Commit
•
a747fb9
1
Parent(s):
d9b7a09
End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: facebook/wav2vec2-base-960h
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: wav2vec2-base-960h-EMOPIA-10sec
|
| 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 |
+
# wav2vec2-base-960h-EMOPIA-10sec
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 2.5866
|
| 22 |
+
- Accuracy: 0.6338
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 1e-05
|
| 42 |
+
- train_batch_size: 1
|
| 43 |
+
- eval_batch_size: 1
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- num_epochs: 30
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 54 |
+
| 1.2014 | 1.0 | 807 | 1.1830 | 0.3662 |
|
| 55 |
+
| 1.0915 | 2.0 | 1614 | 1.5120 | 0.3239 |
|
| 56 |
+
| 1.1433 | 3.0 | 2421 | 1.5699 | 0.4085 |
|
| 57 |
+
| 1.2819 | 4.0 | 3228 | 1.7372 | 0.4789 |
|
| 58 |
+
| 1.2718 | 5.0 | 4035 | 2.2169 | 0.4648 |
|
| 59 |
+
| 1.4535 | 6.0 | 4842 | 1.7296 | 0.5775 |
|
| 60 |
+
| 1.3433 | 7.0 | 5649 | 2.2684 | 0.5493 |
|
| 61 |
+
| 1.4086 | 8.0 | 6456 | 1.8599 | 0.6479 |
|
| 62 |
+
| 1.3923 | 9.0 | 7263 | 1.9420 | 0.6197 |
|
| 63 |
+
| 1.3353 | 10.0 | 8070 | 2.2150 | 0.5775 |
|
| 64 |
+
| 1.367 | 11.0 | 8877 | 1.9826 | 0.6338 |
|
| 65 |
+
| 1.1848 | 12.0 | 9684 | 1.9545 | 0.6479 |
|
| 66 |
+
| 1.1355 | 13.0 | 10491 | 1.9864 | 0.6620 |
|
| 67 |
+
| 1.1549 | 14.0 | 11298 | 1.9428 | 0.6338 |
|
| 68 |
+
| 1.0505 | 15.0 | 12105 | 1.9101 | 0.6901 |
|
| 69 |
+
| 1.0442 | 16.0 | 12912 | 2.1706 | 0.6479 |
|
| 70 |
+
| 0.9922 | 17.0 | 13719 | 2.4620 | 0.6197 |
|
| 71 |
+
| 0.8698 | 18.0 | 14526 | 2.1429 | 0.6620 |
|
| 72 |
+
| 0.8202 | 19.0 | 15333 | 2.3725 | 0.6197 |
|
| 73 |
+
| 0.8612 | 20.0 | 16140 | 2.1631 | 0.6620 |
|
| 74 |
+
| 0.8197 | 21.0 | 16947 | 2.3932 | 0.6338 |
|
| 75 |
+
| 0.7858 | 22.0 | 17754 | 2.2532 | 0.6479 |
|
| 76 |
+
| 0.7717 | 23.0 | 18561 | 2.8132 | 0.5634 |
|
| 77 |
+
| 0.6282 | 24.0 | 19368 | 2.5493 | 0.6197 |
|
| 78 |
+
| 0.7394 | 25.0 | 20175 | 2.3195 | 0.6620 |
|
| 79 |
+
| 0.5895 | 26.0 | 20982 | 2.4331 | 0.6620 |
|
| 80 |
+
| 0.5854 | 27.0 | 21789 | 2.4281 | 0.6761 |
|
| 81 |
+
| 0.6911 | 28.0 | 22596 | 2.4993 | 0.6620 |
|
| 82 |
+
| 0.5502 | 29.0 | 23403 | 2.6458 | 0.6338 |
|
| 83 |
+
| 0.584 | 30.0 | 24210 | 2.5866 | 0.6338 |
|
| 84 |
+
|
| 85 |
+
|
| 86 |
+
### Framework versions
|
| 87 |
+
|
| 88 |
+
- Transformers 4.45.1
|
| 89 |
+
- Pytorch 2.4.1+cu118
|
| 90 |
+
- Datasets 3.0.1
|
| 91 |
+
- Tokenizers 0.20.0
|
config.json
ADDED
|
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/wav2vec2-base-960h",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"adapter_attn_dim": null,
|
| 5 |
+
"adapter_kernel_size": 3,
|
| 6 |
+
"adapter_stride": 2,
|
| 7 |
+
"add_adapter": false,
|
| 8 |
+
"apply_spec_augment": true,
|
| 9 |
+
"architectures": [
|
| 10 |
+
"Wav2Vec2ForSpeechClassification"
|
| 11 |
+
],
|
| 12 |
+
"attention_dropout": 0.1,
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"classifier_proj_size": 256,
|
| 15 |
+
"codevector_dim": 256,
|
| 16 |
+
"contrastive_logits_temperature": 0.1,
|
| 17 |
+
"conv_bias": false,
|
| 18 |
+
"conv_dim": [
|
| 19 |
+
512,
|
| 20 |
+
512,
|
| 21 |
+
512,
|
| 22 |
+
512,
|
| 23 |
+
512,
|
| 24 |
+
512,
|
| 25 |
+
512
|
| 26 |
+
],
|
| 27 |
+
"conv_kernel": [
|
| 28 |
+
10,
|
| 29 |
+
3,
|
| 30 |
+
3,
|
| 31 |
+
3,
|
| 32 |
+
3,
|
| 33 |
+
2,
|
| 34 |
+
2
|
| 35 |
+
],
|
| 36 |
+
"conv_stride": [
|
| 37 |
+
5,
|
| 38 |
+
2,
|
| 39 |
+
2,
|
| 40 |
+
2,
|
| 41 |
+
2,
|
| 42 |
+
2,
|
| 43 |
+
2
|
| 44 |
+
],
|
| 45 |
+
"ctc_loss_reduction": "sum",
|
| 46 |
+
"ctc_zero_infinity": false,
|
| 47 |
+
"diversity_loss_weight": 0.1,
|
| 48 |
+
"do_stable_layer_norm": false,
|
| 49 |
+
"eos_token_id": 2,
|
| 50 |
+
"feat_extract_activation": "gelu",
|
| 51 |
+
"feat_extract_dropout": 0.0,
|
| 52 |
+
"feat_extract_norm": "group",
|
| 53 |
+
"feat_proj_dropout": 0.1,
|
| 54 |
+
"feat_quantizer_dropout": 0.0,
|
| 55 |
+
"final_dropout": 0.1,
|
| 56 |
+
"finetuning_task": "facebook/wav2vec2-base-960h",
|
| 57 |
+
"gradient_checkpointing": false,
|
| 58 |
+
"hidden_act": "gelu",
|
| 59 |
+
"hidden_dropout": 0.1,
|
| 60 |
+
"hidden_dropout_prob": 0.1,
|
| 61 |
+
"hidden_size": 768,
|
| 62 |
+
"id2label": {
|
| 63 |
+
"0": "Q1",
|
| 64 |
+
"1": "Q2",
|
| 65 |
+
"2": "Q3",
|
| 66 |
+
"3": "Q4"
|
| 67 |
+
},
|
| 68 |
+
"initializer_range": 0.02,
|
| 69 |
+
"intermediate_size": 3072,
|
| 70 |
+
"label2id": {
|
| 71 |
+
"Q1": 0,
|
| 72 |
+
"Q2": 1,
|
| 73 |
+
"Q3": 2,
|
| 74 |
+
"Q4": 3
|
| 75 |
+
},
|
| 76 |
+
"layer_norm_eps": 1e-05,
|
| 77 |
+
"layerdrop": 0.1,
|
| 78 |
+
"mask_feature_length": 10,
|
| 79 |
+
"mask_feature_min_masks": 0,
|
| 80 |
+
"mask_feature_prob": 0.0,
|
| 81 |
+
"mask_time_length": 10,
|
| 82 |
+
"mask_time_min_masks": 2,
|
| 83 |
+
"mask_time_prob": 0.05,
|
| 84 |
+
"model_type": "wav2vec2",
|
| 85 |
+
"num_adapter_layers": 3,
|
| 86 |
+
"num_attention_heads": 12,
|
| 87 |
+
"num_codevector_groups": 2,
|
| 88 |
+
"num_codevectors_per_group": 320,
|
| 89 |
+
"num_conv_pos_embedding_groups": 16,
|
| 90 |
+
"num_conv_pos_embeddings": 128,
|
| 91 |
+
"num_feat_extract_layers": 7,
|
| 92 |
+
"num_hidden_layers": 12,
|
| 93 |
+
"num_negatives": 100,
|
| 94 |
+
"output_hidden_size": 768,
|
| 95 |
+
"pad_token_id": 0,
|
| 96 |
+
"pooling_mode": "mean",
|
| 97 |
+
"problem_type": "single_label_classification",
|
| 98 |
+
"proj_codevector_dim": 256,
|
| 99 |
+
"tdnn_dilation": [
|
| 100 |
+
1,
|
| 101 |
+
2,
|
| 102 |
+
3,
|
| 103 |
+
1,
|
| 104 |
+
1
|
| 105 |
+
],
|
| 106 |
+
"tdnn_dim": [
|
| 107 |
+
512,
|
| 108 |
+
512,
|
| 109 |
+
512,
|
| 110 |
+
512,
|
| 111 |
+
1500
|
| 112 |
+
],
|
| 113 |
+
"tdnn_kernel": [
|
| 114 |
+
5,
|
| 115 |
+
3,
|
| 116 |
+
3,
|
| 117 |
+
1,
|
| 118 |
+
1
|
| 119 |
+
],
|
| 120 |
+
"torch_dtype": "float32",
|
| 121 |
+
"transformers_version": "4.45.1",
|
| 122 |
+
"use_weighted_layer_sum": false,
|
| 123 |
+
"vocab_size": 32,
|
| 124 |
+
"xvector_output_dim": 512
|
| 125 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:482e8bab0f2e69d35326aea8975d70a939615ea331df1d691dc758af76f8bae8
|
| 3 |
+
size 379887584
|
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": 0.0,
|
| 7 |
+
"return_attention_mask": false,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
+
}
|
runs/Oct03_10-49-10_ip-172-16-42-38.ap-northeast-1.compute.internal/events.out.tfevents.1727952601.ip-172-16-42-38.ap-northeast-1.compute.internal
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba7aaee20e3a1415301a8852d603cef2a3b1349b03daa6fb7fe79a73e42f9ef9
|
| 3 |
+
size 23127
|
trainer_state.json
ADDED
|
@@ -0,0 +1,522 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 30.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 24210,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 6.501698017120361,
|
| 14 |
+
"learning_rate": 9.66914498141264e-06,
|
| 15 |
+
"loss": 1.2014,
|
| 16 |
+
"step": 807
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.3661971688270569,
|
| 21 |
+
"eval_loss": 1.183009147644043,
|
| 22 |
+
"eval_runtime": 5.7015,
|
| 23 |
+
"eval_samples_per_second": 12.453,
|
| 24 |
+
"eval_steps_per_second": 12.453,
|
| 25 |
+
"step": 807
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 2.0,
|
| 29 |
+
"grad_norm": 11.675583839416504,
|
| 30 |
+
"learning_rate": 9.335811648079307e-06,
|
| 31 |
+
"loss": 1.0915,
|
| 32 |
+
"step": 1614
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.0,
|
| 36 |
+
"eval_accuracy": 0.3239436745643616,
|
| 37 |
+
"eval_loss": 1.5119783878326416,
|
| 38 |
+
"eval_runtime": 5.7636,
|
| 39 |
+
"eval_samples_per_second": 12.319,
|
| 40 |
+
"eval_steps_per_second": 12.319,
|
| 41 |
+
"step": 1614
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 3.0,
|
| 45 |
+
"grad_norm": 16.97098731994629,
|
| 46 |
+
"learning_rate": 9.002478314745973e-06,
|
| 47 |
+
"loss": 1.1433,
|
| 48 |
+
"step": 2421
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.0,
|
| 52 |
+
"eval_accuracy": 0.4084506928920746,
|
| 53 |
+
"eval_loss": 1.5698989629745483,
|
| 54 |
+
"eval_runtime": 5.8045,
|
| 55 |
+
"eval_samples_per_second": 12.232,
|
| 56 |
+
"eval_steps_per_second": 12.232,
|
| 57 |
+
"step": 2421
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.0,
|
| 61 |
+
"grad_norm": 127.35404205322266,
|
| 62 |
+
"learning_rate": 8.669558033870302e-06,
|
| 63 |
+
"loss": 1.2819,
|
| 64 |
+
"step": 3228
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 4.0,
|
| 68 |
+
"eval_accuracy": 0.47887325286865234,
|
| 69 |
+
"eval_loss": 1.737151861190796,
|
| 70 |
+
"eval_runtime": 5.8167,
|
| 71 |
+
"eval_samples_per_second": 12.206,
|
| 72 |
+
"eval_steps_per_second": 12.206,
|
| 73 |
+
"step": 3228
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 5.0,
|
| 77 |
+
"grad_norm": 0.40140867233276367,
|
| 78 |
+
"learning_rate": 8.336224700536968e-06,
|
| 79 |
+
"loss": 1.2718,
|
| 80 |
+
"step": 4035
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 5.0,
|
| 84 |
+
"eval_accuracy": 0.4647887349128723,
|
| 85 |
+
"eval_loss": 2.216925859451294,
|
| 86 |
+
"eval_runtime": 5.8112,
|
| 87 |
+
"eval_samples_per_second": 12.218,
|
| 88 |
+
"eval_steps_per_second": 12.218,
|
| 89 |
+
"step": 4035
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 6.0,
|
| 93 |
+
"grad_norm": 30.236343383789062,
|
| 94 |
+
"learning_rate": 8.003304419661297e-06,
|
| 95 |
+
"loss": 1.4535,
|
| 96 |
+
"step": 4842
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 6.0,
|
| 100 |
+
"eval_accuracy": 0.577464759349823,
|
| 101 |
+
"eval_loss": 1.7295811176300049,
|
| 102 |
+
"eval_runtime": 5.8523,
|
| 103 |
+
"eval_samples_per_second": 12.132,
|
| 104 |
+
"eval_steps_per_second": 12.132,
|
| 105 |
+
"step": 4842
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 7.0,
|
| 109 |
+
"grad_norm": 0.2374914586544037,
|
| 110 |
+
"learning_rate": 7.670384138785627e-06,
|
| 111 |
+
"loss": 1.3433,
|
| 112 |
+
"step": 5649
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 7.0,
|
| 116 |
+
"eval_accuracy": 0.5492957830429077,
|
| 117 |
+
"eval_loss": 2.268446683883667,
|
| 118 |
+
"eval_runtime": 5.8095,
|
| 119 |
+
"eval_samples_per_second": 12.221,
|
| 120 |
+
"eval_steps_per_second": 12.221,
|
| 121 |
+
"step": 5649
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 8.0,
|
| 125 |
+
"grad_norm": 32.27313232421875,
|
| 126 |
+
"learning_rate": 7.3370508054522925e-06,
|
| 127 |
+
"loss": 1.4086,
|
| 128 |
+
"step": 6456
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 8.0,
|
| 132 |
+
"eval_accuracy": 0.6478873491287231,
|
| 133 |
+
"eval_loss": 1.8598684072494507,
|
| 134 |
+
"eval_runtime": 5.7903,
|
| 135 |
+
"eval_samples_per_second": 12.262,
|
| 136 |
+
"eval_steps_per_second": 12.262,
|
| 137 |
+
"step": 6456
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 9.0,
|
| 141 |
+
"grad_norm": 42.521121978759766,
|
| 142 |
+
"learning_rate": 7.003717472118959e-06,
|
| 143 |
+
"loss": 1.3923,
|
| 144 |
+
"step": 7263
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 9.0,
|
| 148 |
+
"eval_accuracy": 0.6197183132171631,
|
| 149 |
+
"eval_loss": 1.9419935941696167,
|
| 150 |
+
"eval_runtime": 5.8464,
|
| 151 |
+
"eval_samples_per_second": 12.144,
|
| 152 |
+
"eval_steps_per_second": 12.144,
|
| 153 |
+
"step": 7263
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 10.0,
|
| 157 |
+
"grad_norm": 0.37923476099967957,
|
| 158 |
+
"learning_rate": 6.670384138785626e-06,
|
| 159 |
+
"loss": 1.3353,
|
| 160 |
+
"step": 8070
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 10.0,
|
| 164 |
+
"eval_accuracy": 0.577464759349823,
|
| 165 |
+
"eval_loss": 2.2150189876556396,
|
| 166 |
+
"eval_runtime": 5.8548,
|
| 167 |
+
"eval_samples_per_second": 12.127,
|
| 168 |
+
"eval_steps_per_second": 12.127,
|
| 169 |
+
"step": 8070
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 11.0,
|
| 173 |
+
"grad_norm": 19.937904357910156,
|
| 174 |
+
"learning_rate": 6.337463857909954e-06,
|
| 175 |
+
"loss": 1.367,
|
| 176 |
+
"step": 8877
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 11.0,
|
| 180 |
+
"eval_accuracy": 0.6338028311729431,
|
| 181 |
+
"eval_loss": 1.9825525283813477,
|
| 182 |
+
"eval_runtime": 5.9069,
|
| 183 |
+
"eval_samples_per_second": 12.02,
|
| 184 |
+
"eval_steps_per_second": 12.02,
|
| 185 |
+
"step": 8877
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 12.0,
|
| 189 |
+
"grad_norm": 454.2120666503906,
|
| 190 |
+
"learning_rate": 6.004543577034284e-06,
|
| 191 |
+
"loss": 1.1848,
|
| 192 |
+
"step": 9684
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 12.0,
|
| 196 |
+
"eval_accuracy": 0.6478873491287231,
|
| 197 |
+
"eval_loss": 1.9545217752456665,
|
| 198 |
+
"eval_runtime": 5.8618,
|
| 199 |
+
"eval_samples_per_second": 12.112,
|
| 200 |
+
"eval_steps_per_second": 12.112,
|
| 201 |
+
"step": 9684
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 13.0,
|
| 205 |
+
"grad_norm": 0.09417306631803513,
|
| 206 |
+
"learning_rate": 5.671210243700951e-06,
|
| 207 |
+
"loss": 1.1355,
|
| 208 |
+
"step": 10491
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 13.0,
|
| 212 |
+
"eval_accuracy": 0.6619718074798584,
|
| 213 |
+
"eval_loss": 1.9863765239715576,
|
| 214 |
+
"eval_runtime": 5.8578,
|
| 215 |
+
"eval_samples_per_second": 12.12,
|
| 216 |
+
"eval_steps_per_second": 12.12,
|
| 217 |
+
"step": 10491
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 14.0,
|
| 221 |
+
"grad_norm": 33.132957458496094,
|
| 222 |
+
"learning_rate": 5.337876910367618e-06,
|
| 223 |
+
"loss": 1.1549,
|
| 224 |
+
"step": 11298
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 14.0,
|
| 228 |
+
"eval_accuracy": 0.6338028311729431,
|
| 229 |
+
"eval_loss": 1.9428231716156006,
|
| 230 |
+
"eval_runtime": 5.8665,
|
| 231 |
+
"eval_samples_per_second": 12.103,
|
| 232 |
+
"eval_steps_per_second": 12.103,
|
| 233 |
+
"step": 11298
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 15.0,
|
| 237 |
+
"grad_norm": 0.12686021625995636,
|
| 238 |
+
"learning_rate": 5.004543577034285e-06,
|
| 239 |
+
"loss": 1.0505,
|
| 240 |
+
"step": 12105
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 15.0,
|
| 244 |
+
"eval_accuracy": 0.6901408433914185,
|
| 245 |
+
"eval_loss": 1.9100552797317505,
|
| 246 |
+
"eval_runtime": 5.8853,
|
| 247 |
+
"eval_samples_per_second": 12.064,
|
| 248 |
+
"eval_steps_per_second": 12.064,
|
| 249 |
+
"step": 12105
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 16.0,
|
| 253 |
+
"grad_norm": 1043.1195068359375,
|
| 254 |
+
"learning_rate": 4.6712102437009505e-06,
|
| 255 |
+
"loss": 1.0442,
|
| 256 |
+
"step": 12912
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 16.0,
|
| 260 |
+
"eval_accuracy": 0.6478873491287231,
|
| 261 |
+
"eval_loss": 2.1706087589263916,
|
| 262 |
+
"eval_runtime": 5.8878,
|
| 263 |
+
"eval_samples_per_second": 12.059,
|
| 264 |
+
"eval_steps_per_second": 12.059,
|
| 265 |
+
"step": 12912
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 17.0,
|
| 269 |
+
"grad_norm": 26.500118255615234,
|
| 270 |
+
"learning_rate": 4.338289962825279e-06,
|
| 271 |
+
"loss": 0.9922,
|
| 272 |
+
"step": 13719
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 17.0,
|
| 276 |
+
"eval_accuracy": 0.6197183132171631,
|
| 277 |
+
"eval_loss": 2.462040901184082,
|
| 278 |
+
"eval_runtime": 5.8428,
|
| 279 |
+
"eval_samples_per_second": 12.152,
|
| 280 |
+
"eval_steps_per_second": 12.152,
|
| 281 |
+
"step": 13719
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 18.0,
|
| 285 |
+
"grad_norm": 162.029052734375,
|
| 286 |
+
"learning_rate": 4.004956629491946e-06,
|
| 287 |
+
"loss": 0.8698,
|
| 288 |
+
"step": 14526
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 18.0,
|
| 292 |
+
"eval_accuracy": 0.6619718074798584,
|
| 293 |
+
"eval_loss": 2.142850637435913,
|
| 294 |
+
"eval_runtime": 5.9312,
|
| 295 |
+
"eval_samples_per_second": 11.971,
|
| 296 |
+
"eval_steps_per_second": 11.971,
|
| 297 |
+
"step": 14526
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 19.0,
|
| 301 |
+
"grad_norm": 0.0350579209625721,
|
| 302 |
+
"learning_rate": 3.6716232961586124e-06,
|
| 303 |
+
"loss": 0.8202,
|
| 304 |
+
"step": 15333
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 19.0,
|
| 308 |
+
"eval_accuracy": 0.6197183132171631,
|
| 309 |
+
"eval_loss": 2.372546911239624,
|
| 310 |
+
"eval_runtime": 5.8453,
|
| 311 |
+
"eval_samples_per_second": 12.147,
|
| 312 |
+
"eval_steps_per_second": 12.147,
|
| 313 |
+
"step": 15333
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 20.0,
|
| 317 |
+
"grad_norm": 0.042548421770334244,
|
| 318 |
+
"learning_rate": 3.3387030152829415e-06,
|
| 319 |
+
"loss": 0.8612,
|
| 320 |
+
"step": 16140
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 20.0,
|
| 324 |
+
"eval_accuracy": 0.6619718074798584,
|
| 325 |
+
"eval_loss": 2.1631431579589844,
|
| 326 |
+
"eval_runtime": 5.8804,
|
| 327 |
+
"eval_samples_per_second": 12.074,
|
| 328 |
+
"eval_steps_per_second": 12.074,
|
| 329 |
+
"step": 16140
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 21.0,
|
| 333 |
+
"grad_norm": 0.09584546834230423,
|
| 334 |
+
"learning_rate": 3.0053696819496083e-06,
|
| 335 |
+
"loss": 0.8197,
|
| 336 |
+
"step": 16947
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 21.0,
|
| 340 |
+
"eval_accuracy": 0.6338028311729431,
|
| 341 |
+
"eval_loss": 2.393216848373413,
|
| 342 |
+
"eval_runtime": 5.8299,
|
| 343 |
+
"eval_samples_per_second": 12.179,
|
| 344 |
+
"eval_steps_per_second": 12.179,
|
| 345 |
+
"step": 16947
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 22.0,
|
| 349 |
+
"grad_norm": 0.0448361337184906,
|
| 350 |
+
"learning_rate": 2.672036348616274e-06,
|
| 351 |
+
"loss": 0.7858,
|
| 352 |
+
"step": 17754
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 22.0,
|
| 356 |
+
"eval_accuracy": 0.6478873491287231,
|
| 357 |
+
"eval_loss": 2.25321364402771,
|
| 358 |
+
"eval_runtime": 5.8111,
|
| 359 |
+
"eval_samples_per_second": 12.218,
|
| 360 |
+
"eval_steps_per_second": 12.218,
|
| 361 |
+
"step": 17754
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 23.0,
|
| 365 |
+
"grad_norm": 0.057099100202322006,
|
| 366 |
+
"learning_rate": 2.3391160677406034e-06,
|
| 367 |
+
"loss": 0.7717,
|
| 368 |
+
"step": 18561
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 23.0,
|
| 372 |
+
"eval_accuracy": 0.5633803009986877,
|
| 373 |
+
"eval_loss": 2.813150644302368,
|
| 374 |
+
"eval_runtime": 5.8476,
|
| 375 |
+
"eval_samples_per_second": 12.142,
|
| 376 |
+
"eval_steps_per_second": 12.142,
|
| 377 |
+
"step": 18561
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 24.0,
|
| 381 |
+
"grad_norm": 202.8040008544922,
|
| 382 |
+
"learning_rate": 2.00578273440727e-06,
|
| 383 |
+
"loss": 0.6282,
|
| 384 |
+
"step": 19368
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 24.0,
|
| 388 |
+
"eval_accuracy": 0.6197183132171631,
|
| 389 |
+
"eval_loss": 2.549309492111206,
|
| 390 |
+
"eval_runtime": 5.839,
|
| 391 |
+
"eval_samples_per_second": 12.16,
|
| 392 |
+
"eval_steps_per_second": 12.16,
|
| 393 |
+
"step": 19368
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 25.0,
|
| 397 |
+
"grad_norm": 0.06747495383024216,
|
| 398 |
+
"learning_rate": 1.6728624535315987e-06,
|
| 399 |
+
"loss": 0.7394,
|
| 400 |
+
"step": 20175
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 25.0,
|
| 404 |
+
"eval_accuracy": 0.6619718074798584,
|
| 405 |
+
"eval_loss": 2.3195266723632812,
|
| 406 |
+
"eval_runtime": 5.8894,
|
| 407 |
+
"eval_samples_per_second": 12.056,
|
| 408 |
+
"eval_steps_per_second": 12.056,
|
| 409 |
+
"step": 20175
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 26.0,
|
| 413 |
+
"grad_norm": 4.30875301361084,
|
| 414 |
+
"learning_rate": 1.3395291201982652e-06,
|
| 415 |
+
"loss": 0.5895,
|
| 416 |
+
"step": 20982
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 26.0,
|
| 420 |
+
"eval_accuracy": 0.6619718074798584,
|
| 421 |
+
"eval_loss": 2.43306565284729,
|
| 422 |
+
"eval_runtime": 5.8283,
|
| 423 |
+
"eval_samples_per_second": 12.182,
|
| 424 |
+
"eval_steps_per_second": 12.182,
|
| 425 |
+
"step": 20982
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 27.0,
|
| 429 |
+
"grad_norm": 0.05214543268084526,
|
| 430 |
+
"learning_rate": 1.006195786864932e-06,
|
| 431 |
+
"loss": 0.5854,
|
| 432 |
+
"step": 21789
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 27.0,
|
| 436 |
+
"eval_accuracy": 0.6760563254356384,
|
| 437 |
+
"eval_loss": 2.428130626678467,
|
| 438 |
+
"eval_runtime": 5.8154,
|
| 439 |
+
"eval_samples_per_second": 12.209,
|
| 440 |
+
"eval_steps_per_second": 12.209,
|
| 441 |
+
"step": 21789
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 28.0,
|
| 445 |
+
"grad_norm": 0.1047598198056221,
|
| 446 |
+
"learning_rate": 6.732755059892606e-07,
|
| 447 |
+
"loss": 0.6911,
|
| 448 |
+
"step": 22596
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 28.0,
|
| 452 |
+
"eval_accuracy": 0.6619718074798584,
|
| 453 |
+
"eval_loss": 2.499279737472534,
|
| 454 |
+
"eval_runtime": 5.8567,
|
| 455 |
+
"eval_samples_per_second": 12.123,
|
| 456 |
+
"eval_steps_per_second": 12.123,
|
| 457 |
+
"step": 22596
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 29.0,
|
| 461 |
+
"grad_norm": 92.8244857788086,
|
| 462 |
+
"learning_rate": 3.3994217265592734e-07,
|
| 463 |
+
"loss": 0.5502,
|
| 464 |
+
"step": 23403
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 29.0,
|
| 468 |
+
"eval_accuracy": 0.6338028311729431,
|
| 469 |
+
"eval_loss": 2.64582896232605,
|
| 470 |
+
"eval_runtime": 5.8325,
|
| 471 |
+
"eval_samples_per_second": 12.173,
|
| 472 |
+
"eval_steps_per_second": 12.173,
|
| 473 |
+
"step": 23403
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 30.0,
|
| 477 |
+
"grad_norm": 0.047546908259391785,
|
| 478 |
+
"learning_rate": 6.60883932259397e-09,
|
| 479 |
+
"loss": 0.584,
|
| 480 |
+
"step": 24210
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 30.0,
|
| 484 |
+
"eval_accuracy": 0.6338028311729431,
|
| 485 |
+
"eval_loss": 2.586568593978882,
|
| 486 |
+
"eval_runtime": 5.8563,
|
| 487 |
+
"eval_samples_per_second": 12.124,
|
| 488 |
+
"eval_steps_per_second": 12.124,
|
| 489 |
+
"step": 24210
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 30.0,
|
| 493 |
+
"step": 24210,
|
| 494 |
+
"total_flos": 2.2475408052256202e+18,
|
| 495 |
+
"train_loss": 1.0049422518175921,
|
| 496 |
+
"train_runtime": 3971.9322,
|
| 497 |
+
"train_samples_per_second": 6.095,
|
| 498 |
+
"train_steps_per_second": 6.095
|
| 499 |
+
}
|
| 500 |
+
],
|
| 501 |
+
"logging_steps": 12,
|
| 502 |
+
"max_steps": 24210,
|
| 503 |
+
"num_input_tokens_seen": 0,
|
| 504 |
+
"num_train_epochs": 30,
|
| 505 |
+
"save_steps": 500,
|
| 506 |
+
"stateful_callbacks": {
|
| 507 |
+
"TrainerControl": {
|
| 508 |
+
"args": {
|
| 509 |
+
"should_epoch_stop": false,
|
| 510 |
+
"should_evaluate": false,
|
| 511 |
+
"should_log": false,
|
| 512 |
+
"should_save": false,
|
| 513 |
+
"should_training_stop": false
|
| 514 |
+
},
|
| 515 |
+
"attributes": {}
|
| 516 |
+
}
|
| 517 |
+
},
|
| 518 |
+
"total_flos": 2.2475408052256202e+18,
|
| 519 |
+
"train_batch_size": 1,
|
| 520 |
+
"trial_name": null,
|
| 521 |
+
"trial_params": null
|
| 522 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1f789aa6d4161781b05d4d9b0a807aede8f8645ccce9e09a81f27bffdd28e51
|
| 3 |
+
size 5304
|