Commit
•
9c57240
1
Parent(s):
65e9ac6
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-full
|
| 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
|
| 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: 1.2928
|
| 22 |
+
- Accuracy: 0.8488
|
| 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 |
+
| 1.2057 | 1.0 | 2248 | 1.4522 | 0.4502 |
|
| 55 |
+
| 1.3873 | 2.0 | 4496 | 1.4503 | 0.6423 |
|
| 56 |
+
| 1.4246 | 3.0 | 6744 | 1.6165 | 0.6673 |
|
| 57 |
+
| 1.3335 | 4.0 | 8992 | 1.4786 | 0.7206 |
|
| 58 |
+
| 1.251 | 5.0 | 11240 | 1.6414 | 0.6886 |
|
| 59 |
+
| 1.1859 | 6.0 | 13488 | 1.3300 | 0.7544 |
|
| 60 |
+
| 1.1132 | 7.0 | 15736 | 1.3665 | 0.7509 |
|
| 61 |
+
| 1.0189 | 8.0 | 17984 | 1.6665 | 0.7153 |
|
| 62 |
+
| 0.9807 | 9.0 | 20232 | 1.1175 | 0.7794 |
|
| 63 |
+
| 0.8786 | 10.0 | 22480 | 1.1786 | 0.7883 |
|
| 64 |
+
| 0.8677 | 11.0 | 24728 | 1.1295 | 0.7811 |
|
| 65 |
+
| 0.7554 | 12.0 | 26976 | 1.1185 | 0.8185 |
|
| 66 |
+
| 0.7196 | 13.0 | 29224 | 1.4067 | 0.7847 |
|
| 67 |
+
| 0.692 | 14.0 | 31472 | 1.1175 | 0.8203 |
|
| 68 |
+
| 0.6276 | 15.0 | 33720 | 1.4490 | 0.7883 |
|
| 69 |
+
| 0.6083 | 16.0 | 35968 | 1.0983 | 0.8345 |
|
| 70 |
+
| 0.5204 | 17.0 | 38216 | 1.1814 | 0.8256 |
|
| 71 |
+
| 0.5197 | 18.0 | 40464 | 1.2945 | 0.8167 |
|
| 72 |
+
| 0.488 | 19.0 | 42712 | 1.4494 | 0.8025 |
|
| 73 |
+
| 0.4714 | 20.0 | 44960 | 1.3499 | 0.8114 |
|
| 74 |
+
| 0.3641 | 21.0 | 47208 | 1.2525 | 0.8381 |
|
| 75 |
+
| 0.3877 | 22.0 | 49456 | 1.2610 | 0.8381 |
|
| 76 |
+
| 0.3253 | 23.0 | 51704 | 1.3913 | 0.8274 |
|
| 77 |
+
| 0.2978 | 24.0 | 53952 | 1.2990 | 0.8416 |
|
| 78 |
+
| 0.3238 | 25.0 | 56200 | 1.4328 | 0.8274 |
|
| 79 |
+
| 0.2669 | 26.0 | 58448 | 1.3079 | 0.8327 |
|
| 80 |
+
| 0.2521 | 27.0 | 60696 | 1.3250 | 0.8399 |
|
| 81 |
+
| 0.2632 | 28.0 | 62944 | 1.3357 | 0.8416 |
|
| 82 |
+
| 0.2655 | 29.0 | 65192 | 1.2957 | 0.8434 |
|
| 83 |
+
| 0.2379 | 30.0 | 67440 | 1.2928 | 0.8488 |
|
| 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 sha256:1622cb85667a6e765fab471293519adb31ebe992efb8e926f1be915b5ba3d20e
|
| 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_11-54-25_ip-172-16-72-75.ap-northeast-1.compute.internal/events.out.tfevents.1728302194.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:b38f8cb310f8cb2dd0d607096a867437293db07744f7c413bc8185130dbaab37
|
| 3 |
+
size 23272
|
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": 67440,
|
| 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": 20.024471282958984,
|
| 14 |
+
"learning_rate": 9.66755634638197e-06,
|
| 15 |
+
"loss": 1.2057,
|
| 16 |
+
"step": 2248
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.450177937746048,
|
| 21 |
+
"eval_loss": 1.4521995782852173,
|
| 22 |
+
"eval_runtime": 46.9769,
|
| 23 |
+
"eval_samples_per_second": 11.963,
|
| 24 |
+
"eval_steps_per_second": 11.963,
|
| 25 |
+
"step": 2248
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 2.0,
|
| 29 |
+
"grad_norm": 40.918148040771484,
|
| 30 |
+
"learning_rate": 9.334371293001186e-06,
|
| 31 |
+
"loss": 1.3873,
|
| 32 |
+
"step": 4496
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.0,
|
| 36 |
+
"eval_accuracy": 0.6423487663269043,
|
| 37 |
+
"eval_loss": 1.4503390789031982,
|
| 38 |
+
"eval_runtime": 47.9141,
|
| 39 |
+
"eval_samples_per_second": 11.729,
|
| 40 |
+
"eval_steps_per_second": 11.729,
|
| 41 |
+
"step": 4496
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 3.0,
|
| 45 |
+
"grad_norm": 14.9369478225708,
|
| 46 |
+
"learning_rate": 9.001334519572953e-06,
|
| 47 |
+
"loss": 1.4246,
|
| 48 |
+
"step": 6744
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.0,
|
| 52 |
+
"eval_accuracy": 0.6672598123550415,
|
| 53 |
+
"eval_loss": 1.6165008544921875,
|
| 54 |
+
"eval_runtime": 47.7427,
|
| 55 |
+
"eval_samples_per_second": 11.771,
|
| 56 |
+
"eval_steps_per_second": 11.771,
|
| 57 |
+
"step": 6744
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.0,
|
| 61 |
+
"grad_norm": 0.12427664548158646,
|
| 62 |
+
"learning_rate": 8.668149466192172e-06,
|
| 63 |
+
"loss": 1.3335,
|
| 64 |
+
"step": 8992
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 4.0,
|
| 68 |
+
"eval_accuracy": 0.7206405401229858,
|
| 69 |
+
"eval_loss": 1.478636384010315,
|
| 70 |
+
"eval_runtime": 47.5592,
|
| 71 |
+
"eval_samples_per_second": 11.817,
|
| 72 |
+
"eval_steps_per_second": 11.817,
|
| 73 |
+
"step": 8992
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 5.0,
|
| 77 |
+
"grad_norm": 0.1769200563430786,
|
| 78 |
+
"learning_rate": 8.334964412811389e-06,
|
| 79 |
+
"loss": 1.251,
|
| 80 |
+
"step": 11240
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 5.0,
|
| 84 |
+
"eval_accuracy": 0.6886121034622192,
|
| 85 |
+
"eval_loss": 1.6414002180099487,
|
| 86 |
+
"eval_runtime": 47.4426,
|
| 87 |
+
"eval_samples_per_second": 11.846,
|
| 88 |
+
"eval_steps_per_second": 11.846,
|
| 89 |
+
"step": 11240
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 6.0,
|
| 93 |
+
"grad_norm": 0.14434462785720825,
|
| 94 |
+
"learning_rate": 8.001779359430606e-06,
|
| 95 |
+
"loss": 1.1859,
|
| 96 |
+
"step": 13488
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 6.0,
|
| 100 |
+
"eval_accuracy": 0.754448413848877,
|
| 101 |
+
"eval_loss": 1.329976201057434,
|
| 102 |
+
"eval_runtime": 47.6847,
|
| 103 |
+
"eval_samples_per_second": 11.786,
|
| 104 |
+
"eval_steps_per_second": 11.786,
|
| 105 |
+
"step": 13488
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 7.0,
|
| 109 |
+
"grad_norm": 24.07697105407715,
|
| 110 |
+
"learning_rate": 7.668446026097273e-06,
|
| 111 |
+
"loss": 1.1132,
|
| 112 |
+
"step": 15736
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 7.0,
|
| 116 |
+
"eval_accuracy": 0.7508896589279175,
|
| 117 |
+
"eval_loss": 1.3665430545806885,
|
| 118 |
+
"eval_runtime": 47.6469,
|
| 119 |
+
"eval_samples_per_second": 11.795,
|
| 120 |
+
"eval_steps_per_second": 11.795,
|
| 121 |
+
"step": 15736
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 8.0,
|
| 125 |
+
"grad_norm": 3.64510178565979,
|
| 126 |
+
"learning_rate": 7.335112692763939e-06,
|
| 127 |
+
"loss": 1.0189,
|
| 128 |
+
"step": 17984
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 8.0,
|
| 132 |
+
"eval_accuracy": 0.7153024673461914,
|
| 133 |
+
"eval_loss": 1.6664679050445557,
|
| 134 |
+
"eval_runtime": 47.663,
|
| 135 |
+
"eval_samples_per_second": 11.791,
|
| 136 |
+
"eval_steps_per_second": 11.791,
|
| 137 |
+
"step": 17984
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 9.0,
|
| 141 |
+
"grad_norm": 0.2391408234834671,
|
| 142 |
+
"learning_rate": 7.001927639383156e-06,
|
| 143 |
+
"loss": 0.9807,
|
| 144 |
+
"step": 20232
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 9.0,
|
| 148 |
+
"eval_accuracy": 0.7793594598770142,
|
| 149 |
+
"eval_loss": 1.1174825429916382,
|
| 150 |
+
"eval_runtime": 47.784,
|
| 151 |
+
"eval_samples_per_second": 11.761,
|
| 152 |
+
"eval_steps_per_second": 11.761,
|
| 153 |
+
"step": 20232
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 10.0,
|
| 157 |
+
"grad_norm": 0.037992771714925766,
|
| 158 |
+
"learning_rate": 6.668890865954924e-06,
|
| 159 |
+
"loss": 0.8786,
|
| 160 |
+
"step": 22480
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 10.0,
|
| 164 |
+
"eval_accuracy": 0.7882562279701233,
|
| 165 |
+
"eval_loss": 1.1786267757415771,
|
| 166 |
+
"eval_runtime": 47.6281,
|
| 167 |
+
"eval_samples_per_second": 11.8,
|
| 168 |
+
"eval_steps_per_second": 11.8,
|
| 169 |
+
"step": 22480
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 11.0,
|
| 173 |
+
"grad_norm": 0.07834123820066452,
|
| 174 |
+
"learning_rate": 6.3355575326215905e-06,
|
| 175 |
+
"loss": 0.8677,
|
| 176 |
+
"step": 24728
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 11.0,
|
| 180 |
+
"eval_accuracy": 0.7811387777328491,
|
| 181 |
+
"eval_loss": 1.1294955015182495,
|
| 182 |
+
"eval_runtime": 47.9525,
|
| 183 |
+
"eval_samples_per_second": 11.72,
|
| 184 |
+
"eval_steps_per_second": 11.72,
|
| 185 |
+
"step": 24728
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 12.0,
|
| 189 |
+
"grad_norm": 0.0959361270070076,
|
| 190 |
+
"learning_rate": 6.0025207591933574e-06,
|
| 191 |
+
"loss": 0.7554,
|
| 192 |
+
"step": 26976
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 12.0,
|
| 196 |
+
"eval_accuracy": 0.8185053467750549,
|
| 197 |
+
"eval_loss": 1.1184855699539185,
|
| 198 |
+
"eval_runtime": 47.4663,
|
| 199 |
+
"eval_samples_per_second": 11.84,
|
| 200 |
+
"eval_steps_per_second": 11.84,
|
| 201 |
+
"step": 26976
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 13.0,
|
| 205 |
+
"grad_norm": 0.06532555818557739,
|
| 206 |
+
"learning_rate": 5.669335705812574e-06,
|
| 207 |
+
"loss": 0.7196,
|
| 208 |
+
"step": 29224
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 13.0,
|
| 212 |
+
"eval_accuracy": 0.7846975326538086,
|
| 213 |
+
"eval_loss": 1.4066756963729858,
|
| 214 |
+
"eval_runtime": 48.1233,
|
| 215 |
+
"eval_samples_per_second": 11.678,
|
| 216 |
+
"eval_steps_per_second": 11.678,
|
| 217 |
+
"step": 29224
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 14.0,
|
| 221 |
+
"grad_norm": 177.36297607421875,
|
| 222 |
+
"learning_rate": 5.336150652431792e-06,
|
| 223 |
+
"loss": 0.692,
|
| 224 |
+
"step": 31472
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 14.0,
|
| 228 |
+
"eval_accuracy": 0.8202847242355347,
|
| 229 |
+
"eval_loss": 1.1174949407577515,
|
| 230 |
+
"eval_runtime": 47.9299,
|
| 231 |
+
"eval_samples_per_second": 11.725,
|
| 232 |
+
"eval_steps_per_second": 11.725,
|
| 233 |
+
"step": 31472
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 15.0,
|
| 237 |
+
"grad_norm": 0.7878779768943787,
|
| 238 |
+
"learning_rate": 5.002817319098459e-06,
|
| 239 |
+
"loss": 0.6276,
|
| 240 |
+
"step": 33720
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 15.0,
|
| 244 |
+
"eval_accuracy": 0.7882562279701233,
|
| 245 |
+
"eval_loss": 1.4490171670913696,
|
| 246 |
+
"eval_runtime": 47.6011,
|
| 247 |
+
"eval_samples_per_second": 11.806,
|
| 248 |
+
"eval_steps_per_second": 11.806,
|
| 249 |
+
"step": 33720
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 16.0,
|
| 253 |
+
"grad_norm": 0.04724971204996109,
|
| 254 |
+
"learning_rate": 4.6696322657176755e-06,
|
| 255 |
+
"loss": 0.6083,
|
| 256 |
+
"step": 35968
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 16.0,
|
| 260 |
+
"eval_accuracy": 0.8345195651054382,
|
| 261 |
+
"eval_loss": 1.0982587337493896,
|
| 262 |
+
"eval_runtime": 47.8014,
|
| 263 |
+
"eval_samples_per_second": 11.757,
|
| 264 |
+
"eval_steps_per_second": 11.757,
|
| 265 |
+
"step": 35968
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 17.0,
|
| 269 |
+
"grad_norm": 0.3455263674259186,
|
| 270 |
+
"learning_rate": 4.336447212336892e-06,
|
| 271 |
+
"loss": 0.5204,
|
| 272 |
+
"step": 38216
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 17.0,
|
| 276 |
+
"eval_accuracy": 0.8256227970123291,
|
| 277 |
+
"eval_loss": 1.181368350982666,
|
| 278 |
+
"eval_runtime": 47.9669,
|
| 279 |
+
"eval_samples_per_second": 11.716,
|
| 280 |
+
"eval_steps_per_second": 11.716,
|
| 281 |
+
"step": 38216
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 18.0,
|
| 285 |
+
"grad_norm": 0.03767940774559975,
|
| 286 |
+
"learning_rate": 4.003262158956109e-06,
|
| 287 |
+
"loss": 0.5197,
|
| 288 |
+
"step": 40464
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 18.0,
|
| 292 |
+
"eval_accuracy": 0.8167259693145752,
|
| 293 |
+
"eval_loss": 1.2945315837860107,
|
| 294 |
+
"eval_runtime": 47.911,
|
| 295 |
+
"eval_samples_per_second": 11.73,
|
| 296 |
+
"eval_steps_per_second": 11.73,
|
| 297 |
+
"step": 40464
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 19.0,
|
| 301 |
+
"grad_norm": 365.2795104980469,
|
| 302 |
+
"learning_rate": 3.6700771055753265e-06,
|
| 303 |
+
"loss": 0.488,
|
| 304 |
+
"step": 42712
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 19.0,
|
| 308 |
+
"eval_accuracy": 0.8024911284446716,
|
| 309 |
+
"eval_loss": 1.4494409561157227,
|
| 310 |
+
"eval_runtime": 44.9229,
|
| 311 |
+
"eval_samples_per_second": 12.51,
|
| 312 |
+
"eval_steps_per_second": 12.51,
|
| 313 |
+
"step": 42712
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 20.0,
|
| 317 |
+
"grad_norm": 31.586769104003906,
|
| 318 |
+
"learning_rate": 3.3368920521945437e-06,
|
| 319 |
+
"loss": 0.4714,
|
| 320 |
+
"step": 44960
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 20.0,
|
| 324 |
+
"eval_accuracy": 0.8113878965377808,
|
| 325 |
+
"eval_loss": 1.3498995304107666,
|
| 326 |
+
"eval_runtime": 44.7889,
|
| 327 |
+
"eval_samples_per_second": 12.548,
|
| 328 |
+
"eval_steps_per_second": 12.548,
|
| 329 |
+
"step": 44960
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 21.0,
|
| 333 |
+
"grad_norm": 4.5781145095825195,
|
| 334 |
+
"learning_rate": 3.0035587188612105e-06,
|
| 335 |
+
"loss": 0.3641,
|
| 336 |
+
"step": 47208
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 21.0,
|
| 340 |
+
"eval_accuracy": 0.8380783200263977,
|
| 341 |
+
"eval_loss": 1.252496600151062,
|
| 342 |
+
"eval_runtime": 44.8551,
|
| 343 |
+
"eval_samples_per_second": 12.529,
|
| 344 |
+
"eval_steps_per_second": 12.529,
|
| 345 |
+
"step": 47208
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 22.0,
|
| 349 |
+
"grad_norm": 0.028242342174053192,
|
| 350 |
+
"learning_rate": 2.6703736654804273e-06,
|
| 351 |
+
"loss": 0.3877,
|
| 352 |
+
"step": 49456
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 22.0,
|
| 356 |
+
"eval_accuracy": 0.8380783200263977,
|
| 357 |
+
"eval_loss": 1.2610100507736206,
|
| 358 |
+
"eval_runtime": 45.2543,
|
| 359 |
+
"eval_samples_per_second": 12.419,
|
| 360 |
+
"eval_steps_per_second": 12.419,
|
| 361 |
+
"step": 49456
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 23.0,
|
| 365 |
+
"grad_norm": 0.02240828238427639,
|
| 366 |
+
"learning_rate": 2.337188612099644e-06,
|
| 367 |
+
"loss": 0.3253,
|
| 368 |
+
"step": 51704
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 23.0,
|
| 372 |
+
"eval_accuracy": 0.8274021148681641,
|
| 373 |
+
"eval_loss": 1.3913415670394897,
|
| 374 |
+
"eval_runtime": 45.0743,
|
| 375 |
+
"eval_samples_per_second": 12.468,
|
| 376 |
+
"eval_steps_per_second": 12.468,
|
| 377 |
+
"step": 51704
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 24.0,
|
| 381 |
+
"grad_norm": 776.1561279296875,
|
| 382 |
+
"learning_rate": 2.0040035587188614e-06,
|
| 383 |
+
"loss": 0.2978,
|
| 384 |
+
"step": 53952
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 24.0,
|
| 388 |
+
"eval_accuracy": 0.8416370153427124,
|
| 389 |
+
"eval_loss": 1.2989881038665771,
|
| 390 |
+
"eval_runtime": 44.7173,
|
| 391 |
+
"eval_samples_per_second": 12.568,
|
| 392 |
+
"eval_steps_per_second": 12.568,
|
| 393 |
+
"step": 53952
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 25.0,
|
| 397 |
+
"grad_norm": 118.77944946289062,
|
| 398 |
+
"learning_rate": 1.6706702253855281e-06,
|
| 399 |
+
"loss": 0.3238,
|
| 400 |
+
"step": 56200
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 25.0,
|
| 404 |
+
"eval_accuracy": 0.8274021148681641,
|
| 405 |
+
"eval_loss": 1.4328011274337769,
|
| 406 |
+
"eval_runtime": 45.0042,
|
| 407 |
+
"eval_samples_per_second": 12.488,
|
| 408 |
+
"eval_steps_per_second": 12.488,
|
| 409 |
+
"step": 56200
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 26.0,
|
| 413 |
+
"grad_norm": 0.006892771925777197,
|
| 414 |
+
"learning_rate": 1.3373368920521945e-06,
|
| 415 |
+
"loss": 0.2669,
|
| 416 |
+
"step": 58448
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 26.0,
|
| 420 |
+
"eval_accuracy": 0.8327401876449585,
|
| 421 |
+
"eval_loss": 1.3079112768173218,
|
| 422 |
+
"eval_runtime": 45.1126,
|
| 423 |
+
"eval_samples_per_second": 12.458,
|
| 424 |
+
"eval_steps_per_second": 12.458,
|
| 425 |
+
"step": 58448
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 27.0,
|
| 429 |
+
"grad_norm": 0.0030675730668008327,
|
| 430 |
+
"learning_rate": 1.0041518386714117e-06,
|
| 431 |
+
"loss": 0.2521,
|
| 432 |
+
"step": 60696
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 27.0,
|
| 436 |
+
"eval_accuracy": 0.8398576378822327,
|
| 437 |
+
"eval_loss": 1.3250336647033691,
|
| 438 |
+
"eval_runtime": 45.3922,
|
| 439 |
+
"eval_samples_per_second": 12.381,
|
| 440 |
+
"eval_steps_per_second": 12.381,
|
| 441 |
+
"step": 60696
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 28.0,
|
| 445 |
+
"grad_norm": 0.06381255388259888,
|
| 446 |
+
"learning_rate": 6.709667852906288e-07,
|
| 447 |
+
"loss": 0.2632,
|
| 448 |
+
"step": 62944
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 28.0,
|
| 452 |
+
"eval_accuracy": 0.8416370153427124,
|
| 453 |
+
"eval_loss": 1.3356966972351074,
|
| 454 |
+
"eval_runtime": 44.8744,
|
| 455 |
+
"eval_samples_per_second": 12.524,
|
| 456 |
+
"eval_steps_per_second": 12.524,
|
| 457 |
+
"step": 62944
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 29.0,
|
| 461 |
+
"grad_norm": 0.0834624245762825,
|
| 462 |
+
"learning_rate": 3.377817319098458e-07,
|
| 463 |
+
"loss": 0.2655,
|
| 464 |
+
"step": 65192
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 29.0,
|
| 468 |
+
"eval_accuracy": 0.8434163928031921,
|
| 469 |
+
"eval_loss": 1.2957476377487183,
|
| 470 |
+
"eval_runtime": 44.9511,
|
| 471 |
+
"eval_samples_per_second": 12.502,
|
| 472 |
+
"eval_steps_per_second": 12.502,
|
| 473 |
+
"step": 65192
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 30.0,
|
| 477 |
+
"grad_norm": 0.026273438706994057,
|
| 478 |
+
"learning_rate": 4.4483985765124555e-09,
|
| 479 |
+
"loss": 0.2379,
|
| 480 |
+
"step": 67440
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 30.0,
|
| 484 |
+
"eval_accuracy": 0.8487544655799866,
|
| 485 |
+
"eval_loss": 1.2928475141525269,
|
| 486 |
+
"eval_runtime": 44.8607,
|
| 487 |
+
"eval_samples_per_second": 12.528,
|
| 488 |
+
"eval_steps_per_second": 12.528,
|
| 489 |
+
"step": 67440
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 30.0,
|
| 493 |
+
"step": 67440,
|
| 494 |
+
"total_flos": 6.148286618112e+18,
|
| 495 |
+
"train_loss": 0.7011247130334024,
|
| 496 |
+
"train_runtime": 11844.845,
|
| 497 |
+
"train_samples_per_second": 5.694,
|
| 498 |
+
"train_steps_per_second": 5.694
|
| 499 |
+
}
|
| 500 |
+
],
|
| 501 |
+
"logging_steps": 35,
|
| 502 |
+
"max_steps": 67440,
|
| 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": 6.148286618112e+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 sha256:078df543824823372c7898922dd6feb667857c64a16ba932883072c2cbf4736f
|
| 3 |
+
size 5304
|