pritamdeka
commited on
Commit
•
24aa96d
1
Parent(s):
8977631
Upload folder using huggingface_hub
Browse files- README.md +74 -0
- all_results.json +16 -0
- config.json +26 -0
- eval_results.json +10 -0
- generation_config.json +5 -0
- model.safetensors +3 -0
- runs/Jul09_18-29-14_c3109aa98e74/events.out.tfevents.1720550282.c3109aa98e74.7081.0 +3 -0
- runs/Jul09_18-29-14_c3109aa98e74/events.out.tfevents.1720559363.c3109aa98e74.7081.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- train_results.json +9 -0
- trainer_state.json +266 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/muril-base-cased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: temp_assamese
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# temp_assamese
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [google/muril-base-cased](https://huggingface.co/google/muril-base-cased) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.4149
|
21 |
+
- Accuracy: 0.7014
|
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: 5e-05
|
41 |
+
- train_batch_size: 16
|
42 |
+
- eval_batch_size: 16
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 2.0
|
47 |
+
- mixed_precision_training: Native AMP
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
+
|:-------------:|:------:|:-----:|:---------------:|:--------:|
|
53 |
+
| 2.2163 | 0.1409 | 2000 | 1.8646 | 0.6320 |
|
54 |
+
| 1.9456 | 0.2818 | 4000 | 1.7492 | 0.6495 |
|
55 |
+
| 1.8391 | 0.4227 | 6000 | 1.6770 | 0.6606 |
|
56 |
+
| 1.7704 | 0.5637 | 8000 | 1.6166 | 0.6707 |
|
57 |
+
| 1.7213 | 0.7046 | 10000 | 1.5818 | 0.6759 |
|
58 |
+
| 1.6802 | 0.8455 | 12000 | 1.5403 | 0.6820 |
|
59 |
+
| 1.6432 | 0.9864 | 14000 | 1.5153 | 0.6858 |
|
60 |
+
| 1.6074 | 1.1273 | 16000 | 1.4965 | 0.6885 |
|
61 |
+
| 1.5833 | 1.2682 | 18000 | 1.4678 | 0.6934 |
|
62 |
+
| 1.5649 | 1.4091 | 20000 | 1.4508 | 0.6950 |
|
63 |
+
| 1.553 | 1.5501 | 22000 | 1.4367 | 0.6985 |
|
64 |
+
| 1.5345 | 1.6910 | 24000 | 1.4231 | 0.7001 |
|
65 |
+
| 1.5261 | 1.8319 | 26000 | 1.4157 | 0.7013 |
|
66 |
+
| 1.5148 | 1.9728 | 28000 | 1.4098 | 0.7027 |
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- Transformers 4.43.0.dev0
|
72 |
+
- Pytorch 2.3.0+cu121
|
73 |
+
- Datasets 2.20.0
|
74 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"eval_accuracy": 0.7014180145490598,
|
4 |
+
"eval_loss": 1.4148573875427246,
|
5 |
+
"eval_runtime": 102.6889,
|
6 |
+
"eval_samples": 11967,
|
7 |
+
"eval_samples_per_second": 116.536,
|
8 |
+
"eval_steps_per_second": 7.284,
|
9 |
+
"perplexity": 4.115899445582212,
|
10 |
+
"total_flos": 1.197729267088466e+17,
|
11 |
+
"train_loss": 1.6903211268009264,
|
12 |
+
"train_runtime": 8975.6005,
|
13 |
+
"train_samples": 227086,
|
14 |
+
"train_samples_per_second": 50.601,
|
15 |
+
"train_steps_per_second": 3.163
|
16 |
+
}
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/muril-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"embedding_size": 768,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.43.0.dev0",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 197285
|
26 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"eval_accuracy": 0.7014180145490598,
|
4 |
+
"eval_loss": 1.4148573875427246,
|
5 |
+
"eval_runtime": 102.6889,
|
6 |
+
"eval_samples": 11967,
|
7 |
+
"eval_samples_per_second": 116.536,
|
8 |
+
"eval_steps_per_second": 7.284,
|
9 |
+
"perplexity": 4.115899445582212
|
10 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"pad_token_id": 0,
|
4 |
+
"transformers_version": "4.43.0.dev0"
|
5 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c367e91281dc25023d6a3185659ce4a7ff0b953b29b3096d4a655e704d5be21c
|
3 |
+
size 951043900
|
runs/Jul09_18-29-14_c3109aa98e74/events.out.tfevents.1720550282.c3109aa98e74.7081.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40fc0dfa0241280baccbcc3fbdb0e7b254e1bc78a8730e3578f0ae444c83beb6
|
3 |
+
size 12820
|
runs/Jul09_18-29-14_c3109aa98e74/events.out.tfevents.1720559363.c3109aa98e74.7081.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d4b45a85641a56f4771ade9ddf44479274f65c41d88bdf57acbd3dc8b46e2b1
|
3 |
+
size 417
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"103": {
|
20 |
+
"content": "[MASK]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"104": {
|
28 |
+
"content": "[CLS]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"105": {
|
36 |
+
"content": "[SEP]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": false,
|
48 |
+
"lowercase": false,
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"model_max_length": 512,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_token": "[PAD]",
|
53 |
+
"sep_token": "[SEP]",
|
54 |
+
"strip_accents": false,
|
55 |
+
"tokenize_chinese_chars": true,
|
56 |
+
"tokenizer_class": "BertTokenizer",
|
57 |
+
"unk_token": "[UNK]"
|
58 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"total_flos": 1.197729267088466e+17,
|
4 |
+
"train_loss": 1.6903211268009264,
|
5 |
+
"train_runtime": 8975.6005,
|
6 |
+
"train_samples": 227086,
|
7 |
+
"train_samples_per_second": 50.601,
|
8 |
+
"train_steps_per_second": 3.163
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,266 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7026871898897578,
|
3 |
+
"best_model_checkpoint": "/content/temp_assamese/checkpoint-28000",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 2000,
|
6 |
+
"global_step": 28386,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.14091453533431975,
|
13 |
+
"grad_norm": 12.538192749023438,
|
14 |
+
"learning_rate": 4.648418234340873e-05,
|
15 |
+
"loss": 2.2163,
|
16 |
+
"step": 2000
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.14091453533431975,
|
20 |
+
"eval_accuracy": 0.6319857833787309,
|
21 |
+
"eval_loss": 1.8646236658096313,
|
22 |
+
"eval_runtime": 102.3117,
|
23 |
+
"eval_samples_per_second": 116.966,
|
24 |
+
"eval_steps_per_second": 7.311,
|
25 |
+
"step": 2000
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 0.2818290706686395,
|
29 |
+
"grad_norm": 12.645801544189453,
|
30 |
+
"learning_rate": 4.296131896005073e-05,
|
31 |
+
"loss": 1.9456,
|
32 |
+
"step": 4000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.2818290706686395,
|
36 |
+
"eval_accuracy": 0.6494802758779904,
|
37 |
+
"eval_loss": 1.749164342880249,
|
38 |
+
"eval_runtime": 102.5618,
|
39 |
+
"eval_samples_per_second": 116.681,
|
40 |
+
"eval_steps_per_second": 7.293,
|
41 |
+
"step": 4000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.4227436060029592,
|
45 |
+
"grad_norm": 9.79688835144043,
|
46 |
+
"learning_rate": 3.943845557669274e-05,
|
47 |
+
"loss": 1.8391,
|
48 |
+
"step": 6000
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 0.4227436060029592,
|
52 |
+
"eval_accuracy": 0.6606430993204072,
|
53 |
+
"eval_loss": 1.6770141124725342,
|
54 |
+
"eval_runtime": 102.5061,
|
55 |
+
"eval_samples_per_second": 116.744,
|
56 |
+
"eval_steps_per_second": 7.297,
|
57 |
+
"step": 6000
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.563658141337279,
|
61 |
+
"grad_norm": 10.446520805358887,
|
62 |
+
"learning_rate": 3.5917353625026426e-05,
|
63 |
+
"loss": 1.7704,
|
64 |
+
"step": 8000
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 0.563658141337279,
|
68 |
+
"eval_accuracy": 0.6706733344622967,
|
69 |
+
"eval_loss": 1.6165672540664673,
|
70 |
+
"eval_runtime": 102.6569,
|
71 |
+
"eval_samples_per_second": 116.573,
|
72 |
+
"eval_steps_per_second": 7.286,
|
73 |
+
"step": 8000
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.7045726766715987,
|
77 |
+
"grad_norm": 9.16817569732666,
|
78 |
+
"learning_rate": 3.23962516733601e-05,
|
79 |
+
"loss": 1.7213,
|
80 |
+
"step": 10000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.7045726766715987,
|
84 |
+
"eval_accuracy": 0.6759152415500662,
|
85 |
+
"eval_loss": 1.5817841291427612,
|
86 |
+
"eval_runtime": 102.3347,
|
87 |
+
"eval_samples_per_second": 116.94,
|
88 |
+
"eval_steps_per_second": 7.309,
|
89 |
+
"step": 10000
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.8454872120059184,
|
93 |
+
"grad_norm": 9.296396255493164,
|
94 |
+
"learning_rate": 2.8875149721693794e-05,
|
95 |
+
"loss": 1.6802,
|
96 |
+
"step": 12000
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 0.8454872120059184,
|
100 |
+
"eval_accuracy": 0.6820033844378066,
|
101 |
+
"eval_loss": 1.5402722358703613,
|
102 |
+
"eval_runtime": 102.6712,
|
103 |
+
"eval_samples_per_second": 116.557,
|
104 |
+
"eval_steps_per_second": 7.285,
|
105 |
+
"step": 12000
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.9864017473402381,
|
109 |
+
"grad_norm": 7.622576713562012,
|
110 |
+
"learning_rate": 2.5354047770027478e-05,
|
111 |
+
"loss": 1.6432,
|
112 |
+
"step": 14000
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 0.9864017473402381,
|
116 |
+
"eval_accuracy": 0.6857634747617221,
|
117 |
+
"eval_loss": 1.5153496265411377,
|
118 |
+
"eval_runtime": 102.6162,
|
119 |
+
"eval_samples_per_second": 116.619,
|
120 |
+
"eval_steps_per_second": 7.289,
|
121 |
+
"step": 14000
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.127316282674558,
|
125 |
+
"grad_norm": 11.516377449035645,
|
126 |
+
"learning_rate": 2.1832945818361165e-05,
|
127 |
+
"loss": 1.6074,
|
128 |
+
"step": 16000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.127316282674558,
|
132 |
+
"eval_accuracy": 0.6885159496543541,
|
133 |
+
"eval_loss": 1.496454119682312,
|
134 |
+
"eval_runtime": 102.8787,
|
135 |
+
"eval_samples_per_second": 116.321,
|
136 |
+
"eval_steps_per_second": 7.271,
|
137 |
+
"step": 16000
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 1.2682308180088775,
|
141 |
+
"grad_norm": 9.480605125427246,
|
142 |
+
"learning_rate": 1.831008243500317e-05,
|
143 |
+
"loss": 1.5833,
|
144 |
+
"step": 18000
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 1.2682308180088775,
|
148 |
+
"eval_accuracy": 0.6934179945828158,
|
149 |
+
"eval_loss": 1.4677945375442505,
|
150 |
+
"eval_runtime": 102.7153,
|
151 |
+
"eval_samples_per_second": 116.506,
|
152 |
+
"eval_steps_per_second": 7.282,
|
153 |
+
"step": 18000
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 1.4091453533431975,
|
157 |
+
"grad_norm": 8.643658638000488,
|
158 |
+
"learning_rate": 1.4788980483336856e-05,
|
159 |
+
"loss": 1.5649,
|
160 |
+
"step": 20000
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 1.4091453533431975,
|
164 |
+
"eval_accuracy": 0.6950099353567151,
|
165 |
+
"eval_loss": 1.4508079290390015,
|
166 |
+
"eval_runtime": 102.6391,
|
167 |
+
"eval_samples_per_second": 116.593,
|
168 |
+
"eval_steps_per_second": 7.288,
|
169 |
+
"step": 20000
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 1.550059888677517,
|
173 |
+
"grad_norm": 7.6539506912231445,
|
174 |
+
"learning_rate": 1.1267878531670542e-05,
|
175 |
+
"loss": 1.553,
|
176 |
+
"step": 22000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 1.550059888677517,
|
180 |
+
"eval_accuracy": 0.698540482055296,
|
181 |
+
"eval_loss": 1.436693787574768,
|
182 |
+
"eval_runtime": 102.5486,
|
183 |
+
"eval_samples_per_second": 116.696,
|
184 |
+
"eval_steps_per_second": 7.294,
|
185 |
+
"step": 22000
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 1.690974424011837,
|
189 |
+
"grad_norm": 8.063584327697754,
|
190 |
+
"learning_rate": 7.746776580004228e-06,
|
191 |
+
"loss": 1.5345,
|
192 |
+
"step": 24000
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 1.690974424011837,
|
196 |
+
"eval_accuracy": 0.7001222876777317,
|
197 |
+
"eval_loss": 1.4230775833129883,
|
198 |
+
"eval_runtime": 102.8829,
|
199 |
+
"eval_samples_per_second": 116.317,
|
200 |
+
"eval_steps_per_second": 7.27,
|
201 |
+
"step": 24000
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 1.8318889593461565,
|
205 |
+
"grad_norm": 8.720465660095215,
|
206 |
+
"learning_rate": 4.2256746283379135e-06,
|
207 |
+
"loss": 1.5261,
|
208 |
+
"step": 26000
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 1.8318889593461565,
|
212 |
+
"eval_accuracy": 0.701337358949075,
|
213 |
+
"eval_loss": 1.4157360792160034,
|
214 |
+
"eval_runtime": 102.7046,
|
215 |
+
"eval_samples_per_second": 116.519,
|
216 |
+
"eval_steps_per_second": 7.283,
|
217 |
+
"step": 26000
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"epoch": 1.9728034946804764,
|
221 |
+
"grad_norm": 9.144937515258789,
|
222 |
+
"learning_rate": 7.045726766715987e-07,
|
223 |
+
"loss": 1.5148,
|
224 |
+
"step": 28000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 1.9728034946804764,
|
228 |
+
"eval_accuracy": 0.7026871898897578,
|
229 |
+
"eval_loss": 1.4097787141799927,
|
230 |
+
"eval_runtime": 102.5398,
|
231 |
+
"eval_samples_per_second": 116.706,
|
232 |
+
"eval_steps_per_second": 7.295,
|
233 |
+
"step": 28000
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 2.0,
|
237 |
+
"step": 28386,
|
238 |
+
"total_flos": 1.197729267088466e+17,
|
239 |
+
"train_loss": 1.6903211268009264,
|
240 |
+
"train_runtime": 8975.6005,
|
241 |
+
"train_samples_per_second": 50.601,
|
242 |
+
"train_steps_per_second": 3.163
|
243 |
+
}
|
244 |
+
],
|
245 |
+
"logging_steps": 2000,
|
246 |
+
"max_steps": 28386,
|
247 |
+
"num_input_tokens_seen": 0,
|
248 |
+
"num_train_epochs": 2,
|
249 |
+
"save_steps": 2000,
|
250 |
+
"stateful_callbacks": {
|
251 |
+
"TrainerControl": {
|
252 |
+
"args": {
|
253 |
+
"should_epoch_stop": false,
|
254 |
+
"should_evaluate": false,
|
255 |
+
"should_log": false,
|
256 |
+
"should_save": true,
|
257 |
+
"should_training_stop": true
|
258 |
+
},
|
259 |
+
"attributes": {}
|
260 |
+
}
|
261 |
+
},
|
262 |
+
"total_flos": 1.197729267088466e+17,
|
263 |
+
"train_batch_size": 16,
|
264 |
+
"trial_name": null,
|
265 |
+
"trial_params": null
|
266 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7f14d1d4ab23358fb655d6b451b96dfc8de5e4a244f655a8173f25485d49272
|
3 |
+
size 5176
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|