adding model files
Browse files- .gitignore +1 -0
- README.md +64 -0
- config.json +46 -0
- pytorch_model.bin +3 -0
- trainer_state.json +1553 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
README.md
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: distilgpt2-emailgen_DS-multi_Ep-5_Bs-8
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# distilgpt2-emailgen_DS-multi_Ep-5_Bs-8
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 2.6247
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 6e-05
|
37 |
+
- train_batch_size: 8
|
38 |
+
- eval_batch_size: 8
|
39 |
+
- seed: 42
|
40 |
+
- distributed_type: multi-GPU
|
41 |
+
- gradient_accumulation_steps: 32
|
42 |
+
- total_train_batch_size: 256
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: cosine
|
45 |
+
- lr_scheduler_warmup_ratio: 0.02
|
46 |
+
- num_epochs: 5
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
+
| 2.8299 | 1.0 | 248 | 2.7971 |
|
53 |
+
| 2.6984 | 2.0 | 496 | 2.6826 |
|
54 |
+
| 2.7022 | 3.0 | 744 | 2.6361 |
|
55 |
+
| 2.6436 | 4.0 | 992 | 2.6245 |
|
56 |
+
| 2.6195 | 5.0 | 1240 | 2.6247 |
|
57 |
+
|
58 |
+
|
59 |
+
### Framework versions
|
60 |
+
|
61 |
+
- Transformers 4.21.1
|
62 |
+
- Pytorch 1.12.0+cu113
|
63 |
+
- Datasets 2.4.0
|
64 |
+
- Tokenizers 0.12.1
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilgpt2",
|
3 |
+
"_num_labels": 1,
|
4 |
+
"activation_function": "gelu_new",
|
5 |
+
"architectures": [
|
6 |
+
"GPT2LMHeadModel"
|
7 |
+
],
|
8 |
+
"attn_pdrop": 0.1,
|
9 |
+
"bos_token_id": 50256,
|
10 |
+
"embd_pdrop": 0.1,
|
11 |
+
"eos_token_id": 50256,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"label2id": {
|
17 |
+
"LABEL_0": 0
|
18 |
+
},
|
19 |
+
"layer_norm_epsilon": 1e-05,
|
20 |
+
"model_type": "gpt2",
|
21 |
+
"n_ctx": 1024,
|
22 |
+
"n_embd": 768,
|
23 |
+
"n_head": 12,
|
24 |
+
"n_inner": null,
|
25 |
+
"n_layer": 6,
|
26 |
+
"n_positions": 1024,
|
27 |
+
"reorder_and_upcast_attn": false,
|
28 |
+
"resid_pdrop": 0.1,
|
29 |
+
"scale_attn_by_inverse_layer_idx": false,
|
30 |
+
"scale_attn_weights": true,
|
31 |
+
"summary_activation": null,
|
32 |
+
"summary_first_dropout": 0.1,
|
33 |
+
"summary_proj_to_labels": true,
|
34 |
+
"summary_type": "cls_index",
|
35 |
+
"summary_use_proj": true,
|
36 |
+
"task_specific_params": {
|
37 |
+
"text-generation": {
|
38 |
+
"do_sample": true,
|
39 |
+
"max_length": 50
|
40 |
+
}
|
41 |
+
},
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.21.1",
|
44 |
+
"use_cache": false,
|
45 |
+
"vocab_size": 50257
|
46 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fad802183788f166a8b6f8f9c0e4230c82058cfb9f4a6dcfed3701dd2bce0505
|
3 |
+
size 333954750
|
trainer_state.json
ADDED
@@ -0,0 +1,1553 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.9984901862103674,
|
5 |
+
"global_step": 1240,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.02,
|
12 |
+
"learning_rate": 1.2e-05,
|
13 |
+
"loss": 6.4085,
|
14 |
+
"step": 5
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.04,
|
18 |
+
"learning_rate": 2.4e-05,
|
19 |
+
"loss": 5.2039,
|
20 |
+
"step": 10
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.06,
|
24 |
+
"learning_rate": 3.6e-05,
|
25 |
+
"loss": 4.8094,
|
26 |
+
"step": 15
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.08,
|
30 |
+
"learning_rate": 4.8e-05,
|
31 |
+
"loss": 4.3557,
|
32 |
+
"step": 20
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.1,
|
36 |
+
"learning_rate": 6e-05,
|
37 |
+
"loss": 4.0778,
|
38 |
+
"step": 25
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.12,
|
42 |
+
"learning_rate": 5.999749289566312e-05,
|
43 |
+
"loss": 3.9019,
|
44 |
+
"step": 30
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.14,
|
48 |
+
"learning_rate": 5.998997200169063e-05,
|
49 |
+
"loss": 3.744,
|
50 |
+
"step": 35
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.16,
|
54 |
+
"learning_rate": 5.9977438575126904e-05,
|
55 |
+
"loss": 3.5981,
|
56 |
+
"step": 40
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.18,
|
60 |
+
"learning_rate": 5.99598947108125e-05,
|
61 |
+
"loss": 3.4746,
|
62 |
+
"step": 45
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.2,
|
66 |
+
"learning_rate": 5.993734334103397e-05,
|
67 |
+
"loss": 3.3712,
|
68 |
+
"step": 50
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.22,
|
72 |
+
"learning_rate": 5.990978823503376e-05,
|
73 |
+
"loss": 3.3405,
|
74 |
+
"step": 55
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.24,
|
78 |
+
"learning_rate": 5.987723399838028e-05,
|
79 |
+
"loss": 3.3019,
|
80 |
+
"step": 60
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.26,
|
84 |
+
"learning_rate": 5.983968607219804e-05,
|
85 |
+
"loss": 3.2548,
|
86 |
+
"step": 65
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.28,
|
90 |
+
"learning_rate": 5.979715073225829e-05,
|
91 |
+
"loss": 3.2847,
|
92 |
+
"step": 70
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.3,
|
96 |
+
"learning_rate": 5.974963508793003e-05,
|
97 |
+
"loss": 3.2371,
|
98 |
+
"step": 75
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.32,
|
102 |
+
"learning_rate": 5.9697147080991817e-05,
|
103 |
+
"loss": 3.1677,
|
104 |
+
"step": 80
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.34,
|
108 |
+
"learning_rate": 5.963969548430428e-05,
|
109 |
+
"loss": 3.1617,
|
110 |
+
"step": 85
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.36,
|
114 |
+
"learning_rate": 5.957728990034389e-05,
|
115 |
+
"loss": 3.2266,
|
116 |
+
"step": 90
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.38,
|
120 |
+
"learning_rate": 5.950994075959803e-05,
|
121 |
+
"loss": 3.1008,
|
122 |
+
"step": 95
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.4,
|
126 |
+
"learning_rate": 5.9437659318821544e-05,
|
127 |
+
"loss": 3.0858,
|
128 |
+
"step": 100
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.42,
|
132 |
+
"learning_rate": 5.9360457659155325e-05,
|
133 |
+
"loss": 3.018,
|
134 |
+
"step": 105
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.44,
|
138 |
+
"learning_rate": 5.927834868410711e-05,
|
139 |
+
"loss": 3.0951,
|
140 |
+
"step": 110
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.46,
|
144 |
+
"learning_rate": 5.919134611739472e-05,
|
145 |
+
"loss": 3.1038,
|
146 |
+
"step": 115
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.48,
|
150 |
+
"learning_rate": 5.90994645006523e-05,
|
151 |
+
"loss": 3.0275,
|
152 |
+
"step": 120
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.5,
|
156 |
+
"learning_rate": 5.900271919099987e-05,
|
157 |
+
"loss": 3.0632,
|
158 |
+
"step": 125
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.52,
|
162 |
+
"learning_rate": 5.8901126358476414e-05,
|
163 |
+
"loss": 3.0435,
|
164 |
+
"step": 130
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.54,
|
168 |
+
"learning_rate": 5.8794702983337354e-05,
|
169 |
+
"loss": 3.0403,
|
170 |
+
"step": 135
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.56,
|
174 |
+
"learning_rate": 5.868346685321639e-05,
|
175 |
+
"loss": 3.0174,
|
176 |
+
"step": 140
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.58,
|
180 |
+
"learning_rate": 5.856743656015246e-05,
|
181 |
+
"loss": 2.9917,
|
182 |
+
"step": 145
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.6,
|
186 |
+
"learning_rate": 5.844663149748229e-05,
|
187 |
+
"loss": 2.9663,
|
188 |
+
"step": 150
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.62,
|
192 |
+
"learning_rate": 5.8321071856599e-05,
|
193 |
+
"loss": 2.8901,
|
194 |
+
"step": 155
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.64,
|
198 |
+
"learning_rate": 5.819077862357725e-05,
|
199 |
+
"loss": 2.9219,
|
200 |
+
"step": 160
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.66,
|
204 |
+
"learning_rate": 5.8055773575665695e-05,
|
205 |
+
"loss": 2.9779,
|
206 |
+
"step": 165
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.68,
|
210 |
+
"learning_rate": 5.791607927764706e-05,
|
211 |
+
"loss": 2.8977,
|
212 |
+
"step": 170
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.7,
|
216 |
+
"learning_rate": 5.777171907806672e-05,
|
217 |
+
"loss": 2.8961,
|
218 |
+
"step": 175
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.72,
|
222 |
+
"learning_rate": 5.762271710533015e-05,
|
223 |
+
"loss": 2.8841,
|
224 |
+
"step": 180
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.74,
|
228 |
+
"learning_rate": 5.746909826367018e-05,
|
229 |
+
"loss": 2.8661,
|
230 |
+
"step": 185
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.76,
|
234 |
+
"learning_rate": 5.73108882289844e-05,
|
235 |
+
"loss": 2.8671,
|
236 |
+
"step": 190
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.79,
|
240 |
+
"learning_rate": 5.714811344454376e-05,
|
241 |
+
"loss": 2.9775,
|
242 |
+
"step": 195
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.81,
|
246 |
+
"learning_rate": 5.698080111657279e-05,
|
247 |
+
"loss": 2.9726,
|
248 |
+
"step": 200
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.83,
|
252 |
+
"learning_rate": 5.680897920970237e-05,
|
253 |
+
"loss": 2.9081,
|
254 |
+
"step": 205
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.85,
|
258 |
+
"learning_rate": 5.663267644229568e-05,
|
259 |
+
"loss": 2.8349,
|
260 |
+
"step": 210
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.87,
|
264 |
+
"learning_rate": 5.645192228164824e-05,
|
265 |
+
"loss": 2.9355,
|
266 |
+
"step": 215
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.89,
|
270 |
+
"learning_rate": 5.6266746939062725e-05,
|
271 |
+
"loss": 2.904,
|
272 |
+
"step": 220
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.91,
|
276 |
+
"learning_rate": 5.607718136479943e-05,
|
277 |
+
"loss": 2.9315,
|
278 |
+
"step": 225
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.93,
|
282 |
+
"learning_rate": 5.5883257242903255e-05,
|
283 |
+
"loss": 2.8953,
|
284 |
+
"step": 230
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.95,
|
288 |
+
"learning_rate": 5.568500698590799e-05,
|
289 |
+
"loss": 2.818,
|
290 |
+
"step": 235
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.97,
|
294 |
+
"learning_rate": 5.548246372941892e-05,
|
295 |
+
"loss": 2.8779,
|
296 |
+
"step": 240
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.99,
|
300 |
+
"learning_rate": 5.5275661326574485e-05,
|
301 |
+
"loss": 2.8299,
|
302 |
+
"step": 245
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 1.0,
|
306 |
+
"eval_loss": 2.7971479892730713,
|
307 |
+
"eval_runtime": 163.2621,
|
308 |
+
"eval_samples_per_second": 49.638,
|
309 |
+
"eval_steps_per_second": 6.205,
|
310 |
+
"step": 248
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 1.01,
|
314 |
+
"learning_rate": 5.50646343423881e-05,
|
315 |
+
"loss": 3.1054,
|
316 |
+
"step": 250
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 1.03,
|
320 |
+
"learning_rate": 5.48494180479709e-05,
|
321 |
+
"loss": 2.8559,
|
322 |
+
"step": 255
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 1.05,
|
326 |
+
"learning_rate": 5.463004841463656e-05,
|
327 |
+
"loss": 2.8828,
|
328 |
+
"step": 260
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 1.07,
|
332 |
+
"learning_rate": 5.4406562107889024e-05,
|
333 |
+
"loss": 2.8264,
|
334 |
+
"step": 265
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 1.09,
|
338 |
+
"learning_rate": 5.417899648129423e-05,
|
339 |
+
"loss": 2.8157,
|
340 |
+
"step": 270
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 1.11,
|
344 |
+
"learning_rate": 5.3947389570236784e-05,
|
345 |
+
"loss": 2.8592,
|
346 |
+
"step": 275
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 1.13,
|
350 |
+
"learning_rate": 5.371178008556278e-05,
|
351 |
+
"loss": 2.8296,
|
352 |
+
"step": 280
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 1.15,
|
356 |
+
"learning_rate": 5.347220740710959e-05,
|
357 |
+
"loss": 2.8519,
|
358 |
+
"step": 285
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"epoch": 1.17,
|
362 |
+
"learning_rate": 5.322871157712397e-05,
|
363 |
+
"loss": 2.8342,
|
364 |
+
"step": 290
|
365 |
+
},
|
366 |
+
{
|
367 |
+
"epoch": 1.19,
|
368 |
+
"learning_rate": 5.298133329356934e-05,
|
369 |
+
"loss": 2.8232,
|
370 |
+
"step": 295
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 1.21,
|
374 |
+
"learning_rate": 5.273011390332354e-05,
|
375 |
+
"loss": 2.7835,
|
376 |
+
"step": 300
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"epoch": 1.23,
|
380 |
+
"learning_rate": 5.247509539526808e-05,
|
381 |
+
"loss": 2.8445,
|
382 |
+
"step": 305
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 1.25,
|
386 |
+
"learning_rate": 5.221632039327014e-05,
|
387 |
+
"loss": 2.8093,
|
388 |
+
"step": 310
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 1.27,
|
392 |
+
"learning_rate": 5.195383214905837e-05,
|
393 |
+
"loss": 2.8389,
|
394 |
+
"step": 315
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 1.29,
|
398 |
+
"learning_rate": 5.168767453499379e-05,
|
399 |
+
"loss": 2.8264,
|
400 |
+
"step": 320
|
401 |
+
},
|
402 |
+
{
|
403 |
+
"epoch": 1.31,
|
404 |
+
"learning_rate": 5.141789203673698e-05,
|
405 |
+
"loss": 2.7895,
|
406 |
+
"step": 325
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"epoch": 1.33,
|
410 |
+
"learning_rate": 5.114452974581269e-05,
|
411 |
+
"loss": 2.7584,
|
412 |
+
"step": 330
|
413 |
+
},
|
414 |
+
{
|
415 |
+
"epoch": 1.35,
|
416 |
+
"learning_rate": 5.0867633352073254e-05,
|
417 |
+
"loss": 2.7946,
|
418 |
+
"step": 335
|
419 |
+
},
|
420 |
+
{
|
421 |
+
"epoch": 1.37,
|
422 |
+
"learning_rate": 5.0587249136062016e-05,
|
423 |
+
"loss": 2.7828,
|
424 |
+
"step": 340
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 1.39,
|
428 |
+
"learning_rate": 5.0303423961277864e-05,
|
429 |
+
"loss": 2.833,
|
430 |
+
"step": 345
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 1.41,
|
434 |
+
"learning_rate": 5.001620526634258e-05,
|
435 |
+
"loss": 2.7956,
|
436 |
+
"step": 350
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 1.43,
|
440 |
+
"learning_rate": 4.972564105707191e-05,
|
441 |
+
"loss": 2.8566,
|
442 |
+
"step": 355
|
443 |
+
},
|
444 |
+
{
|
445 |
+
"epoch": 1.45,
|
446 |
+
"learning_rate": 4.943177989845176e-05,
|
447 |
+
"loss": 2.7128,
|
448 |
+
"step": 360
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 1.47,
|
452 |
+
"learning_rate": 4.9134670906521176e-05,
|
453 |
+
"loss": 2.7443,
|
454 |
+
"step": 365
|
455 |
+
},
|
456 |
+
{
|
457 |
+
"epoch": 1.49,
|
458 |
+
"learning_rate": 4.883436374016296e-05,
|
459 |
+
"loss": 2.8008,
|
460 |
+
"step": 370
|
461 |
+
},
|
462 |
+
{
|
463 |
+
"epoch": 1.51,
|
464 |
+
"learning_rate": 4.8530908592803714e-05,
|
465 |
+
"loss": 2.7743,
|
466 |
+
"step": 375
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 1.53,
|
470 |
+
"learning_rate": 4.8224356184024506e-05,
|
471 |
+
"loss": 2.7487,
|
472 |
+
"step": 380
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 1.55,
|
476 |
+
"learning_rate": 4.791475775108359e-05,
|
477 |
+
"loss": 2.7707,
|
478 |
+
"step": 385
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 1.57,
|
482 |
+
"learning_rate": 4.760216504035254e-05,
|
483 |
+
"loss": 2.7924,
|
484 |
+
"step": 390
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 1.59,
|
488 |
+
"learning_rate": 4.7286630298667406e-05,
|
489 |
+
"loss": 2.8114,
|
490 |
+
"step": 395
|
491 |
+
},
|
492 |
+
{
|
493 |
+
"epoch": 1.61,
|
494 |
+
"learning_rate": 4.6968206264596164e-05,
|
495 |
+
"loss": 2.7762,
|
496 |
+
"step": 400
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 1.63,
|
500 |
+
"learning_rate": 4.664694615962391e-05,
|
501 |
+
"loss": 2.7792,
|
502 |
+
"step": 405
|
503 |
+
},
|
504 |
+
{
|
505 |
+
"epoch": 1.65,
|
506 |
+
"learning_rate": 4.632290367925748e-05,
|
507 |
+
"loss": 2.8243,
|
508 |
+
"step": 410
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 1.67,
|
512 |
+
"learning_rate": 4.5996132984050744e-05,
|
513 |
+
"loss": 2.7644,
|
514 |
+
"step": 415
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 1.69,
|
518 |
+
"learning_rate": 4.566668869055216e-05,
|
519 |
+
"loss": 2.7652,
|
520 |
+
"step": 420
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 1.71,
|
524 |
+
"learning_rate": 4.5334625862176195e-05,
|
525 |
+
"loss": 2.7722,
|
526 |
+
"step": 425
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 1.73,
|
530 |
+
"learning_rate": 4.5e-05,
|
531 |
+
"loss": 2.7455,
|
532 |
+
"step": 430
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"epoch": 1.75,
|
536 |
+
"learning_rate": 4.4662867033486924e-05,
|
537 |
+
"loss": 2.7365,
|
538 |
+
"step": 435
|
539 |
+
},
|
540 |
+
{
|
541 |
+
"epoch": 1.77,
|
542 |
+
"learning_rate": 4.4323283311138474e-05,
|
543 |
+
"loss": 2.7176,
|
544 |
+
"step": 440
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 1.79,
|
548 |
+
"learning_rate": 4.398130559107617e-05,
|
549 |
+
"loss": 2.7344,
|
550 |
+
"step": 445
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 1.81,
|
554 |
+
"learning_rate": 4.363699103155502e-05,
|
555 |
+
"loss": 2.7425,
|
556 |
+
"step": 450
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 1.83,
|
560 |
+
"learning_rate": 4.3290397181410056e-05,
|
561 |
+
"loss": 2.7304,
|
562 |
+
"step": 455
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 1.85,
|
566 |
+
"learning_rate": 4.294158197043761e-05,
|
567 |
+
"loss": 2.7893,
|
568 |
+
"step": 460
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"epoch": 1.87,
|
572 |
+
"learning_rate": 4.259060369971287e-05,
|
573 |
+
"loss": 2.7134,
|
574 |
+
"step": 465
|
575 |
+
},
|
576 |
+
{
|
577 |
+
"epoch": 1.89,
|
578 |
+
"learning_rate": 4.2237521031845506e-05,
|
579 |
+
"loss": 2.82,
|
580 |
+
"step": 470
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 1.91,
|
584 |
+
"learning_rate": 4.1882392981174704e-05,
|
585 |
+
"loss": 2.7194,
|
586 |
+
"step": 475
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 1.93,
|
590 |
+
"learning_rate": 4.152527890390553e-05,
|
591 |
+
"loss": 2.7565,
|
592 |
+
"step": 480
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 1.95,
|
596 |
+
"learning_rate": 4.11662384881881e-05,
|
597 |
+
"loss": 2.7037,
|
598 |
+
"step": 485
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 1.97,
|
602 |
+
"learning_rate": 4.080533174414131e-05,
|
603 |
+
"loss": 2.7439,
|
604 |
+
"step": 490
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 1.99,
|
608 |
+
"learning_rate": 4.0442618993822714e-05,
|
609 |
+
"loss": 2.6984,
|
610 |
+
"step": 495
|
611 |
+
},
|
612 |
+
{
|
613 |
+
"epoch": 2.0,
|
614 |
+
"eval_loss": 2.6826047897338867,
|
615 |
+
"eval_runtime": 163.0962,
|
616 |
+
"eval_samples_per_second": 49.688,
|
617 |
+
"eval_steps_per_second": 6.211,
|
618 |
+
"step": 496
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 2.02,
|
622 |
+
"learning_rate": 4.007816086114627e-05,
|
623 |
+
"loss": 2.8637,
|
624 |
+
"step": 500
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 2.04,
|
628 |
+
"learning_rate": 3.971201826174964e-05,
|
629 |
+
"loss": 2.709,
|
630 |
+
"step": 505
|
631 |
+
},
|
632 |
+
{
|
633 |
+
"epoch": 2.06,
|
634 |
+
"learning_rate": 3.934425239281274e-05,
|
635 |
+
"loss": 2.6646,
|
636 |
+
"step": 510
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 2.08,
|
640 |
+
"learning_rate": 3.897492472282926e-05,
|
641 |
+
"loss": 2.7183,
|
642 |
+
"step": 515
|
643 |
+
},
|
644 |
+
{
|
645 |
+
"epoch": 2.1,
|
646 |
+
"learning_rate": 3.860409698133271e-05,
|
647 |
+
"loss": 2.7506,
|
648 |
+
"step": 520
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 2.12,
|
652 |
+
"learning_rate": 3.8231831148579046e-05,
|
653 |
+
"loss": 2.7579,
|
654 |
+
"step": 525
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 2.14,
|
658 |
+
"learning_rate": 3.785818944518718e-05,
|
659 |
+
"loss": 2.685,
|
660 |
+
"step": 530
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 2.16,
|
664 |
+
"learning_rate": 3.748323432173944e-05,
|
665 |
+
"loss": 2.6694,
|
666 |
+
"step": 535
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"epoch": 2.18,
|
670 |
+
"learning_rate": 3.710702844834357e-05,
|
671 |
+
"loss": 2.7386,
|
672 |
+
"step": 540
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 2.2,
|
676 |
+
"learning_rate": 3.672963470415803e-05,
|
677 |
+
"loss": 2.692,
|
678 |
+
"step": 545
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 2.22,
|
682 |
+
"learning_rate": 3.6351116166882325e-05,
|
683 |
+
"loss": 2.7219,
|
684 |
+
"step": 550
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 2.24,
|
688 |
+
"learning_rate": 3.5971536102214215e-05,
|
689 |
+
"loss": 2.769,
|
690 |
+
"step": 555
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 2.26,
|
694 |
+
"learning_rate": 3.559095795327547e-05,
|
695 |
+
"loss": 2.7076,
|
696 |
+
"step": 560
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 2.28,
|
700 |
+
"learning_rate": 3.520944533000792e-05,
|
701 |
+
"loss": 2.7279,
|
702 |
+
"step": 565
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 2.3,
|
706 |
+
"learning_rate": 3.482706199854172e-05,
|
707 |
+
"loss": 2.7273,
|
708 |
+
"step": 570
|
709 |
+
},
|
710 |
+
{
|
711 |
+
"epoch": 2.32,
|
712 |
+
"learning_rate": 3.444387187053747e-05,
|
713 |
+
"loss": 2.6949,
|
714 |
+
"step": 575
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 2.34,
|
718 |
+
"learning_rate": 3.405993899250394e-05,
|
719 |
+
"loss": 2.681,
|
720 |
+
"step": 580
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 2.36,
|
724 |
+
"learning_rate": 3.3675327535093366e-05,
|
725 |
+
"loss": 2.8151,
|
726 |
+
"step": 585
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"epoch": 2.38,
|
730 |
+
"learning_rate": 3.329010178237595e-05,
|
731 |
+
"loss": 2.7137,
|
732 |
+
"step": 590
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 2.4,
|
736 |
+
"learning_rate": 3.2904326121095375e-05,
|
737 |
+
"loss": 2.6656,
|
738 |
+
"step": 595
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 2.42,
|
742 |
+
"learning_rate": 3.25180650299072e-05,
|
743 |
+
"loss": 2.7158,
|
744 |
+
"step": 600
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 2.44,
|
748 |
+
"learning_rate": 3.2131383068601905e-05,
|
749 |
+
"loss": 2.7081,
|
750 |
+
"step": 605
|
751 |
+
},
|
752 |
+
{
|
753 |
+
"epoch": 2.46,
|
754 |
+
"learning_rate": 3.174434486731428e-05,
|
755 |
+
"loss": 2.644,
|
756 |
+
"step": 610
|
757 |
+
},
|
758 |
+
{
|
759 |
+
"epoch": 2.48,
|
760 |
+
"learning_rate": 3.135701511572119e-05,
|
761 |
+
"loss": 2.698,
|
762 |
+
"step": 615
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 2.5,
|
766 |
+
"learning_rate": 3.0969458552229324e-05,
|
767 |
+
"loss": 2.6591,
|
768 |
+
"step": 620
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 2.52,
|
772 |
+
"learning_rate": 3.058173995315473e-05,
|
773 |
+
"loss": 2.6591,
|
774 |
+
"step": 625
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 2.54,
|
778 |
+
"learning_rate": 3.019392412189618e-05,
|
779 |
+
"loss": 2.7327,
|
780 |
+
"step": 630
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 2.56,
|
784 |
+
"learning_rate": 2.9806075878103817e-05,
|
785 |
+
"loss": 2.6711,
|
786 |
+
"step": 635
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 2.58,
|
790 |
+
"learning_rate": 2.9418260046845272e-05,
|
791 |
+
"loss": 2.7034,
|
792 |
+
"step": 640
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 2.6,
|
796 |
+
"learning_rate": 2.9030541447770684e-05,
|
797 |
+
"loss": 2.6119,
|
798 |
+
"step": 645
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"epoch": 2.62,
|
802 |
+
"learning_rate": 2.8642984884278812e-05,
|
803 |
+
"loss": 2.641,
|
804 |
+
"step": 650
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 2.64,
|
808 |
+
"learning_rate": 2.8255655132685727e-05,
|
809 |
+
"loss": 2.6479,
|
810 |
+
"step": 655
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 2.66,
|
814 |
+
"learning_rate": 2.7868616931398106e-05,
|
815 |
+
"loss": 2.6298,
|
816 |
+
"step": 660
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 2.68,
|
820 |
+
"learning_rate": 2.7481934970092792e-05,
|
821 |
+
"loss": 2.6951,
|
822 |
+
"step": 665
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 2.7,
|
826 |
+
"learning_rate": 2.709567387890463e-05,
|
827 |
+
"loss": 2.681,
|
828 |
+
"step": 670
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 2.72,
|
832 |
+
"learning_rate": 2.6709898217624053e-05,
|
833 |
+
"loss": 2.6787,
|
834 |
+
"step": 675
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 2.74,
|
838 |
+
"learning_rate": 2.6324672464906643e-05,
|
839 |
+
"loss": 2.7171,
|
840 |
+
"step": 680
|
841 |
+
},
|
842 |
+
{
|
843 |
+
"epoch": 2.76,
|
844 |
+
"learning_rate": 2.5940061007496078e-05,
|
845 |
+
"loss": 2.7116,
|
846 |
+
"step": 685
|
847 |
+
},
|
848 |
+
{
|
849 |
+
"epoch": 2.78,
|
850 |
+
"learning_rate": 2.5556128129462543e-05,
|
851 |
+
"loss": 2.6834,
|
852 |
+
"step": 690
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 2.8,
|
856 |
+
"learning_rate": 2.517293800145828e-05,
|
857 |
+
"loss": 2.6827,
|
858 |
+
"step": 695
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 2.82,
|
862 |
+
"learning_rate": 2.479055466999209e-05,
|
863 |
+
"loss": 2.6158,
|
864 |
+
"step": 700
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 2.84,
|
868 |
+
"learning_rate": 2.4409042046724537e-05,
|
869 |
+
"loss": 2.7102,
|
870 |
+
"step": 705
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 2.86,
|
874 |
+
"learning_rate": 2.4028463897785787e-05,
|
875 |
+
"loss": 2.6505,
|
876 |
+
"step": 710
|
877 |
+
},
|
878 |
+
{
|
879 |
+
"epoch": 2.88,
|
880 |
+
"learning_rate": 2.3648883833117687e-05,
|
881 |
+
"loss": 2.6876,
|
882 |
+
"step": 715
|
883 |
+
},
|
884 |
+
{
|
885 |
+
"epoch": 2.9,
|
886 |
+
"learning_rate": 2.327036529584198e-05,
|
887 |
+
"loss": 2.6841,
|
888 |
+
"step": 720
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 2.92,
|
892 |
+
"learning_rate": 2.2892971551656424e-05,
|
893 |
+
"loss": 2.683,
|
894 |
+
"step": 725
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 2.94,
|
898 |
+
"learning_rate": 2.2516765678260564e-05,
|
899 |
+
"loss": 2.714,
|
900 |
+
"step": 730
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 2.96,
|
904 |
+
"learning_rate": 2.2141810554812824e-05,
|
905 |
+
"loss": 2.6786,
|
906 |
+
"step": 735
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 2.98,
|
910 |
+
"learning_rate": 2.176816885142096e-05,
|
911 |
+
"loss": 2.7022,
|
912 |
+
"step": 740
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 3.0,
|
916 |
+
"eval_loss": 2.6361331939697266,
|
917 |
+
"eval_runtime": 163.5049,
|
918 |
+
"eval_samples_per_second": 49.564,
|
919 |
+
"eval_steps_per_second": 6.196,
|
920 |
+
"step": 744
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 3.0,
|
924 |
+
"learning_rate": 2.132162043617224e-05,
|
925 |
+
"loss": 2.8742,
|
926 |
+
"step": 745
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 3.02,
|
930 |
+
"learning_rate": 2.0951087758432035e-05,
|
931 |
+
"loss": 2.6404,
|
932 |
+
"step": 750
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 3.04,
|
936 |
+
"learning_rate": 2.0582067518500164e-05,
|
937 |
+
"loss": 2.7206,
|
938 |
+
"step": 755
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 3.06,
|
942 |
+
"learning_rate": 2.0214621394526204e-05,
|
943 |
+
"loss": 2.6592,
|
944 |
+
"step": 760
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 3.08,
|
948 |
+
"learning_rate": 1.984881080156157e-05,
|
949 |
+
"loss": 2.6667,
|
950 |
+
"step": 765
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 3.1,
|
954 |
+
"learning_rate": 1.9484696881294518e-05,
|
955 |
+
"loss": 2.6568,
|
956 |
+
"step": 770
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 3.12,
|
960 |
+
"learning_rate": 1.9122340491830983e-05,
|
961 |
+
"loss": 2.645,
|
962 |
+
"step": 775
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 3.14,
|
966 |
+
"learning_rate": 1.8761802197522638e-05,
|
967 |
+
"loss": 2.5945,
|
968 |
+
"step": 780
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 3.17,
|
972 |
+
"learning_rate": 1.8403142258844258e-05,
|
973 |
+
"loss": 2.6536,
|
974 |
+
"step": 785
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 3.19,
|
978 |
+
"learning_rate": 1.8046420622321678e-05,
|
979 |
+
"loss": 2.6664,
|
980 |
+
"step": 790
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"epoch": 3.21,
|
984 |
+
"learning_rate": 1.769169691051236e-05,
|
985 |
+
"loss": 2.6797,
|
986 |
+
"step": 795
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 3.23,
|
990 |
+
"learning_rate": 1.733903041204006e-05,
|
991 |
+
"loss": 2.6706,
|
992 |
+
"step": 800
|
993 |
+
},
|
994 |
+
{
|
995 |
+
"epoch": 3.25,
|
996 |
+
"learning_rate": 1.6988480071685293e-05,
|
997 |
+
"loss": 2.7273,
|
998 |
+
"step": 805
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 3.27,
|
1002 |
+
"learning_rate": 1.664010448053332e-05,
|
1003 |
+
"loss": 2.6833,
|
1004 |
+
"step": 810
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 3.29,
|
1008 |
+
"learning_rate": 1.6293961866181154e-05,
|
1009 |
+
"loss": 2.7188,
|
1010 |
+
"step": 815
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 3.31,
|
1014 |
+
"learning_rate": 1.5950110083005433e-05,
|
1015 |
+
"loss": 2.6276,
|
1016 |
+
"step": 820
|
1017 |
+
},
|
1018 |
+
{
|
1019 |
+
"epoch": 3.33,
|
1020 |
+
"learning_rate": 1.5608606602492622e-05,
|
1021 |
+
"loss": 2.7026,
|
1022 |
+
"step": 825
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 3.35,
|
1026 |
+
"learning_rate": 1.526950850363318e-05,
|
1027 |
+
"loss": 2.6412,
|
1028 |
+
"step": 830
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 3.37,
|
1032 |
+
"learning_rate": 1.4932872463381392e-05,
|
1033 |
+
"loss": 2.6308,
|
1034 |
+
"step": 835
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 3.39,
|
1038 |
+
"learning_rate": 1.4598754747182377e-05,
|
1039 |
+
"loss": 2.5865,
|
1040 |
+
"step": 840
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 3.41,
|
1044 |
+
"learning_rate": 1.4267211199567806e-05,
|
1045 |
+
"loss": 2.7103,
|
1046 |
+
"step": 845
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 3.43,
|
1050 |
+
"learning_rate": 1.3938297234822089e-05,
|
1051 |
+
"loss": 2.6321,
|
1052 |
+
"step": 850
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 3.45,
|
1056 |
+
"learning_rate": 1.361206782772039e-05,
|
1057 |
+
"loss": 2.6398,
|
1058 |
+
"step": 855
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 3.47,
|
1062 |
+
"learning_rate": 1.328857750434012e-05,
|
1063 |
+
"loss": 2.6513,
|
1064 |
+
"step": 860
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 3.49,
|
1068 |
+
"learning_rate": 1.2967880332947474e-05,
|
1069 |
+
"loss": 2.692,
|
1070 |
+
"step": 865
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 3.51,
|
1074 |
+
"learning_rate": 1.2650029914960406e-05,
|
1075 |
+
"loss": 2.5955,
|
1076 |
+
"step": 870
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 3.53,
|
1080 |
+
"learning_rate": 1.2335079375989666e-05,
|
1081 |
+
"loss": 2.6501,
|
1082 |
+
"step": 875
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 3.55,
|
1086 |
+
"learning_rate": 1.2023081356959398e-05,
|
1087 |
+
"loss": 2.646,
|
1088 |
+
"step": 880
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 3.57,
|
1092 |
+
"learning_rate": 1.1714088005308714e-05,
|
1093 |
+
"loss": 2.6988,
|
1094 |
+
"step": 885
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 3.59,
|
1098 |
+
"learning_rate": 1.140815096627573e-05,
|
1099 |
+
"loss": 2.6395,
|
1100 |
+
"step": 890
|
1101 |
+
},
|
1102 |
+
{
|
1103 |
+
"epoch": 3.61,
|
1104 |
+
"learning_rate": 1.1105321374265619e-05,
|
1105 |
+
"loss": 2.7236,
|
1106 |
+
"step": 895
|
1107 |
+
},
|
1108 |
+
{
|
1109 |
+
"epoch": 3.63,
|
1110 |
+
"learning_rate": 1.0805649844303954e-05,
|
1111 |
+
"loss": 2.7175,
|
1112 |
+
"step": 900
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 3.65,
|
1116 |
+
"learning_rate": 1.0509186463576888e-05,
|
1117 |
+
"loss": 2.7241,
|
1118 |
+
"step": 905
|
1119 |
+
},
|
1120 |
+
{
|
1121 |
+
"epoch": 3.67,
|
1122 |
+
"learning_rate": 1.0215980783059585e-05,
|
1123 |
+
"loss": 2.6334,
|
1124 |
+
"step": 910
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 3.69,
|
1128 |
+
"learning_rate": 9.926081809234262e-06,
|
1129 |
+
"loss": 2.6283,
|
1130 |
+
"step": 915
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 3.71,
|
1134 |
+
"learning_rate": 9.639537995899214e-06,
|
1135 |
+
"loss": 2.6598,
|
1136 |
+
"step": 920
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 3.73,
|
1140 |
+
"learning_rate": 9.356397236070267e-06,
|
1141 |
+
"loss": 2.6099,
|
1142 |
+
"step": 925
|
1143 |
+
},
|
1144 |
+
{
|
1145 |
+
"epoch": 3.75,
|
1146 |
+
"learning_rate": 9.076706853975862e-06,
|
1147 |
+
"loss": 2.613,
|
1148 |
+
"step": 930
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"epoch": 3.77,
|
1152 |
+
"learning_rate": 8.800513597147349e-06,
|
1153 |
+
"loss": 2.5609,
|
1154 |
+
"step": 935
|
1155 |
+
},
|
1156 |
+
{
|
1157 |
+
"epoch": 3.79,
|
1158 |
+
"learning_rate": 8.527863628605514e-06,
|
1159 |
+
"loss": 2.7093,
|
1160 |
+
"step": 940
|
1161 |
+
},
|
1162 |
+
{
|
1163 |
+
"epoch": 3.81,
|
1164 |
+
"learning_rate": 8.258802519144935e-06,
|
1165 |
+
"loss": 2.5844,
|
1166 |
+
"step": 945
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 3.83,
|
1170 |
+
"learning_rate": 7.993375239717228e-06,
|
1171 |
+
"loss": 2.6648,
|
1172 |
+
"step": 950
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 3.85,
|
1176 |
+
"learning_rate": 7.731626153914636e-06,
|
1177 |
+
"loss": 2.6364,
|
1178 |
+
"step": 955
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 3.87,
|
1182 |
+
"learning_rate": 7.473599010555025e-06,
|
1183 |
+
"loss": 2.738,
|
1184 |
+
"step": 960
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 3.89,
|
1188 |
+
"learning_rate": 7.219336936369749e-06,
|
1189 |
+
"loss": 2.6826,
|
1190 |
+
"step": 965
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 3.91,
|
1194 |
+
"learning_rate": 6.968882428795393e-06,
|
1195 |
+
"loss": 2.717,
|
1196 |
+
"step": 970
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 3.93,
|
1200 |
+
"learning_rate": 6.722277348870772e-06,
|
1201 |
+
"loss": 2.7357,
|
1202 |
+
"step": 975
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 3.95,
|
1206 |
+
"learning_rate": 6.47956291424023e-06,
|
1207 |
+
"loss": 2.648,
|
1208 |
+
"step": 980
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 3.97,
|
1212 |
+
"learning_rate": 6.240779692264567e-06,
|
1213 |
+
"loss": 2.6178,
|
1214 |
+
"step": 985
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 3.99,
|
1218 |
+
"learning_rate": 6.005967593240522e-06,
|
1219 |
+
"loss": 2.6436,
|
1220 |
+
"step": 990
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 4.0,
|
1224 |
+
"eval_loss": 2.6245498657226562,
|
1225 |
+
"eval_runtime": 163.5799,
|
1226 |
+
"eval_samples_per_second": 49.542,
|
1227 |
+
"eval_steps_per_second": 6.193,
|
1228 |
+
"step": 992
|
1229 |
+
},
|
1230 |
+
{
|
1231 |
+
"epoch": 4.01,
|
1232 |
+
"learning_rate": 5.7751658637302344e-06,
|
1233 |
+
"loss": 2.8379,
|
1234 |
+
"step": 995
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 4.03,
|
1238 |
+
"learning_rate": 5.548413080001497e-06,
|
1239 |
+
"loss": 2.6199,
|
1240 |
+
"step": 1000
|
1241 |
+
},
|
1242 |
+
{
|
1243 |
+
"epoch": 4.05,
|
1244 |
+
"learning_rate": 5.325747141580131e-06,
|
1245 |
+
"loss": 2.6231,
|
1246 |
+
"step": 1005
|
1247 |
+
},
|
1248 |
+
{
|
1249 |
+
"epoch": 4.07,
|
1250 |
+
"learning_rate": 5.107205264915482e-06,
|
1251 |
+
"loss": 2.6267,
|
1252 |
+
"step": 1010
|
1253 |
+
},
|
1254 |
+
{
|
1255 |
+
"epoch": 4.09,
|
1256 |
+
"learning_rate": 4.8928239771599935e-06,
|
1257 |
+
"loss": 2.69,
|
1258 |
+
"step": 1015
|
1259 |
+
},
|
1260 |
+
{
|
1261 |
+
"epoch": 4.11,
|
1262 |
+
"learning_rate": 4.6826391100640785e-06,
|
1263 |
+
"loss": 2.7156,
|
1264 |
+
"step": 1020
|
1265 |
+
},
|
1266 |
+
{
|
1267 |
+
"epoch": 4.13,
|
1268 |
+
"learning_rate": 4.476685793987202e-06,
|
1269 |
+
"loss": 2.729,
|
1270 |
+
"step": 1025
|
1271 |
+
},
|
1272 |
+
{
|
1273 |
+
"epoch": 4.15,
|
1274 |
+
"learning_rate": 4.274998452026159e-06,
|
1275 |
+
"loss": 2.6732,
|
1276 |
+
"step": 1030
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 4.17,
|
1280 |
+
"learning_rate": 4.0776107942615855e-06,
|
1281 |
+
"loss": 2.6484,
|
1282 |
+
"step": 1035
|
1283 |
+
},
|
1284 |
+
{
|
1285 |
+
"epoch": 4.19,
|
1286 |
+
"learning_rate": 3.884555812123685e-06,
|
1287 |
+
"loss": 2.6133,
|
1288 |
+
"step": 1040
|
1289 |
+
},
|
1290 |
+
{
|
1291 |
+
"epoch": 4.21,
|
1292 |
+
"learning_rate": 3.6958657728779856e-06,
|
1293 |
+
"loss": 2.6863,
|
1294 |
+
"step": 1045
|
1295 |
+
},
|
1296 |
+
{
|
1297 |
+
"epoch": 4.23,
|
1298 |
+
"learning_rate": 3.5115722142321906e-06,
|
1299 |
+
"loss": 2.6385,
|
1300 |
+
"step": 1050
|
1301 |
+
},
|
1302 |
+
{
|
1303 |
+
"epoch": 4.25,
|
1304 |
+
"learning_rate": 3.3317059390649906e-06,
|
1305 |
+
"loss": 2.6193,
|
1306 |
+
"step": 1055
|
1307 |
+
},
|
1308 |
+
{
|
1309 |
+
"epoch": 4.27,
|
1310 |
+
"learning_rate": 3.1562970102776177e-06,
|
1311 |
+
"loss": 2.655,
|
1312 |
+
"step": 1060
|
1313 |
+
},
|
1314 |
+
{
|
1315 |
+
"epoch": 4.29,
|
1316 |
+
"learning_rate": 2.985374745769134e-06,
|
1317 |
+
"loss": 2.6629,
|
1318 |
+
"step": 1065
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 4.31,
|
1322 |
+
"learning_rate": 2.8189677135362635e-06,
|
1323 |
+
"loss": 2.6214,
|
1324 |
+
"step": 1070
|
1325 |
+
},
|
1326 |
+
{
|
1327 |
+
"epoch": 4.33,
|
1328 |
+
"learning_rate": 2.6571037268984742e-06,
|
1329 |
+
"loss": 2.7275,
|
1330 |
+
"step": 1075
|
1331 |
+
},
|
1332 |
+
{
|
1333 |
+
"epoch": 4.35,
|
1334 |
+
"learning_rate": 2.499809839849292e-06,
|
1335 |
+
"loss": 2.6338,
|
1336 |
+
"step": 1080
|
1337 |
+
},
|
1338 |
+
{
|
1339 |
+
"epoch": 4.37,
|
1340 |
+
"learning_rate": 2.3471123425344863e-06,
|
1341 |
+
"loss": 2.6312,
|
1342 |
+
"step": 1085
|
1343 |
+
},
|
1344 |
+
{
|
1345 |
+
"epoch": 4.39,
|
1346 |
+
"learning_rate": 2.1990367568578982e-06,
|
1347 |
+
"loss": 2.5713,
|
1348 |
+
"step": 1090
|
1349 |
+
},
|
1350 |
+
{
|
1351 |
+
"epoch": 4.41,
|
1352 |
+
"learning_rate": 2.055607832215727e-06,
|
1353 |
+
"loss": 2.708,
|
1354 |
+
"step": 1095
|
1355 |
+
},
|
1356 |
+
{
|
1357 |
+
"epoch": 4.43,
|
1358 |
+
"learning_rate": 1.9168495413599183e-06,
|
1359 |
+
"loss": 2.6313,
|
1360 |
+
"step": 1100
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 4.45,
|
1364 |
+
"learning_rate": 1.7827850763913167e-06,
|
1365 |
+
"loss": 2.5938,
|
1366 |
+
"step": 1105
|
1367 |
+
},
|
1368 |
+
{
|
1369 |
+
"epoch": 4.48,
|
1370 |
+
"learning_rate": 1.6534368448833581e-06,
|
1371 |
+
"loss": 2.6137,
|
1372 |
+
"step": 1110
|
1373 |
+
},
|
1374 |
+
{
|
1375 |
+
"epoch": 4.5,
|
1376 |
+
"learning_rate": 1.5288264661368523e-06,
|
1377 |
+
"loss": 2.6919,
|
1378 |
+
"step": 1115
|
1379 |
+
},
|
1380 |
+
{
|
1381 |
+
"epoch": 4.52,
|
1382 |
+
"learning_rate": 1.4089747675665387e-06,
|
1383 |
+
"loss": 2.6168,
|
1384 |
+
"step": 1120
|
1385 |
+
},
|
1386 |
+
{
|
1387 |
+
"epoch": 4.54,
|
1388 |
+
"learning_rate": 1.2939017812199584e-06,
|
1389 |
+
"loss": 2.6687,
|
1390 |
+
"step": 1125
|
1391 |
+
},
|
1392 |
+
{
|
1393 |
+
"epoch": 4.56,
|
1394 |
+
"learning_rate": 1.1836267404293311e-06,
|
1395 |
+
"loss": 2.5993,
|
1396 |
+
"step": 1130
|
1397 |
+
},
|
1398 |
+
{
|
1399 |
+
"epoch": 4.58,
|
1400 |
+
"learning_rate": 1.0781680765968515e-06,
|
1401 |
+
"loss": 2.6695,
|
1402 |
+
"step": 1135
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 4.6,
|
1406 |
+
"learning_rate": 9.775434161140861e-07,
|
1407 |
+
"loss": 2.6461,
|
1408 |
+
"step": 1140
|
1409 |
+
},
|
1410 |
+
{
|
1411 |
+
"epoch": 4.62,
|
1412 |
+
"learning_rate": 8.817695774158729e-07,
|
1413 |
+
"loss": 2.6796,
|
1414 |
+
"step": 1145
|
1415 |
+
},
|
1416 |
+
{
|
1417 |
+
"epoch": 4.64,
|
1418 |
+
"learning_rate": 7.908625681693138e-07,
|
1419 |
+
"loss": 2.6503,
|
1420 |
+
"step": 1150
|
1421 |
+
},
|
1422 |
+
{
|
1423 |
+
"epoch": 4.66,
|
1424 |
+
"learning_rate": 7.048375825982112e-07,
|
1425 |
+
"loss": 2.6532,
|
1426 |
+
"step": 1155
|
1427 |
+
},
|
1428 |
+
{
|
1429 |
+
"epoch": 4.68,
|
1430 |
+
"learning_rate": 6.237089989435263e-07,
|
1431 |
+
"loss": 2.6171,
|
1432 |
+
"step": 1160
|
1433 |
+
},
|
1434 |
+
{
|
1435 |
+
"epoch": 4.7,
|
1436 |
+
"learning_rate": 5.474903770601913e-07,
|
1437 |
+
"loss": 2.6785,
|
1438 |
+
"step": 1165
|
1439 |
+
},
|
1440 |
+
{
|
1441 |
+
"epoch": 4.72,
|
1442 |
+
"learning_rate": 4.7619445615070256e-07,
|
1443 |
+
"loss": 2.7045,
|
1444 |
+
"step": 1170
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"epoch": 4.74,
|
1448 |
+
"learning_rate": 4.0983315263589004e-07,
|
1449 |
+
"loss": 2.7024,
|
1450 |
+
"step": 1175
|
1451 |
+
},
|
1452 |
+
{
|
1453 |
+
"epoch": 4.76,
|
1454 |
+
"learning_rate": 3.484175581632143e-07,
|
1455 |
+
"loss": 2.648,
|
1456 |
+
"step": 1180
|
1457 |
+
},
|
1458 |
+
{
|
1459 |
+
"epoch": 4.78,
|
1460 |
+
"learning_rate": 2.9195793775288916e-07,
|
1461 |
+
"loss": 2.6865,
|
1462 |
+
"step": 1185
|
1463 |
+
},
|
1464 |
+
{
|
1465 |
+
"epoch": 4.8,
|
1466 |
+
"learning_rate": 2.4046372808220084e-07,
|
1467 |
+
"loss": 2.6769,
|
1468 |
+
"step": 1190
|
1469 |
+
},
|
1470 |
+
{
|
1471 |
+
"epoch": 4.82,
|
1472 |
+
"learning_rate": 1.939435359082331e-07,
|
1473 |
+
"loss": 2.6381,
|
1474 |
+
"step": 1195
|
1475 |
+
},
|
1476 |
+
{
|
1477 |
+
"epoch": 4.84,
|
1478 |
+
"learning_rate": 1.524051366293644e-07,
|
1479 |
+
"loss": 2.6804,
|
1480 |
+
"step": 1200
|
1481 |
+
},
|
1482 |
+
{
|
1483 |
+
"epoch": 4.86,
|
1484 |
+
"learning_rate": 1.1585547298565091e-07,
|
1485 |
+
"loss": 2.5962,
|
1486 |
+
"step": 1205
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 4.88,
|
1490 |
+
"learning_rate": 8.43006538984481e-08,
|
1491 |
+
"loss": 2.6744,
|
1492 |
+
"step": 1210
|
1493 |
+
},
|
1494 |
+
{
|
1495 |
+
"epoch": 4.9,
|
1496 |
+
"learning_rate": 5.774595344934075e-08,
|
1497 |
+
"loss": 2.6654,
|
1498 |
+
"step": 1215
|
1499 |
+
},
|
1500 |
+
{
|
1501 |
+
"epoch": 4.92,
|
1502 |
+
"learning_rate": 3.6195809998638144e-08,
|
1503 |
+
"loss": 2.673,
|
1504 |
+
"step": 1220
|
1505 |
+
},
|
1506 |
+
{
|
1507 |
+
"epoch": 4.94,
|
1508 |
+
"learning_rate": 1.9653825443547435e-08,
|
1509 |
+
"loss": 2.6151,
|
1510 |
+
"step": 1225
|
1511 |
+
},
|
1512 |
+
{
|
1513 |
+
"epoch": 4.96,
|
1514 |
+
"learning_rate": 8.122764616148581e-09,
|
1515 |
+
"loss": 2.7565,
|
1516 |
+
"step": 1230
|
1517 |
+
},
|
1518 |
+
{
|
1519 |
+
"epoch": 4.98,
|
1520 |
+
"learning_rate": 1.6045548212872963e-09,
|
1521 |
+
"loss": 2.6162,
|
1522 |
+
"step": 1235
|
1523 |
+
},
|
1524 |
+
{
|
1525 |
+
"epoch": 5.0,
|
1526 |
+
"learning_rate": 1.0028551442609057e-10,
|
1527 |
+
"loss": 2.6195,
|
1528 |
+
"step": 1240
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 5.0,
|
1532 |
+
"eval_loss": 2.62469482421875,
|
1533 |
+
"eval_runtime": 163.7545,
|
1534 |
+
"eval_samples_per_second": 49.489,
|
1535 |
+
"eval_steps_per_second": 6.186,
|
1536 |
+
"step": 1240
|
1537 |
+
},
|
1538 |
+
{
|
1539 |
+
"epoch": 5.0,
|
1540 |
+
"step": 1240,
|
1541 |
+
"total_flos": 8.30390621259694e+16,
|
1542 |
+
"train_loss": 2.8163739796607725,
|
1543 |
+
"train_runtime": 27047.4241,
|
1544 |
+
"train_samples_per_second": 11.753,
|
1545 |
+
"train_steps_per_second": 0.046
|
1546 |
+
}
|
1547 |
+
],
|
1548 |
+
"max_steps": 1240,
|
1549 |
+
"num_train_epochs": 5,
|
1550 |
+
"total_flos": 8.30390621259694e+16,
|
1551 |
+
"trial_name": null,
|
1552 |
+
"trial_params": null
|
1553 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5faf230624239da33ce9fa7402078f1feb8fe63e989383c38f0ba875e0a88772
|
3 |
+
size 4719
|