Serega6678
commited on
Commit
•
acd72fd
1
Parent(s):
6da339a
Model save
Browse files- README.md +66 -0
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +3 -0
- all_results.json +13 -0
- eval_results.json +8 -0
- mm_projector.bin +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +51 -0
- train_results.json +8 -0
- trainer_state.json +1130 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: mistralai/Mistral-7B-v0.1
|
7 |
+
datasets:
|
8 |
+
- generator
|
9 |
+
model-index:
|
10 |
+
- name: prototype_joint_trained
|
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 |
+
# prototype_joint_trained
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.0049
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 2e-05
|
41 |
+
- train_batch_size: 32
|
42 |
+
- eval_batch_size: 8
|
43 |
+
- seed: 42
|
44 |
+
- distributed_type: multi-GPU
|
45 |
+
- num_devices: 2
|
46 |
+
- total_train_batch_size: 64
|
47 |
+
- total_eval_batch_size: 16
|
48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: cosine
|
50 |
+
- lr_scheduler_warmup_ratio: 0.1
|
51 |
+
- num_epochs: 1
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
57 |
+
| 1.014 | 1.0 | 907 | 1.0049 |
|
58 |
+
|
59 |
+
|
60 |
+
### Framework versions
|
61 |
+
|
62 |
+
- PEFT 0.7.1
|
63 |
+
- Transformers 4.36.2
|
64 |
+
- Pytorch 2.1.0+cu118
|
65 |
+
- Datasets 2.14.6
|
66 |
+
- Tokenizers 0.15.2
|
adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
|
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": 16,
|
13 |
+
"lora_dropout": 0.05,
|
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 |
+
"down_proj",
|
23 |
+
"k_proj",
|
24 |
+
"q_proj",
|
25 |
+
"o_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"v_proj",
|
28 |
+
"up_proj"
|
29 |
+
],
|
30 |
+
"task_type": "CAUSAL_LM"
|
31 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc14609ca315b97b3758c29270849a5256adaaa461c05d5ea55a750a9b49334a
|
3 |
+
size 83946192
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<EMBEDDING>": 32000
|
3 |
+
}
|
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_loss": 1.004878044128418,
|
4 |
+
"eval_runtime": 471.0388,
|
5 |
+
"eval_samples": 6440,
|
6 |
+
"eval_samples_per_second": 13.672,
|
7 |
+
"eval_steps_per_second": 0.856,
|
8 |
+
"train_loss": 1.0006486285219118,
|
9 |
+
"train_runtime": 14584.0452,
|
10 |
+
"train_samples": 58034,
|
11 |
+
"train_samples_per_second": 3.979,
|
12 |
+
"train_steps_per_second": 0.062
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_loss": 1.004878044128418,
|
4 |
+
"eval_runtime": 471.0388,
|
5 |
+
"eval_samples": 6440,
|
6 |
+
"eval_samples_per_second": 13.672,
|
7 |
+
"eval_steps_per_second": 0.856
|
8 |
+
}
|
mm_projector.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d54411c2d3d50d0c12264a2beae97b294062e3d6e94c3c5a348322592750450
|
3 |
+
size 16795126
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<EMBEDDING>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"additional_special_tokens": [],
|
39 |
+
"bos_token": "<s>",
|
40 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
41 |
+
"clean_up_tokenization_spaces": false,
|
42 |
+
"eos_token": "</s>",
|
43 |
+
"legacy": true,
|
44 |
+
"model_max_length": 2048,
|
45 |
+
"pad_token": "</s>",
|
46 |
+
"sp_model_kwargs": {},
|
47 |
+
"spaces_between_special_tokens": false,
|
48 |
+
"tokenizer_class": "LlamaTokenizer",
|
49 |
+
"unk_token": "<unk>",
|
50 |
+
"use_default_system_prompt": false
|
51 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 1.0006486285219118,
|
4 |
+
"train_runtime": 14584.0452,
|
5 |
+
"train_samples": 58034,
|
6 |
+
"train_samples_per_second": 3.979,
|
7 |
+
"train_steps_per_second": 0.062
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 907,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 2.197802197802198e-07,
|
14 |
+
"loss": 0.998,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.01,
|
19 |
+
"learning_rate": 1.098901098901099e-06,
|
20 |
+
"loss": 1.0162,
|
21 |
+
"step": 5
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.01,
|
25 |
+
"learning_rate": 2.197802197802198e-06,
|
26 |
+
"loss": 0.9881,
|
27 |
+
"step": 10
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.02,
|
31 |
+
"learning_rate": 3.2967032967032968e-06,
|
32 |
+
"loss": 1.0192,
|
33 |
+
"step": 15
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.02,
|
37 |
+
"learning_rate": 4.395604395604396e-06,
|
38 |
+
"loss": 1.0097,
|
39 |
+
"step": 20
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.03,
|
43 |
+
"learning_rate": 5.494505494505495e-06,
|
44 |
+
"loss": 1.0106,
|
45 |
+
"step": 25
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.03,
|
49 |
+
"learning_rate": 6.5934065934065935e-06,
|
50 |
+
"loss": 1.0132,
|
51 |
+
"step": 30
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.04,
|
55 |
+
"learning_rate": 7.692307692307694e-06,
|
56 |
+
"loss": 0.9951,
|
57 |
+
"step": 35
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.04,
|
61 |
+
"learning_rate": 8.791208791208792e-06,
|
62 |
+
"loss": 1.0027,
|
63 |
+
"step": 40
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.05,
|
67 |
+
"learning_rate": 9.890109890109892e-06,
|
68 |
+
"loss": 1.0178,
|
69 |
+
"step": 45
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.06,
|
73 |
+
"learning_rate": 1.098901098901099e-05,
|
74 |
+
"loss": 1.0272,
|
75 |
+
"step": 50
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.06,
|
79 |
+
"learning_rate": 1.2087912087912089e-05,
|
80 |
+
"loss": 1.0013,
|
81 |
+
"step": 55
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.07,
|
85 |
+
"learning_rate": 1.3186813186813187e-05,
|
86 |
+
"loss": 1.0244,
|
87 |
+
"step": 60
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.07,
|
91 |
+
"learning_rate": 1.4285714285714287e-05,
|
92 |
+
"loss": 1.0224,
|
93 |
+
"step": 65
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.08,
|
97 |
+
"learning_rate": 1.5384615384615387e-05,
|
98 |
+
"loss": 1.0138,
|
99 |
+
"step": 70
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.08,
|
103 |
+
"learning_rate": 1.6483516483516486e-05,
|
104 |
+
"loss": 1.0,
|
105 |
+
"step": 75
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.09,
|
109 |
+
"learning_rate": 1.7582417582417584e-05,
|
110 |
+
"loss": 1.0053,
|
111 |
+
"step": 80
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.09,
|
115 |
+
"learning_rate": 1.8681318681318682e-05,
|
116 |
+
"loss": 0.9828,
|
117 |
+
"step": 85
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.1,
|
121 |
+
"learning_rate": 1.9780219780219784e-05,
|
122 |
+
"loss": 1.0125,
|
123 |
+
"step": 90
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.1,
|
127 |
+
"learning_rate": 1.999881422898077e-05,
|
128 |
+
"loss": 0.9976,
|
129 |
+
"step": 95
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.11,
|
133 |
+
"learning_rate": 1.999399751616869e-05,
|
134 |
+
"loss": 1.0147,
|
135 |
+
"step": 100
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.12,
|
139 |
+
"learning_rate": 1.9985477534331582e-05,
|
140 |
+
"loss": 0.9959,
|
141 |
+
"step": 105
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.12,
|
145 |
+
"learning_rate": 1.9973257440542974e-05,
|
146 |
+
"loss": 0.9702,
|
147 |
+
"step": 110
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.13,
|
151 |
+
"learning_rate": 1.9957341762950346e-05,
|
152 |
+
"loss": 0.996,
|
153 |
+
"step": 115
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.13,
|
157 |
+
"learning_rate": 1.9937736399097282e-05,
|
158 |
+
"loss": 1.0323,
|
159 |
+
"step": 120
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.14,
|
163 |
+
"learning_rate": 1.9914448613738107e-05,
|
164 |
+
"loss": 0.9941,
|
165 |
+
"step": 125
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.14,
|
169 |
+
"learning_rate": 1.9887487036145942e-05,
|
170 |
+
"loss": 0.9852,
|
171 |
+
"step": 130
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.15,
|
175 |
+
"learning_rate": 1.985686165691514e-05,
|
176 |
+
"loss": 1.0073,
|
177 |
+
"step": 135
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.15,
|
181 |
+
"learning_rate": 1.9822583824259283e-05,
|
182 |
+
"loss": 1.0148,
|
183 |
+
"step": 140
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.16,
|
187 |
+
"learning_rate": 1.978466623980609e-05,
|
188 |
+
"loss": 0.9903,
|
189 |
+
"step": 145
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.17,
|
193 |
+
"learning_rate": 1.9743122953890857e-05,
|
194 |
+
"loss": 1.0055,
|
195 |
+
"step": 150
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.17,
|
199 |
+
"learning_rate": 1.9697969360350098e-05,
|
200 |
+
"loss": 0.9805,
|
201 |
+
"step": 155
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.18,
|
205 |
+
"learning_rate": 1.9649222190817382e-05,
|
206 |
+
"loss": 1.0283,
|
207 |
+
"step": 160
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.18,
|
211 |
+
"learning_rate": 1.9596899508523432e-05,
|
212 |
+
"loss": 1.0133,
|
213 |
+
"step": 165
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.19,
|
217 |
+
"learning_rate": 1.9541020701602814e-05,
|
218 |
+
"loss": 0.9921,
|
219 |
+
"step": 170
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.19,
|
223 |
+
"learning_rate": 1.948160647590966e-05,
|
224 |
+
"loss": 1.0006,
|
225 |
+
"step": 175
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.2,
|
229 |
+
"learning_rate": 1.941867884734515e-05,
|
230 |
+
"loss": 0.9872,
|
231 |
+
"step": 180
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.2,
|
235 |
+
"learning_rate": 1.9352261133699513e-05,
|
236 |
+
"loss": 1.0126,
|
237 |
+
"step": 185
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.21,
|
241 |
+
"learning_rate": 1.928237794601165e-05,
|
242 |
+
"loss": 1.0073,
|
243 |
+
"step": 190
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.21,
|
247 |
+
"learning_rate": 1.920905517944954e-05,
|
248 |
+
"loss": 1.0,
|
249 |
+
"step": 195
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.22,
|
253 |
+
"learning_rate": 1.9132320003714756e-05,
|
254 |
+
"loss": 1.0282,
|
255 |
+
"step": 200
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.23,
|
259 |
+
"learning_rate": 1.905220085297482e-05,
|
260 |
+
"loss": 1.0059,
|
261 |
+
"step": 205
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.23,
|
265 |
+
"learning_rate": 1.8968727415326885e-05,
|
266 |
+
"loss": 0.9929,
|
267 |
+
"step": 210
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.24,
|
271 |
+
"learning_rate": 1.888193062179685e-05,
|
272 |
+
"loss": 1.0006,
|
273 |
+
"step": 215
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.24,
|
277 |
+
"learning_rate": 1.87918426348779e-05,
|
278 |
+
"loss": 1.0212,
|
279 |
+
"step": 220
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.25,
|
283 |
+
"learning_rate": 1.8698496836612693e-05,
|
284 |
+
"loss": 1.0126,
|
285 |
+
"step": 225
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.25,
|
289 |
+
"learning_rate": 1.86019278162237e-05,
|
290 |
+
"loss": 0.9942,
|
291 |
+
"step": 230
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.26,
|
295 |
+
"learning_rate": 1.8502171357296144e-05,
|
296 |
+
"loss": 1.0087,
|
297 |
+
"step": 235
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.26,
|
301 |
+
"learning_rate": 1.8399264424518466e-05,
|
302 |
+
"loss": 0.9935,
|
303 |
+
"step": 240
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.27,
|
307 |
+
"learning_rate": 1.8293245149985055e-05,
|
308 |
+
"loss": 0.9924,
|
309 |
+
"step": 245
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.28,
|
313 |
+
"learning_rate": 1.8184152819066437e-05,
|
314 |
+
"loss": 0.9907,
|
315 |
+
"step": 250
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.28,
|
319 |
+
"learning_rate": 1.8072027855852098e-05,
|
320 |
+
"loss": 1.0176,
|
321 |
+
"step": 255
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.29,
|
325 |
+
"learning_rate": 1.7956911808171375e-05,
|
326 |
+
"loss": 0.9896,
|
327 |
+
"step": 260
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.29,
|
331 |
+
"learning_rate": 1.783884733219794e-05,
|
332 |
+
"loss": 1.0203,
|
333 |
+
"step": 265
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.3,
|
337 |
+
"learning_rate": 1.7717878176643563e-05,
|
338 |
+
"loss": 0.983,
|
339 |
+
"step": 270
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.3,
|
343 |
+
"learning_rate": 1.7594049166547073e-05,
|
344 |
+
"loss": 1.0278,
|
345 |
+
"step": 275
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.31,
|
349 |
+
"learning_rate": 1.7467406186664474e-05,
|
350 |
+
"loss": 1.0015,
|
351 |
+
"step": 280
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.31,
|
355 |
+
"learning_rate": 1.7337996164466373e-05,
|
356 |
+
"loss": 1.0147,
|
357 |
+
"step": 285
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.32,
|
361 |
+
"learning_rate": 1.7205867052749025e-05,
|
362 |
+
"loss": 0.989,
|
363 |
+
"step": 290
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.33,
|
367 |
+
"learning_rate": 1.7071067811865477e-05,
|
368 |
+
"loss": 0.9706,
|
369 |
+
"step": 295
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.33,
|
373 |
+
"learning_rate": 1.693364839158333e-05,
|
374 |
+
"loss": 0.9683,
|
375 |
+
"step": 300
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.34,
|
379 |
+
"learning_rate": 1.67936597125759e-05,
|
380 |
+
"loss": 0.9861,
|
381 |
+
"step": 305
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.34,
|
385 |
+
"learning_rate": 1.665115364755357e-05,
|
386 |
+
"loss": 1.0121,
|
387 |
+
"step": 310
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.35,
|
391 |
+
"learning_rate": 1.650618300204242e-05,
|
392 |
+
"loss": 1.0203,
|
393 |
+
"step": 315
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.35,
|
397 |
+
"learning_rate": 1.6358801494817172e-05,
|
398 |
+
"loss": 1.0106,
|
399 |
+
"step": 320
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.36,
|
403 |
+
"learning_rate": 1.6209063737995716e-05,
|
404 |
+
"loss": 1.0004,
|
405 |
+
"step": 325
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.36,
|
409 |
+
"learning_rate": 1.605702521680263e-05,
|
410 |
+
"loss": 0.994,
|
411 |
+
"step": 330
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.37,
|
415 |
+
"learning_rate": 1.5902742269009198e-05,
|
416 |
+
"loss": 1.0014,
|
417 |
+
"step": 335
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.37,
|
421 |
+
"learning_rate": 1.5746272064057438e-05,
|
422 |
+
"loss": 0.9998,
|
423 |
+
"step": 340
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.38,
|
427 |
+
"learning_rate": 1.5587672581876053e-05,
|
428 |
+
"loss": 0.9931,
|
429 |
+
"step": 345
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.39,
|
433 |
+
"learning_rate": 1.5427002591395966e-05,
|
434 |
+
"loss": 0.9998,
|
435 |
+
"step": 350
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.39,
|
439 |
+
"learning_rate": 1.526432162877356e-05,
|
440 |
+
"loss": 1.0229,
|
441 |
+
"step": 355
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.4,
|
445 |
+
"learning_rate": 1.5099689975329584e-05,
|
446 |
+
"loss": 0.998,
|
447 |
+
"step": 360
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.4,
|
451 |
+
"learning_rate": 1.4933168635211956e-05,
|
452 |
+
"loss": 0.9845,
|
453 |
+
"step": 365
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.41,
|
457 |
+
"learning_rate": 1.4764819312790706e-05,
|
458 |
+
"loss": 1.0018,
|
459 |
+
"step": 370
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.41,
|
463 |
+
"learning_rate": 1.4594704389793477e-05,
|
464 |
+
"loss": 0.9998,
|
465 |
+
"step": 375
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.42,
|
469 |
+
"learning_rate": 1.4422886902190014e-05,
|
470 |
+
"loss": 0.9824,
|
471 |
+
"step": 380
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.42,
|
475 |
+
"learning_rate": 1.4249430516834222e-05,
|
476 |
+
"loss": 1.0235,
|
477 |
+
"step": 385
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.43,
|
481 |
+
"learning_rate": 1.4074399507872455e-05,
|
482 |
+
"loss": 1.0178,
|
483 |
+
"step": 390
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.44,
|
487 |
+
"learning_rate": 1.3897858732926794e-05,
|
488 |
+
"loss": 0.9851,
|
489 |
+
"step": 395
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.44,
|
493 |
+
"learning_rate": 1.3719873609062078e-05,
|
494 |
+
"loss": 0.985,
|
495 |
+
"step": 400
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.45,
|
499 |
+
"learning_rate": 1.3540510088545652e-05,
|
500 |
+
"loss": 1.007,
|
501 |
+
"step": 405
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.45,
|
505 |
+
"learning_rate": 1.3359834634408828e-05,
|
506 |
+
"loss": 0.9794,
|
507 |
+
"step": 410
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.46,
|
511 |
+
"learning_rate": 1.3177914195819018e-05,
|
512 |
+
"loss": 1.0081,
|
513 |
+
"step": 415
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.46,
|
517 |
+
"learning_rate": 1.2994816183271787e-05,
|
518 |
+
"loss": 0.9973,
|
519 |
+
"step": 420
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.47,
|
523 |
+
"learning_rate": 1.2810608443611943e-05,
|
524 |
+
"loss": 1.0084,
|
525 |
+
"step": 425
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.47,
|
529 |
+
"learning_rate": 1.2625359234892906e-05,
|
530 |
+
"loss": 1.0051,
|
531 |
+
"step": 430
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.48,
|
535 |
+
"learning_rate": 1.2439137201083772e-05,
|
536 |
+
"loss": 1.0212,
|
537 |
+
"step": 435
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.49,
|
541 |
+
"learning_rate": 1.2252011346633306e-05,
|
542 |
+
"loss": 0.9887,
|
543 |
+
"step": 440
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.49,
|
547 |
+
"learning_rate": 1.2064051010900397e-05,
|
548 |
+
"loss": 0.9977,
|
549 |
+
"step": 445
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.5,
|
553 |
+
"learning_rate": 1.1875325842460424e-05,
|
554 |
+
"loss": 0.9808,
|
555 |
+
"step": 450
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.5,
|
559 |
+
"learning_rate": 1.1685905773296992e-05,
|
560 |
+
"loss": 0.9953,
|
561 |
+
"step": 455
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.51,
|
565 |
+
"learning_rate": 1.1495860992888712e-05,
|
566 |
+
"loss": 1.0066,
|
567 |
+
"step": 460
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 0.51,
|
571 |
+
"learning_rate": 1.130526192220052e-05,
|
572 |
+
"loss": 1.0059,
|
573 |
+
"step": 465
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.52,
|
577 |
+
"learning_rate": 1.1114179187589233e-05,
|
578 |
+
"loss": 1.0161,
|
579 |
+
"step": 470
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.52,
|
583 |
+
"learning_rate": 1.092268359463302e-05,
|
584 |
+
"loss": 0.9895,
|
585 |
+
"step": 475
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.53,
|
589 |
+
"learning_rate": 1.0730846101894428e-05,
|
590 |
+
"loss": 0.9961,
|
591 |
+
"step": 480
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.53,
|
595 |
+
"learning_rate": 1.0538737794626735e-05,
|
596 |
+
"loss": 1.0135,
|
597 |
+
"step": 485
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.54,
|
601 |
+
"learning_rate": 1.0346429858433354e-05,
|
602 |
+
"loss": 1.0086,
|
603 |
+
"step": 490
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 0.55,
|
607 |
+
"learning_rate": 1.0153993552890069e-05,
|
608 |
+
"loss": 0.9978,
|
609 |
+
"step": 495
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.55,
|
613 |
+
"learning_rate": 9.961500185139843e-06,
|
614 |
+
"loss": 0.9962,
|
615 |
+
"step": 500
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.56,
|
619 |
+
"learning_rate": 9.769021083469991e-06,
|
620 |
+
"loss": 0.9872,
|
621 |
+
"step": 505
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.56,
|
625 |
+
"learning_rate": 9.576627570881551e-06,
|
626 |
+
"loss": 0.9868,
|
627 |
+
"step": 510
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.57,
|
631 |
+
"learning_rate": 9.384390938660572e-06,
|
632 |
+
"loss": 1.0103,
|
633 |
+
"step": 515
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.57,
|
637 |
+
"learning_rate": 9.192382419961208e-06,
|
638 |
+
"loss": 0.9979,
|
639 |
+
"step": 520
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.58,
|
643 |
+
"learning_rate": 9.000673163410287e-06,
|
644 |
+
"loss": 0.9763,
|
645 |
+
"step": 525
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 0.58,
|
649 |
+
"learning_rate": 8.809334206743251e-06,
|
650 |
+
"loss": 0.9916,
|
651 |
+
"step": 530
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 0.59,
|
655 |
+
"learning_rate": 8.618436450481182e-06,
|
656 |
+
"loss": 0.991,
|
657 |
+
"step": 535
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.6,
|
661 |
+
"learning_rate": 8.428050631658628e-06,
|
662 |
+
"loss": 1.0002,
|
663 |
+
"step": 540
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 0.6,
|
667 |
+
"learning_rate": 8.238247297612092e-06,
|
668 |
+
"loss": 0.9959,
|
669 |
+
"step": 545
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.61,
|
673 |
+
"learning_rate": 8.04909677983872e-06,
|
674 |
+
"loss": 0.97,
|
675 |
+
"step": 550
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.61,
|
679 |
+
"learning_rate": 7.860669167935028e-06,
|
680 |
+
"loss": 0.9843,
|
681 |
+
"step": 555
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.62,
|
685 |
+
"learning_rate": 7.673034283625258e-06,
|
686 |
+
"loss": 0.985,
|
687 |
+
"step": 560
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 0.62,
|
691 |
+
"learning_rate": 7.486261654888974e-06,
|
692 |
+
"loss": 1.0089,
|
693 |
+
"step": 565
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 0.63,
|
697 |
+
"learning_rate": 7.300420490197524e-06,
|
698 |
+
"loss": 1.0078,
|
699 |
+
"step": 570
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.63,
|
703 |
+
"learning_rate": 7.115579652868878e-06,
|
704 |
+
"loss": 0.9974,
|
705 |
+
"step": 575
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 0.64,
|
709 |
+
"learning_rate": 6.9318076355503835e-06,
|
710 |
+
"loss": 1.0002,
|
711 |
+
"step": 580
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.64,
|
715 |
+
"learning_rate": 6.749172534838849e-06,
|
716 |
+
"loss": 0.989,
|
717 |
+
"step": 585
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.65,
|
721 |
+
"learning_rate": 6.5677420260474055e-06,
|
722 |
+
"loss": 0.9956,
|
723 |
+
"step": 590
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.66,
|
727 |
+
"learning_rate": 6.387583338128471e-06,
|
728 |
+
"loss": 0.9893,
|
729 |
+
"step": 595
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.66,
|
733 |
+
"learning_rate": 6.208763228762082e-06,
|
734 |
+
"loss": 1.0192,
|
735 |
+
"step": 600
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 0.67,
|
739 |
+
"learning_rate": 6.031347959618914e-06,
|
740 |
+
"loss": 0.9641,
|
741 |
+
"step": 605
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.67,
|
745 |
+
"learning_rate": 5.855403271807033e-06,
|
746 |
+
"loss": 0.9919,
|
747 |
+
"step": 610
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 0.68,
|
751 |
+
"learning_rate": 5.6809943615115915e-06,
|
752 |
+
"loss": 1.0092,
|
753 |
+
"step": 615
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.68,
|
757 |
+
"learning_rate": 5.508185855836426e-06,
|
758 |
+
"loss": 1.0071,
|
759 |
+
"step": 620
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.69,
|
763 |
+
"learning_rate": 5.337041788856518e-06,
|
764 |
+
"loss": 1.0032,
|
765 |
+
"step": 625
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.69,
|
769 |
+
"learning_rate": 5.1676255778902225e-06,
|
770 |
+
"loss": 1.0175,
|
771 |
+
"step": 630
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 0.7,
|
775 |
+
"learning_rate": 5.000000000000003e-06,
|
776 |
+
"loss": 1.0074,
|
777 |
+
"step": 635
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 0.71,
|
781 |
+
"learning_rate": 4.834227168730451e-06,
|
782 |
+
"loss": 1.0327,
|
783 |
+
"step": 640
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.71,
|
787 |
+
"learning_rate": 4.670368511092166e-06,
|
788 |
+
"loss": 1.0093,
|
789 |
+
"step": 645
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.72,
|
793 |
+
"learning_rate": 4.508484744799979e-06,
|
794 |
+
"loss": 1.0004,
|
795 |
+
"step": 650
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.72,
|
799 |
+
"learning_rate": 4.348635855774082e-06,
|
800 |
+
"loss": 0.9893,
|
801 |
+
"step": 655
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.73,
|
805 |
+
"learning_rate": 4.190881075912269e-06,
|
806 |
+
"loss": 0.9921,
|
807 |
+
"step": 660
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.73,
|
811 |
+
"learning_rate": 4.035278861141588e-06,
|
812 |
+
"loss": 1.0021,
|
813 |
+
"step": 665
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 0.74,
|
817 |
+
"learning_rate": 3.881886869757565e-06,
|
818 |
+
"loss": 1.0096,
|
819 |
+
"step": 670
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.74,
|
823 |
+
"learning_rate": 3.730761941058938e-06,
|
824 |
+
"loss": 0.9959,
|
825 |
+
"step": 675
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 0.75,
|
829 |
+
"learning_rate": 3.581960074285885e-06,
|
830 |
+
"loss": 0.9875,
|
831 |
+
"step": 680
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.76,
|
835 |
+
"learning_rate": 3.435536407869575e-06,
|
836 |
+
"loss": 0.9872,
|
837 |
+
"step": 685
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.76,
|
841 |
+
"learning_rate": 3.2915451990006365e-06,
|
842 |
+
"loss": 0.9988,
|
843 |
+
"step": 690
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.77,
|
847 |
+
"learning_rate": 3.150039803524194e-06,
|
848 |
+
"loss": 0.9843,
|
849 |
+
"step": 695
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.77,
|
853 |
+
"learning_rate": 3.011072656168906e-06,
|
854 |
+
"loss": 0.9997,
|
855 |
+
"step": 700
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 0.78,
|
859 |
+
"learning_rate": 2.874695251117303e-06,
|
860 |
+
"loss": 0.9938,
|
861 |
+
"step": 705
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 0.78,
|
865 |
+
"learning_rate": 2.7409581229246496e-06,
|
866 |
+
"loss": 0.9863,
|
867 |
+
"step": 710
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.79,
|
871 |
+
"learning_rate": 2.6099108277934105e-06,
|
872 |
+
"loss": 1.0175,
|
873 |
+
"step": 715
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 0.79,
|
877 |
+
"learning_rate": 2.4816019252102274e-06,
|
878 |
+
"loss": 0.9998,
|
879 |
+
"step": 720
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.8,
|
883 |
+
"learning_rate": 2.3560789599522325e-06,
|
884 |
+
"loss": 0.9945,
|
885 |
+
"step": 725
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.8,
|
889 |
+
"learning_rate": 2.2333884444693656e-06,
|
890 |
+
"loss": 0.99,
|
891 |
+
"step": 730
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.81,
|
895 |
+
"learning_rate": 2.1135758416492168e-06,
|
896 |
+
"loss": 0.9848,
|
897 |
+
"step": 735
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.82,
|
901 |
+
"learning_rate": 1.996685547970787e-06,
|
902 |
+
"loss": 0.9955,
|
903 |
+
"step": 740
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 0.82,
|
907 |
+
"learning_rate": 1.882760877053388e-06,
|
908 |
+
"loss": 0.9842,
|
909 |
+
"step": 745
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.83,
|
913 |
+
"learning_rate": 1.7718440436068385e-06,
|
914 |
+
"loss": 1.0163,
|
915 |
+
"step": 750
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 0.83,
|
919 |
+
"learning_rate": 1.663976147788806e-06,
|
920 |
+
"loss": 0.9938,
|
921 |
+
"step": 755
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 0.84,
|
925 |
+
"learning_rate": 1.55919715997518e-06,
|
926 |
+
"loss": 1.0167,
|
927 |
+
"step": 760
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.84,
|
931 |
+
"learning_rate": 1.4575459059490771e-06,
|
932 |
+
"loss": 1.0017,
|
933 |
+
"step": 765
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.85,
|
937 |
+
"learning_rate": 1.3590600525139764e-06,
|
938 |
+
"loss": 0.9964,
|
939 |
+
"step": 770
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.85,
|
943 |
+
"learning_rate": 1.2637760935363053e-06,
|
944 |
+
"loss": 1.0156,
|
945 |
+
"step": 775
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 0.86,
|
949 |
+
"learning_rate": 1.1717293364226612e-06,
|
950 |
+
"loss": 1.0111,
|
951 |
+
"step": 780
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 0.87,
|
955 |
+
"learning_rate": 1.0829538890366864e-06,
|
956 |
+
"loss": 1.007,
|
957 |
+
"step": 785
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 0.87,
|
961 |
+
"learning_rate": 9.97482647060405e-07,
|
962 |
+
"loss": 0.9782,
|
963 |
+
"step": 790
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.88,
|
967 |
+
"learning_rate": 9.153472818047627e-07,
|
968 |
+
"loss": 1.012,
|
969 |
+
"step": 795
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.88,
|
973 |
+
"learning_rate": 8.365782284738488e-07,
|
974 |
+
"loss": 0.9846,
|
975 |
+
"step": 800
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.89,
|
979 |
+
"learning_rate": 7.612046748871327e-07,
|
980 |
+
"loss": 1.0234,
|
981 |
+
"step": 805
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 0.89,
|
985 |
+
"learning_rate": 6.892545506639559e-07,
|
986 |
+
"loss": 1.0155,
|
987 |
+
"step": 810
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 0.9,
|
991 |
+
"learning_rate": 6.207545168742212e-07,
|
992 |
+
"loss": 1.0099,
|
993 |
+
"step": 815
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.9,
|
997 |
+
"learning_rate": 5.557299561591478e-07,
|
998 |
+
"loss": 0.982,
|
999 |
+
"step": 820
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.91,
|
1003 |
+
"learning_rate": 4.942049633257673e-07,
|
1004 |
+
"loss": 1.0155,
|
1005 |
+
"step": 825
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 0.92,
|
1009 |
+
"learning_rate": 4.3620233641858855e-07,
|
1010 |
+
"loss": 1.0128,
|
1011 |
+
"step": 830
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.92,
|
1015 |
+
"learning_rate": 3.817435682718096e-07,
|
1016 |
+
"loss": 0.9917,
|
1017 |
+
"step": 835
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.93,
|
1021 |
+
"learning_rate": 3.3084883854516136e-07,
|
1022 |
+
"loss": 1.0075,
|
1023 |
+
"step": 840
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 0.93,
|
1027 |
+
"learning_rate": 2.835370062463449e-07,
|
1028 |
+
"loss": 0.9815,
|
1029 |
+
"step": 845
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.94,
|
1033 |
+
"learning_rate": 2.398256027428436e-07,
|
1034 |
+
"loss": 0.9992,
|
1035 |
+
"step": 850
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.94,
|
1039 |
+
"learning_rate": 1.9973082526568155e-07,
|
1040 |
+
"loss": 1.0018,
|
1041 |
+
"step": 855
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 0.95,
|
1045 |
+
"learning_rate": 1.6326753090755487e-07,
|
1046 |
+
"loss": 1.0033,
|
1047 |
+
"step": 860
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 0.95,
|
1051 |
+
"learning_rate": 1.3044923111754427e-07,
|
1052 |
+
"loss": 0.9775,
|
1053 |
+
"step": 865
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.96,
|
1057 |
+
"learning_rate": 1.0128808669445323e-07,
|
1058 |
+
"loss": 0.9933,
|
1059 |
+
"step": 870
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.96,
|
1063 |
+
"learning_rate": 7.579490328064265e-08,
|
1064 |
+
"loss": 0.9935,
|
1065 |
+
"step": 875
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 0.97,
|
1069 |
+
"learning_rate": 5.397912735799371e-08,
|
1070 |
+
"loss": 0.9873,
|
1071 |
+
"step": 880
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 0.98,
|
1075 |
+
"learning_rate": 3.5848842747532306e-08,
|
1076 |
+
"loss": 0.9878,
|
1077 |
+
"step": 885
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 0.98,
|
1081 |
+
"learning_rate": 2.1410767613965212e-08,
|
1082 |
+
"loss": 1.0115,
|
1083 |
+
"step": 890
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 0.99,
|
1087 |
+
"learning_rate": 1.0670251976275803e-08,
|
1088 |
+
"loss": 1.0062,
|
1089 |
+
"step": 895
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.99,
|
1093 |
+
"learning_rate": 3.63127572527433e-09,
|
1094 |
+
"loss": 0.9915,
|
1095 |
+
"step": 900
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 1.0,
|
1099 |
+
"learning_rate": 2.964471488531295e-10,
|
1100 |
+
"loss": 1.014,
|
1101 |
+
"step": 905
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 1.0,
|
1105 |
+
"eval_loss": 1.004878044128418,
|
1106 |
+
"eval_runtime": 471.2518,
|
1107 |
+
"eval_samples_per_second": 13.666,
|
1108 |
+
"eval_steps_per_second": 0.855,
|
1109 |
+
"step": 907
|
1110 |
+
},
|
1111 |
+
{
|
1112 |
+
"epoch": 1.0,
|
1113 |
+
"step": 907,
|
1114 |
+
"total_flos": 5.321288023160127e+18,
|
1115 |
+
"train_loss": 1.0006486285219118,
|
1116 |
+
"train_runtime": 14584.0452,
|
1117 |
+
"train_samples_per_second": 3.979,
|
1118 |
+
"train_steps_per_second": 0.062
|
1119 |
+
}
|
1120 |
+
],
|
1121 |
+
"logging_steps": 5,
|
1122 |
+
"max_steps": 907,
|
1123 |
+
"num_input_tokens_seen": 0,
|
1124 |
+
"num_train_epochs": 1,
|
1125 |
+
"save_steps": 100,
|
1126 |
+
"total_flos": 5.321288023160127e+18,
|
1127 |
+
"train_batch_size": 32,
|
1128 |
+
"trial_name": null,
|
1129 |
+
"trial_params": null
|
1130 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83b954d34248394117f3285ae60cb26b5583f52dba1d2f1601296096333fc136
|
3 |
+
size 4856
|