Commit
•
9dab44b
1
Parent(s):
cca2c14
End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-full-50epoc
|
| 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-full-50epoc
|
| 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: 1.2688
|
| 22 |
+
- Accuracy: 0.8630
|
| 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: 50
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
+
|:-------------:|:-----:|:------:|:---------------:|:--------:|
|
| 54 |
+
| 1.2025 | 1.0 | 2248 | 1.3446 | 0.5196 |
|
| 55 |
+
| 1.415 | 2.0 | 4496 | 1.6350 | 0.6032 |
|
| 56 |
+
| 1.4176 | 3.0 | 6744 | 1.6250 | 0.6584 |
|
| 57 |
+
| 1.384 | 4.0 | 8992 | 1.3694 | 0.7242 |
|
| 58 |
+
| 1.3658 | 5.0 | 11240 | 1.4331 | 0.7100 |
|
| 59 |
+
| 1.2763 | 6.0 | 13488 | 1.3311 | 0.7438 |
|
| 60 |
+
| 1.2175 | 7.0 | 15736 | 1.2727 | 0.7580 |
|
| 61 |
+
| 1.1276 | 8.0 | 17984 | 1.4520 | 0.7331 |
|
| 62 |
+
| 1.1053 | 9.0 | 20232 | 1.2134 | 0.7722 |
|
| 63 |
+
| 1.0314 | 10.0 | 22480 | 1.2143 | 0.7829 |
|
| 64 |
+
| 1.0029 | 11.0 | 24728 | 1.3312 | 0.7811 |
|
| 65 |
+
| 0.9108 | 12.0 | 26976 | 1.2228 | 0.8025 |
|
| 66 |
+
| 0.8335 | 13.0 | 29224 | 1.1526 | 0.8078 |
|
| 67 |
+
| 0.8514 | 14.0 | 31472 | 0.9904 | 0.8203 |
|
| 68 |
+
| 0.7389 | 15.0 | 33720 | 1.3000 | 0.8025 |
|
| 69 |
+
| 0.6993 | 16.0 | 35968 | 1.0873 | 0.8203 |
|
| 70 |
+
| 0.6177 | 17.0 | 38216 | 1.0856 | 0.8327 |
|
| 71 |
+
| 0.641 | 18.0 | 40464 | 1.3224 | 0.7972 |
|
| 72 |
+
| 0.611 | 19.0 | 42712 | 1.1800 | 0.8292 |
|
| 73 |
+
| 0.5744 | 20.0 | 44960 | 1.2937 | 0.8096 |
|
| 74 |
+
| 0.5008 | 21.0 | 47208 | 1.1565 | 0.8416 |
|
| 75 |
+
| 0.4396 | 22.0 | 49456 | 1.3663 | 0.8149 |
|
| 76 |
+
| 0.4313 | 23.0 | 51704 | 1.3267 | 0.8221 |
|
| 77 |
+
| 0.3954 | 24.0 | 53952 | 1.1824 | 0.8470 |
|
| 78 |
+
| 0.4217 | 25.0 | 56200 | 1.5586 | 0.8043 |
|
| 79 |
+
| 0.3797 | 26.0 | 58448 | 1.1746 | 0.8523 |
|
| 80 |
+
| 0.358 | 27.0 | 60696 | 1.1937 | 0.8452 |
|
| 81 |
+
| 0.2963 | 28.0 | 62944 | 1.4036 | 0.8310 |
|
| 82 |
+
| 0.3338 | 29.0 | 65192 | 1.3134 | 0.8505 |
|
| 83 |
+
| 0.2565 | 30.0 | 67440 | 1.4806 | 0.8345 |
|
| 84 |
+
| 0.2798 | 31.0 | 69688 | 1.5173 | 0.8310 |
|
| 85 |
+
| 0.2674 | 32.0 | 71936 | 1.5758 | 0.8132 |
|
| 86 |
+
| 0.2334 | 33.0 | 74184 | 1.3401 | 0.8559 |
|
| 87 |
+
| 0.2352 | 34.0 | 76432 | 1.2717 | 0.8470 |
|
| 88 |
+
| 0.2406 | 35.0 | 78680 | 1.6163 | 0.8256 |
|
| 89 |
+
| 0.2208 | 36.0 | 80928 | 1.3815 | 0.8505 |
|
| 90 |
+
| 0.1796 | 37.0 | 83176 | 1.3929 | 0.8577 |
|
| 91 |
+
| 0.2127 | 38.0 | 85424 | 1.5271 | 0.8274 |
|
| 92 |
+
| 0.1748 | 39.0 | 87672 | 1.5069 | 0.8416 |
|
| 93 |
+
| 0.1612 | 40.0 | 89920 | 1.3966 | 0.8470 |
|
| 94 |
+
| 0.1757 | 41.0 | 92168 | 1.4628 | 0.8470 |
|
| 95 |
+
| 0.1664 | 42.0 | 94416 | 1.3363 | 0.8523 |
|
| 96 |
+
| 0.1313 | 43.0 | 96664 | 1.4388 | 0.8434 |
|
| 97 |
+
| 0.1272 | 44.0 | 98912 | 1.3670 | 0.8630 |
|
| 98 |
+
| 0.1127 | 45.0 | 101160 | 1.4244 | 0.8541 |
|
| 99 |
+
| 0.1062 | 46.0 | 103408 | 1.3812 | 0.8541 |
|
| 100 |
+
| 0.0924 | 47.0 | 105656 | 1.4448 | 0.8541 |
|
| 101 |
+
| 0.0998 | 48.0 | 107904 | 1.3051 | 0.8683 |
|
| 102 |
+
| 0.1055 | 49.0 | 110152 | 1.2630 | 0.8701 |
|
| 103 |
+
| 0.1073 | 50.0 | 112400 | 1.2688 | 0.8630 |
|
| 104 |
+
|
| 105 |
+
|
| 106 |
+
### Framework versions
|
| 107 |
+
|
| 108 |
+
- Transformers 4.45.1
|
| 109 |
+
- Pytorch 2.4.1+cu118
|
| 110 |
+
- Datasets 3.0.1
|
| 111 |
+
- 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 sha256:77a1bd47864165619ddadb35f4e998ef5ae72a09929fab2fd26355f4691500cb
|
| 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/Oct07_15-18-07_ip-172-16-72-75.ap-northeast-1.compute.internal/events.out.tfevents.1728314406.ip-172-16-72-75.ap-northeast-1.compute.internal
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efd297e765ad105723738e3371090b86b1fcecfefe74b811a01814196710ab69
|
| 3 |
+
size 34173
|
trainer_state.json
ADDED
|
@@ -0,0 +1,842 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 50.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 112400,
|
| 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": 39.0721435546875,
|
| 14 |
+
"learning_rate": 9.800622775800713e-06,
|
| 15 |
+
"loss": 1.2025,
|
| 16 |
+
"step": 2248
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.5195729732513428,
|
| 21 |
+
"eval_loss": 1.3446124792099,
|
| 22 |
+
"eval_runtime": 43.8683,
|
| 23 |
+
"eval_samples_per_second": 12.811,
|
| 24 |
+
"eval_steps_per_second": 12.811,
|
| 25 |
+
"step": 2248
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 2.0,
|
| 29 |
+
"grad_norm": 0.9895684123039246,
|
| 30 |
+
"learning_rate": 9.600800711743772e-06,
|
| 31 |
+
"loss": 1.415,
|
| 32 |
+
"step": 4496
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.0,
|
| 36 |
+
"eval_accuracy": 0.6032028198242188,
|
| 37 |
+
"eval_loss": 1.6350069046020508,
|
| 38 |
+
"eval_runtime": 43.9062,
|
| 39 |
+
"eval_samples_per_second": 12.8,
|
| 40 |
+
"eval_steps_per_second": 12.8,
|
| 41 |
+
"step": 4496
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 3.0,
|
| 45 |
+
"grad_norm": 0.6042933464050293,
|
| 46 |
+
"learning_rate": 9.400800711743772e-06,
|
| 47 |
+
"loss": 1.4176,
|
| 48 |
+
"step": 6744
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.0,
|
| 52 |
+
"eval_accuracy": 0.6583629846572876,
|
| 53 |
+
"eval_loss": 1.6250243186950684,
|
| 54 |
+
"eval_runtime": 44.433,
|
| 55 |
+
"eval_samples_per_second": 12.648,
|
| 56 |
+
"eval_steps_per_second": 12.648,
|
| 57 |
+
"step": 6744
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.0,
|
| 61 |
+
"grad_norm": 0.39769357442855835,
|
| 62 |
+
"learning_rate": 9.200889679715304e-06,
|
| 63 |
+
"loss": 1.384,
|
| 64 |
+
"step": 8992
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 4.0,
|
| 68 |
+
"eval_accuracy": 0.7241992950439453,
|
| 69 |
+
"eval_loss": 1.3693625926971436,
|
| 70 |
+
"eval_runtime": 44.1124,
|
| 71 |
+
"eval_samples_per_second": 12.74,
|
| 72 |
+
"eval_steps_per_second": 12.74,
|
| 73 |
+
"step": 8992
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 5.0,
|
| 77 |
+
"grad_norm": 18.08792495727539,
|
| 78 |
+
"learning_rate": 9.000978647686834e-06,
|
| 79 |
+
"loss": 1.3658,
|
| 80 |
+
"step": 11240
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 5.0,
|
| 84 |
+
"eval_accuracy": 0.709964394569397,
|
| 85 |
+
"eval_loss": 1.4330979585647583,
|
| 86 |
+
"eval_runtime": 44.4448,
|
| 87 |
+
"eval_samples_per_second": 12.645,
|
| 88 |
+
"eval_steps_per_second": 12.645,
|
| 89 |
+
"step": 11240
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 6.0,
|
| 93 |
+
"grad_norm": 0.2233850061893463,
|
| 94 |
+
"learning_rate": 8.800978647686834e-06,
|
| 95 |
+
"loss": 1.2763,
|
| 96 |
+
"step": 13488
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 6.0,
|
| 100 |
+
"eval_accuracy": 0.7437722682952881,
|
| 101 |
+
"eval_loss": 1.3310519456863403,
|
| 102 |
+
"eval_runtime": 45.1045,
|
| 103 |
+
"eval_samples_per_second": 12.46,
|
| 104 |
+
"eval_steps_per_second": 12.46,
|
| 105 |
+
"step": 13488
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 7.0,
|
| 109 |
+
"grad_norm": 27.293367385864258,
|
| 110 |
+
"learning_rate": 8.601156583629893e-06,
|
| 111 |
+
"loss": 1.2175,
|
| 112 |
+
"step": 15736
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 7.0,
|
| 116 |
+
"eval_accuracy": 0.7580071091651917,
|
| 117 |
+
"eval_loss": 1.2726552486419678,
|
| 118 |
+
"eval_runtime": 44.7638,
|
| 119 |
+
"eval_samples_per_second": 12.555,
|
| 120 |
+
"eval_steps_per_second": 12.555,
|
| 121 |
+
"step": 15736
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 8.0,
|
| 125 |
+
"grad_norm": 4.855543613433838,
|
| 126 |
+
"learning_rate": 8.401156583629893e-06,
|
| 127 |
+
"loss": 1.1276,
|
| 128 |
+
"step": 17984
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 8.0,
|
| 132 |
+
"eval_accuracy": 0.7330960631370544,
|
| 133 |
+
"eval_loss": 1.4520480632781982,
|
| 134 |
+
"eval_runtime": 44.2783,
|
| 135 |
+
"eval_samples_per_second": 12.692,
|
| 136 |
+
"eval_steps_per_second": 12.692,
|
| 137 |
+
"step": 17984
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 9.0,
|
| 141 |
+
"grad_norm": 0.08200906962156296,
|
| 142 |
+
"learning_rate": 8.201245551601425e-06,
|
| 143 |
+
"loss": 1.1053,
|
| 144 |
+
"step": 20232
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 9.0,
|
| 148 |
+
"eval_accuracy": 0.77224200963974,
|
| 149 |
+
"eval_loss": 1.2134090662002563,
|
| 150 |
+
"eval_runtime": 44.2632,
|
| 151 |
+
"eval_samples_per_second": 12.697,
|
| 152 |
+
"eval_steps_per_second": 12.697,
|
| 153 |
+
"step": 20232
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 10.0,
|
| 157 |
+
"grad_norm": 0.09874199330806732,
|
| 158 |
+
"learning_rate": 8.001334519572955e-06,
|
| 159 |
+
"loss": 1.0314,
|
| 160 |
+
"step": 22480
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 10.0,
|
| 164 |
+
"eval_accuracy": 0.7829181551933289,
|
| 165 |
+
"eval_loss": 1.2143168449401855,
|
| 166 |
+
"eval_runtime": 44.2853,
|
| 167 |
+
"eval_samples_per_second": 12.69,
|
| 168 |
+
"eval_steps_per_second": 12.69,
|
| 169 |
+
"step": 22480
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 11.0,
|
| 173 |
+
"grad_norm": 0.23497702181339264,
|
| 174 |
+
"learning_rate": 7.801423487544484e-06,
|
| 175 |
+
"loss": 1.0029,
|
| 176 |
+
"step": 24728
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 11.0,
|
| 180 |
+
"eval_accuracy": 0.7811387777328491,
|
| 181 |
+
"eval_loss": 1.3311693668365479,
|
| 182 |
+
"eval_runtime": 44.0086,
|
| 183 |
+
"eval_samples_per_second": 12.77,
|
| 184 |
+
"eval_steps_per_second": 12.77,
|
| 185 |
+
"step": 24728
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 12.0,
|
| 189 |
+
"grad_norm": 0.08876941353082657,
|
| 190 |
+
"learning_rate": 7.6014234875444846e-06,
|
| 191 |
+
"loss": 0.9108,
|
| 192 |
+
"step": 26976
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 12.0,
|
| 196 |
+
"eval_accuracy": 0.8024911284446716,
|
| 197 |
+
"eval_loss": 1.2227764129638672,
|
| 198 |
+
"eval_runtime": 44.4307,
|
| 199 |
+
"eval_samples_per_second": 12.649,
|
| 200 |
+
"eval_steps_per_second": 12.649,
|
| 201 |
+
"step": 26976
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 13.0,
|
| 205 |
+
"grad_norm": 0.13910023868083954,
|
| 206 |
+
"learning_rate": 7.401512455516014e-06,
|
| 207 |
+
"loss": 0.8335,
|
| 208 |
+
"step": 29224
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 13.0,
|
| 212 |
+
"eval_accuracy": 0.8078292012214661,
|
| 213 |
+
"eval_loss": 1.1526196002960205,
|
| 214 |
+
"eval_runtime": 44.5737,
|
| 215 |
+
"eval_samples_per_second": 12.608,
|
| 216 |
+
"eval_steps_per_second": 12.608,
|
| 217 |
+
"step": 29224
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 14.0,
|
| 221 |
+
"grad_norm": 159.14675903320312,
|
| 222 |
+
"learning_rate": 7.201601423487545e-06,
|
| 223 |
+
"loss": 0.8514,
|
| 224 |
+
"step": 31472
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 14.0,
|
| 228 |
+
"eval_accuracy": 0.8202847242355347,
|
| 229 |
+
"eval_loss": 0.9904452562332153,
|
| 230 |
+
"eval_runtime": 44.2371,
|
| 231 |
+
"eval_samples_per_second": 12.704,
|
| 232 |
+
"eval_steps_per_second": 12.704,
|
| 233 |
+
"step": 31472
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 15.0,
|
| 237 |
+
"grad_norm": 0.09662589430809021,
|
| 238 |
+
"learning_rate": 7.001601423487545e-06,
|
| 239 |
+
"loss": 0.7389,
|
| 240 |
+
"step": 33720
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 15.0,
|
| 244 |
+
"eval_accuracy": 0.8024911284446716,
|
| 245 |
+
"eval_loss": 1.2999956607818604,
|
| 246 |
+
"eval_runtime": 43.9303,
|
| 247 |
+
"eval_samples_per_second": 12.793,
|
| 248 |
+
"eval_steps_per_second": 12.793,
|
| 249 |
+
"step": 33720
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 16.0,
|
| 253 |
+
"grad_norm": 0.1123761385679245,
|
| 254 |
+
"learning_rate": 6.801690391459075e-06,
|
| 255 |
+
"loss": 0.6993,
|
| 256 |
+
"step": 35968
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 16.0,
|
| 260 |
+
"eval_accuracy": 0.8202847242355347,
|
| 261 |
+
"eval_loss": 1.0872814655303955,
|
| 262 |
+
"eval_runtime": 44.4779,
|
| 263 |
+
"eval_samples_per_second": 12.636,
|
| 264 |
+
"eval_steps_per_second": 12.636,
|
| 265 |
+
"step": 35968
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 17.0,
|
| 269 |
+
"grad_norm": 0.5431187748908997,
|
| 270 |
+
"learning_rate": 6.601690391459076e-06,
|
| 271 |
+
"loss": 0.6177,
|
| 272 |
+
"step": 38216
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 17.0,
|
| 276 |
+
"eval_accuracy": 0.8327401876449585,
|
| 277 |
+
"eval_loss": 1.0856190919876099,
|
| 278 |
+
"eval_runtime": 44.047,
|
| 279 |
+
"eval_samples_per_second": 12.759,
|
| 280 |
+
"eval_steps_per_second": 12.759,
|
| 281 |
+
"step": 38216
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 18.0,
|
| 285 |
+
"grad_norm": 0.034104421734809875,
|
| 286 |
+
"learning_rate": 6.401868327402135e-06,
|
| 287 |
+
"loss": 0.641,
|
| 288 |
+
"step": 40464
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 18.0,
|
| 292 |
+
"eval_accuracy": 0.7971529960632324,
|
| 293 |
+
"eval_loss": 1.3224000930786133,
|
| 294 |
+
"eval_runtime": 43.8821,
|
| 295 |
+
"eval_samples_per_second": 12.807,
|
| 296 |
+
"eval_steps_per_second": 12.807,
|
| 297 |
+
"step": 40464
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 19.0,
|
| 301 |
+
"grad_norm": 0.05449577793478966,
|
| 302 |
+
"learning_rate": 6.201957295373666e-06,
|
| 303 |
+
"loss": 0.611,
|
| 304 |
+
"step": 42712
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 19.0,
|
| 308 |
+
"eval_accuracy": 0.8291814923286438,
|
| 309 |
+
"eval_loss": 1.1800107955932617,
|
| 310 |
+
"eval_runtime": 43.8606,
|
| 311 |
+
"eval_samples_per_second": 12.813,
|
| 312 |
+
"eval_steps_per_second": 12.813,
|
| 313 |
+
"step": 42712
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 20.0,
|
| 317 |
+
"grad_norm": 24.56753158569336,
|
| 318 |
+
"learning_rate": 6.001957295373666e-06,
|
| 319 |
+
"loss": 0.5744,
|
| 320 |
+
"step": 44960
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 20.0,
|
| 324 |
+
"eval_accuracy": 0.809608519077301,
|
| 325 |
+
"eval_loss": 1.2937426567077637,
|
| 326 |
+
"eval_runtime": 44.1614,
|
| 327 |
+
"eval_samples_per_second": 12.726,
|
| 328 |
+
"eval_steps_per_second": 12.726,
|
| 329 |
+
"step": 44960
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 21.0,
|
| 333 |
+
"grad_norm": 0.14437897503376007,
|
| 334 |
+
"learning_rate": 5.802046263345196e-06,
|
| 335 |
+
"loss": 0.5008,
|
| 336 |
+
"step": 47208
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 21.0,
|
| 340 |
+
"eval_accuracy": 0.8416370153427124,
|
| 341 |
+
"eval_loss": 1.1565003395080566,
|
| 342 |
+
"eval_runtime": 44.2577,
|
| 343 |
+
"eval_samples_per_second": 12.698,
|
| 344 |
+
"eval_steps_per_second": 12.698,
|
| 345 |
+
"step": 47208
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 22.0,
|
| 349 |
+
"grad_norm": 0.044370945543050766,
|
| 350 |
+
"learning_rate": 5.6021352313167265e-06,
|
| 351 |
+
"loss": 0.4396,
|
| 352 |
+
"step": 49456
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 22.0,
|
| 356 |
+
"eval_accuracy": 0.8149465918540955,
|
| 357 |
+
"eval_loss": 1.366288661956787,
|
| 358 |
+
"eval_runtime": 44.4773,
|
| 359 |
+
"eval_samples_per_second": 12.636,
|
| 360 |
+
"eval_steps_per_second": 12.636,
|
| 361 |
+
"step": 49456
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 23.0,
|
| 365 |
+
"grad_norm": 0.21999333798885345,
|
| 366 |
+
"learning_rate": 5.402224199288256e-06,
|
| 367 |
+
"loss": 0.4313,
|
| 368 |
+
"step": 51704
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 23.0,
|
| 372 |
+
"eval_accuracy": 0.8220640420913696,
|
| 373 |
+
"eval_loss": 1.3266714811325073,
|
| 374 |
+
"eval_runtime": 43.9122,
|
| 375 |
+
"eval_samples_per_second": 12.798,
|
| 376 |
+
"eval_steps_per_second": 12.798,
|
| 377 |
+
"step": 51704
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 24.0,
|
| 381 |
+
"grad_norm": 0.037919577211141586,
|
| 382 |
+
"learning_rate": 5.202313167259787e-06,
|
| 383 |
+
"loss": 0.3954,
|
| 384 |
+
"step": 53952
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 24.0,
|
| 388 |
+
"eval_accuracy": 0.8469750881195068,
|
| 389 |
+
"eval_loss": 1.1824334859848022,
|
| 390 |
+
"eval_runtime": 44.2008,
|
| 391 |
+
"eval_samples_per_second": 12.715,
|
| 392 |
+
"eval_steps_per_second": 12.715,
|
| 393 |
+
"step": 53952
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 25.0,
|
| 397 |
+
"grad_norm": 106.5145263671875,
|
| 398 |
+
"learning_rate": 5.002491103202848e-06,
|
| 399 |
+
"loss": 0.4217,
|
| 400 |
+
"step": 56200
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 25.0,
|
| 404 |
+
"eval_accuracy": 0.8042704463005066,
|
| 405 |
+
"eval_loss": 1.5585525035858154,
|
| 406 |
+
"eval_runtime": 43.9488,
|
| 407 |
+
"eval_samples_per_second": 12.788,
|
| 408 |
+
"eval_steps_per_second": 12.788,
|
| 409 |
+
"step": 56200
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 26.0,
|
| 413 |
+
"grad_norm": 0.015882058069109917,
|
| 414 |
+
"learning_rate": 4.802491103202847e-06,
|
| 415 |
+
"loss": 0.3797,
|
| 416 |
+
"step": 58448
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 26.0,
|
| 420 |
+
"eval_accuracy": 0.8523131608963013,
|
| 421 |
+
"eval_loss": 1.1745574474334717,
|
| 422 |
+
"eval_runtime": 43.9074,
|
| 423 |
+
"eval_samples_per_second": 12.8,
|
| 424 |
+
"eval_steps_per_second": 12.8,
|
| 425 |
+
"step": 58448
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 27.0,
|
| 429 |
+
"grad_norm": 0.03550243377685547,
|
| 430 |
+
"learning_rate": 4.602580071174377e-06,
|
| 431 |
+
"loss": 0.358,
|
| 432 |
+
"step": 60696
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 27.0,
|
| 436 |
+
"eval_accuracy": 0.8451957106590271,
|
| 437 |
+
"eval_loss": 1.1937276124954224,
|
| 438 |
+
"eval_runtime": 43.8357,
|
| 439 |
+
"eval_samples_per_second": 12.821,
|
| 440 |
+
"eval_steps_per_second": 12.821,
|
| 441 |
+
"step": 60696
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 28.0,
|
| 445 |
+
"grad_norm": 0.009829429909586906,
|
| 446 |
+
"learning_rate": 4.402669039145908e-06,
|
| 447 |
+
"loss": 0.2963,
|
| 448 |
+
"step": 62944
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 28.0,
|
| 452 |
+
"eval_accuracy": 0.8309608697891235,
|
| 453 |
+
"eval_loss": 1.4036489725112915,
|
| 454 |
+
"eval_runtime": 44.7776,
|
| 455 |
+
"eval_samples_per_second": 12.551,
|
| 456 |
+
"eval_steps_per_second": 12.551,
|
| 457 |
+
"step": 62944
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 29.0,
|
| 461 |
+
"grad_norm": Infinity,
|
| 462 |
+
"learning_rate": 4.202758007117438e-06,
|
| 463 |
+
"loss": 0.3338,
|
| 464 |
+
"step": 65192
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 29.0,
|
| 468 |
+
"eval_accuracy": 0.8505337834358215,
|
| 469 |
+
"eval_loss": 1.3133819103240967,
|
| 470 |
+
"eval_runtime": 43.9603,
|
| 471 |
+
"eval_samples_per_second": 12.784,
|
| 472 |
+
"eval_steps_per_second": 12.784,
|
| 473 |
+
"step": 65192
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 30.0,
|
| 477 |
+
"grad_norm": 0.012281532399356365,
|
| 478 |
+
"learning_rate": 4.0027580071174384e-06,
|
| 479 |
+
"loss": 0.2565,
|
| 480 |
+
"step": 67440
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 30.0,
|
| 484 |
+
"eval_accuracy": 0.8345195651054382,
|
| 485 |
+
"eval_loss": 1.480637788772583,
|
| 486 |
+
"eval_runtime": 44.0574,
|
| 487 |
+
"eval_samples_per_second": 12.756,
|
| 488 |
+
"eval_steps_per_second": 12.756,
|
| 489 |
+
"step": 67440
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 31.0,
|
| 493 |
+
"grad_norm": 0.0023416499607264996,
|
| 494 |
+
"learning_rate": 3.8028469750889686e-06,
|
| 495 |
+
"loss": 0.2798,
|
| 496 |
+
"step": 69688
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 31.0,
|
| 500 |
+
"eval_accuracy": 0.8309608697891235,
|
| 501 |
+
"eval_loss": 1.5173381567001343,
|
| 502 |
+
"eval_runtime": 44.0999,
|
| 503 |
+
"eval_samples_per_second": 12.744,
|
| 504 |
+
"eval_steps_per_second": 12.744,
|
| 505 |
+
"step": 69688
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 32.0,
|
| 509 |
+
"grad_norm": 5.919681072235107,
|
| 510 |
+
"learning_rate": 3.602935943060499e-06,
|
| 511 |
+
"loss": 0.2674,
|
| 512 |
+
"step": 71936
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 32.0,
|
| 516 |
+
"eval_accuracy": 0.8131672739982605,
|
| 517 |
+
"eval_loss": 1.5758373737335205,
|
| 518 |
+
"eval_runtime": 44.4876,
|
| 519 |
+
"eval_samples_per_second": 12.633,
|
| 520 |
+
"eval_steps_per_second": 12.633,
|
| 521 |
+
"step": 71936
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 33.0,
|
| 525 |
+
"grad_norm": 0.0024983042385429144,
|
| 526 |
+
"learning_rate": 3.4029359430604986e-06,
|
| 527 |
+
"loss": 0.2334,
|
| 528 |
+
"step": 74184
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 33.0,
|
| 532 |
+
"eval_accuracy": 0.8558719158172607,
|
| 533 |
+
"eval_loss": 1.3400838375091553,
|
| 534 |
+
"eval_runtime": 44.5806,
|
| 535 |
+
"eval_samples_per_second": 12.606,
|
| 536 |
+
"eval_steps_per_second": 12.606,
|
| 537 |
+
"step": 74184
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 34.0,
|
| 541 |
+
"grad_norm": 0.0015680283540859818,
|
| 542 |
+
"learning_rate": 3.2030249110320288e-06,
|
| 543 |
+
"loss": 0.2352,
|
| 544 |
+
"step": 76432
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 34.0,
|
| 548 |
+
"eval_accuracy": 0.8469750881195068,
|
| 549 |
+
"eval_loss": 1.2716737985610962,
|
| 550 |
+
"eval_runtime": 44.3768,
|
| 551 |
+
"eval_samples_per_second": 12.664,
|
| 552 |
+
"eval_steps_per_second": 12.664,
|
| 553 |
+
"step": 76432
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 35.0,
|
| 557 |
+
"grad_norm": 0.0035891232546418905,
|
| 558 |
+
"learning_rate": 3.003113879003559e-06,
|
| 559 |
+
"loss": 0.2406,
|
| 560 |
+
"step": 78680
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 35.0,
|
| 564 |
+
"eval_accuracy": 0.8256227970123291,
|
| 565 |
+
"eval_loss": 1.6162846088409424,
|
| 566 |
+
"eval_runtime": 44.1614,
|
| 567 |
+
"eval_samples_per_second": 12.726,
|
| 568 |
+
"eval_steps_per_second": 12.726,
|
| 569 |
+
"step": 78680
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 36.0,
|
| 573 |
+
"grad_norm": 0.003527622204273939,
|
| 574 |
+
"learning_rate": 2.8032028469750896e-06,
|
| 575 |
+
"loss": 0.2208,
|
| 576 |
+
"step": 80928
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 36.0,
|
| 580 |
+
"eval_accuracy": 0.8505337834358215,
|
| 581 |
+
"eval_loss": 1.3815460205078125,
|
| 582 |
+
"eval_runtime": 44.6638,
|
| 583 |
+
"eval_samples_per_second": 12.583,
|
| 584 |
+
"eval_steps_per_second": 12.583,
|
| 585 |
+
"step": 80928
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 37.0,
|
| 589 |
+
"grad_norm": 0.0015290452865883708,
|
| 590 |
+
"learning_rate": 2.6033807829181497e-06,
|
| 591 |
+
"loss": 0.1796,
|
| 592 |
+
"step": 83176
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 37.0,
|
| 596 |
+
"eval_accuracy": 0.8576512336730957,
|
| 597 |
+
"eval_loss": 1.392934799194336,
|
| 598 |
+
"eval_runtime": 44.8201,
|
| 599 |
+
"eval_samples_per_second": 12.539,
|
| 600 |
+
"eval_steps_per_second": 12.539,
|
| 601 |
+
"step": 83176
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 38.0,
|
| 605 |
+
"grad_norm": 0.00960911251604557,
|
| 606 |
+
"learning_rate": 2.4033807829181495e-06,
|
| 607 |
+
"loss": 0.2127,
|
| 608 |
+
"step": 85424
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 38.0,
|
| 612 |
+
"eval_accuracy": 0.8274021148681641,
|
| 613 |
+
"eval_loss": 1.5271013975143433,
|
| 614 |
+
"eval_runtime": 44.255,
|
| 615 |
+
"eval_samples_per_second": 12.699,
|
| 616 |
+
"eval_steps_per_second": 12.699,
|
| 617 |
+
"step": 85424
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 39.0,
|
| 621 |
+
"grad_norm": 0.004349031951278448,
|
| 622 |
+
"learning_rate": 2.20355871886121e-06,
|
| 623 |
+
"loss": 0.1748,
|
| 624 |
+
"step": 87672
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 39.0,
|
| 628 |
+
"eval_accuracy": 0.8416370153427124,
|
| 629 |
+
"eval_loss": 1.50688636302948,
|
| 630 |
+
"eval_runtime": 44.0422,
|
| 631 |
+
"eval_samples_per_second": 12.76,
|
| 632 |
+
"eval_steps_per_second": 12.76,
|
| 633 |
+
"step": 87672
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 40.0,
|
| 637 |
+
"grad_norm": 0.0012758744414895773,
|
| 638 |
+
"learning_rate": 2.0035587188612103e-06,
|
| 639 |
+
"loss": 0.1612,
|
| 640 |
+
"step": 89920
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 40.0,
|
| 644 |
+
"eval_accuracy": 0.8469750881195068,
|
| 645 |
+
"eval_loss": 1.396645426750183,
|
| 646 |
+
"eval_runtime": 44.1524,
|
| 647 |
+
"eval_samples_per_second": 12.729,
|
| 648 |
+
"eval_steps_per_second": 12.729,
|
| 649 |
+
"step": 89920
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 41.0,
|
| 653 |
+
"grad_norm": 0.0022624109406024218,
|
| 654 |
+
"learning_rate": 1.8036476868327405e-06,
|
| 655 |
+
"loss": 0.1757,
|
| 656 |
+
"step": 92168
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 41.0,
|
| 660 |
+
"eval_accuracy": 0.8469750881195068,
|
| 661 |
+
"eval_loss": 1.4628039598464966,
|
| 662 |
+
"eval_runtime": 44.3029,
|
| 663 |
+
"eval_samples_per_second": 12.685,
|
| 664 |
+
"eval_steps_per_second": 12.685,
|
| 665 |
+
"step": 92168
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 42.0,
|
| 669 |
+
"grad_norm": 0.007528578396886587,
|
| 670 |
+
"learning_rate": 1.6037366548042707e-06,
|
| 671 |
+
"loss": 0.1664,
|
| 672 |
+
"step": 94416
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 42.0,
|
| 676 |
+
"eval_accuracy": 0.8523131608963013,
|
| 677 |
+
"eval_loss": 1.3362900018692017,
|
| 678 |
+
"eval_runtime": 43.78,
|
| 679 |
+
"eval_samples_per_second": 12.837,
|
| 680 |
+
"eval_steps_per_second": 12.837,
|
| 681 |
+
"step": 94416
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 43.0,
|
| 685 |
+
"grad_norm": 0.0013060200726613402,
|
| 686 |
+
"learning_rate": 1.4038256227758006e-06,
|
| 687 |
+
"loss": 0.1313,
|
| 688 |
+
"step": 96664
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 43.0,
|
| 692 |
+
"eval_accuracy": 0.8434163928031921,
|
| 693 |
+
"eval_loss": 1.438825011253357,
|
| 694 |
+
"eval_runtime": 43.9878,
|
| 695 |
+
"eval_samples_per_second": 12.776,
|
| 696 |
+
"eval_steps_per_second": 12.776,
|
| 697 |
+
"step": 96664
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 44.0,
|
| 701 |
+
"grad_norm": 0.042194243520498276,
|
| 702 |
+
"learning_rate": 1.203914590747331e-06,
|
| 703 |
+
"loss": 0.1272,
|
| 704 |
+
"step": 98912
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 44.0,
|
| 708 |
+
"eval_accuracy": 0.8629893064498901,
|
| 709 |
+
"eval_loss": 1.3669886589050293,
|
| 710 |
+
"eval_runtime": 43.6968,
|
| 711 |
+
"eval_samples_per_second": 12.861,
|
| 712 |
+
"eval_steps_per_second": 12.861,
|
| 713 |
+
"step": 98912
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 45.0,
|
| 717 |
+
"grad_norm": 0.00658341683447361,
|
| 718 |
+
"learning_rate": 1.0040035587188612e-06,
|
| 719 |
+
"loss": 0.1127,
|
| 720 |
+
"step": 101160
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 45.0,
|
| 724 |
+
"eval_accuracy": 0.854092538356781,
|
| 725 |
+
"eval_loss": 1.4244239330291748,
|
| 726 |
+
"eval_runtime": 43.9697,
|
| 727 |
+
"eval_samples_per_second": 12.782,
|
| 728 |
+
"eval_steps_per_second": 12.782,
|
| 729 |
+
"step": 101160
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 46.0,
|
| 733 |
+
"grad_norm": 0.0009845913155004382,
|
| 734 |
+
"learning_rate": 8.040035587188613e-07,
|
| 735 |
+
"loss": 0.1062,
|
| 736 |
+
"step": 103408
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 46.0,
|
| 740 |
+
"eval_accuracy": 0.854092538356781,
|
| 741 |
+
"eval_loss": 1.3811708688735962,
|
| 742 |
+
"eval_runtime": 44.3254,
|
| 743 |
+
"eval_samples_per_second": 12.679,
|
| 744 |
+
"eval_steps_per_second": 12.679,
|
| 745 |
+
"step": 103408
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 47.0,
|
| 749 |
+
"grad_norm": 0.0018777468940243125,
|
| 750 |
+
"learning_rate": 6.040925266903915e-07,
|
| 751 |
+
"loss": 0.0924,
|
| 752 |
+
"step": 105656
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 47.0,
|
| 756 |
+
"eval_accuracy": 0.854092538356781,
|
| 757 |
+
"eval_loss": 1.4448031187057495,
|
| 758 |
+
"eval_runtime": 44.1197,
|
| 759 |
+
"eval_samples_per_second": 12.738,
|
| 760 |
+
"eval_steps_per_second": 12.738,
|
| 761 |
+
"step": 105656
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 48.0,
|
| 765 |
+
"grad_norm": 0.0018540391465649009,
|
| 766 |
+
"learning_rate": 4.040925266903915e-07,
|
| 767 |
+
"loss": 0.0998,
|
| 768 |
+
"step": 107904
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 48.0,
|
| 772 |
+
"eval_accuracy": 0.8683273792266846,
|
| 773 |
+
"eval_loss": 1.305090069770813,
|
| 774 |
+
"eval_runtime": 43.7364,
|
| 775 |
+
"eval_samples_per_second": 12.85,
|
| 776 |
+
"eval_steps_per_second": 12.85,
|
| 777 |
+
"step": 107904
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 49.0,
|
| 781 |
+
"grad_norm": 0.0024543912149965763,
|
| 782 |
+
"learning_rate": 2.0418149466192174e-07,
|
| 783 |
+
"loss": 0.1055,
|
| 784 |
+
"step": 110152
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 49.0,
|
| 788 |
+
"eval_accuracy": 0.8701067566871643,
|
| 789 |
+
"eval_loss": 1.262986660003662,
|
| 790 |
+
"eval_runtime": 44.2858,
|
| 791 |
+
"eval_samples_per_second": 12.69,
|
| 792 |
+
"eval_steps_per_second": 12.69,
|
| 793 |
+
"step": 110152
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 50.0,
|
| 797 |
+
"grad_norm": 0.00034937995951622725,
|
| 798 |
+
"learning_rate": 4.181494661921708e-09,
|
| 799 |
+
"loss": 0.1073,
|
| 800 |
+
"step": 112400
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 50.0,
|
| 804 |
+
"eval_accuracy": 0.8629893064498901,
|
| 805 |
+
"eval_loss": 1.268770456314087,
|
| 806 |
+
"eval_runtime": 44.0645,
|
| 807 |
+
"eval_samples_per_second": 12.754,
|
| 808 |
+
"eval_steps_per_second": 12.754,
|
| 809 |
+
"step": 112400
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 50.0,
|
| 813 |
+
"step": 112400,
|
| 814 |
+
"total_flos": 1.024714436352e+19,
|
| 815 |
+
"train_loss": 0.5453376764589357,
|
| 816 |
+
"train_runtime": 19116.6154,
|
| 817 |
+
"train_samples_per_second": 5.88,
|
| 818 |
+
"train_steps_per_second": 5.88
|
| 819 |
+
}
|
| 820 |
+
],
|
| 821 |
+
"logging_steps": 35,
|
| 822 |
+
"max_steps": 112400,
|
| 823 |
+
"num_input_tokens_seen": 0,
|
| 824 |
+
"num_train_epochs": 50,
|
| 825 |
+
"save_steps": 500,
|
| 826 |
+
"stateful_callbacks": {
|
| 827 |
+
"TrainerControl": {
|
| 828 |
+
"args": {
|
| 829 |
+
"should_epoch_stop": false,
|
| 830 |
+
"should_evaluate": false,
|
| 831 |
+
"should_log": false,
|
| 832 |
+
"should_save": false,
|
| 833 |
+
"should_training_stop": false
|
| 834 |
+
},
|
| 835 |
+
"attributes": {}
|
| 836 |
+
}
|
| 837 |
+
},
|
| 838 |
+
"total_flos": 1.024714436352e+19,
|
| 839 |
+
"train_batch_size": 1,
|
| 840 |
+
"trial_name": null,
|
| 841 |
+
"trial_params": null
|
| 842 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:339e930e7d3feb742c3ca02cb436e6be9b39f68e55532d41ce0713d4718b683d
|
| 3 |
+
size 5304
|