End of training
Browse files- README.md +64 -0
- all_results.json +9 -0
- config.json +93 -0
- model.safetensors +3 -0
- preprocessor_config.json +9 -0
- runs/Apr12_16-09-39_6c0ec431eb03/events.out.tfevents.1712938183.6c0ec431eb03.34.0 +3 -0
- runs/Apr12_16-09-39_6c0ec431eb03/events.out.tfevents.1712939900.6c0ec431eb03.34.1 +3 -0
- runs/Apr12_16-09-39_6c0ec431eb03/events.out.tfevents.1712940214.6c0ec431eb03.34.2 +3 -0
- runs/Apr12_16-09-39_6c0ec431eb03/events.out.tfevents.1712940242.6c0ec431eb03.34.3 +3 -0
- runs/Apr12_16-09-39_6c0ec431eb03/events.out.tfevents.1712940289.6c0ec431eb03.34.4 +3 -0
- runs/Apr12_16-09-39_6c0ec431eb03/events.out.tfevents.1712940482.6c0ec431eb03.34.5 +3 -0
- runs/Apr12_16-09-39_6c0ec431eb03/events.out.tfevents.1712940519.6c0ec431eb03.34.6 +3 -0
- runs/Apr12_16-09-39_6c0ec431eb03/events.out.tfevents.1712940671.6c0ec431eb03.34.7 +3 -0
- runs/Apr12_16-09-39_6c0ec431eb03/events.out.tfevents.1712941086.6c0ec431eb03.34.8 +3 -0
- runs/Apr12_16-58-56_6c0ec431eb03/events.out.tfevents.1712941164.6c0ec431eb03.34.9 +3 -0
- runs/Apr12_17-02-10_6c0ec431eb03/events.out.tfevents.1712941348.6c0ec431eb03.34.10 +3 -0
- runs/Apr12_17-17-03_6c0ec431eb03/events.out.tfevents.1712942228.6c0ec431eb03.34.11 +3 -0
- train_results.json +9 -0
- trainer_state.json +132 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/hubert-base-ls960
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: ckpts
|
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 |
+
# ckpts
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.1910
|
21 |
+
- Accuracy: 0.9697
|
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: 1e-05
|
41 |
+
- train_batch_size: 4
|
42 |
+
- eval_batch_size: 4
|
43 |
+
- seed: 42
|
44 |
+
- gradient_accumulation_steps: 2
|
45 |
+
- total_train_batch_size: 8
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- num_epochs: 5.0
|
49 |
+
- mixed_precision_training: Native AMP
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
55 |
+
| 0.0228 | 2.02 | 500 | 0.1773 | 0.9737 |
|
56 |
+
| 0.0385 | 4.04 | 1000 | 0.1910 | 0.9697 |
|
57 |
+
|
58 |
+
|
59 |
+
### Framework versions
|
60 |
+
|
61 |
+
- Transformers 4.40.0.dev0
|
62 |
+
- Pytorch 2.1.2
|
63 |
+
- Datasets 2.18.1.dev0
|
64 |
+
- Tokenizers 0.15.2
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.99,
|
3 |
+
"total_flos": 3.160649695892544e+17,
|
4 |
+
"train_loss": 0.03992950008948322,
|
5 |
+
"train_runtime": 666.1547,
|
6 |
+
"train_samples": 1979,
|
7 |
+
"train_samples_per_second": 14.854,
|
8 |
+
"train_steps_per_second": 1.854
|
9 |
+
}
|
config.json
ADDED
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/hubert-base-ls960",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"apply_spec_augment": true,
|
5 |
+
"architectures": [
|
6 |
+
"HubertForSpeechClassification"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"bos_token_id": 1,
|
10 |
+
"classifier_proj_size": 256,
|
11 |
+
"conv_bias": false,
|
12 |
+
"conv_dim": [
|
13 |
+
512,
|
14 |
+
512,
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512,
|
18 |
+
512,
|
19 |
+
512
|
20 |
+
],
|
21 |
+
"conv_kernel": [
|
22 |
+
10,
|
23 |
+
3,
|
24 |
+
3,
|
25 |
+
3,
|
26 |
+
3,
|
27 |
+
2,
|
28 |
+
2
|
29 |
+
],
|
30 |
+
"conv_stride": [
|
31 |
+
5,
|
32 |
+
2,
|
33 |
+
2,
|
34 |
+
2,
|
35 |
+
2,
|
36 |
+
2,
|
37 |
+
2
|
38 |
+
],
|
39 |
+
"ctc_loss_reduction": "sum",
|
40 |
+
"ctc_zero_infinity": false,
|
41 |
+
"do_stable_layer_norm": false,
|
42 |
+
"eos_token_id": 2,
|
43 |
+
"feat_extract_activation": "gelu",
|
44 |
+
"feat_extract_dropout": 0.0,
|
45 |
+
"feat_extract_norm": "group",
|
46 |
+
"feat_proj_dropout": 0.1,
|
47 |
+
"feat_proj_layer_norm": true,
|
48 |
+
"final_dropout": 0.1,
|
49 |
+
"finetuning_task": "wav2vec2_clf",
|
50 |
+
"gradient_checkpointing": false,
|
51 |
+
"hidden_act": "gelu",
|
52 |
+
"hidden_dropout": 0.1,
|
53 |
+
"hidden_dropout_prob": 0.1,
|
54 |
+
"hidden_size": 768,
|
55 |
+
"id2label": {
|
56 |
+
"0": "01Neutral",
|
57 |
+
"1": "02Fearful",
|
58 |
+
"2": "03Happy",
|
59 |
+
"3": "04Sad",
|
60 |
+
"4": "05Angry"
|
61 |
+
},
|
62 |
+
"initializer_range": 0.02,
|
63 |
+
"intermediate_size": 3072,
|
64 |
+
"label2id": {
|
65 |
+
"01Neutral": 0,
|
66 |
+
"02Fearful": 1,
|
67 |
+
"03Happy": 2,
|
68 |
+
"04Sad": 3,
|
69 |
+
"05Angry": 4
|
70 |
+
},
|
71 |
+
"layer_norm_eps": 1e-05,
|
72 |
+
"layerdrop": 0.1,
|
73 |
+
"mask_feature_length": 10,
|
74 |
+
"mask_feature_min_masks": 0,
|
75 |
+
"mask_feature_prob": 0.0,
|
76 |
+
"mask_time_length": 10,
|
77 |
+
"mask_time_min_masks": 2,
|
78 |
+
"mask_time_prob": 0.05,
|
79 |
+
"model_type": "hubert",
|
80 |
+
"num_attention_heads": 12,
|
81 |
+
"num_conv_pos_embedding_groups": 16,
|
82 |
+
"num_conv_pos_embeddings": 128,
|
83 |
+
"num_feat_extract_layers": 7,
|
84 |
+
"num_hidden_layers": 12,
|
85 |
+
"pad_token_id": 0,
|
86 |
+
"pooling_mode": "mean",
|
87 |
+
"problem_type": "single_label_classification",
|
88 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
89 |
+
"torch_dtype": "float32",
|
90 |
+
"transformers_version": "4.40.0.dev0",
|
91 |
+
"use_weighted_layer_sum": false,
|
92 |
+
"vocab_size": 32
|
93 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d0debed0760df769d15ac8682084547cc2c5e3cc04ab2f3880eafb91150c315
|
3 |
+
size 379890236
|
preprocessor_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0,
|
7 |
+
"return_attention_mask": false,
|
8 |
+
"sampling_rate": 16000
|
9 |
+
}
|
runs/Apr12_16-09-39_6c0ec431eb03/events.out.tfevents.1712938183.6c0ec431eb03.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdcff2c21cd7f636d16377c28120e72a5ac1fa8cc3bb0e2eeabae20537f34203
|
3 |
+
size 5852
|
runs/Apr12_16-09-39_6c0ec431eb03/events.out.tfevents.1712939900.6c0ec431eb03.34.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5a26b3cf658a40031ab93cd221b1b85f63d448d90769cd6ebb026ae8000a109
|
3 |
+
size 5852
|
runs/Apr12_16-09-39_6c0ec431eb03/events.out.tfevents.1712940214.6c0ec431eb03.34.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42c6e5e2b531bef51b9a1303b98309a19bf20aa3e65a7ef0c43525bf8d31ea96
|
3 |
+
size 5852
|
runs/Apr12_16-09-39_6c0ec431eb03/events.out.tfevents.1712940242.6c0ec431eb03.34.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7aa7443b5c435809a0a78667e31a4b04019df27788ed5d224e4c4baca446f28f
|
3 |
+
size 5901
|
runs/Apr12_16-09-39_6c0ec431eb03/events.out.tfevents.1712940289.6c0ec431eb03.34.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7dcc8bceed9ca96ab476010eb4b5cf67083ae7f47d9aa983484707f7d9866ba0
|
3 |
+
size 5901
|
runs/Apr12_16-09-39_6c0ec431eb03/events.out.tfevents.1712940482.6c0ec431eb03.34.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc1355b1381c53cf6d4686bb1e90599724bb30f23b5ee8c50b7dc0b8248286d2
|
3 |
+
size 5901
|
runs/Apr12_16-09-39_6c0ec431eb03/events.out.tfevents.1712940519.6c0ec431eb03.34.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55481ceeb53a61c1b9145543cf11fd6c32b8b375f90a52f7c3279e2172c49b70
|
3 |
+
size 5901
|
runs/Apr12_16-09-39_6c0ec431eb03/events.out.tfevents.1712940671.6c0ec431eb03.34.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:763299b2ea96af62e59c0c7cd6e45fc7c0fec7810d2143e0f4df56fd0b62235c
|
3 |
+
size 5901
|
runs/Apr12_16-09-39_6c0ec431eb03/events.out.tfevents.1712941086.6c0ec431eb03.34.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:789d74ec93d39b683919e14627f5569d54d5624eb84ec44cec62a169ba53c70d
|
3 |
+
size 5901
|
runs/Apr12_16-58-56_6c0ec431eb03/events.out.tfevents.1712941164.6c0ec431eb03.34.9
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d32147e7aba5a7843309f6903031ae02315424ed1e2ea6707f32f1536dad38c8
|
3 |
+
size 8204
|
runs/Apr12_17-02-10_6c0ec431eb03/events.out.tfevents.1712941348.6c0ec431eb03.34.10
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7ac6b5b4834e9ba4c703845d7ae5c501441e9dafdb437ea7b401aa5889f912e
|
3 |
+
size 25289
|
runs/Apr12_17-17-03_6c0ec431eb03/events.out.tfevents.1712942228.6c0ec431eb03.34.11
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97b4720817badaf1e0159123c5a6324b528b7c3e563172f2b8fe1d151b38260b
|
3 |
+
size 9476
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.99,
|
3 |
+
"total_flos": 3.160649695892544e+17,
|
4 |
+
"train_loss": 0.03992950008948322,
|
5 |
+
"train_runtime": 666.1547,
|
6 |
+
"train_samples": 1979,
|
7 |
+
"train_samples_per_second": 14.854,
|
8 |
+
"train_steps_per_second": 1.854
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.98989898989899,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1235,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.4,
|
13 |
+
"grad_norm": 0.006182590499520302,
|
14 |
+
"learning_rate": 9.206477732793523e-06,
|
15 |
+
"loss": 0.0729,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.81,
|
20 |
+
"grad_norm": 21.23886489868164,
|
21 |
+
"learning_rate": 8.39676113360324e-06,
|
22 |
+
"loss": 0.0698,
|
23 |
+
"step": 200
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.21,
|
27 |
+
"grad_norm": 0.006576939485967159,
|
28 |
+
"learning_rate": 7.587044534412956e-06,
|
29 |
+
"loss": 0.0464,
|
30 |
+
"step": 300
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 1.62,
|
34 |
+
"grad_norm": 0.009822617284953594,
|
35 |
+
"learning_rate": 6.785425101214575e-06,
|
36 |
+
"loss": 0.0689,
|
37 |
+
"step": 400
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 2.02,
|
41 |
+
"grad_norm": 0.00560363894328475,
|
42 |
+
"learning_rate": 5.975708502024292e-06,
|
43 |
+
"loss": 0.0228,
|
44 |
+
"step": 500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 2.02,
|
48 |
+
"eval_accuracy": 0.973737359046936,
|
49 |
+
"eval_loss": 0.17728736996650696,
|
50 |
+
"eval_runtime": 23.1344,
|
51 |
+
"eval_samples_per_second": 21.397,
|
52 |
+
"eval_steps_per_second": 5.36,
|
53 |
+
"step": 500
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 2.42,
|
57 |
+
"grad_norm": 0.010259171947836876,
|
58 |
+
"learning_rate": 5.165991902834009e-06,
|
59 |
+
"loss": 0.0253,
|
60 |
+
"step": 600
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 2.83,
|
64 |
+
"grad_norm": 0.5489621758460999,
|
65 |
+
"learning_rate": 4.356275303643725e-06,
|
66 |
+
"loss": 0.0227,
|
67 |
+
"step": 700
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 3.23,
|
71 |
+
"grad_norm": 0.003071287414059043,
|
72 |
+
"learning_rate": 3.5465587044534415e-06,
|
73 |
+
"loss": 0.0398,
|
74 |
+
"step": 800
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 3.64,
|
78 |
+
"grad_norm": 0.0034055381547659636,
|
79 |
+
"learning_rate": 2.7368421052631583e-06,
|
80 |
+
"loss": 0.0299,
|
81 |
+
"step": 900
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 4.04,
|
85 |
+
"grad_norm": 0.005517472513020039,
|
86 |
+
"learning_rate": 1.9271255060728746e-06,
|
87 |
+
"loss": 0.0385,
|
88 |
+
"step": 1000
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 4.04,
|
92 |
+
"eval_accuracy": 0.9696969985961914,
|
93 |
+
"eval_loss": 0.190963014960289,
|
94 |
+
"eval_runtime": 23.4329,
|
95 |
+
"eval_samples_per_second": 21.124,
|
96 |
+
"eval_steps_per_second": 5.292,
|
97 |
+
"step": 1000
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 4.44,
|
101 |
+
"grad_norm": 19.359519958496094,
|
102 |
+
"learning_rate": 1.1174089068825912e-06,
|
103 |
+
"loss": 0.0365,
|
104 |
+
"step": 1100
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 4.85,
|
108 |
+
"grad_norm": 1.323317527770996,
|
109 |
+
"learning_rate": 3.0769230769230774e-07,
|
110 |
+
"loss": 0.0064,
|
111 |
+
"step": 1200
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 4.99,
|
115 |
+
"step": 1235,
|
116 |
+
"total_flos": 3.160649695892544e+17,
|
117 |
+
"train_loss": 0.03992950008948322,
|
118 |
+
"train_runtime": 666.1547,
|
119 |
+
"train_samples_per_second": 14.854,
|
120 |
+
"train_steps_per_second": 1.854
|
121 |
+
}
|
122 |
+
],
|
123 |
+
"logging_steps": 100,
|
124 |
+
"max_steps": 1235,
|
125 |
+
"num_input_tokens_seen": 0,
|
126 |
+
"num_train_epochs": 5,
|
127 |
+
"save_steps": 500,
|
128 |
+
"total_flos": 3.160649695892544e+17,
|
129 |
+
"train_batch_size": 4,
|
130 |
+
"trial_name": null,
|
131 |
+
"trial_params": null
|
132 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f507758a89624d13b7bed17a703fed0e8a853809c160f6b3fee91839d462fc37
|
3 |
+
size 4984
|