_time": "0:38:01", "remaining_time": "1:38:03", "throughput": "0.00", "total_tokens": 0}
|
58 |
+
{"current_steps": 116, "total_steps": 408, "loss": 0.2555, "accuracy": 0.984375, "learning_rate": 4.502227182201035e-06, "epoch": 0.8513761467889909, "percentage": 28.43, "elapsed_time": "0:38:36", "remaining_time": "1:37:10", "throughput": "0.00", "total_tokens": 0}
|
59 |
+
{"current_steps": 118, "total_steps": 408, "loss": 0.2852, "accuracy": 0.984375, "learning_rate": 4.476305332245662e-06, "epoch": 0.8660550458715597, "percentage": 28.92, "elapsed_time": "0:39:26", "remaining_time": "1:36:56", "throughput": "0.00", "total_tokens": 0}
|
60 |
+
{"current_steps": 120, "total_steps": 408, "loss": 0.273, "accuracy": 0.953125, "learning_rate": 4.449804225621116e-06, "epoch": 0.8807339449541285, "percentage": 29.41, "elapsed_time": "0:40:01", "remaining_time": "1:36:03", "throughput": "0.00", "total_tokens": 0}
|
61 |
+
{"current_steps": 122, "total_steps": 408, "loss": 0.2744, "accuracy": 0.984375, "learning_rate": 4.422731629822887e-06, "epoch": 0.8954128440366973, "percentage": 29.9, "elapsed_time": "0:40:41", "remaining_time": "1:35:24", "throughput": "0.00", "total_tokens": 0}
|
62 |
+
{"current_steps": 124, "total_steps": 408, "loss": 0.298, "accuracy": 0.96875, "learning_rate": 4.395095479850396e-06, "epoch": 0.9100917431192661, "percentage": 30.39, "elapsed_time": "0:41:13", "remaining_time": "1:34:24", "throughput": "0.00", "total_tokens": 0}
|
63 |
+
{"current_steps": 126, "total_steps": 408, "loss": 0.2327, "accuracy": 0.984375, "learning_rate": 4.366903875881243e-06, "epoch": 0.9247706422018349, "percentage": 30.88, "elapsed_time": "0:41:57", "remaining_time": "1:33:55", "throughput": "0.00", "total_tokens": 0}
|
64 |
+
{"current_steps": 128, "total_steps": 408, "loss": 0.2276, "accuracy": 0.984375, "learning_rate": 4.3381650808970365e-06, "epoch": 0.9394495412844037, "percentage": 31.37, "elapsed_time": "0:42:30", "remaining_time": "1:32:59", "throughput": "0.00", "total_tokens": 0}
|
65 |
+
{"current_steps": 130, "total_steps": 408, "loss": 0.2147, "accuracy": 0.984375, "learning_rate": 4.308887518261507e-06, "epoch": 0.9541284403669725, "percentage": 31.86, "elapsed_time": "0:43:08", "remaining_time": "1:32:14", "throughput": "0.00", "total_tokens": 0}
|
66 |
+
{"current_steps": 132, "total_steps": 408, "loss": 0.2101, "accuracy": 1.0, "learning_rate": 4.279079769251617e-06, "epoch": 0.9688073394495413, "percentage": 32.35, "elapsed_time": "0:43:54", "remaining_time": "1:31:48", "throughput": "0.00", "total_tokens": 0}
|
67 |
+
{"current_steps": 134, "total_steps": 408, "loss": 0.2094, "accuracy": 0.984375, "learning_rate": 4.248750570542373e-06, "epoch": 0.9834862385321101, "percentage": 32.84, "elapsed_time": "0:44:30", "remaining_time": "1:30:59", "throughput": "0.00", "total_tokens": 0}
|
68 |
+
{"current_steps": 136, "total_steps": 408, "loss": 0.1783, "accuracy": 1.0, "learning_rate": 4.21790881164611e-06, "epoch": 0.998165137614679, "percentage": 33.33, "elapsed_time": "0:45:06", "remaining_time": "1:30:13", "throughput": "0.00", "total_tokens": 0}
|
69 |
+
{"current_steps": 138, "total_steps": 408, "loss": 0.2379, "accuracy": 0.96875, "learning_rate": 4.186563532306957e-06, "epoch": 1.0128440366972478, "percentage": 33.82, "elapsed_time": "0:45:40", "remaining_time": "1:29:21", "throughput": "0.00", "total_tokens": 0}
|
70 |
+
{"current_steps": 140, "total_steps": 408, "loss": 0.2287, "accuracy": 0.96875, "learning_rate": 4.154723919851291e-06, "epoch": 1.0275229357798166, "percentage": 34.31, "elapsed_time": "0:46:16", "remaining_time": "1:28:35", "throughput": "0.00", "total_tokens": 0}
|
71 |
+
{"current_steps": 142, "total_steps": 408, "loss": 0.2024, "accuracy": 0.96875, "learning_rate": 4.122399306494918e-06, "epoch": 1.0422018348623854, "percentage": 34.8, "elapsed_time": "0:47:01", "remaining_time": "1:28:05", "throughput": "0.00", "total_tokens": 0}
|
72 |
+
{"current_steps": 144, "total_steps": 408, "loss": 0.1682, "accuracy": 1.0, "learning_rate": 4.089599166607794e-06, "epoch": 1.0568807339449542, "percentage": 35.29, "elapsed_time": "0:47:37", "remaining_time": "1:27:18", "throughput": "0.00", "total_tokens": 0}
|
73 |
+
{"current_steps": 146, "total_steps": 408, "loss": 0.1732, "accuracy": 0.984375, "learning_rate": 4.05633311393708e-06, "epoch": 1.071559633027523, "percentage": 35.78, "elapsed_time": "0:48:18", "remaining_time": "1:26:41", "throughput": "0.00", "total_tokens": 0}
|
74 |
+
{"current_steps": 148, "total_steps": 408, "loss": 0.1719, "accuracy": 0.96875, "learning_rate": 4.022610898789349e-06, "epoch": 1.0862385321100918, "percentage": 36.27, "elapsed_time": "0:48:50", "remaining_time": "1:25:49", "throughput": "0.00", "total_tokens": 0}
|
75 |
+
{"current_steps": 150, "total_steps": 408, "loss": 0.1474, "accuracy": 0.984375, "learning_rate": 3.988442405172755e-06, "epoch": 1.1009174311926606, "percentage": 36.76, "elapsed_time": "0:49:32", "remaining_time": "1:25:11", "throughput": "0.00", "total_tokens": 0}
|
76 |
+
{"current_steps": 152, "total_steps": 408, "loss": 0.1388, "accuracy": 0.984375, "learning_rate": 3.953837647900031e-06, "epoch": 1.1155963302752294, "percentage": 37.25, "elapsed_time": "0:50:14", "remaining_time": "1:24:36", "throughput": "0.00", "total_tokens": 0}
|
77 |
+
{"current_steps": 154, "total_steps": 408, "loss": 0.2011, "accuracy": 0.96875, "learning_rate": 3.918806769653135e-06, "epoch": 1.1302752293577982, "percentage": 37.75, "elapsed_time": "0:50:59", "remaining_time": "1:24:06", "throughput": "0.00", "total_tokens": 0}
|
78 |
+
{"current_steps": 156, "total_steps": 408, "loss": 0.1966, "accuracy": 0.953125, "learning_rate": 3.88336003801042e-06, "epoch": 1.144954128440367, "percentage": 38.24, "elapsed_time": "0:51:31", "remaining_time": "1:23:13", "throughput": "0.00", "total_tokens": 0}
|
79 |
+
{"current_steps": 158, "total_steps": 408, "loss": 0.1418, "accuracy": 1.0, "learning_rate": 3.847507842437205e-06, "epoch": 1.1596330275229358, "percentage": 38.73, "elapsed_time": "0:52:05", "remaining_time": "1:22:25", "throughput": "0.00", "total_tokens": 0}
|
80 |
+
{"current_steps": 160, "total_steps": 408, "loss": 0.1652, "accuracy": 0.96875, "learning_rate": 3.811260691240604e-06, "epoch": 1.1743119266055047, "percentage": 39.22, "elapsed_time": "0:52:41", "remaining_time": "1:21:40", "throughput": "0.00", "total_tokens": 0}
|
81 |
+
{"current_steps": 162, "total_steps": 408, "loss": 0.1554, "accuracy": 0.984375, "learning_rate": 3.774629208489547e-06, "epoch": 1.1889908256880735, "percentage": 39.71, "elapsed_time": "0:53:16", "remaining_time": "1:20:53", "throughput": "0.00", "total_tokens": 0}
|
82 |
+
{"current_steps": 164, "total_steps": 408, "loss": 0.1339, "accuracy": 0.984375, "learning_rate": 3.7376241309008433e-06, "epoch": 1.2036697247706423, "percentage": 40.2, "elapsed_time": "0:53:55", "remaining_time": "1:20:13", "throughput": "0.00", "total_tokens": 0}
|
83 |
+
{"current_steps": 166, "total_steps": 408, "loss": 0.1372, "accuracy": 0.984375, "learning_rate": 3.7002563046922502e-06, "epoch": 1.218348623853211, "percentage": 40.69, "elapsed_time": "0:54:47", "remaining_time": "1:19:53", "throughput": "0.00", "total_tokens": 0}
|
84 |
+
{"current_steps": 168, "total_steps": 408, "loss": 0.1086, "accuracy": 0.984375, "learning_rate": 3.6625366824034337e-06, "epoch": 1.2330275229357799, "percentage": 41.18, "elapsed_time": "0:55:28", "remaining_time": "1:19:14", "throughput": "0.00", "total_tokens": 0}
|
85 |
+
{"current_steps": 170, "total_steps": 408, "loss": 0.141, "accuracy": 0.984375, "learning_rate": 3.6244763196857714e-06, "epoch": 1.2477064220183487, "percentage": 41.67, "elapsed_time": "0:56:13", "remaining_time": "1:18:42", "throughput": "0.00", "total_tokens": 0}
|
86 |
+
{"current_steps": 172, "total_steps": 408, "loss": 0.1117, "accuracy": 1.0, "learning_rate": 3.5860863720619333e-06, "epoch": 1.2623853211009175, "percentage": 42.16, "elapsed_time": "0:57:01", "remaining_time": "1:18:14", "throughput": "0.00", "total_tokens": 0}
|
87 |
+
{"current_steps": 174, "total_steps": 408, "loss": 0.114, "accuracy": 0.984375, "learning_rate": 3.547378091656186e-06, "epoch": 1.2770642201834863, "percentage": 42.65, "elapsed_time": "0:57:36", "remaining_time": "1:17:28", "throughput": "0.00", "total_tokens": 0}
|
88 |
+
{"current_steps": 176, "total_steps": 408, "loss": 0.1515, "accuracy": 0.96875, "learning_rate": 3.5083628238963913e-06, "epoch": 1.2917431192660551, "percentage": 43.14, "elapsed_time": "0:58:26", "remaining_time": "1:17:01", "throughput": "0.00", "total_tokens": 0}
|
89 |
+
{"current_steps": 178, "total_steps": 408, "loss": 0.0978, "accuracy": 0.984375, "learning_rate": 3.4690520041886473e-06, "epoch": 1.306422018348624, "percentage": 43.63, "elapsed_time": "0:59:07", "remaining_time": "1:16:23", "throughput": "0.00", "total_tokens": 0}
|
90 |
+
{"current_steps": 180, "total_steps": 408, "loss": 0.0795, "accuracy": 1.0, "learning_rate": 3.4294571545655653e-06, "epoch": 1.3211009174311927, "percentage": 44.12, "elapsed_time": "0:59:48", "remaining_time": "1:15:45", "throughput": "0.00", "total_tokens": 0}
|
91 |
+
{"current_steps": 182, "total_steps": 408, "loss": 0.1353, "accuracy": 0.96875, "learning_rate": 3.38958988030915e-06, "epoch": 1.3357798165137615, "percentage": 44.61, "elapsed_time": "1:00:36", "remaining_time": "1:15:16", "throughput": "0.00", "total_tokens": 0}
|
92 |
+
{"current_steps": 184, "total_steps": 408, "loss": 0.1522, "accuracy": 0.96875, "learning_rate": 3.3494618665492833e-06, "epoch": 1.3504587155963304, "percentage": 45.1, "elapsed_time": "1:01:14", "remaining_time": "1:14:33", "throughput": "0.00", "total_tokens": 0}
|
93 |
+
{"current_steps": 186, "total_steps": 408, "loss": 0.1274, "accuracy": 0.953125, "learning_rate": 3.3090848748388042e-06, "epoch": 1.3651376146788992, "percentage": 45.59, "elapsed_time": "1:01:58", "remaining_time": "1:13:58", "throughput": "0.00", "total_tokens": 0}
|
94 |
+
{"current_steps": 188, "total_steps": 408, "loss": 0.1099, "accuracy": 0.96875, "learning_rate": 3.2684707397061887e-06, "epoch": 1.379816513761468, "percentage": 46.08, "elapsed_time": "1:02:56", "remaining_time": "1:13:39", "throughput": "0.00", "total_tokens": 0}
|
95 |
+
{"current_steps": 190, "total_steps": 408, "loss": 0.1137, "accuracy": 0.984375, "learning_rate": 3.2276313651868364e-06, "epoch": 1.3944954128440368, "percentage": 46.57, "elapsed_time": "1:03:28", "remaining_time": "1:12:50", "throughput": "0.00", "total_tokens": 0}
|
96 |
+
{"current_steps": 192, "total_steps": 408, "loss": 0.1071, "accuracy": 1.0, "learning_rate": 3.1865787213339926e-06, "epoch": 1.4091743119266056, "percentage": 47.06, "elapsed_time": "1:04:03", "remaining_time": "1:12:03", "throughput": "0.00", "total_tokens": 0}
|
97 |
+
{"current_steps": 194, "total_steps": 408, "loss": 0.1227, "accuracy": 0.984375, "learning_rate": 3.1453248407103156e-06, "epoch": 1.4238532110091744, "percentage": 47.55, "elapsed_time": "1:04:40", "remaining_time": "1:11:20", "throughput": "0.00", "total_tokens": 0}
|
98 |
+
{"current_steps": 196, "total_steps": 408, "loss": 0.135, "accuracy": 0.953125, "learning_rate": 3.1038818148611178e-06, "epoch": 1.4385321100917432, "percentage": 48.04, "elapsed_time": "1:05:14", "remaining_time": "1:10:33", "throughput": "0.00", "total_tokens": 0}
|
99 |
+
{"current_steps": 198, "total_steps": 408, "loss": 0.1372, "accuracy": 0.953125, "learning_rate": 3.062261790770331e-06, "epoch": 1.453211009174312, "percentage": 48.53, "elapsed_time": "1:05:48", "remaining_time": "1:09:47", "throughput": "0.00", "total_tokens": 0}
|
100 |
+
{"current_steps": 200, "total_steps": 408, "loss": 0.1041, "accuracy": 0.984375, "learning_rate": 3.0204769673002123e-06, "epoch": 1.4678899082568808, "percentage": 49.02, "elapsed_time": "1:06:23", "remaining_time": "1:09:02", "throughput": "0.00", "total_tokens": 0}
|
101 |
+
{"current_steps": 202, "total_steps": 408, "loss": 0.0991, "accuracy": 1.0, "learning_rate": 2.978539591615848e-06, "epoch": 1.4825688073394496, "percentage": 49.51, "elapsed_time": "1:06:55", "remaining_time": "1:08:15", "throughput": "0.00", "total_tokens": 0}
|
102 |
+
{"current_steps": 204, "total_steps": 408, "loss": 0.1185, "accuracy": 0.984375, "learning_rate": 2.936461955595501e-06, "epoch": 1.4972477064220184, "percentage": 50.0, "elapsed_time": "1:07:28", "remaining_time": "1:07:28", "throughput": "0.00", "total_tokens": 0}
|
103 |
+
{"current_steps": 206, "total_steps": 408, "loss": 0.0849, "accuracy": 1.0, "learning_rate": 2.8942563922278487e-06, "epoch": 1.5119266055045872, "percentage": 50.49, "elapsed_time": "1:08:05", "remaining_time": "1:06:45", "throughput": "0.00", "total_tokens": 0}
|
104 |
+
{"current_steps": 208, "total_steps": 408, "loss": 0.1431, "accuracy": 0.96875, "learning_rate": 2.8519352719971783e-06, "epoch": 1.526605504587156, "percentage": 50.98, "elapsed_time": "1:08:51", "remaining_time": "1:06:12", "throughput": "0.00", "total_tokens": 0}
|
105 |
+
{"current_steps": 210, "total_steps": 408, "loss": 0.0775, "accuracy": 1.0, "learning_rate": 2.8095109992575824e-06, "epoch": 1.5412844036697249, "percentage": 51.47, "elapsed_time": "1:09:34", "remaining_time": "1:05:36", "throughput": "0.00", "total_tokens": 0}
|
106 |
+
{"current_steps": 212, "total_steps": 408, "loss": 0.0919, "accuracy": 0.984375, "learning_rate": 2.7669960085972407e-06, "epoch": 1.5559633027522937, "percentage": 51.96, "elapsed_time": "1:10:16", "remaining_time": "1:04:58", "throughput": "0.00", "total_tokens": 0}
|
107 |
+
{"current_steps": 214, "total_steps": 408, "loss": 0.0837, "accuracy": 1.0, "learning_rate": 2.7244027611938247e-06, "epoch": 1.5706422018348625, "percentage": 52.45, "elapsed_time": "1:10:52", "remaining_time": "1:04:14", "throughput": "0.00", "total_tokens": 0}
|
108 |
+
{"current_steps": 216, "total_steps": 408, "loss": 0.1234, "accuracy": 0.953125, "learning_rate": 2.6817437411621194e-06, "epoch": 1.5853211009174313, "percentage": 52.94, "elapsed_time": "1:11:33", "remaining_time": "1:03:36", "throughput": "0.00", "total_tokens": 0}
|
109 |
+
{"current_steps": 218, "total_steps": 408, "loss": 0.0921, "accuracy": 0.96875, "learning_rate": 2.639031451894923e-06, "epoch": 1.6, "percentage": 53.43, "elapsed_time": "1:12:25", "remaining_time": "1:03:07", "throughput": "0.00", "total_tokens": 0}
|
110 |
+
{"current_steps": 220, "total_steps": 408, "loss": 0.1152, "accuracy": 0.953125, "learning_rate": 2.5962784123982843e-06, "epoch": 1.614678899082569, "percentage": 53.92, "elapsed_time": "1:13:06", "remaining_time": "1:02:28", "throughput": "0.00", "total_tokens": 0}
|
111 |
+
{"current_steps": 222, "total_steps": 408, "loss": 0.0729, "accuracy": 1.0, "learning_rate": 2.5534971536221804e-06, "epoch": 1.6293577981651377, "percentage": 54.41, "elapsed_time": "1:13:44", "remaining_time": "1:01:46", "throughput": "0.00", "total_tokens": 0}
|
112 |
+
{"current_steps": 224, "total_steps": 408, "loss": 0.0712, "accuracy": 1.0, "learning_rate": 2.5107002147876814e-06, "epoch": 1.6440366972477065, "percentage": 54.9, "elapsed_time": "1:14:22", "remaining_time": "1:01:05", "throughput": "0.00", "total_tokens": 0}
|
113 |
+
{"current_steps": 226, "total_steps": 408, "loss": 0.1394, "accuracy": 0.953125, "learning_rate": 2.467900139711693e-06, "epoch": 1.6587155963302753, "percentage": 55.39, "elapsed_time": "1:15:02", "remaining_time": "1:00:25", "throughput": "0.00", "total_tokens": 0}
|
114 |
+
{"current_steps": 228, "total_steps": 408, "loss": 0.0863, "accuracy": 0.96875, "learning_rate": 2.4251094731303586e-06, "epoch": 1.6733944954128441, "percentage": 55.88, "elapsed_time": "1:15:48", "remaining_time": "0:59:50", "throughput": "0.00", "total_tokens": 0}
|
115 |
+
{"current_steps": 230, "total_steps": 408, "loss": 0.0741, "accuracy": 1.0, "learning_rate": 2.3823407570221812e-06, "epoch": 1.688073394495413, "percentage": 56.37, "elapsed_time": "1:16:22", "remaining_time": "0:59:06", "throughput": "0.00", "total_tokens": 0}
|
116 |
+
{"current_steps": 232, "total_steps": 408, "loss": 0.0842, "accuracy": 0.984375, "learning_rate": 2.3396065269319655e-06, "epoch": 1.7027522935779817, "percentage": 56.86, "elapsed_time": "1:16:56", "remaining_time": "0:58:22", "throughput": "0.00", "total_tokens": 0}
|
117 |
+
{"current_steps": 234, "total_steps": 408, "loss": 0.0526, "accuracy": 1.0, "learning_rate": 2.2969193082966353e-06, "epoch": 1.7174311926605506, "percentage": 57.35, "elapsed_time": "1:17:30", "remaining_time": "0:57:37", "throughput": "0.00", "total_tokens": 0}
|
118 |
+
{"current_steps": 236, "total_steps": 408, "loss": 0.0559, "accuracy": 1.0, "learning_rate": 2.2542916127740194e-06, "epoch": 1.7321100917431194, "percentage": 57.84, "elapsed_time": "1:18:08", "remaining_time": "0:56:57", "throughput": "0.00", "total_tokens": 0}
|
119 |
+
{"current_steps": 238, "total_steps": 408, "loss": 0.117, "accuracy": 0.984375, "learning_rate": 2.211735934575674e-06, "epoch": 1.7467889908256882, "percentage": 58.33, "elapsed_time": "1:18:46", "remaining_time": "0:56:16", "throughput": "0.00", "total_tokens": 0}
|
120 |
+
{"current_steps": 240, "total_steps": 408, "loss": 0.0538, "accuracy": 1.0, "learning_rate": 2.1692647468048235e-06, "epoch": 1.761467889908257, "percentage": 58.82, "elapsed_time": "1:19:21", "remaining_time": "0:55:33", "throughput": "0.00", "total_tokens": 0}
|
121 |
+
{"current_steps": 242, "total_steps": 408, "loss": 0.116, "accuracy": 1.0, "learning_rate": 2.126890497800477e-06, "epoch": 1.7761467889908258, "percentage": 59.31, "elapsed_time": "1:19:56", "remaining_time": "0:54:50", "throughput": "0.00", "total_tokens": 0}
|
122 |
+
{"current_steps": 244, "total_steps": 408, "loss": 0.0667, "accuracy": 1.0, "learning_rate": 2.084625607488816e-06, "epoch": 1.7908256880733946, "percentage": 59.8, "elapsed_time": "1:20:34", "remaining_time": "0:54:09", "throughput": "0.00", "total_tokens": 0}
|
123 |
+
{"current_steps": 246, "total_steps": 408, "loss": 0.053, "accuracy": 1.0, "learning_rate": 2.0424824637428995e-06, "epoch": 1.8055045871559634, "percentage": 60.29, "elapsed_time": "1:21:11", "remaining_time": "0:53:27", "throughput": "0.00", "total_tokens": 0}
|
124 |
+
{"current_steps": 248, "total_steps": 408, "loss": 0.0986, "accuracy": 0.984375, "learning_rate": 2.0004734187517744e-06, "epoch": 1.8201834862385322, "percentage": 60.78, "elapsed_time": "1:22:04", "remaining_time": "0:52:57", "throughput": "0.00", "total_tokens": 0}
|
125 |
+
{"current_steps": 250, "total_steps": 408, "loss": 0.0871, "accuracy": 0.984375, "learning_rate": 1.9586107854000327e-06, "epoch": 1.834862385321101, "percentage": 61.27, "elapsed_time": "1:22:55", "remaining_time": "0:52:24", "throughput": "0.00", "total_tokens": 0}
|
126 |
+
{"current_steps": 252, "total_steps": 408, "loss": 0.0714, "accuracy": 0.96875, "learning_rate": 1.916906833658899e-06, "epoch": 1.8495412844036698, "percentage": 61.76, "elapsed_time": "1:23:30", "remaining_time": "0:51:41", "throughput": "0.00", "total_tokens": 0}
|
127 |
+
{"current_steps": 254, "total_steps": 408, "loss": 0.051, "accuracy": 1.0, "learning_rate": 1.8753737869898921e-06, "epoch": 1.8642201834862386, "percentage": 62.25, "elapsed_time": "1:24:10", "remaining_time": "0:51:02", "throughput": "0.00", "total_tokens": 0}
|
128 |
+
{"current_steps": 256, "total_steps": 408, "loss": 0.1047, "accuracy": 0.984375, "learning_rate": 1.8340238187621185e-06, "epoch": 1.8788990825688074, "percentage": 62.75, "elapsed_time": "1:24:45", "remaining_time": "0:50:19", "throughput": "0.00", "total_tokens": 0}
|
129 |
+
{"current_steps": 258, "total_steps": 408, "loss": 0.0772, "accuracy": 1.0, "learning_rate": 1.7928690486842438e-06, "epoch": 1.8935779816513763, "percentage": 63.24, "elapsed_time": "1:25:26", "remaining_time": "0:49:40", "throughput": "0.00", "total_tokens": 0}
|
130 |
+
{"current_steps": 260, "total_steps": 408, "loss": 0.0681, "accuracy": 0.984375, "learning_rate": 1.7519215392522026e-06, "epoch": 1.908256880733945, "percentage": 63.73, "elapsed_time": "1:26:06", "remaining_time": "0:49:01", "throughput": "0.00", "total_tokens": 0}
|
131 |
+
{"current_steps": 262, "total_steps": 408, "loss": 0.062, "accuracy": 1.0, "learning_rate": 1.7111932922136715e-06, "epoch": 1.9229357798165139, "percentage": 64.22, "elapsed_time": "1:26:41", "remaining_time": "0:48:18", "throughput": "0.00", "total_tokens": 0}
|
132 |
+
{"current_steps": 264, "total_steps": 408, "loss": 0.0459, "accuracy": 1.0, "learning_rate": 1.6706962450503408e-06, "epoch": 1.9376146788990827, "percentage": 64.71, "elapsed_time": "1:27:17", "remaining_time": "0:47:37", "throughput": "0.00", "total_tokens": 0}
|
133 |
+
{"current_steps": 266, "total_steps": 408, "loss": 0.061, "accuracy": 1.0, "learning_rate": 1.630442267479034e-06, "epoch": 1.9522935779816515, "percentage": 65.2, "elapsed_time": "1:27:58", "remaining_time": "0:46:58", "throughput": "0.00", "total_tokens": 0}
|
134 |
+
{"current_steps": 268, "total_steps": 408, "loss": 0.0583, "accuracy": 1.0, "learning_rate": 1.5904431579726837e-06, "epoch": 1.9669724770642203, "percentage": 65.69, "elapsed_time": "1:28:34", "remaining_time": "0:46:16", "throughput": "0.00", "total_tokens": 0}
|
135 |
+
{"current_steps": 270, "total_steps": 408, "loss": 0.074, "accuracy": 1.0, "learning_rate": 1.5507106403021897e-06, "epoch": 1.981651376146789, "percentage": 66.18, "elapsed_time": "1:29:13", "remaining_time": "0:45:36", "throughput": "0.00", "total_tokens": 0}
|
136 |
+
{"current_steps": 272, "total_steps": 408, "loss": 0.0755, "accuracy": 0.984375, "learning_rate": 1.511256360100171e-06, "epoch": 1.996330275229358, "percentage": 66.67, "elapsed_time": "1:29:47", "remaining_time": "0:44:53", "throughput": "0.00", "total_tokens": 0}
|
137 |
+
{"current_steps": 274, "total_steps": 408, "loss": 0.0833, "accuracy": 0.96875, "learning_rate": 1.4720918814476234e-06, "epoch": 2.0110091743119267, "percentage": 67.16, "elapsed_time": "1:30:32", "remaining_time": "0:44:16", "throughput": "0.00", "total_tokens": 0}
|
138 |
+
{"current_steps": 276, "total_steps": 408, "loss": 0.0923, "accuracy": 0.984375, "learning_rate": 1.4332286834844792e-06, "epoch": 2.0256880733944955, "percentage": 67.65, "elapsed_time": "1:31:21", "remaining_time": "0:43:41", "throughput": "0.00", "total_tokens": 0}
|
139 |
+
{"current_steps": 278, "total_steps": 408, "loss": 0.0472, "accuracy": 1.0, "learning_rate": 1.3946781570450563e-06, "epoch": 2.0403669724770643, "percentage": 68.14, "elapsed_time": "1:32:06", "remaining_time": "0:43:04", "throughput": "0.00", "total_tokens": 0}
|
140 |
+
{"current_steps": 280, "total_steps": 408, "loss": 0.0461, "accuracy": 1.0, "learning_rate": 1.3564516013194023e-06, "epoch": 2.055045871559633, "percentage": 68.63, "elapsed_time": "1:32:37", "remaining_time": "0:42:20", "throughput": "0.00", "total_tokens": 0}
|
141 |
+
{"current_steps": 282, "total_steps": 408, "loss": 0.0774, "accuracy": 0.984375, "learning_rate": 1.3185602205414894e-06, "epoch": 2.069724770642202, "percentage": 69.12, "elapsed_time": "1:33:19", "remaining_time": "0:41:41", "throughput": "0.00", "total_tokens": 0}
|
142 |
+
{"current_steps": 284, "total_steps": 408, "loss": 0.0692, "accuracy": 1.0, "learning_rate": 1.2810151207052465e-06, "epoch": 2.0844036697247708, "percentage": 69.61, "elapsed_time": "1:34:11", "remaining_time": "0:41:07", "throughput": "0.00", "total_tokens": 0}
|
143 |
+
{"current_steps": 286, "total_steps": 408, "loss": 0.0851, "accuracy": 0.96875, "learning_rate": 1.2438273063093811e-06, "epoch": 2.0990825688073396, "percentage": 70.1, "elapsed_time": "1:34:44", "remaining_time": "0:40:24", "throughput": "0.00", "total_tokens": 0}
|
144 |
+
{"current_steps": 288, "total_steps": 408, "loss": 0.1044, "accuracy": 0.984375, "learning_rate": 1.2070076771319536e-06, "epoch": 2.1137614678899084, "percentage": 70.59, "elapsed_time": "1:35:35", "remaining_time": "0:39:49", "throughput": "0.00", "total_tokens": 0}
|
145 |
+
{"current_steps": 290, "total_steps": 408, "loss": 0.0566, "accuracy": 1.0, "learning_rate": 1.1705670250356417e-06, "epoch": 2.128440366972477, "percentage": 71.08, "elapsed_time": "1:36:13", "remaining_time": "0:39:09", "throughput": "0.00", "total_tokens": 0}
|
146 |
+
{"current_steps": 292, "total_steps": 408, "loss": 0.0635, "accuracy": 0.984375, "learning_rate": 1.1345160308046413e-06, "epoch": 2.143119266055046, "percentage": 71.57, "elapsed_time": "1:36:54", "remaining_time": "0:38:30", "throughput": "0.00", "total_tokens": 0}
|
147 |
+
{"current_steps": 294, "total_steps": 408, "loss": 0.06, "accuracy": 1.0, "learning_rate": 1.0988652610141154e-06, "epoch": 2.157798165137615, "percentage": 72.06, "elapsed_time": "1:37:28", "remaining_time": "0:37:47", "throughput": "0.00", "total_tokens": 0}
|
148 |
+
{"current_steps": 296, "total_steps": 408, "loss": 0.0498, "accuracy": 0.984375, "learning_rate": 1.063625164933124e-06, "epoch": 2.1724770642201836, "percentage": 72.55, "elapsed_time": "1:38:05", "remaining_time": "0:37:07", "throughput": "0.00", "total_tokens": 0}
|
149 |
+
{"current_steps": 298, "total_steps": 408, "loss": 0.0694, "accuracy": 1.0, "learning_rate": 1.0288060714619359e-06, "epoch": 2.1871559633027524, "percentage": 73.04, "elapsed_time": "1:38:50", "remaining_time": "0:36:29", "throughput": "0.00", "total_tokens": 0}
|
150 |
+
{"current_steps": 300, "total_steps": 408, "loss": 0.1021, "accuracy": 0.984375, "learning_rate": 9.944181861046188e-07, "epoch": 2.2018348623853212, "percentage": 73.53, "elapsed_time": "1:39:26", "remaining_time": "0:35:47", "throughput": "0.00", "total_tokens": 0}
|
151 |
+
{"current_steps": 302, "total_steps": 408, "loss": 0.076, "accuracy": 1.0, "learning_rate": 9.604715879777986e-07, "epoch": 2.21651376146789, "percentage": 74.02, "elapsed_time": "1:40:01", "remaining_time": "0:35:06", "throughput": "0.00", "total_tokens": 0}
|
152 |
+
{"current_steps": 304, "total_steps": 408, "loss": 0.0652, "accuracy": 1.0, "learning_rate": 9.269762268564616e-07, "epoch": 2.231192660550459, "percentage": 74.51, "elapsed_time": "1:40:44", "remaining_time": "0:34:27", "throughput": "0.00", "total_tokens": 0}
|
153 |
+
{"current_steps": 306, "total_steps": 408, "loss": 0.0903, "accuracy": 1.0, "learning_rate": 8.939419202576694e-07, "epoch": 2.2458715596330276, "percentage": 75.0, "elapsed_time": "1:41:14", "remaining_time": "0:33:44", "throughput": "0.00", "total_tokens": 0}
|
154 |
+
{"current_steps": 308, "total_steps": 408, "loss": 0.0611, "accuracy": 1.0, "learning_rate": 8.61378350563033e-07, "epoch": 2.2605504587155965, "percentage": 75.49, "elapsed_time": "1:41:47", "remaining_time": "0:33:02", "throughput": "0.00", "total_tokens": 0}
|
155 |
+
{"current_steps": 310, "total_steps": 408, "loss": 0.0573, "accuracy": 1.0, "learning_rate": 8.292950621808022e-07, "epoch": 2.2752293577981653, "percentage": 75.98, "elapsed_time": "1:42:21", "remaining_time": "0:32:21", "throughput": "0.00", "total_tokens": 0}
|
156 |
+
{"current_steps": 312, "total_steps": 408, "loss": 0.0607, "accuracy": 0.984375, "learning_rate": 7.977014587483925e-07, "epoch": 2.289908256880734, "percentage": 76.47, "elapsed_time": "1:43:11", "remaining_time": "0:31:45", "throughput": "0.00", "total_tokens": 0}
|
157 |
+
{"current_steps": 314, "total_steps": 408, "loss": 0.06, "accuracy": 0.984375, "learning_rate": 7.666068003761684e-07, "epoch": 2.304587155963303, "percentage": 76.96, "elapsed_time": "1:43:49", "remaining_time": "0:31:04", "throughput": "0.00", "total_tokens": 0}
|
158 |
+
{"current_steps": 316, "total_steps": 408, "loss": 0.0489, "accuracy": 1.0, "learning_rate": 7.360202009332993e-07, "epoch": 2.3192660550458717, "percentage": 77.45, "elapsed_time": "1:44:28", "remaining_time": "0:30:25", "throughput": "0.00", "total_tokens": 0}
|
159 |
+
{"current_steps": 318, "total_steps": 408, "loss": 0.0501, "accuracy": 1.0, "learning_rate": 7.059506253764773e-07, "epoch": 2.3339449541284405, "percentage": 77.94, "elapsed_time": "1:45:08", "remaining_time": "0:29:45", "throughput": "0.00", "total_tokens": 0}
|
160 |
+
{"current_steps": 320, "total_steps": 408, "loss": 0.0592, "accuracy": 1.0, "learning_rate": 6.764068871222825e-07, "epoch": 2.3486238532110093, "percentage": 78.43, "elapsed_time": "1:45:46", "remaining_time": "0:29:05", "throughput": "0.00", "total_tokens": 0}
|
161 |
+
{"current_steps": 322, "total_steps": 408, "loss": 0.055, "accuracy": 1.0, "learning_rate": 6.473976454639608e-07, "epoch": 2.363302752293578, "percentage": 78.92, "elapsed_time": "1:46:22", "remaining_time": "0:28:24", "throughput": "0.00", "total_tokens": 0}
|
162 |
+
{"current_steps": 324, "total_steps": 408, "loss": 0.0458, "accuracy": 1.0, "learning_rate": 6.189314030333796e-07, "epoch": 2.377981651376147, "percentage": 79.41, "elapsed_time": "1:46:58", "remaining_time": "0:27:44", "throughput": "0.00", "total_tokens": 0}
|
163 |
+
{"current_steps": 326, "total_steps": 408, "loss": 0.058, "accuracy": 0.984375, "learning_rate": 5.910165033089e-07, "epoch": 2.3926605504587157, "percentage": 79.9, "elapsed_time": "1:47:38", "remaining_time": "0:27:04", "throughput": "0.00", "total_tokens": 0}
|
164 |
+
{"current_steps": 328, "total_steps": 408, "loss": 0.055, "accuracy": 1.0, "learning_rate": 5.636611281698956e-07, "epoch": 2.4073394495412845, "percentage": 80.39, "elapsed_time": "1:48:17", "remaining_time": "0:26:24", "throughput": "0.00", "total_tokens": 0}
|
165 |
+
{"current_steps": 330, "total_steps": 408, "loss": 0.0729, "accuracy": 1.0, "learning_rate": 5.368732954986389e-07, "epoch": 2.4220183486238533, "percentage": 80.88, "elapsed_time": "1:49:11", "remaining_time": "0:25:48", "throughput": "0.00", "total_tokens": 0}
|
166 |
+
{"current_steps": 332, "total_steps": 408, "loss": 0.0686, "accuracy": 0.984375, "learning_rate": 5.106608568302504e-07, "epoch": 2.436697247706422, "percentage": 81.37, "elapsed_time": "1:49:55", "remaining_time": "0:25:09", "throughput": "0.00", "total_tokens": 0}
|
167 |
+
{"current_steps": 334, "total_steps": 408, "loss": 0.0605, "accuracy": 0.984375, "learning_rate": 4.850314950514124e-07, "epoch": 2.451376146788991, "percentage": 81.86, "elapsed_time": "1:50:26", "remaining_time": "0:24:28", "throughput": "0.00", "total_tokens": 0}
|
168 |
+
{"current_steps": 336, "total_steps": 408, "loss": 0.0726, "accuracy": 0.984375, "learning_rate": 4.599927221485034e-07, "epoch": 2.4660550458715598, "percentage": 82.35, "elapsed_time": "1:51:06", "remaining_time": "0:23:48", "throughput": "0.00", "total_tokens": 0}
|
169 |
+
{"current_steps": 338, "total_steps": 408, "loss": 0.0352, "accuracy": 1.0, "learning_rate": 4.3555187700583175e-07, "epoch": 2.4807339449541286, "percentage": 82.84, "elapsed_time": "1:51:45", "remaining_time": "0:23:08", "throughput": "0.00", "total_tokens": 0}
|
170 |
+
{"current_steps": 340, "total_steps": 408, "loss": 0.0792, "accuracy": 0.984375, "learning_rate": 4.1171612325460244e-07, "epoch": 2.4954128440366974, "percentage": 83.33, "elapsed_time": "1:52:26", "remaining_time": "0:22:29", "throughput": "0.00", "total_tokens": 0}
|
171 |
+
{"current_steps": 342, "total_steps": 408, "loss": 0.049, "accuracy": 1.0, "learning_rate": 3.8849244717325206e-07, "epoch": 2.510091743119266, "percentage": 83.82, "elapsed_time": "1:53:08", "remaining_time": "0:21:50", "throughput": "0.00", "total_tokens": 0}
|
172 |
+
{"current_steps": 344, "total_steps": 408, "loss": 0.0831, "accuracy": 0.96875, "learning_rate": 3.658876556397628e-07, "epoch": 2.524770642201835, "percentage": 84.31, "elapsed_time": "1:53:50", "remaining_time": "0:21:10", "throughput": "0.00", "total_tokens": 0}
|
173 |
+
{"current_steps": 346, "total_steps": 408, "loss": 0.0622, "accuracy": 1.0, "learning_rate": 3.4390837413656256e-07, "epoch": 2.539449541284404, "percentage": 84.8, "elapsed_time": "1:54:31", "remaining_time": "0:20:31", "throughput": "0.00", "total_tokens": 0}
|
174 |
+
{"current_steps": 348, "total_steps": 408, "loss": 0.08, "accuracy": 0.953125, "learning_rate": 3.225610448085903e-07, "epoch": 2.5541284403669726, "percentage": 85.29, "elapsed_time": "1:55:06", "remaining_time": "0:19:50", "throughput": "0.00", "total_tokens": 0}
|
175 |
+
{"current_steps": 350, "total_steps": 408, "loss": 0.0602, "accuracy": 1.0, "learning_rate": 3.018519245750989e-07, "epoch": 2.5688073394495414, "percentage": 85.78, "elapsed_time": "1:55:43", "remaining_time": "0:19:10", "throughput": "0.00", "total_tokens": 0}
|
176 |
+
{"current_steps": 352, "total_steps": 408, "loss": 0.0814, "accuracy": 1.0, "learning_rate": 2.817870832957459e-07, "epoch": 2.5834862385321102, "percentage": 86.27, "elapsed_time": "1:56:13", "remaining_time": "0:18:29", "throughput": "0.00", "total_tokens": 0}
|
177 |
+
{"current_steps": 354, "total_steps": 408, "loss": 0.0855, "accuracy": 0.984375, "learning_rate": 2.6237240199151386e-07, "epoch": 2.598165137614679, "percentage": 86.76, "elapsed_time": "1:56:59", "remaining_time": "0:17:50", "throughput": "0.00", "total_tokens": 0}
|
178 |
+
{"current_steps": 356, "total_steps": 408, "loss": 0.0888, "accuracy": 0.984375, "learning_rate": 2.436135711209786e-07, "epoch": 2.612844036697248, "percentage": 87.25, "elapsed_time": "1:57:47", "remaining_time": "0:17:12", "throughput": "0.00", "total_tokens": 0}
|
179 |
+
{"current_steps": 358, "total_steps": 408, "loss": 0.064, "accuracy": 1.0, "learning_rate": 2.2551608891243026e-07, "epoch": 2.6275229357798167, "percentage": 87.75, "elapsed_time": "1:58:31", "remaining_time": "0:16:33", "throughput": "0.00", "total_tokens": 0}
|
180 |
+
{"current_steps": 360, "total_steps": 408, "loss": 0.0537, "accuracy": 1.0, "learning_rate": 2.0808525975233807e-07, "epoch": 2.6422018348623855, "percentage": 88.24, "elapsed_time": "1:59:05", "remaining_time": "0:15:52", "throughput": "0.00", "total_tokens": 0}
|
181 |
+
{"current_steps": 362, "total_steps": 408, "loss": 0.0568, "accuracy": 1.0, "learning_rate": 1.9132619263063144e-07, "epoch": 2.6568807339449543, "percentage": 88.73, "elapsed_time": "1:59:50", "remaining_time": "0:15:13", "throughput": "0.00", "total_tokens": 0}
|
182 |
+
{"current_steps": 364, "total_steps": 408, "loss": 0.0737, "accuracy": 0.96875, "learning_rate": 1.7524379964325155e-07, "epoch": 2.671559633027523, "percentage": 89.22, "elapsed_time": "2:00:30", "remaining_time": "0:14:34", "throughput": "0.00", "total_tokens": 0}
|
183 |
+
{"current_steps": 366, "total_steps": 408, "loss": 0.0408, "accuracy": 1.0, "learning_rate": 1.5984279455240975e-07, "epoch": 2.686238532110092, "percentage": 89.71, "elapsed_time": "2:01:10", "remaining_time": "0:13:54", "throughput": "0.00", "total_tokens": 0}
|
184 |
+
{"current_steps": 368, "total_steps": 408, "loss": 0.0514, "accuracy": 1.0, "learning_rate": 1.451276914049818e-07, "epoch": 2.7009174311926607, "percentage": 90.2, "elapsed_time": "2:01:47", "remaining_time": "0:13:14", "throughput": "0.00", "total_tokens": 0}
|
185 |
+
{"current_steps": 370, "total_steps": 408, "loss": 0.045, "accuracy": 1.0, "learning_rate": 1.3110280320943692e-07, "epoch": 2.7155963302752295, "percentage": 90.69, "elapsed_time": "2:02:23", "remaining_time": "0:12:34", "throughput": "0.00", "total_tokens": 0}
|
186 |
+
{"current_steps": 372, "total_steps": 408, "loss": 0.0493, "accuracy": 1.0, "learning_rate": 1.1777224067169218e-07, "epoch": 2.7302752293577983, "percentage": 91.18, "elapsed_time": "2:03:02", "remaining_time": "0:11:54", "throughput": "0.00", "total_tokens": 0}
|
187 |
+
{"current_steps": 374, "total_steps": 408, "loss": 0.0739, "accuracy": 0.984375, "learning_rate": 1.0513991099025872e-07, "epoch": 2.744954128440367, "percentage": 91.67, "elapsed_time": "2:03:46", "remaining_time": "0:11:15", "throughput": "0.00", "total_tokens": 0}
|
188 |
+
{"current_steps": 376, "total_steps": 408, "loss": 0.0622, "accuracy": 1.0, "learning_rate": 9.320951671104194e-08, "epoch": 2.759633027522936, "percentage": 92.16, "elapsed_time": "2:04:27", "remaining_time": "0:10:35", "throughput": "0.00", "total_tokens": 0}
|
189 |
+
{"current_steps": 378, "total_steps": 408, "loss": 0.0447, "accuracy": 1.0, "learning_rate": 8.198455464212108e-08, "epoch": 2.7743119266055047, "percentage": 92.65, "elapsed_time": "2:05:05", "remaining_time": "0:09:55", "throughput": "0.00", "total_tokens": 0}
|
190 |
+
{"current_steps": 380, "total_steps": 408, "loss": 0.0673, "accuracy": 0.96875, "learning_rate": 7.146831482883115e-08, "epoch": 2.7889908256880735, "percentage": 93.14, "elapsed_time": "2:05:38", "remaining_time": "0:09:15", "throughput": "0.00", "total_tokens": 0}
|
191 |
+
{"current_steps": 382, "total_steps": 408, "loss": 0.0655, "accuracy": 1.0, "learning_rate": 6.16638795894492e-08, "epoch": 2.8036697247706424, "percentage": 93.63, "elapsed_time": "2:06:11", "remaining_time": "0:08:35", "throughput": "0.00", "total_tokens": 0}
|
192 |
+
{"current_steps": 384, "total_steps": 408, "loss": 0.0516, "accuracy": 1.0, "learning_rate": 5.257412261176375e-08, "epoch": 2.818348623853211, "percentage": 94.12, "elapsed_time": "2:06:58", "remaining_time": "0:07:56", "throughput": "0.00", "total_tokens": 0}
|
193 |
+
{"current_steps": 386, "total_steps": 408, "loss": 0.0643, "accuracy": 1.0, "learning_rate": 4.4201708110795384e-08, "epoch": 2.83302752293578, "percentage": 94.61, "elapsed_time": "2:07:32", "remaining_time": "0:07:16", "throughput": "0.00", "total_tokens": 0}
|
194 |
+
{"current_steps": 388, "total_steps": 408, "loss": 0.0604, "accuracy": 0.984375, "learning_rate": 3.654909004791152e-08, "epoch": 2.847706422018349, "percentage": 95.1, "elapsed_time": "2:08:15", "remaining_time": "0:06:36", "throughput": "0.00", "total_tokens": 0}
|
195 |
+
{"current_steps": 390, "total_steps": 408, "loss": 0.0692, "accuracy": 0.984375, "learning_rate": 2.9618511411570462e-08, "epoch": 2.8623853211009176, "percentage": 95.59, "elapsed_time": "2:08:46", "remaining_time": "0:05:56", "throughput": "0.00", "total_tokens": 0}
|
196 |
+
{"current_steps": 392, "total_steps": 408, "loss": 0.0697, "accuracy": 0.984375, "learning_rate": 2.3412003559898088e-08, "epoch": 2.8770642201834864, "percentage": 96.08, "elapsed_time": "2:09:22", "remaining_time": "0:05:16", "throughput": "0.00", "total_tokens": 0}
|
197 |
+
{"current_steps": 394, "total_steps": 408, "loss": 0.0654, "accuracy": 0.984375, "learning_rate": 1.793138562529634e-08, "epoch": 2.891743119266055, "percentage": 96.57, "elapsed_time": "2:10:07", "remaining_time": "0:04:37", "throughput": "0.00", "total_tokens": 0}
|
198 |
+
{"current_steps": 396, "total_steps": 408, "loss": 0.0492, "accuracy": 1.0, "learning_rate": 1.317826398125277e-08, "epoch": 2.906422018348624, "percentage": 97.06, "elapsed_time": "2:11:04", "remaining_time": "0:03:58", "throughput": "0.00", "total_tokens": 0}
|
199 |
+
{"current_steps": 398, "total_steps": 408, "loss": 0.0367, "accuracy": 1.0, "learning_rate": 9.15403177151275e-09, "epoch": 2.921100917431193, "percentage": 97.55, "elapsed_time": "2:11:45", "remaining_time": "0:03:18", "throughput": "0.00", "total_tokens": 0}
|
200 |
+
{"current_steps": 400, "total_steps": 408, "loss": 0.0519, "accuracy": 1.0, "learning_rate": 5.85986850174608e-09, "epoch": 2.9357798165137616, "percentage": 98.04, "elapsed_time": "2:12:19", "remaining_time": "0:02:38", "throughput": "0.00", "total_tokens": 0}
|
201 |
+
{"current_steps": 402, "total_steps": 408, "loss": 0.0999, "accuracy": 0.96875, "learning_rate": 3.296739693834927e-09, "epoch": 2.9504587155963304, "percentage": 98.53, "elapsed_time": "2:12:55", "remaining_time": "0:01:59", "throughput": "0.00", "total_tokens": 0}
|
202 |
+
{"current_steps": 404, "total_steps": 408, "loss": 0.0371, "accuracy": 1.0, "learning_rate": 1.4653966028774225e-09, "epoch": 2.9651376146788992, "percentage": 99.02, "elapsed_time": "2:13:28", "remaining_time": "0:01:19", "throughput": "0.00", "total_tokens": 0}
|
203 |
+
{"current_steps": 406, "total_steps": 408, "loss": 0.0817, "accuracy": 1.0, "learning_rate": 3.6637599699351766e-10, "epoch": 2.979816513761468, "percentage": 99.51, "elapsed_time": "2:14:08", "remaining_time": "0:00:39", "throughput": "0.00", "total_tokens": 0}
|
204 |
+
{"current_steps": 408, "total_steps": 408, "loss": 0.065, "accuracy": 0.96875, "learning_rate": 0.0, "epoch": 2.994495412844037, "percentage": 100.0, "elapsed_time": "2:14:50", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
|
205 |
+
{"current_steps": 408, "total_steps": 408, "epoch": 2.994495412844037, "percentage": 100.0, "elapsed_time": "2:14:50", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2eb2a8d501dfc58c7f772ba73a12ab3104de6550a30558daf77dc6c9e67f23b1
|
3 |
+
size 5240
|
training_loss.png
ADDED
![]() |
training_rewards_accuracies.png
ADDED
![]() |
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|