Commit
•
8fe0224
1
Parent(s):
b8afdfb
Upload folder using huggingface_hub
Browse files- README.md +7 -10
- checkpoint-1600/config.json +85 -0
- checkpoint-1600/model.safetensors +3 -0
- checkpoint-1600/optimizer.pt +3 -0
- checkpoint-1600/rng_state.pth +3 -0
- checkpoint-1600/scheduler.pt +3 -0
- checkpoint-1600/trainer_state.json +570 -0
- checkpoint-1600/training_args.bin +3 -0
- checkpoint-1800/config.json +85 -0
- checkpoint-1800/model.safetensors +3 -0
- checkpoint-1800/optimizer.pt +3 -0
- checkpoint-1800/rng_state.pth +3 -0
- checkpoint-1800/scheduler.pt +3 -0
- checkpoint-1800/trainer_state.json +636 -0
- checkpoint-1800/training_args.bin +3 -0
- checkpoint-2000/config.json +85 -0
- checkpoint-2000/model.safetensors +3 -0
- checkpoint-2000/optimizer.pt +3 -0
- checkpoint-2000/rng_state.pth +3 -0
- checkpoint-2000/scheduler.pt +3 -0
- checkpoint-2000/trainer_state.json +702 -0
- checkpoint-2000/training_args.bin +3 -0
- checkpoint-2200/config.json +85 -0
- checkpoint-2200/model.safetensors +3 -0
- checkpoint-2200/optimizer.pt +3 -0
- checkpoint-2200/rng_state.pth +3 -0
- checkpoint-2200/scheduler.pt +3 -0
- checkpoint-2200/trainer_state.json +768 -0
- checkpoint-2200/training_args.bin +3 -0
- checkpoint-2400/config.json +85 -0
- checkpoint-2400/model.safetensors +3 -0
- checkpoint-2400/optimizer.pt +3 -0
- checkpoint-2400/rng_state.pth +3 -0
- checkpoint-2400/scheduler.pt +3 -0
- checkpoint-2400/trainer_state.json +834 -0
- checkpoint-2400/training_args.bin +3 -0
- model.safetensors +1 -1
- runs/Sep14_17-06-50_ubumarcos/events.out.tfevents.1726327100.ubumarcos +2 -2
- runs/Sep14_18-07-00_ubumarcos/events.out.tfevents.1726330021.ubumarcos +3 -0
- runs/Sep14_18-24-29_ubumarcos/events.out.tfevents.1726331070.ubumarcos +3 -0
- runs/Sep14_18-24-29_ubumarcos/events.out.tfevents.1726331984.ubumarcos +3 -0
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -21,12 +21,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 21 |
|
| 22 |
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on an unknown dataset.
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
-
- Loss: 0.
|
| 25 |
-
- Accuracy: 0.
|
| 26 |
-
- F1: 0.
|
| 27 |
-
- Precision: 0.
|
| 28 |
-
- Recall: 0.
|
| 29 |
-
- Confusion Matrix: [[
|
| 30 |
|
| 31 |
## Model description
|
| 32 |
|
|
@@ -54,14 +54,11 @@ The following hyperparameters were used during training:
|
|
| 54 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 55 |
- lr_scheduler_type: cosine_with_restarts
|
| 56 |
- lr_scheduler_warmup_ratio: 0.1
|
| 57 |
-
- num_epochs:
|
| 58 |
- label_smoothing_factor: 0.1
|
| 59 |
|
| 60 |
### Training results
|
| 61 |
|
| 62 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Confusion Matrix |
|
| 63 |
-
|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:--------------------------------------------------------------:|
|
| 64 |
-
| 0.3691 | 22.2222 | 100 | 0.7942 | 0.8242 | 0.8278 | 0.8347 | 0.8242 | [[51, 10, 0, 2], [5, 44, 9, 0], [1, 14, 67, 0], [7, 0, 0, 63]] |
|
| 65 |
|
| 66 |
|
| 67 |
### Framework versions
|
|
|
|
| 21 |
|
| 22 |
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on an unknown dataset.
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 0.6498
|
| 25 |
+
- Accuracy: 0.8645
|
| 26 |
+
- F1: 0.8634
|
| 27 |
+
- Precision: 0.8632
|
| 28 |
+
- Recall: 0.8645
|
| 29 |
+
- Confusion Matrix: [[50, 8, 0, 2], [7, 53, 12, 0], [0, 8, 60, 0], [0, 0, 0, 73]]
|
| 30 |
|
| 31 |
## Model description
|
| 32 |
|
|
|
|
| 54 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 55 |
- lr_scheduler_type: cosine_with_restarts
|
| 56 |
- lr_scheduler_warmup_ratio: 0.1
|
| 57 |
+
- num_epochs: 40
|
| 58 |
- label_smoothing_factor: 0.1
|
| 59 |
|
| 60 |
### Training results
|
| 61 |
|
|
|
|
|
|
|
|
|
|
| 62 |
|
| 63 |
|
| 64 |
### Framework versions
|
checkpoint-1600/config.json
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ntu-spml/distilhubert",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"apply_spec_augment": false,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"HubertForSequenceClassification"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"classifier_proj_size": 256,
|
| 11 |
+
"conv_bias": false,
|
| 12 |
+
"conv_dim": [
|
| 13 |
+
512,
|
| 14 |
+
512,
|
| 15 |
+
512,
|
| 16 |
+
512,
|
| 17 |
+
512,
|
| 18 |
+
512,
|
| 19 |
+
512
|
| 20 |
+
],
|
| 21 |
+
"conv_kernel": [
|
| 22 |
+
10,
|
| 23 |
+
3,
|
| 24 |
+
3,
|
| 25 |
+
3,
|
| 26 |
+
3,
|
| 27 |
+
2,
|
| 28 |
+
2
|
| 29 |
+
],
|
| 30 |
+
"conv_stride": [
|
| 31 |
+
5,
|
| 32 |
+
2,
|
| 33 |
+
2,
|
| 34 |
+
2,
|
| 35 |
+
2,
|
| 36 |
+
2,
|
| 37 |
+
2
|
| 38 |
+
],
|
| 39 |
+
"ctc_loss_reduction": "sum",
|
| 40 |
+
"ctc_zero_infinity": false,
|
| 41 |
+
"do_stable_layer_norm": false,
|
| 42 |
+
"eos_token_id": 2,
|
| 43 |
+
"feat_extract_activation": "gelu",
|
| 44 |
+
"feat_extract_norm": "group",
|
| 45 |
+
"feat_proj_dropout": 0.0,
|
| 46 |
+
"feat_proj_layer_norm": false,
|
| 47 |
+
"final_dropout": 0.0,
|
| 48 |
+
"finetuning_task": "audio-classification",
|
| 49 |
+
"hidden_act": "gelu",
|
| 50 |
+
"hidden_dropout": 0.1,
|
| 51 |
+
"hidden_size": 768,
|
| 52 |
+
"id2label": {
|
| 53 |
+
"0": "1s_normal",
|
| 54 |
+
"1": "1s_pain",
|
| 55 |
+
"2": "1s_hunger",
|
| 56 |
+
"3": "1s_asphyxia"
|
| 57 |
+
},
|
| 58 |
+
"initializer_range": 0.02,
|
| 59 |
+
"intermediate_size": 3072,
|
| 60 |
+
"label2id": {
|
| 61 |
+
"LABEL_0": 0,
|
| 62 |
+
"LABEL_1": 1,
|
| 63 |
+
"LABEL_2": 2,
|
| 64 |
+
"LABEL_3": 3
|
| 65 |
+
},
|
| 66 |
+
"layer_norm_eps": 1e-05,
|
| 67 |
+
"layerdrop": 0.0,
|
| 68 |
+
"mask_feature_length": 10,
|
| 69 |
+
"mask_feature_min_masks": 0,
|
| 70 |
+
"mask_feature_prob": 0.0,
|
| 71 |
+
"mask_time_length": 10,
|
| 72 |
+
"mask_time_min_masks": 2,
|
| 73 |
+
"mask_time_prob": 0.05,
|
| 74 |
+
"model_type": "hubert",
|
| 75 |
+
"num_attention_heads": 12,
|
| 76 |
+
"num_conv_pos_embedding_groups": 16,
|
| 77 |
+
"num_conv_pos_embeddings": 128,
|
| 78 |
+
"num_feat_extract_layers": 7,
|
| 79 |
+
"num_hidden_layers": 2,
|
| 80 |
+
"pad_token_id": 0,
|
| 81 |
+
"torch_dtype": "float32",
|
| 82 |
+
"transformers_version": "4.44.2",
|
| 83 |
+
"use_weighted_layer_sum": false,
|
| 84 |
+
"vocab_size": 32
|
| 85 |
+
}
|
checkpoint-1600/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6aef261b8260f4ac3a6428f02db7c4bcca3a99bc5665fb8044d613ce39c6fb8
|
| 3 |
+
size 94765560
|
checkpoint-1600/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d29862664d27f45e2f2994143a8262a93a21f00e9daf67dfc1cbc1691c418eae
|
| 3 |
+
size 189556666
|
checkpoint-1600/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ef17f9c931698b6c110fc829b63100d0d1fc71bac548498af01bb1827cde472
|
| 3 |
+
size 14308
|
checkpoint-1600/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddaa3a198579e44a64f9285103acba7ea329354b730d6cc3596b8951d6c763d2
|
| 3 |
+
size 1064
|
checkpoint-1600/trainer_state.json
ADDED
|
@@ -0,0 +1,570 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8462423027109934,
|
| 3 |
+
"best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-1400",
|
| 4 |
+
"epoch": 23.357664233576642,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 1600,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.7299270072992701,
|
| 13 |
+
"grad_norm": 2.289438486099243,
|
| 14 |
+
"learning_rate": 5.5147058823529414e-05,
|
| 15 |
+
"loss": 1.2878,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.4598540145985401,
|
| 20 |
+
"grad_norm": 2.5048491954803467,
|
| 21 |
+
"learning_rate": 0.00011029411764705883,
|
| 22 |
+
"loss": 0.8322,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.18978102189781,
|
| 27 |
+
"grad_norm": 11.18371295928955,
|
| 28 |
+
"learning_rate": 0.00016544117647058823,
|
| 29 |
+
"loss": 0.7897,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.9197080291970803,
|
| 34 |
+
"grad_norm": 9.702393531799316,
|
| 35 |
+
"learning_rate": 0.00022058823529411765,
|
| 36 |
+
"loss": 0.7149,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 2.9197080291970803,
|
| 41 |
+
"eval_accuracy": 0.7252747252747253,
|
| 42 |
+
"eval_confusion_matrix": [
|
| 43 |
+
[
|
| 44 |
+
34,
|
| 45 |
+
39,
|
| 46 |
+
0,
|
| 47 |
+
2
|
| 48 |
+
],
|
| 49 |
+
[
|
| 50 |
+
7,
|
| 51 |
+
62,
|
| 52 |
+
6,
|
| 53 |
+
0
|
| 54 |
+
],
|
| 55 |
+
[
|
| 56 |
+
0,
|
| 57 |
+
19,
|
| 58 |
+
43,
|
| 59 |
+
0
|
| 60 |
+
],
|
| 61 |
+
[
|
| 62 |
+
0,
|
| 63 |
+
2,
|
| 64 |
+
0,
|
| 65 |
+
59
|
| 66 |
+
]
|
| 67 |
+
],
|
| 68 |
+
"eval_f1": 0.7260427659517454,
|
| 69 |
+
"eval_loss": 0.9058456420898438,
|
| 70 |
+
"eval_precision": 0.7828499608603893,
|
| 71 |
+
"eval_recall": 0.7252747252747253,
|
| 72 |
+
"eval_runtime": 3.7417,
|
| 73 |
+
"eval_samples_per_second": 72.962,
|
| 74 |
+
"eval_steps_per_second": 0.802,
|
| 75 |
+
"step": 200
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 3.6496350364963503,
|
| 79 |
+
"grad_norm": 8.47255802154541,
|
| 80 |
+
"learning_rate": 0.000275735294117647,
|
| 81 |
+
"loss": 0.6917,
|
| 82 |
+
"step": 250
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 4.37956204379562,
|
| 86 |
+
"grad_norm": 16.689321517944336,
|
| 87 |
+
"learning_rate": 0.0002999031705390845,
|
| 88 |
+
"loss": 0.7264,
|
| 89 |
+
"step": 300
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 5.109489051094891,
|
| 93 |
+
"grad_norm": 1.7369310855865479,
|
| 94 |
+
"learning_rate": 0.00029924913005299595,
|
| 95 |
+
"loss": 0.6895,
|
| 96 |
+
"step": 350
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 5.839416058394161,
|
| 100 |
+
"grad_norm": 2.210369348526001,
|
| 101 |
+
"learning_rate": 0.0002979807906935489,
|
| 102 |
+
"loss": 0.6939,
|
| 103 |
+
"step": 400
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 5.839416058394161,
|
| 107 |
+
"eval_accuracy": 0.7509157509157509,
|
| 108 |
+
"eval_confusion_matrix": [
|
| 109 |
+
[
|
| 110 |
+
66,
|
| 111 |
+
2,
|
| 112 |
+
0,
|
| 113 |
+
7
|
| 114 |
+
],
|
| 115 |
+
[
|
| 116 |
+
29,
|
| 117 |
+
38,
|
| 118 |
+
7,
|
| 119 |
+
1
|
| 120 |
+
],
|
| 121 |
+
[
|
| 122 |
+
2,
|
| 123 |
+
20,
|
| 124 |
+
40,
|
| 125 |
+
0
|
| 126 |
+
],
|
| 127 |
+
[
|
| 128 |
+
0,
|
| 129 |
+
0,
|
| 130 |
+
0,
|
| 131 |
+
61
|
| 132 |
+
]
|
| 133 |
+
],
|
| 134 |
+
"eval_f1": 0.7418721712792054,
|
| 135 |
+
"eval_loss": 0.8107791543006897,
|
| 136 |
+
"eval_precision": 0.7517378077426524,
|
| 137 |
+
"eval_recall": 0.7509157509157509,
|
| 138 |
+
"eval_runtime": 3.7702,
|
| 139 |
+
"eval_samples_per_second": 72.409,
|
| 140 |
+
"eval_steps_per_second": 0.796,
|
| 141 |
+
"step": 400
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 6.569343065693431,
|
| 145 |
+
"grad_norm": 2.1358511447906494,
|
| 146 |
+
"learning_rate": 0.000296103372855926,
|
| 147 |
+
"loss": 0.5986,
|
| 148 |
+
"step": 450
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 7.299270072992701,
|
| 152 |
+
"grad_norm": 13.704009056091309,
|
| 153 |
+
"learning_rate": 0.0002936246038592886,
|
| 154 |
+
"loss": 0.5932,
|
| 155 |
+
"step": 500
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 8.02919708029197,
|
| 159 |
+
"grad_norm": 2.032876968383789,
|
| 160 |
+
"learning_rate": 0.00029055468614167716,
|
| 161 |
+
"loss": 0.5633,
|
| 162 |
+
"step": 550
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 8.75912408759124,
|
| 166 |
+
"grad_norm": 28.525798797607422,
|
| 167 |
+
"learning_rate": 0.00028690625526749705,
|
| 168 |
+
"loss": 0.4941,
|
| 169 |
+
"step": 600
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 8.75912408759124,
|
| 173 |
+
"eval_accuracy": 0.8241758241758241,
|
| 174 |
+
"eval_confusion_matrix": [
|
| 175 |
+
[
|
| 176 |
+
63,
|
| 177 |
+
8,
|
| 178 |
+
1,
|
| 179 |
+
3
|
| 180 |
+
],
|
| 181 |
+
[
|
| 182 |
+
8,
|
| 183 |
+
50,
|
| 184 |
+
17,
|
| 185 |
+
0
|
| 186 |
+
],
|
| 187 |
+
[
|
| 188 |
+
2,
|
| 189 |
+
9,
|
| 190 |
+
51,
|
| 191 |
+
0
|
| 192 |
+
],
|
| 193 |
+
[
|
| 194 |
+
0,
|
| 195 |
+
0,
|
| 196 |
+
0,
|
| 197 |
+
61
|
| 198 |
+
]
|
| 199 |
+
],
|
| 200 |
+
"eval_f1": 0.8222676260809794,
|
| 201 |
+
"eval_loss": 0.7625077366828918,
|
| 202 |
+
"eval_precision": 0.8229409839103053,
|
| 203 |
+
"eval_recall": 0.8241758241758241,
|
| 204 |
+
"eval_runtime": 3.757,
|
| 205 |
+
"eval_samples_per_second": 72.664,
|
| 206 |
+
"eval_steps_per_second": 0.799,
|
| 207 |
+
"step": 600
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 9.489051094890511,
|
| 211 |
+
"grad_norm": 0.18371808528900146,
|
| 212 |
+
"learning_rate": 0.0002826943279204283,
|
| 213 |
+
"loss": 0.4842,
|
| 214 |
+
"step": 650
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 10.218978102189782,
|
| 218 |
+
"grad_norm": 11.426072120666504,
|
| 219 |
+
"learning_rate": 0.0002779362400958168,
|
| 220 |
+
"loss": 0.4352,
|
| 221 |
+
"step": 700
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 10.94890510948905,
|
| 225 |
+
"grad_norm": 8.062601089477539,
|
| 226 |
+
"learning_rate": 0.0002726515757469423,
|
| 227 |
+
"loss": 0.4447,
|
| 228 |
+
"step": 750
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 11.678832116788321,
|
| 232 |
+
"grad_norm": 0.3985881805419922,
|
| 233 |
+
"learning_rate": 0.00026686208617885055,
|
| 234 |
+
"loss": 0.442,
|
| 235 |
+
"step": 800
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 11.678832116788321,
|
| 239 |
+
"eval_accuracy": 0.7985347985347986,
|
| 240 |
+
"eval_confusion_matrix": [
|
| 241 |
+
[
|
| 242 |
+
66,
|
| 243 |
+
6,
|
| 244 |
+
1,
|
| 245 |
+
2
|
| 246 |
+
],
|
| 247 |
+
[
|
| 248 |
+
15,
|
| 249 |
+
32,
|
| 250 |
+
26,
|
| 251 |
+
2
|
| 252 |
+
],
|
| 253 |
+
[
|
| 254 |
+
2,
|
| 255 |
+
1,
|
| 256 |
+
59,
|
| 257 |
+
0
|
| 258 |
+
],
|
| 259 |
+
[
|
| 260 |
+
0,
|
| 261 |
+
0,
|
| 262 |
+
0,
|
| 263 |
+
61
|
| 264 |
+
]
|
| 265 |
+
],
|
| 266 |
+
"eval_f1": 0.781170020153555,
|
| 267 |
+
"eval_loss": 0.9623217582702637,
|
| 268 |
+
"eval_precision": 0.8093701586901577,
|
| 269 |
+
"eval_recall": 0.7985347985347986,
|
| 270 |
+
"eval_runtime": 3.774,
|
| 271 |
+
"eval_samples_per_second": 72.337,
|
| 272 |
+
"eval_steps_per_second": 0.795,
|
| 273 |
+
"step": 800
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 12.408759124087592,
|
| 277 |
+
"grad_norm": 38.726985931396484,
|
| 278 |
+
"learning_rate": 0.0002605916005215186,
|
| 279 |
+
"loss": 0.4504,
|
| 280 |
+
"step": 850
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 13.138686131386862,
|
| 284 |
+
"grad_norm": 0.026563748717308044,
|
| 285 |
+
"learning_rate": 0.0002538659276508397,
|
| 286 |
+
"loss": 0.3903,
|
| 287 |
+
"step": 900
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 13.86861313868613,
|
| 291 |
+
"grad_norm": 0.06770322471857071,
|
| 292 |
+
"learning_rate": 0.0002467127499611136,
|
| 293 |
+
"loss": 0.4094,
|
| 294 |
+
"step": 950
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 14.598540145985401,
|
| 298 |
+
"grad_norm": 1.2612749338150024,
|
| 299 |
+
"learning_rate": 0.00023916150942626798,
|
| 300 |
+
"loss": 0.4188,
|
| 301 |
+
"step": 1000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 14.598540145985401,
|
| 305 |
+
"eval_accuracy": 0.8315018315018315,
|
| 306 |
+
"eval_confusion_matrix": [
|
| 307 |
+
[
|
| 308 |
+
60,
|
| 309 |
+
9,
|
| 310 |
+
2,
|
| 311 |
+
4
|
| 312 |
+
],
|
| 313 |
+
[
|
| 314 |
+
8,
|
| 315 |
+
56,
|
| 316 |
+
11,
|
| 317 |
+
0
|
| 318 |
+
],
|
| 319 |
+
[
|
| 320 |
+
1,
|
| 321 |
+
11,
|
| 322 |
+
50,
|
| 323 |
+
0
|
| 324 |
+
],
|
| 325 |
+
[
|
| 326 |
+
0,
|
| 327 |
+
0,
|
| 328 |
+
0,
|
| 329 |
+
61
|
| 330 |
+
]
|
| 331 |
+
],
|
| 332 |
+
"eval_f1": 0.8307422385946511,
|
| 333 |
+
"eval_loss": 0.8534455299377441,
|
| 334 |
+
"eval_precision": 0.8312566016541674,
|
| 335 |
+
"eval_recall": 0.8315018315018315,
|
| 336 |
+
"eval_runtime": 3.796,
|
| 337 |
+
"eval_samples_per_second": 71.917,
|
| 338 |
+
"eval_steps_per_second": 0.79,
|
| 339 |
+
"step": 1000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 15.328467153284672,
|
| 343 |
+
"grad_norm": 28.980899810791016,
|
| 344 |
+
"learning_rate": 0.0002312432864187738,
|
| 345 |
+
"loss": 0.3798,
|
| 346 |
+
"step": 1050
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 16.05839416058394,
|
| 350 |
+
"grad_norm": 0.022609323263168335,
|
| 351 |
+
"learning_rate": 0.0002229906717850284,
|
| 352 |
+
"loss": 0.3672,
|
| 353 |
+
"step": 1100
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 16.78832116788321,
|
| 357 |
+
"grad_norm": 0.02360348217189312,
|
| 358 |
+
"learning_rate": 0.00021443763270373483,
|
| 359 |
+
"loss": 0.3715,
|
| 360 |
+
"step": 1150
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 17.51824817518248,
|
| 364 |
+
"grad_norm": 0.014020542614161968,
|
| 365 |
+
"learning_rate": 0.0002056193728793941,
|
| 366 |
+
"loss": 0.349,
|
| 367 |
+
"step": 1200
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 17.51824817518248,
|
| 371 |
+
"eval_accuracy": 0.8351648351648352,
|
| 372 |
+
"eval_confusion_matrix": [
|
| 373 |
+
[
|
| 374 |
+
62,
|
| 375 |
+
10,
|
| 376 |
+
1,
|
| 377 |
+
2
|
| 378 |
+
],
|
| 379 |
+
[
|
| 380 |
+
9,
|
| 381 |
+
57,
|
| 382 |
+
9,
|
| 383 |
+
0
|
| 384 |
+
],
|
| 385 |
+
[
|
| 386 |
+
2,
|
| 387 |
+
12,
|
| 388 |
+
48,
|
| 389 |
+
0
|
| 390 |
+
],
|
| 391 |
+
[
|
| 392 |
+
0,
|
| 393 |
+
0,
|
| 394 |
+
0,
|
| 395 |
+
61
|
| 396 |
+
]
|
| 397 |
+
],
|
| 398 |
+
"eval_f1": 0.8350675728555914,
|
| 399 |
+
"eval_loss": 0.8131950497627258,
|
| 400 |
+
"eval_precision": 0.8358475863688551,
|
| 401 |
+
"eval_recall": 0.8351648351648352,
|
| 402 |
+
"eval_runtime": 3.7788,
|
| 403 |
+
"eval_samples_per_second": 72.246,
|
| 404 |
+
"eval_steps_per_second": 0.794,
|
| 405 |
+
"step": 1200
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 18.248175182481752,
|
| 409 |
+
"grad_norm": 0.006028232164680958,
|
| 410 |
+
"learning_rate": 0.0001965721876463452,
|
| 411 |
+
"loss": 0.3491,
|
| 412 |
+
"step": 1250
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 18.978102189781023,
|
| 416 |
+
"grad_norm": 0.008285734802484512,
|
| 417 |
+
"learning_rate": 0.00018733331457973358,
|
| 418 |
+
"loss": 0.3489,
|
| 419 |
+
"step": 1300
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 19.708029197080293,
|
| 423 |
+
"grad_norm": 0.008053851313889027,
|
| 424 |
+
"learning_rate": 0.00017794078022828275,
|
| 425 |
+
"loss": 0.3497,
|
| 426 |
+
"step": 1350
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 20.437956204379564,
|
| 430 |
+
"grad_norm": 0.003234422067180276,
|
| 431 |
+
"learning_rate": 0.00016843324359970712,
|
| 432 |
+
"loss": 0.3488,
|
| 433 |
+
"step": 1400
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 20.437956204379564,
|
| 437 |
+
"eval_accuracy": 0.8461538461538461,
|
| 438 |
+
"eval_confusion_matrix": [
|
| 439 |
+
[
|
| 440 |
+
61,
|
| 441 |
+
11,
|
| 442 |
+
1,
|
| 443 |
+
2
|
| 444 |
+
],
|
| 445 |
+
[
|
| 446 |
+
8,
|
| 447 |
+
57,
|
| 448 |
+
10,
|
| 449 |
+
0
|
| 450 |
+
],
|
| 451 |
+
[
|
| 452 |
+
0,
|
| 453 |
+
10,
|
| 454 |
+
52,
|
| 455 |
+
0
|
| 456 |
+
],
|
| 457 |
+
[
|
| 458 |
+
0,
|
| 459 |
+
0,
|
| 460 |
+
0,
|
| 461 |
+
61
|
| 462 |
+
]
|
| 463 |
+
],
|
| 464 |
+
"eval_f1": 0.8462423027109934,
|
| 465 |
+
"eval_loss": 0.7859560251235962,
|
| 466 |
+
"eval_precision": 0.8474363933035696,
|
| 467 |
+
"eval_recall": 0.8461538461538461,
|
| 468 |
+
"eval_runtime": 3.7947,
|
| 469 |
+
"eval_samples_per_second": 71.942,
|
| 470 |
+
"eval_steps_per_second": 0.791,
|
| 471 |
+
"step": 1400
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 21.16788321167883,
|
| 475 |
+
"grad_norm": 0.004595920909196138,
|
| 476 |
+
"learning_rate": 0.00015884983704296757,
|
| 477 |
+
"loss": 0.3488,
|
| 478 |
+
"step": 1450
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 21.8978102189781,
|
| 482 |
+
"grad_norm": 0.002511706668883562,
|
| 483 |
+
"learning_rate": 0.00014923000518228847,
|
| 484 |
+
"loss": 0.3488,
|
| 485 |
+
"step": 1500
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 22.62773722627737,
|
| 489 |
+
"grad_norm": 0.002340014325454831,
|
| 490 |
+
"learning_rate": 0.00013961334256587125,
|
| 491 |
+
"loss": 0.3488,
|
| 492 |
+
"step": 1550
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 23.357664233576642,
|
| 496 |
+
"grad_norm": 0.0028287076856940985,
|
| 497 |
+
"learning_rate": 0.00013003943069753198,
|
| 498 |
+
"loss": 0.3488,
|
| 499 |
+
"step": 1600
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 23.357664233576642,
|
| 503 |
+
"eval_accuracy": 0.8461538461538461,
|
| 504 |
+
"eval_confusion_matrix": [
|
| 505 |
+
[
|
| 506 |
+
61,
|
| 507 |
+
11,
|
| 508 |
+
1,
|
| 509 |
+
2
|
| 510 |
+
],
|
| 511 |
+
[
|
| 512 |
+
8,
|
| 513 |
+
57,
|
| 514 |
+
10,
|
| 515 |
+
0
|
| 516 |
+
],
|
| 517 |
+
[
|
| 518 |
+
0,
|
| 519 |
+
10,
|
| 520 |
+
52,
|
| 521 |
+
0
|
| 522 |
+
],
|
| 523 |
+
[
|
| 524 |
+
0,
|
| 525 |
+
0,
|
| 526 |
+
0,
|
| 527 |
+
61
|
| 528 |
+
]
|
| 529 |
+
],
|
| 530 |
+
"eval_f1": 0.8462423027109934,
|
| 531 |
+
"eval_loss": 0.7856015563011169,
|
| 532 |
+
"eval_precision": 0.8474363933035696,
|
| 533 |
+
"eval_recall": 0.8461538461538461,
|
| 534 |
+
"eval_runtime": 3.7861,
|
| 535 |
+
"eval_samples_per_second": 72.105,
|
| 536 |
+
"eval_steps_per_second": 0.792,
|
| 537 |
+
"step": 1600
|
| 538 |
+
}
|
| 539 |
+
],
|
| 540 |
+
"logging_steps": 50,
|
| 541 |
+
"max_steps": 2720,
|
| 542 |
+
"num_input_tokens_seen": 0,
|
| 543 |
+
"num_train_epochs": 40,
|
| 544 |
+
"save_steps": 200,
|
| 545 |
+
"stateful_callbacks": {
|
| 546 |
+
"EarlyStoppingCallback": {
|
| 547 |
+
"args": {
|
| 548 |
+
"early_stopping_patience": 5,
|
| 549 |
+
"early_stopping_threshold": 0.001
|
| 550 |
+
},
|
| 551 |
+
"attributes": {
|
| 552 |
+
"early_stopping_patience_counter": 0
|
| 553 |
+
}
|
| 554 |
+
},
|
| 555 |
+
"TrainerControl": {
|
| 556 |
+
"args": {
|
| 557 |
+
"should_epoch_stop": false,
|
| 558 |
+
"should_evaluate": false,
|
| 559 |
+
"should_log": false,
|
| 560 |
+
"should_save": true,
|
| 561 |
+
"should_training_stop": false
|
| 562 |
+
},
|
| 563 |
+
"attributes": {}
|
| 564 |
+
}
|
| 565 |
+
},
|
| 566 |
+
"total_flos": 5.790635667072e+16,
|
| 567 |
+
"train_batch_size": 8,
|
| 568 |
+
"trial_name": null,
|
| 569 |
+
"trial_params": null
|
| 570 |
+
}
|
checkpoint-1600/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1cd6053c9e08edd46715ea6144f2b03c4f4ac31b547b8ae042d0b5e4a21ad64
|
| 3 |
+
size 5240
|
checkpoint-1800/config.json
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ntu-spml/distilhubert",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"apply_spec_augment": false,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"HubertForSequenceClassification"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"classifier_proj_size": 256,
|
| 11 |
+
"conv_bias": false,
|
| 12 |
+
"conv_dim": [
|
| 13 |
+
512,
|
| 14 |
+
512,
|
| 15 |
+
512,
|
| 16 |
+
512,
|
| 17 |
+
512,
|
| 18 |
+
512,
|
| 19 |
+
512
|
| 20 |
+
],
|
| 21 |
+
"conv_kernel": [
|
| 22 |
+
10,
|
| 23 |
+
3,
|
| 24 |
+
3,
|
| 25 |
+
3,
|
| 26 |
+
3,
|
| 27 |
+
2,
|
| 28 |
+
2
|
| 29 |
+
],
|
| 30 |
+
"conv_stride": [
|
| 31 |
+
5,
|
| 32 |
+
2,
|
| 33 |
+
2,
|
| 34 |
+
2,
|
| 35 |
+
2,
|
| 36 |
+
2,
|
| 37 |
+
2
|
| 38 |
+
],
|
| 39 |
+
"ctc_loss_reduction": "sum",
|
| 40 |
+
"ctc_zero_infinity": false,
|
| 41 |
+
"do_stable_layer_norm": false,
|
| 42 |
+
"eos_token_id": 2,
|
| 43 |
+
"feat_extract_activation": "gelu",
|
| 44 |
+
"feat_extract_norm": "group",
|
| 45 |
+
"feat_proj_dropout": 0.0,
|
| 46 |
+
"feat_proj_layer_norm": false,
|
| 47 |
+
"final_dropout": 0.0,
|
| 48 |
+
"finetuning_task": "audio-classification",
|
| 49 |
+
"hidden_act": "gelu",
|
| 50 |
+
"hidden_dropout": 0.1,
|
| 51 |
+
"hidden_size": 768,
|
| 52 |
+
"id2label": {
|
| 53 |
+
"0": "1s_normal",
|
| 54 |
+
"1": "1s_pain",
|
| 55 |
+
"2": "1s_hunger",
|
| 56 |
+
"3": "1s_asphyxia"
|
| 57 |
+
},
|
| 58 |
+
"initializer_range": 0.02,
|
| 59 |
+
"intermediate_size": 3072,
|
| 60 |
+
"label2id": {
|
| 61 |
+
"LABEL_0": 0,
|
| 62 |
+
"LABEL_1": 1,
|
| 63 |
+
"LABEL_2": 2,
|
| 64 |
+
"LABEL_3": 3
|
| 65 |
+
},
|
| 66 |
+
"layer_norm_eps": 1e-05,
|
| 67 |
+
"layerdrop": 0.0,
|
| 68 |
+
"mask_feature_length": 10,
|
| 69 |
+
"mask_feature_min_masks": 0,
|
| 70 |
+
"mask_feature_prob": 0.0,
|
| 71 |
+
"mask_time_length": 10,
|
| 72 |
+
"mask_time_min_masks": 2,
|
| 73 |
+
"mask_time_prob": 0.05,
|
| 74 |
+
"model_type": "hubert",
|
| 75 |
+
"num_attention_heads": 12,
|
| 76 |
+
"num_conv_pos_embedding_groups": 16,
|
| 77 |
+
"num_conv_pos_embeddings": 128,
|
| 78 |
+
"num_feat_extract_layers": 7,
|
| 79 |
+
"num_hidden_layers": 2,
|
| 80 |
+
"pad_token_id": 0,
|
| 81 |
+
"torch_dtype": "float32",
|
| 82 |
+
"transformers_version": "4.44.2",
|
| 83 |
+
"use_weighted_layer_sum": false,
|
| 84 |
+
"vocab_size": 32
|
| 85 |
+
}
|
checkpoint-1800/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3892e9230bb2f7ce41c962ffb147c373f6606471a9ef74da585894adff1bfb70
|
| 3 |
+
size 94765560
|
checkpoint-1800/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41acf717dcb1a8f15aa79d79b64f778e5f5dd6e316eec73482e77fb1177cb39c
|
| 3 |
+
size 189556666
|
checkpoint-1800/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c4142f79ad6a7fc590ff6315301e758c94ec69a4bddf4dbd0f59cb647a60bed
|
| 3 |
+
size 14308
|
checkpoint-1800/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64558c90d8f26d69b3225a367b121a3b1f071de723e5c1c651fdece834417a36
|
| 3 |
+
size 1064
|
checkpoint-1800/trainer_state.json
ADDED
|
@@ -0,0 +1,636 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8535663673078441,
|
| 3 |
+
"best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-1800",
|
| 4 |
+
"epoch": 26.277372262773724,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 1800,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.7299270072992701,
|
| 13 |
+
"grad_norm": 2.289438486099243,
|
| 14 |
+
"learning_rate": 5.5147058823529414e-05,
|
| 15 |
+
"loss": 1.2878,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.4598540145985401,
|
| 20 |
+
"grad_norm": 2.5048491954803467,
|
| 21 |
+
"learning_rate": 0.00011029411764705883,
|
| 22 |
+
"loss": 0.8322,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.18978102189781,
|
| 27 |
+
"grad_norm": 11.18371295928955,
|
| 28 |
+
"learning_rate": 0.00016544117647058823,
|
| 29 |
+
"loss": 0.7897,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.9197080291970803,
|
| 34 |
+
"grad_norm": 9.702393531799316,
|
| 35 |
+
"learning_rate": 0.00022058823529411765,
|
| 36 |
+
"loss": 0.7149,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 2.9197080291970803,
|
| 41 |
+
"eval_accuracy": 0.7252747252747253,
|
| 42 |
+
"eval_confusion_matrix": [
|
| 43 |
+
[
|
| 44 |
+
34,
|
| 45 |
+
39,
|
| 46 |
+
0,
|
| 47 |
+
2
|
| 48 |
+
],
|
| 49 |
+
[
|
| 50 |
+
7,
|
| 51 |
+
62,
|
| 52 |
+
6,
|
| 53 |
+
0
|
| 54 |
+
],
|
| 55 |
+
[
|
| 56 |
+
0,
|
| 57 |
+
19,
|
| 58 |
+
43,
|
| 59 |
+
0
|
| 60 |
+
],
|
| 61 |
+
[
|
| 62 |
+
0,
|
| 63 |
+
2,
|
| 64 |
+
0,
|
| 65 |
+
59
|
| 66 |
+
]
|
| 67 |
+
],
|
| 68 |
+
"eval_f1": 0.7260427659517454,
|
| 69 |
+
"eval_loss": 0.9058456420898438,
|
| 70 |
+
"eval_precision": 0.7828499608603893,
|
| 71 |
+
"eval_recall": 0.7252747252747253,
|
| 72 |
+
"eval_runtime": 3.7417,
|
| 73 |
+
"eval_samples_per_second": 72.962,
|
| 74 |
+
"eval_steps_per_second": 0.802,
|
| 75 |
+
"step": 200
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 3.6496350364963503,
|
| 79 |
+
"grad_norm": 8.47255802154541,
|
| 80 |
+
"learning_rate": 0.000275735294117647,
|
| 81 |
+
"loss": 0.6917,
|
| 82 |
+
"step": 250
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 4.37956204379562,
|
| 86 |
+
"grad_norm": 16.689321517944336,
|
| 87 |
+
"learning_rate": 0.0002999031705390845,
|
| 88 |
+
"loss": 0.7264,
|
| 89 |
+
"step": 300
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 5.109489051094891,
|
| 93 |
+
"grad_norm": 1.7369310855865479,
|
| 94 |
+
"learning_rate": 0.00029924913005299595,
|
| 95 |
+
"loss": 0.6895,
|
| 96 |
+
"step": 350
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 5.839416058394161,
|
| 100 |
+
"grad_norm": 2.210369348526001,
|
| 101 |
+
"learning_rate": 0.0002979807906935489,
|
| 102 |
+
"loss": 0.6939,
|
| 103 |
+
"step": 400
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 5.839416058394161,
|
| 107 |
+
"eval_accuracy": 0.7509157509157509,
|
| 108 |
+
"eval_confusion_matrix": [
|
| 109 |
+
[
|
| 110 |
+
66,
|
| 111 |
+
2,
|
| 112 |
+
0,
|
| 113 |
+
7
|
| 114 |
+
],
|
| 115 |
+
[
|
| 116 |
+
29,
|
| 117 |
+
38,
|
| 118 |
+
7,
|
| 119 |
+
1
|
| 120 |
+
],
|
| 121 |
+
[
|
| 122 |
+
2,
|
| 123 |
+
20,
|
| 124 |
+
40,
|
| 125 |
+
0
|
| 126 |
+
],
|
| 127 |
+
[
|
| 128 |
+
0,
|
| 129 |
+
0,
|
| 130 |
+
0,
|
| 131 |
+
61
|
| 132 |
+
]
|
| 133 |
+
],
|
| 134 |
+
"eval_f1": 0.7418721712792054,
|
| 135 |
+
"eval_loss": 0.8107791543006897,
|
| 136 |
+
"eval_precision": 0.7517378077426524,
|
| 137 |
+
"eval_recall": 0.7509157509157509,
|
| 138 |
+
"eval_runtime": 3.7702,
|
| 139 |
+
"eval_samples_per_second": 72.409,
|
| 140 |
+
"eval_steps_per_second": 0.796,
|
| 141 |
+
"step": 400
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 6.569343065693431,
|
| 145 |
+
"grad_norm": 2.1358511447906494,
|
| 146 |
+
"learning_rate": 0.000296103372855926,
|
| 147 |
+
"loss": 0.5986,
|
| 148 |
+
"step": 450
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 7.299270072992701,
|
| 152 |
+
"grad_norm": 13.704009056091309,
|
| 153 |
+
"learning_rate": 0.0002936246038592886,
|
| 154 |
+
"loss": 0.5932,
|
| 155 |
+
"step": 500
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 8.02919708029197,
|
| 159 |
+
"grad_norm": 2.032876968383789,
|
| 160 |
+
"learning_rate": 0.00029055468614167716,
|
| 161 |
+
"loss": 0.5633,
|
| 162 |
+
"step": 550
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 8.75912408759124,
|
| 166 |
+
"grad_norm": 28.525798797607422,
|
| 167 |
+
"learning_rate": 0.00028690625526749705,
|
| 168 |
+
"loss": 0.4941,
|
| 169 |
+
"step": 600
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 8.75912408759124,
|
| 173 |
+
"eval_accuracy": 0.8241758241758241,
|
| 174 |
+
"eval_confusion_matrix": [
|
| 175 |
+
[
|
| 176 |
+
63,
|
| 177 |
+
8,
|
| 178 |
+
1,
|
| 179 |
+
3
|
| 180 |
+
],
|
| 181 |
+
[
|
| 182 |
+
8,
|
| 183 |
+
50,
|
| 184 |
+
17,
|
| 185 |
+
0
|
| 186 |
+
],
|
| 187 |
+
[
|
| 188 |
+
2,
|
| 189 |
+
9,
|
| 190 |
+
51,
|
| 191 |
+
0
|
| 192 |
+
],
|
| 193 |
+
[
|
| 194 |
+
0,
|
| 195 |
+
0,
|
| 196 |
+
0,
|
| 197 |
+
61
|
| 198 |
+
]
|
| 199 |
+
],
|
| 200 |
+
"eval_f1": 0.8222676260809794,
|
| 201 |
+
"eval_loss": 0.7625077366828918,
|
| 202 |
+
"eval_precision": 0.8229409839103053,
|
| 203 |
+
"eval_recall": 0.8241758241758241,
|
| 204 |
+
"eval_runtime": 3.757,
|
| 205 |
+
"eval_samples_per_second": 72.664,
|
| 206 |
+
"eval_steps_per_second": 0.799,
|
| 207 |
+
"step": 600
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 9.489051094890511,
|
| 211 |
+
"grad_norm": 0.18371808528900146,
|
| 212 |
+
"learning_rate": 0.0002826943279204283,
|
| 213 |
+
"loss": 0.4842,
|
| 214 |
+
"step": 650
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 10.218978102189782,
|
| 218 |
+
"grad_norm": 11.426072120666504,
|
| 219 |
+
"learning_rate": 0.0002779362400958168,
|
| 220 |
+
"loss": 0.4352,
|
| 221 |
+
"step": 700
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 10.94890510948905,
|
| 225 |
+
"grad_norm": 8.062601089477539,
|
| 226 |
+
"learning_rate": 0.0002726515757469423,
|
| 227 |
+
"loss": 0.4447,
|
| 228 |
+
"step": 750
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 11.678832116788321,
|
| 232 |
+
"grad_norm": 0.3985881805419922,
|
| 233 |
+
"learning_rate": 0.00026686208617885055,
|
| 234 |
+
"loss": 0.442,
|
| 235 |
+
"step": 800
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 11.678832116788321,
|
| 239 |
+
"eval_accuracy": 0.7985347985347986,
|
| 240 |
+
"eval_confusion_matrix": [
|
| 241 |
+
[
|
| 242 |
+
66,
|
| 243 |
+
6,
|
| 244 |
+
1,
|
| 245 |
+
2
|
| 246 |
+
],
|
| 247 |
+
[
|
| 248 |
+
15,
|
| 249 |
+
32,
|
| 250 |
+
26,
|
| 251 |
+
2
|
| 252 |
+
],
|
| 253 |
+
[
|
| 254 |
+
2,
|
| 255 |
+
1,
|
| 256 |
+
59,
|
| 257 |
+
0
|
| 258 |
+
],
|
| 259 |
+
[
|
| 260 |
+
0,
|
| 261 |
+
0,
|
| 262 |
+
0,
|
| 263 |
+
61
|
| 264 |
+
]
|
| 265 |
+
],
|
| 266 |
+
"eval_f1": 0.781170020153555,
|
| 267 |
+
"eval_loss": 0.9623217582702637,
|
| 268 |
+
"eval_precision": 0.8093701586901577,
|
| 269 |
+
"eval_recall": 0.7985347985347986,
|
| 270 |
+
"eval_runtime": 3.774,
|
| 271 |
+
"eval_samples_per_second": 72.337,
|
| 272 |
+
"eval_steps_per_second": 0.795,
|
| 273 |
+
"step": 800
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 12.408759124087592,
|
| 277 |
+
"grad_norm": 38.726985931396484,
|
| 278 |
+
"learning_rate": 0.0002605916005215186,
|
| 279 |
+
"loss": 0.4504,
|
| 280 |
+
"step": 850
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 13.138686131386862,
|
| 284 |
+
"grad_norm": 0.026563748717308044,
|
| 285 |
+
"learning_rate": 0.0002538659276508397,
|
| 286 |
+
"loss": 0.3903,
|
| 287 |
+
"step": 900
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 13.86861313868613,
|
| 291 |
+
"grad_norm": 0.06770322471857071,
|
| 292 |
+
"learning_rate": 0.0002467127499611136,
|
| 293 |
+
"loss": 0.4094,
|
| 294 |
+
"step": 950
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 14.598540145985401,
|
| 298 |
+
"grad_norm": 1.2612749338150024,
|
| 299 |
+
"learning_rate": 0.00023916150942626798,
|
| 300 |
+
"loss": 0.4188,
|
| 301 |
+
"step": 1000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 14.598540145985401,
|
| 305 |
+
"eval_accuracy": 0.8315018315018315,
|
| 306 |
+
"eval_confusion_matrix": [
|
| 307 |
+
[
|
| 308 |
+
60,
|
| 309 |
+
9,
|
| 310 |
+
2,
|
| 311 |
+
4
|
| 312 |
+
],
|
| 313 |
+
[
|
| 314 |
+
8,
|
| 315 |
+
56,
|
| 316 |
+
11,
|
| 317 |
+
0
|
| 318 |
+
],
|
| 319 |
+
[
|
| 320 |
+
1,
|
| 321 |
+
11,
|
| 322 |
+
50,
|
| 323 |
+
0
|
| 324 |
+
],
|
| 325 |
+
[
|
| 326 |
+
0,
|
| 327 |
+
0,
|
| 328 |
+
0,
|
| 329 |
+
61
|
| 330 |
+
]
|
| 331 |
+
],
|
| 332 |
+
"eval_f1": 0.8307422385946511,
|
| 333 |
+
"eval_loss": 0.8534455299377441,
|
| 334 |
+
"eval_precision": 0.8312566016541674,
|
| 335 |
+
"eval_recall": 0.8315018315018315,
|
| 336 |
+
"eval_runtime": 3.796,
|
| 337 |
+
"eval_samples_per_second": 71.917,
|
| 338 |
+
"eval_steps_per_second": 0.79,
|
| 339 |
+
"step": 1000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 15.328467153284672,
|
| 343 |
+
"grad_norm": 28.980899810791016,
|
| 344 |
+
"learning_rate": 0.0002312432864187738,
|
| 345 |
+
"loss": 0.3798,
|
| 346 |
+
"step": 1050
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 16.05839416058394,
|
| 350 |
+
"grad_norm": 0.022609323263168335,
|
| 351 |
+
"learning_rate": 0.0002229906717850284,
|
| 352 |
+
"loss": 0.3672,
|
| 353 |
+
"step": 1100
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 16.78832116788321,
|
| 357 |
+
"grad_norm": 0.02360348217189312,
|
| 358 |
+
"learning_rate": 0.00021443763270373483,
|
| 359 |
+
"loss": 0.3715,
|
| 360 |
+
"step": 1150
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 17.51824817518248,
|
| 364 |
+
"grad_norm": 0.014020542614161968,
|
| 365 |
+
"learning_rate": 0.0002056193728793941,
|
| 366 |
+
"loss": 0.349,
|
| 367 |
+
"step": 1200
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 17.51824817518248,
|
| 371 |
+
"eval_accuracy": 0.8351648351648352,
|
| 372 |
+
"eval_confusion_matrix": [
|
| 373 |
+
[
|
| 374 |
+
62,
|
| 375 |
+
10,
|
| 376 |
+
1,
|
| 377 |
+
2
|
| 378 |
+
],
|
| 379 |
+
[
|
| 380 |
+
9,
|
| 381 |
+
57,
|
| 382 |
+
9,
|
| 383 |
+
0
|
| 384 |
+
],
|
| 385 |
+
[
|
| 386 |
+
2,
|
| 387 |
+
12,
|
| 388 |
+
48,
|
| 389 |
+
0
|
| 390 |
+
],
|
| 391 |
+
[
|
| 392 |
+
0,
|
| 393 |
+
0,
|
| 394 |
+
0,
|
| 395 |
+
61
|
| 396 |
+
]
|
| 397 |
+
],
|
| 398 |
+
"eval_f1": 0.8350675728555914,
|
| 399 |
+
"eval_loss": 0.8131950497627258,
|
| 400 |
+
"eval_precision": 0.8358475863688551,
|
| 401 |
+
"eval_recall": 0.8351648351648352,
|
| 402 |
+
"eval_runtime": 3.7788,
|
| 403 |
+
"eval_samples_per_second": 72.246,
|
| 404 |
+
"eval_steps_per_second": 0.794,
|
| 405 |
+
"step": 1200
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 18.248175182481752,
|
| 409 |
+
"grad_norm": 0.006028232164680958,
|
| 410 |
+
"learning_rate": 0.0001965721876463452,
|
| 411 |
+
"loss": 0.3491,
|
| 412 |
+
"step": 1250
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 18.978102189781023,
|
| 416 |
+
"grad_norm": 0.008285734802484512,
|
| 417 |
+
"learning_rate": 0.00018733331457973358,
|
| 418 |
+
"loss": 0.3489,
|
| 419 |
+
"step": 1300
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 19.708029197080293,
|
| 423 |
+
"grad_norm": 0.008053851313889027,
|
| 424 |
+
"learning_rate": 0.00017794078022828275,
|
| 425 |
+
"loss": 0.3497,
|
| 426 |
+
"step": 1350
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 20.437956204379564,
|
| 430 |
+
"grad_norm": 0.003234422067180276,
|
| 431 |
+
"learning_rate": 0.00016843324359970712,
|
| 432 |
+
"loss": 0.3488,
|
| 433 |
+
"step": 1400
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 20.437956204379564,
|
| 437 |
+
"eval_accuracy": 0.8461538461538461,
|
| 438 |
+
"eval_confusion_matrix": [
|
| 439 |
+
[
|
| 440 |
+
61,
|
| 441 |
+
11,
|
| 442 |
+
1,
|
| 443 |
+
2
|
| 444 |
+
],
|
| 445 |
+
[
|
| 446 |
+
8,
|
| 447 |
+
57,
|
| 448 |
+
10,
|
| 449 |
+
0
|
| 450 |
+
],
|
| 451 |
+
[
|
| 452 |
+
0,
|
| 453 |
+
10,
|
| 454 |
+
52,
|
| 455 |
+
0
|
| 456 |
+
],
|
| 457 |
+
[
|
| 458 |
+
0,
|
| 459 |
+
0,
|
| 460 |
+
0,
|
| 461 |
+
61
|
| 462 |
+
]
|
| 463 |
+
],
|
| 464 |
+
"eval_f1": 0.8462423027109934,
|
| 465 |
+
"eval_loss": 0.7859560251235962,
|
| 466 |
+
"eval_precision": 0.8474363933035696,
|
| 467 |
+
"eval_recall": 0.8461538461538461,
|
| 468 |
+
"eval_runtime": 3.7947,
|
| 469 |
+
"eval_samples_per_second": 71.942,
|
| 470 |
+
"eval_steps_per_second": 0.791,
|
| 471 |
+
"step": 1400
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 21.16788321167883,
|
| 475 |
+
"grad_norm": 0.004595920909196138,
|
| 476 |
+
"learning_rate": 0.00015884983704296757,
|
| 477 |
+
"loss": 0.3488,
|
| 478 |
+
"step": 1450
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 21.8978102189781,
|
| 482 |
+
"grad_norm": 0.002511706668883562,
|
| 483 |
+
"learning_rate": 0.00014923000518228847,
|
| 484 |
+
"loss": 0.3488,
|
| 485 |
+
"step": 1500
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 22.62773722627737,
|
| 489 |
+
"grad_norm": 0.002340014325454831,
|
| 490 |
+
"learning_rate": 0.00013961334256587125,
|
| 491 |
+
"loss": 0.3488,
|
| 492 |
+
"step": 1550
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 23.357664233576642,
|
| 496 |
+
"grad_norm": 0.0028287076856940985,
|
| 497 |
+
"learning_rate": 0.00013003943069753198,
|
| 498 |
+
"loss": 0.3488,
|
| 499 |
+
"step": 1600
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 23.357664233576642,
|
| 503 |
+
"eval_accuracy": 0.8461538461538461,
|
| 504 |
+
"eval_confusion_matrix": [
|
| 505 |
+
[
|
| 506 |
+
61,
|
| 507 |
+
11,
|
| 508 |
+
1,
|
| 509 |
+
2
|
| 510 |
+
],
|
| 511 |
+
[
|
| 512 |
+
8,
|
| 513 |
+
57,
|
| 514 |
+
10,
|
| 515 |
+
0
|
| 516 |
+
],
|
| 517 |
+
[
|
| 518 |
+
0,
|
| 519 |
+
10,
|
| 520 |
+
52,
|
| 521 |
+
0
|
| 522 |
+
],
|
| 523 |
+
[
|
| 524 |
+
0,
|
| 525 |
+
0,
|
| 526 |
+
0,
|
| 527 |
+
61
|
| 528 |
+
]
|
| 529 |
+
],
|
| 530 |
+
"eval_f1": 0.8462423027109934,
|
| 531 |
+
"eval_loss": 0.7856015563011169,
|
| 532 |
+
"eval_precision": 0.8474363933035696,
|
| 533 |
+
"eval_recall": 0.8461538461538461,
|
| 534 |
+
"eval_runtime": 3.7861,
|
| 535 |
+
"eval_samples_per_second": 72.105,
|
| 536 |
+
"eval_steps_per_second": 0.792,
|
| 537 |
+
"step": 1600
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 24.087591240875913,
|
| 541 |
+
"grad_norm": 0.0027960864827036858,
|
| 542 |
+
"learning_rate": 0.00012054767512202832,
|
| 543 |
+
"loss": 0.3488,
|
| 544 |
+
"step": 1650
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 24.817518248175183,
|
| 548 |
+
"grad_norm": 0.0033820979297161102,
|
| 549 |
+
"learning_rate": 0.00011117714323462186,
|
| 550 |
+
"loss": 0.3488,
|
| 551 |
+
"step": 1700
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 25.547445255474454,
|
| 555 |
+
"grad_norm": 0.0034969367552548647,
|
| 556 |
+
"learning_rate": 0.00010196640348243974,
|
| 557 |
+
"loss": 0.3488,
|
| 558 |
+
"step": 1750
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 26.277372262773724,
|
| 562 |
+
"grad_norm": 0.0014958898536860943,
|
| 563 |
+
"learning_rate": 9.295336661947115e-05,
|
| 564 |
+
"loss": 0.3488,
|
| 565 |
+
"step": 1800
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 26.277372262773724,
|
| 569 |
+
"eval_accuracy": 0.8534798534798534,
|
| 570 |
+
"eval_confusion_matrix": [
|
| 571 |
+
[
|
| 572 |
+
61,
|
| 573 |
+
11,
|
| 574 |
+
1,
|
| 575 |
+
2
|
| 576 |
+
],
|
| 577 |
+
[
|
| 578 |
+
7,
|
| 579 |
+
58,
|
| 580 |
+
10,
|
| 581 |
+
0
|
| 582 |
+
],
|
| 583 |
+
[
|
| 584 |
+
0,
|
| 585 |
+
9,
|
| 586 |
+
53,
|
| 587 |
+
0
|
| 588 |
+
],
|
| 589 |
+
[
|
| 590 |
+
0,
|
| 591 |
+
0,
|
| 592 |
+
0,
|
| 593 |
+
61
|
| 594 |
+
]
|
| 595 |
+
],
|
| 596 |
+
"eval_f1": 0.8535663673078441,
|
| 597 |
+
"eval_loss": 0.7831193804740906,
|
| 598 |
+
"eval_precision": 0.8551497604301419,
|
| 599 |
+
"eval_recall": 0.8534798534798534,
|
| 600 |
+
"eval_runtime": 3.7976,
|
| 601 |
+
"eval_samples_per_second": 71.888,
|
| 602 |
+
"eval_steps_per_second": 0.79,
|
| 603 |
+
"step": 1800
|
| 604 |
+
}
|
| 605 |
+
],
|
| 606 |
+
"logging_steps": 50,
|
| 607 |
+
"max_steps": 2720,
|
| 608 |
+
"num_input_tokens_seen": 0,
|
| 609 |
+
"num_train_epochs": 40,
|
| 610 |
+
"save_steps": 200,
|
| 611 |
+
"stateful_callbacks": {
|
| 612 |
+
"EarlyStoppingCallback": {
|
| 613 |
+
"args": {
|
| 614 |
+
"early_stopping_patience": 5,
|
| 615 |
+
"early_stopping_threshold": 0.001
|
| 616 |
+
},
|
| 617 |
+
"attributes": {
|
| 618 |
+
"early_stopping_patience_counter": 0
|
| 619 |
+
}
|
| 620 |
+
},
|
| 621 |
+
"TrainerControl": {
|
| 622 |
+
"args": {
|
| 623 |
+
"should_epoch_stop": false,
|
| 624 |
+
"should_evaluate": false,
|
| 625 |
+
"should_log": false,
|
| 626 |
+
"should_save": true,
|
| 627 |
+
"should_training_stop": false
|
| 628 |
+
},
|
| 629 |
+
"attributes": {}
|
| 630 |
+
}
|
| 631 |
+
},
|
| 632 |
+
"total_flos": 6.514294558464e+16,
|
| 633 |
+
"train_batch_size": 8,
|
| 634 |
+
"trial_name": null,
|
| 635 |
+
"trial_params": null
|
| 636 |
+
}
|
checkpoint-1800/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1cd6053c9e08edd46715ea6144f2b03c4f4ac31b547b8ae042d0b5e4a21ad64
|
| 3 |
+
size 5240
|
checkpoint-2000/config.json
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ntu-spml/distilhubert",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"apply_spec_augment": false,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"HubertForSequenceClassification"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"classifier_proj_size": 256,
|
| 11 |
+
"conv_bias": false,
|
| 12 |
+
"conv_dim": [
|
| 13 |
+
512,
|
| 14 |
+
512,
|
| 15 |
+
512,
|
| 16 |
+
512,
|
| 17 |
+
512,
|
| 18 |
+
512,
|
| 19 |
+
512
|
| 20 |
+
],
|
| 21 |
+
"conv_kernel": [
|
| 22 |
+
10,
|
| 23 |
+
3,
|
| 24 |
+
3,
|
| 25 |
+
3,
|
| 26 |
+
3,
|
| 27 |
+
2,
|
| 28 |
+
2
|
| 29 |
+
],
|
| 30 |
+
"conv_stride": [
|
| 31 |
+
5,
|
| 32 |
+
2,
|
| 33 |
+
2,
|
| 34 |
+
2,
|
| 35 |
+
2,
|
| 36 |
+
2,
|
| 37 |
+
2
|
| 38 |
+
],
|
| 39 |
+
"ctc_loss_reduction": "sum",
|
| 40 |
+
"ctc_zero_infinity": false,
|
| 41 |
+
"do_stable_layer_norm": false,
|
| 42 |
+
"eos_token_id": 2,
|
| 43 |
+
"feat_extract_activation": "gelu",
|
| 44 |
+
"feat_extract_norm": "group",
|
| 45 |
+
"feat_proj_dropout": 0.0,
|
| 46 |
+
"feat_proj_layer_norm": false,
|
| 47 |
+
"final_dropout": 0.0,
|
| 48 |
+
"finetuning_task": "audio-classification",
|
| 49 |
+
"hidden_act": "gelu",
|
| 50 |
+
"hidden_dropout": 0.1,
|
| 51 |
+
"hidden_size": 768,
|
| 52 |
+
"id2label": {
|
| 53 |
+
"0": "1s_normal",
|
| 54 |
+
"1": "1s_pain",
|
| 55 |
+
"2": "1s_hunger",
|
| 56 |
+
"3": "1s_asphyxia"
|
| 57 |
+
},
|
| 58 |
+
"initializer_range": 0.02,
|
| 59 |
+
"intermediate_size": 3072,
|
| 60 |
+
"label2id": {
|
| 61 |
+
"LABEL_0": 0,
|
| 62 |
+
"LABEL_1": 1,
|
| 63 |
+
"LABEL_2": 2,
|
| 64 |
+
"LABEL_3": 3
|
| 65 |
+
},
|
| 66 |
+
"layer_norm_eps": 1e-05,
|
| 67 |
+
"layerdrop": 0.0,
|
| 68 |
+
"mask_feature_length": 10,
|
| 69 |
+
"mask_feature_min_masks": 0,
|
| 70 |
+
"mask_feature_prob": 0.0,
|
| 71 |
+
"mask_time_length": 10,
|
| 72 |
+
"mask_time_min_masks": 2,
|
| 73 |
+
"mask_time_prob": 0.05,
|
| 74 |
+
"model_type": "hubert",
|
| 75 |
+
"num_attention_heads": 12,
|
| 76 |
+
"num_conv_pos_embedding_groups": 16,
|
| 77 |
+
"num_conv_pos_embeddings": 128,
|
| 78 |
+
"num_feat_extract_layers": 7,
|
| 79 |
+
"num_hidden_layers": 2,
|
| 80 |
+
"pad_token_id": 0,
|
| 81 |
+
"torch_dtype": "float32",
|
| 82 |
+
"transformers_version": "4.44.2",
|
| 83 |
+
"use_weighted_layer_sum": false,
|
| 84 |
+
"vocab_size": 32
|
| 85 |
+
}
|
checkpoint-2000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fa71495d44ac6eb2b2936ce624cab10e3a56f3350942326bf8ebe031bf375b2
|
| 3 |
+
size 94765560
|
checkpoint-2000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:117dd1e658d23c2a6479a784272551423c67159733df85da2aa7fca20ddda9ce
|
| 3 |
+
size 189556666
|
checkpoint-2000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6d0b969a93825609a509fcaba6d3524f8e7e0e5c183dc65390e343f717261d8
|
| 3 |
+
size 14308
|
checkpoint-2000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c93d911c49d2a76eb941abe8dfcb1f8e265e872f188a8d3a69f77a40a24421e8
|
| 3 |
+
size 1064
|
checkpoint-2000/trainer_state.json
ADDED
|
@@ -0,0 +1,702 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8535663673078441,
|
| 3 |
+
"best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-1800",
|
| 4 |
+
"epoch": 29.197080291970803,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 2000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.7299270072992701,
|
| 13 |
+
"grad_norm": 2.289438486099243,
|
| 14 |
+
"learning_rate": 5.5147058823529414e-05,
|
| 15 |
+
"loss": 1.2878,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.4598540145985401,
|
| 20 |
+
"grad_norm": 2.5048491954803467,
|
| 21 |
+
"learning_rate": 0.00011029411764705883,
|
| 22 |
+
"loss": 0.8322,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.18978102189781,
|
| 27 |
+
"grad_norm": 11.18371295928955,
|
| 28 |
+
"learning_rate": 0.00016544117647058823,
|
| 29 |
+
"loss": 0.7897,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.9197080291970803,
|
| 34 |
+
"grad_norm": 9.702393531799316,
|
| 35 |
+
"learning_rate": 0.00022058823529411765,
|
| 36 |
+
"loss": 0.7149,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 2.9197080291970803,
|
| 41 |
+
"eval_accuracy": 0.7252747252747253,
|
| 42 |
+
"eval_confusion_matrix": [
|
| 43 |
+
[
|
| 44 |
+
34,
|
| 45 |
+
39,
|
| 46 |
+
0,
|
| 47 |
+
2
|
| 48 |
+
],
|
| 49 |
+
[
|
| 50 |
+
7,
|
| 51 |
+
62,
|
| 52 |
+
6,
|
| 53 |
+
0
|
| 54 |
+
],
|
| 55 |
+
[
|
| 56 |
+
0,
|
| 57 |
+
19,
|
| 58 |
+
43,
|
| 59 |
+
0
|
| 60 |
+
],
|
| 61 |
+
[
|
| 62 |
+
0,
|
| 63 |
+
2,
|
| 64 |
+
0,
|
| 65 |
+
59
|
| 66 |
+
]
|
| 67 |
+
],
|
| 68 |
+
"eval_f1": 0.7260427659517454,
|
| 69 |
+
"eval_loss": 0.9058456420898438,
|
| 70 |
+
"eval_precision": 0.7828499608603893,
|
| 71 |
+
"eval_recall": 0.7252747252747253,
|
| 72 |
+
"eval_runtime": 3.7417,
|
| 73 |
+
"eval_samples_per_second": 72.962,
|
| 74 |
+
"eval_steps_per_second": 0.802,
|
| 75 |
+
"step": 200
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 3.6496350364963503,
|
| 79 |
+
"grad_norm": 8.47255802154541,
|
| 80 |
+
"learning_rate": 0.000275735294117647,
|
| 81 |
+
"loss": 0.6917,
|
| 82 |
+
"step": 250
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 4.37956204379562,
|
| 86 |
+
"grad_norm": 16.689321517944336,
|
| 87 |
+
"learning_rate": 0.0002999031705390845,
|
| 88 |
+
"loss": 0.7264,
|
| 89 |
+
"step": 300
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 5.109489051094891,
|
| 93 |
+
"grad_norm": 1.7369310855865479,
|
| 94 |
+
"learning_rate": 0.00029924913005299595,
|
| 95 |
+
"loss": 0.6895,
|
| 96 |
+
"step": 350
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 5.839416058394161,
|
| 100 |
+
"grad_norm": 2.210369348526001,
|
| 101 |
+
"learning_rate": 0.0002979807906935489,
|
| 102 |
+
"loss": 0.6939,
|
| 103 |
+
"step": 400
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 5.839416058394161,
|
| 107 |
+
"eval_accuracy": 0.7509157509157509,
|
| 108 |
+
"eval_confusion_matrix": [
|
| 109 |
+
[
|
| 110 |
+
66,
|
| 111 |
+
2,
|
| 112 |
+
0,
|
| 113 |
+
7
|
| 114 |
+
],
|
| 115 |
+
[
|
| 116 |
+
29,
|
| 117 |
+
38,
|
| 118 |
+
7,
|
| 119 |
+
1
|
| 120 |
+
],
|
| 121 |
+
[
|
| 122 |
+
2,
|
| 123 |
+
20,
|
| 124 |
+
40,
|
| 125 |
+
0
|
| 126 |
+
],
|
| 127 |
+
[
|
| 128 |
+
0,
|
| 129 |
+
0,
|
| 130 |
+
0,
|
| 131 |
+
61
|
| 132 |
+
]
|
| 133 |
+
],
|
| 134 |
+
"eval_f1": 0.7418721712792054,
|
| 135 |
+
"eval_loss": 0.8107791543006897,
|
| 136 |
+
"eval_precision": 0.7517378077426524,
|
| 137 |
+
"eval_recall": 0.7509157509157509,
|
| 138 |
+
"eval_runtime": 3.7702,
|
| 139 |
+
"eval_samples_per_second": 72.409,
|
| 140 |
+
"eval_steps_per_second": 0.796,
|
| 141 |
+
"step": 400
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 6.569343065693431,
|
| 145 |
+
"grad_norm": 2.1358511447906494,
|
| 146 |
+
"learning_rate": 0.000296103372855926,
|
| 147 |
+
"loss": 0.5986,
|
| 148 |
+
"step": 450
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 7.299270072992701,
|
| 152 |
+
"grad_norm": 13.704009056091309,
|
| 153 |
+
"learning_rate": 0.0002936246038592886,
|
| 154 |
+
"loss": 0.5932,
|
| 155 |
+
"step": 500
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 8.02919708029197,
|
| 159 |
+
"grad_norm": 2.032876968383789,
|
| 160 |
+
"learning_rate": 0.00029055468614167716,
|
| 161 |
+
"loss": 0.5633,
|
| 162 |
+
"step": 550
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 8.75912408759124,
|
| 166 |
+
"grad_norm": 28.525798797607422,
|
| 167 |
+
"learning_rate": 0.00028690625526749705,
|
| 168 |
+
"loss": 0.4941,
|
| 169 |
+
"step": 600
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 8.75912408759124,
|
| 173 |
+
"eval_accuracy": 0.8241758241758241,
|
| 174 |
+
"eval_confusion_matrix": [
|
| 175 |
+
[
|
| 176 |
+
63,
|
| 177 |
+
8,
|
| 178 |
+
1,
|
| 179 |
+
3
|
| 180 |
+
],
|
| 181 |
+
[
|
| 182 |
+
8,
|
| 183 |
+
50,
|
| 184 |
+
17,
|
| 185 |
+
0
|
| 186 |
+
],
|
| 187 |
+
[
|
| 188 |
+
2,
|
| 189 |
+
9,
|
| 190 |
+
51,
|
| 191 |
+
0
|
| 192 |
+
],
|
| 193 |
+
[
|
| 194 |
+
0,
|
| 195 |
+
0,
|
| 196 |
+
0,
|
| 197 |
+
61
|
| 198 |
+
]
|
| 199 |
+
],
|
| 200 |
+
"eval_f1": 0.8222676260809794,
|
| 201 |
+
"eval_loss": 0.7625077366828918,
|
| 202 |
+
"eval_precision": 0.8229409839103053,
|
| 203 |
+
"eval_recall": 0.8241758241758241,
|
| 204 |
+
"eval_runtime": 3.757,
|
| 205 |
+
"eval_samples_per_second": 72.664,
|
| 206 |
+
"eval_steps_per_second": 0.799,
|
| 207 |
+
"step": 600
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 9.489051094890511,
|
| 211 |
+
"grad_norm": 0.18371808528900146,
|
| 212 |
+
"learning_rate": 0.0002826943279204283,
|
| 213 |
+
"loss": 0.4842,
|
| 214 |
+
"step": 650
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 10.218978102189782,
|
| 218 |
+
"grad_norm": 11.426072120666504,
|
| 219 |
+
"learning_rate": 0.0002779362400958168,
|
| 220 |
+
"loss": 0.4352,
|
| 221 |
+
"step": 700
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 10.94890510948905,
|
| 225 |
+
"grad_norm": 8.062601089477539,
|
| 226 |
+
"learning_rate": 0.0002726515757469423,
|
| 227 |
+
"loss": 0.4447,
|
| 228 |
+
"step": 750
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 11.678832116788321,
|
| 232 |
+
"grad_norm": 0.3985881805419922,
|
| 233 |
+
"learning_rate": 0.00026686208617885055,
|
| 234 |
+
"loss": 0.442,
|
| 235 |
+
"step": 800
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 11.678832116788321,
|
| 239 |
+
"eval_accuracy": 0.7985347985347986,
|
| 240 |
+
"eval_confusion_matrix": [
|
| 241 |
+
[
|
| 242 |
+
66,
|
| 243 |
+
6,
|
| 244 |
+
1,
|
| 245 |
+
2
|
| 246 |
+
],
|
| 247 |
+
[
|
| 248 |
+
15,
|
| 249 |
+
32,
|
| 250 |
+
26,
|
| 251 |
+
2
|
| 252 |
+
],
|
| 253 |
+
[
|
| 254 |
+
2,
|
| 255 |
+
1,
|
| 256 |
+
59,
|
| 257 |
+
0
|
| 258 |
+
],
|
| 259 |
+
[
|
| 260 |
+
0,
|
| 261 |
+
0,
|
| 262 |
+
0,
|
| 263 |
+
61
|
| 264 |
+
]
|
| 265 |
+
],
|
| 266 |
+
"eval_f1": 0.781170020153555,
|
| 267 |
+
"eval_loss": 0.9623217582702637,
|
| 268 |
+
"eval_precision": 0.8093701586901577,
|
| 269 |
+
"eval_recall": 0.7985347985347986,
|
| 270 |
+
"eval_runtime": 3.774,
|
| 271 |
+
"eval_samples_per_second": 72.337,
|
| 272 |
+
"eval_steps_per_second": 0.795,
|
| 273 |
+
"step": 800
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 12.408759124087592,
|
| 277 |
+
"grad_norm": 38.726985931396484,
|
| 278 |
+
"learning_rate": 0.0002605916005215186,
|
| 279 |
+
"loss": 0.4504,
|
| 280 |
+
"step": 850
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 13.138686131386862,
|
| 284 |
+
"grad_norm": 0.026563748717308044,
|
| 285 |
+
"learning_rate": 0.0002538659276508397,
|
| 286 |
+
"loss": 0.3903,
|
| 287 |
+
"step": 900
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 13.86861313868613,
|
| 291 |
+
"grad_norm": 0.06770322471857071,
|
| 292 |
+
"learning_rate": 0.0002467127499611136,
|
| 293 |
+
"loss": 0.4094,
|
| 294 |
+
"step": 950
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 14.598540145985401,
|
| 298 |
+
"grad_norm": 1.2612749338150024,
|
| 299 |
+
"learning_rate": 0.00023916150942626798,
|
| 300 |
+
"loss": 0.4188,
|
| 301 |
+
"step": 1000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 14.598540145985401,
|
| 305 |
+
"eval_accuracy": 0.8315018315018315,
|
| 306 |
+
"eval_confusion_matrix": [
|
| 307 |
+
[
|
| 308 |
+
60,
|
| 309 |
+
9,
|
| 310 |
+
2,
|
| 311 |
+
4
|
| 312 |
+
],
|
| 313 |
+
[
|
| 314 |
+
8,
|
| 315 |
+
56,
|
| 316 |
+
11,
|
| 317 |
+
0
|
| 318 |
+
],
|
| 319 |
+
[
|
| 320 |
+
1,
|
| 321 |
+
11,
|
| 322 |
+
50,
|
| 323 |
+
0
|
| 324 |
+
],
|
| 325 |
+
[
|
| 326 |
+
0,
|
| 327 |
+
0,
|
| 328 |
+
0,
|
| 329 |
+
61
|
| 330 |
+
]
|
| 331 |
+
],
|
| 332 |
+
"eval_f1": 0.8307422385946511,
|
| 333 |
+
"eval_loss": 0.8534455299377441,
|
| 334 |
+
"eval_precision": 0.8312566016541674,
|
| 335 |
+
"eval_recall": 0.8315018315018315,
|
| 336 |
+
"eval_runtime": 3.796,
|
| 337 |
+
"eval_samples_per_second": 71.917,
|
| 338 |
+
"eval_steps_per_second": 0.79,
|
| 339 |
+
"step": 1000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 15.328467153284672,
|
| 343 |
+
"grad_norm": 28.980899810791016,
|
| 344 |
+
"learning_rate": 0.0002312432864187738,
|
| 345 |
+
"loss": 0.3798,
|
| 346 |
+
"step": 1050
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 16.05839416058394,
|
| 350 |
+
"grad_norm": 0.022609323263168335,
|
| 351 |
+
"learning_rate": 0.0002229906717850284,
|
| 352 |
+
"loss": 0.3672,
|
| 353 |
+
"step": 1100
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 16.78832116788321,
|
| 357 |
+
"grad_norm": 0.02360348217189312,
|
| 358 |
+
"learning_rate": 0.00021443763270373483,
|
| 359 |
+
"loss": 0.3715,
|
| 360 |
+
"step": 1150
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 17.51824817518248,
|
| 364 |
+
"grad_norm": 0.014020542614161968,
|
| 365 |
+
"learning_rate": 0.0002056193728793941,
|
| 366 |
+
"loss": 0.349,
|
| 367 |
+
"step": 1200
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 17.51824817518248,
|
| 371 |
+
"eval_accuracy": 0.8351648351648352,
|
| 372 |
+
"eval_confusion_matrix": [
|
| 373 |
+
[
|
| 374 |
+
62,
|
| 375 |
+
10,
|
| 376 |
+
1,
|
| 377 |
+
2
|
| 378 |
+
],
|
| 379 |
+
[
|
| 380 |
+
9,
|
| 381 |
+
57,
|
| 382 |
+
9,
|
| 383 |
+
0
|
| 384 |
+
],
|
| 385 |
+
[
|
| 386 |
+
2,
|
| 387 |
+
12,
|
| 388 |
+
48,
|
| 389 |
+
0
|
| 390 |
+
],
|
| 391 |
+
[
|
| 392 |
+
0,
|
| 393 |
+
0,
|
| 394 |
+
0,
|
| 395 |
+
61
|
| 396 |
+
]
|
| 397 |
+
],
|
| 398 |
+
"eval_f1": 0.8350675728555914,
|
| 399 |
+
"eval_loss": 0.8131950497627258,
|
| 400 |
+
"eval_precision": 0.8358475863688551,
|
| 401 |
+
"eval_recall": 0.8351648351648352,
|
| 402 |
+
"eval_runtime": 3.7788,
|
| 403 |
+
"eval_samples_per_second": 72.246,
|
| 404 |
+
"eval_steps_per_second": 0.794,
|
| 405 |
+
"step": 1200
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 18.248175182481752,
|
| 409 |
+
"grad_norm": 0.006028232164680958,
|
| 410 |
+
"learning_rate": 0.0001965721876463452,
|
| 411 |
+
"loss": 0.3491,
|
| 412 |
+
"step": 1250
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 18.978102189781023,
|
| 416 |
+
"grad_norm": 0.008285734802484512,
|
| 417 |
+
"learning_rate": 0.00018733331457973358,
|
| 418 |
+
"loss": 0.3489,
|
| 419 |
+
"step": 1300
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 19.708029197080293,
|
| 423 |
+
"grad_norm": 0.008053851313889027,
|
| 424 |
+
"learning_rate": 0.00017794078022828275,
|
| 425 |
+
"loss": 0.3497,
|
| 426 |
+
"step": 1350
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 20.437956204379564,
|
| 430 |
+
"grad_norm": 0.003234422067180276,
|
| 431 |
+
"learning_rate": 0.00016843324359970712,
|
| 432 |
+
"loss": 0.3488,
|
| 433 |
+
"step": 1400
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 20.437956204379564,
|
| 437 |
+
"eval_accuracy": 0.8461538461538461,
|
| 438 |
+
"eval_confusion_matrix": [
|
| 439 |
+
[
|
| 440 |
+
61,
|
| 441 |
+
11,
|
| 442 |
+
1,
|
| 443 |
+
2
|
| 444 |
+
],
|
| 445 |
+
[
|
| 446 |
+
8,
|
| 447 |
+
57,
|
| 448 |
+
10,
|
| 449 |
+
0
|
| 450 |
+
],
|
| 451 |
+
[
|
| 452 |
+
0,
|
| 453 |
+
10,
|
| 454 |
+
52,
|
| 455 |
+
0
|
| 456 |
+
],
|
| 457 |
+
[
|
| 458 |
+
0,
|
| 459 |
+
0,
|
| 460 |
+
0,
|
| 461 |
+
61
|
| 462 |
+
]
|
| 463 |
+
],
|
| 464 |
+
"eval_f1": 0.8462423027109934,
|
| 465 |
+
"eval_loss": 0.7859560251235962,
|
| 466 |
+
"eval_precision": 0.8474363933035696,
|
| 467 |
+
"eval_recall": 0.8461538461538461,
|
| 468 |
+
"eval_runtime": 3.7947,
|
| 469 |
+
"eval_samples_per_second": 71.942,
|
| 470 |
+
"eval_steps_per_second": 0.791,
|
| 471 |
+
"step": 1400
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 21.16788321167883,
|
| 475 |
+
"grad_norm": 0.004595920909196138,
|
| 476 |
+
"learning_rate": 0.00015884983704296757,
|
| 477 |
+
"loss": 0.3488,
|
| 478 |
+
"step": 1450
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 21.8978102189781,
|
| 482 |
+
"grad_norm": 0.002511706668883562,
|
| 483 |
+
"learning_rate": 0.00014923000518228847,
|
| 484 |
+
"loss": 0.3488,
|
| 485 |
+
"step": 1500
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 22.62773722627737,
|
| 489 |
+
"grad_norm": 0.002340014325454831,
|
| 490 |
+
"learning_rate": 0.00013961334256587125,
|
| 491 |
+
"loss": 0.3488,
|
| 492 |
+
"step": 1550
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 23.357664233576642,
|
| 496 |
+
"grad_norm": 0.0028287076856940985,
|
| 497 |
+
"learning_rate": 0.00013003943069753198,
|
| 498 |
+
"loss": 0.3488,
|
| 499 |
+
"step": 1600
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 23.357664233576642,
|
| 503 |
+
"eval_accuracy": 0.8461538461538461,
|
| 504 |
+
"eval_confusion_matrix": [
|
| 505 |
+
[
|
| 506 |
+
61,
|
| 507 |
+
11,
|
| 508 |
+
1,
|
| 509 |
+
2
|
| 510 |
+
],
|
| 511 |
+
[
|
| 512 |
+
8,
|
| 513 |
+
57,
|
| 514 |
+
10,
|
| 515 |
+
0
|
| 516 |
+
],
|
| 517 |
+
[
|
| 518 |
+
0,
|
| 519 |
+
10,
|
| 520 |
+
52,
|
| 521 |
+
0
|
| 522 |
+
],
|
| 523 |
+
[
|
| 524 |
+
0,
|
| 525 |
+
0,
|
| 526 |
+
0,
|
| 527 |
+
61
|
| 528 |
+
]
|
| 529 |
+
],
|
| 530 |
+
"eval_f1": 0.8462423027109934,
|
| 531 |
+
"eval_loss": 0.7856015563011169,
|
| 532 |
+
"eval_precision": 0.8474363933035696,
|
| 533 |
+
"eval_recall": 0.8461538461538461,
|
| 534 |
+
"eval_runtime": 3.7861,
|
| 535 |
+
"eval_samples_per_second": 72.105,
|
| 536 |
+
"eval_steps_per_second": 0.792,
|
| 537 |
+
"step": 1600
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 24.087591240875913,
|
| 541 |
+
"grad_norm": 0.0027960864827036858,
|
| 542 |
+
"learning_rate": 0.00012054767512202832,
|
| 543 |
+
"loss": 0.3488,
|
| 544 |
+
"step": 1650
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 24.817518248175183,
|
| 548 |
+
"grad_norm": 0.0033820979297161102,
|
| 549 |
+
"learning_rate": 0.00011117714323462186,
|
| 550 |
+
"loss": 0.3488,
|
| 551 |
+
"step": 1700
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 25.547445255474454,
|
| 555 |
+
"grad_norm": 0.0034969367552548647,
|
| 556 |
+
"learning_rate": 0.00010196640348243974,
|
| 557 |
+
"loss": 0.3488,
|
| 558 |
+
"step": 1750
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 26.277372262773724,
|
| 562 |
+
"grad_norm": 0.0014958898536860943,
|
| 563 |
+
"learning_rate": 9.295336661947115e-05,
|
| 564 |
+
"loss": 0.3488,
|
| 565 |
+
"step": 1800
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 26.277372262773724,
|
| 569 |
+
"eval_accuracy": 0.8534798534798534,
|
| 570 |
+
"eval_confusion_matrix": [
|
| 571 |
+
[
|
| 572 |
+
61,
|
| 573 |
+
11,
|
| 574 |
+
1,
|
| 575 |
+
2
|
| 576 |
+
],
|
| 577 |
+
[
|
| 578 |
+
7,
|
| 579 |
+
58,
|
| 580 |
+
10,
|
| 581 |
+
0
|
| 582 |
+
],
|
| 583 |
+
[
|
| 584 |
+
0,
|
| 585 |
+
9,
|
| 586 |
+
53,
|
| 587 |
+
0
|
| 588 |
+
],
|
| 589 |
+
[
|
| 590 |
+
0,
|
| 591 |
+
0,
|
| 592 |
+
0,
|
| 593 |
+
61
|
| 594 |
+
]
|
| 595 |
+
],
|
| 596 |
+
"eval_f1": 0.8535663673078441,
|
| 597 |
+
"eval_loss": 0.7831193804740906,
|
| 598 |
+
"eval_precision": 0.8551497604301419,
|
| 599 |
+
"eval_recall": 0.8534798534798534,
|
| 600 |
+
"eval_runtime": 3.7976,
|
| 601 |
+
"eval_samples_per_second": 71.888,
|
| 602 |
+
"eval_steps_per_second": 0.79,
|
| 603 |
+
"step": 1800
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 27.00729927007299,
|
| 607 |
+
"grad_norm": 0.004900149069726467,
|
| 608 |
+
"learning_rate": 8.417512966858319e-05,
|
| 609 |
+
"loss": 0.3488,
|
| 610 |
+
"step": 1850
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 27.73722627737226,
|
| 614 |
+
"grad_norm": 0.0018804975552484393,
|
| 615 |
+
"learning_rate": 7.566782323279578e-05,
|
| 616 |
+
"loss": 0.3488,
|
| 617 |
+
"step": 1900
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 28.467153284671532,
|
| 621 |
+
"grad_norm": 0.0019178036600351334,
|
| 622 |
+
"learning_rate": 6.746646278427247e-05,
|
| 623 |
+
"loss": 0.3488,
|
| 624 |
+
"step": 1950
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 29.197080291970803,
|
| 628 |
+
"grad_norm": 0.001025234698317945,
|
| 629 |
+
"learning_rate": 5.960480454311155e-05,
|
| 630 |
+
"loss": 0.3488,
|
| 631 |
+
"step": 2000
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 29.197080291970803,
|
| 635 |
+
"eval_accuracy": 0.8498168498168498,
|
| 636 |
+
"eval_confusion_matrix": [
|
| 637 |
+
[
|
| 638 |
+
61,
|
| 639 |
+
11,
|
| 640 |
+
1,
|
| 641 |
+
2
|
| 642 |
+
],
|
| 643 |
+
[
|
| 644 |
+
8,
|
| 645 |
+
57,
|
| 646 |
+
10,
|
| 647 |
+
0
|
| 648 |
+
],
|
| 649 |
+
[
|
| 650 |
+
0,
|
| 651 |
+
9,
|
| 652 |
+
53,
|
| 653 |
+
0
|
| 654 |
+
],
|
| 655 |
+
[
|
| 656 |
+
0,
|
| 657 |
+
0,
|
| 658 |
+
0,
|
| 659 |
+
61
|
| 660 |
+
]
|
| 661 |
+
],
|
| 662 |
+
"eval_f1": 0.8496942339108237,
|
| 663 |
+
"eval_loss": 0.7866398692131042,
|
| 664 |
+
"eval_precision": 0.8506632615716467,
|
| 665 |
+
"eval_recall": 0.8498168498168498,
|
| 666 |
+
"eval_runtime": 3.7892,
|
| 667 |
+
"eval_samples_per_second": 72.047,
|
| 668 |
+
"eval_steps_per_second": 0.792,
|
| 669 |
+
"step": 2000
|
| 670 |
+
}
|
| 671 |
+
],
|
| 672 |
+
"logging_steps": 50,
|
| 673 |
+
"max_steps": 2720,
|
| 674 |
+
"num_input_tokens_seen": 0,
|
| 675 |
+
"num_train_epochs": 40,
|
| 676 |
+
"save_steps": 200,
|
| 677 |
+
"stateful_callbacks": {
|
| 678 |
+
"EarlyStoppingCallback": {
|
| 679 |
+
"args": {
|
| 680 |
+
"early_stopping_patience": 5,
|
| 681 |
+
"early_stopping_threshold": 0.001
|
| 682 |
+
},
|
| 683 |
+
"attributes": {
|
| 684 |
+
"early_stopping_patience_counter": 0
|
| 685 |
+
}
|
| 686 |
+
},
|
| 687 |
+
"TrainerControl": {
|
| 688 |
+
"args": {
|
| 689 |
+
"should_epoch_stop": false,
|
| 690 |
+
"should_evaluate": false,
|
| 691 |
+
"should_log": false,
|
| 692 |
+
"should_save": true,
|
| 693 |
+
"should_training_stop": false
|
| 694 |
+
},
|
| 695 |
+
"attributes": {}
|
| 696 |
+
}
|
| 697 |
+
},
|
| 698 |
+
"total_flos": 7.237953449856e+16,
|
| 699 |
+
"train_batch_size": 8,
|
| 700 |
+
"trial_name": null,
|
| 701 |
+
"trial_params": null
|
| 702 |
+
}
|
checkpoint-2000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1cd6053c9e08edd46715ea6144f2b03c4f4ac31b547b8ae042d0b5e4a21ad64
|
| 3 |
+
size 5240
|
checkpoint-2200/config.json
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ntu-spml/distilhubert",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"apply_spec_augment": false,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"HubertForSequenceClassification"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"classifier_proj_size": 256,
|
| 11 |
+
"conv_bias": false,
|
| 12 |
+
"conv_dim": [
|
| 13 |
+
512,
|
| 14 |
+
512,
|
| 15 |
+
512,
|
| 16 |
+
512,
|
| 17 |
+
512,
|
| 18 |
+
512,
|
| 19 |
+
512
|
| 20 |
+
],
|
| 21 |
+
"conv_kernel": [
|
| 22 |
+
10,
|
| 23 |
+
3,
|
| 24 |
+
3,
|
| 25 |
+
3,
|
| 26 |
+
3,
|
| 27 |
+
2,
|
| 28 |
+
2
|
| 29 |
+
],
|
| 30 |
+
"conv_stride": [
|
| 31 |
+
5,
|
| 32 |
+
2,
|
| 33 |
+
2,
|
| 34 |
+
2,
|
| 35 |
+
2,
|
| 36 |
+
2,
|
| 37 |
+
2
|
| 38 |
+
],
|
| 39 |
+
"ctc_loss_reduction": "sum",
|
| 40 |
+
"ctc_zero_infinity": false,
|
| 41 |
+
"do_stable_layer_norm": false,
|
| 42 |
+
"eos_token_id": 2,
|
| 43 |
+
"feat_extract_activation": "gelu",
|
| 44 |
+
"feat_extract_norm": "group",
|
| 45 |
+
"feat_proj_dropout": 0.0,
|
| 46 |
+
"feat_proj_layer_norm": false,
|
| 47 |
+
"final_dropout": 0.0,
|
| 48 |
+
"finetuning_task": "audio-classification",
|
| 49 |
+
"hidden_act": "gelu",
|
| 50 |
+
"hidden_dropout": 0.1,
|
| 51 |
+
"hidden_size": 768,
|
| 52 |
+
"id2label": {
|
| 53 |
+
"0": "1s_normal",
|
| 54 |
+
"1": "1s_pain",
|
| 55 |
+
"2": "1s_hunger",
|
| 56 |
+
"3": "1s_asphyxia"
|
| 57 |
+
},
|
| 58 |
+
"initializer_range": 0.02,
|
| 59 |
+
"intermediate_size": 3072,
|
| 60 |
+
"label2id": {
|
| 61 |
+
"LABEL_0": 0,
|
| 62 |
+
"LABEL_1": 1,
|
| 63 |
+
"LABEL_2": 2,
|
| 64 |
+
"LABEL_3": 3
|
| 65 |
+
},
|
| 66 |
+
"layer_norm_eps": 1e-05,
|
| 67 |
+
"layerdrop": 0.0,
|
| 68 |
+
"mask_feature_length": 10,
|
| 69 |
+
"mask_feature_min_masks": 0,
|
| 70 |
+
"mask_feature_prob": 0.0,
|
| 71 |
+
"mask_time_length": 10,
|
| 72 |
+
"mask_time_min_masks": 2,
|
| 73 |
+
"mask_time_prob": 0.05,
|
| 74 |
+
"model_type": "hubert",
|
| 75 |
+
"num_attention_heads": 12,
|
| 76 |
+
"num_conv_pos_embedding_groups": 16,
|
| 77 |
+
"num_conv_pos_embeddings": 128,
|
| 78 |
+
"num_feat_extract_layers": 7,
|
| 79 |
+
"num_hidden_layers": 2,
|
| 80 |
+
"pad_token_id": 0,
|
| 81 |
+
"torch_dtype": "float32",
|
| 82 |
+
"transformers_version": "4.44.2",
|
| 83 |
+
"use_weighted_layer_sum": false,
|
| 84 |
+
"vocab_size": 32
|
| 85 |
+
}
|
checkpoint-2200/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3c2d5edd9e72d71a658460a72f7eade4b945fee18b8ed3e0894b518b5620f57
|
| 3 |
+
size 94765560
|
checkpoint-2200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fac40752229bb8e74f81bd6991f7eb8726e1b1ac23e5d515ff28f6b8eb48a9b
|
| 3 |
+
size 189556666
|
checkpoint-2200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:623badb81ceb5d9e1a453f79a7cb1eace1544e4c3d7187e9e4ee4efb585b685c
|
| 3 |
+
size 14308
|
checkpoint-2200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:406a44cce484614116f6be37f7336e180742882a67b41259e3e9eabb076d0fd3
|
| 3 |
+
size 1064
|
checkpoint-2200/trainer_state.json
ADDED
|
@@ -0,0 +1,768 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8535663673078441,
|
| 3 |
+
"best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-1800",
|
| 4 |
+
"epoch": 32.11678832116788,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 2200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.7299270072992701,
|
| 13 |
+
"grad_norm": 2.289438486099243,
|
| 14 |
+
"learning_rate": 5.5147058823529414e-05,
|
| 15 |
+
"loss": 1.2878,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.4598540145985401,
|
| 20 |
+
"grad_norm": 2.5048491954803467,
|
| 21 |
+
"learning_rate": 0.00011029411764705883,
|
| 22 |
+
"loss": 0.8322,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.18978102189781,
|
| 27 |
+
"grad_norm": 11.18371295928955,
|
| 28 |
+
"learning_rate": 0.00016544117647058823,
|
| 29 |
+
"loss": 0.7897,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.9197080291970803,
|
| 34 |
+
"grad_norm": 9.702393531799316,
|
| 35 |
+
"learning_rate": 0.00022058823529411765,
|
| 36 |
+
"loss": 0.7149,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 2.9197080291970803,
|
| 41 |
+
"eval_accuracy": 0.7252747252747253,
|
| 42 |
+
"eval_confusion_matrix": [
|
| 43 |
+
[
|
| 44 |
+
34,
|
| 45 |
+
39,
|
| 46 |
+
0,
|
| 47 |
+
2
|
| 48 |
+
],
|
| 49 |
+
[
|
| 50 |
+
7,
|
| 51 |
+
62,
|
| 52 |
+
6,
|
| 53 |
+
0
|
| 54 |
+
],
|
| 55 |
+
[
|
| 56 |
+
0,
|
| 57 |
+
19,
|
| 58 |
+
43,
|
| 59 |
+
0
|
| 60 |
+
],
|
| 61 |
+
[
|
| 62 |
+
0,
|
| 63 |
+
2,
|
| 64 |
+
0,
|
| 65 |
+
59
|
| 66 |
+
]
|
| 67 |
+
],
|
| 68 |
+
"eval_f1": 0.7260427659517454,
|
| 69 |
+
"eval_loss": 0.9058456420898438,
|
| 70 |
+
"eval_precision": 0.7828499608603893,
|
| 71 |
+
"eval_recall": 0.7252747252747253,
|
| 72 |
+
"eval_runtime": 3.7417,
|
| 73 |
+
"eval_samples_per_second": 72.962,
|
| 74 |
+
"eval_steps_per_second": 0.802,
|
| 75 |
+
"step": 200
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 3.6496350364963503,
|
| 79 |
+
"grad_norm": 8.47255802154541,
|
| 80 |
+
"learning_rate": 0.000275735294117647,
|
| 81 |
+
"loss": 0.6917,
|
| 82 |
+
"step": 250
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 4.37956204379562,
|
| 86 |
+
"grad_norm": 16.689321517944336,
|
| 87 |
+
"learning_rate": 0.0002999031705390845,
|
| 88 |
+
"loss": 0.7264,
|
| 89 |
+
"step": 300
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 5.109489051094891,
|
| 93 |
+
"grad_norm": 1.7369310855865479,
|
| 94 |
+
"learning_rate": 0.00029924913005299595,
|
| 95 |
+
"loss": 0.6895,
|
| 96 |
+
"step": 350
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 5.839416058394161,
|
| 100 |
+
"grad_norm": 2.210369348526001,
|
| 101 |
+
"learning_rate": 0.0002979807906935489,
|
| 102 |
+
"loss": 0.6939,
|
| 103 |
+
"step": 400
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 5.839416058394161,
|
| 107 |
+
"eval_accuracy": 0.7509157509157509,
|
| 108 |
+
"eval_confusion_matrix": [
|
| 109 |
+
[
|
| 110 |
+
66,
|
| 111 |
+
2,
|
| 112 |
+
0,
|
| 113 |
+
7
|
| 114 |
+
],
|
| 115 |
+
[
|
| 116 |
+
29,
|
| 117 |
+
38,
|
| 118 |
+
7,
|
| 119 |
+
1
|
| 120 |
+
],
|
| 121 |
+
[
|
| 122 |
+
2,
|
| 123 |
+
20,
|
| 124 |
+
40,
|
| 125 |
+
0
|
| 126 |
+
],
|
| 127 |
+
[
|
| 128 |
+
0,
|
| 129 |
+
0,
|
| 130 |
+
0,
|
| 131 |
+
61
|
| 132 |
+
]
|
| 133 |
+
],
|
| 134 |
+
"eval_f1": 0.7418721712792054,
|
| 135 |
+
"eval_loss": 0.8107791543006897,
|
| 136 |
+
"eval_precision": 0.7517378077426524,
|
| 137 |
+
"eval_recall": 0.7509157509157509,
|
| 138 |
+
"eval_runtime": 3.7702,
|
| 139 |
+
"eval_samples_per_second": 72.409,
|
| 140 |
+
"eval_steps_per_second": 0.796,
|
| 141 |
+
"step": 400
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 6.569343065693431,
|
| 145 |
+
"grad_norm": 2.1358511447906494,
|
| 146 |
+
"learning_rate": 0.000296103372855926,
|
| 147 |
+
"loss": 0.5986,
|
| 148 |
+
"step": 450
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 7.299270072992701,
|
| 152 |
+
"grad_norm": 13.704009056091309,
|
| 153 |
+
"learning_rate": 0.0002936246038592886,
|
| 154 |
+
"loss": 0.5932,
|
| 155 |
+
"step": 500
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 8.02919708029197,
|
| 159 |
+
"grad_norm": 2.032876968383789,
|
| 160 |
+
"learning_rate": 0.00029055468614167716,
|
| 161 |
+
"loss": 0.5633,
|
| 162 |
+
"step": 550
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 8.75912408759124,
|
| 166 |
+
"grad_norm": 28.525798797607422,
|
| 167 |
+
"learning_rate": 0.00028690625526749705,
|
| 168 |
+
"loss": 0.4941,
|
| 169 |
+
"step": 600
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 8.75912408759124,
|
| 173 |
+
"eval_accuracy": 0.8241758241758241,
|
| 174 |
+
"eval_confusion_matrix": [
|
| 175 |
+
[
|
| 176 |
+
63,
|
| 177 |
+
8,
|
| 178 |
+
1,
|
| 179 |
+
3
|
| 180 |
+
],
|
| 181 |
+
[
|
| 182 |
+
8,
|
| 183 |
+
50,
|
| 184 |
+
17,
|
| 185 |
+
0
|
| 186 |
+
],
|
| 187 |
+
[
|
| 188 |
+
2,
|
| 189 |
+
9,
|
| 190 |
+
51,
|
| 191 |
+
0
|
| 192 |
+
],
|
| 193 |
+
[
|
| 194 |
+
0,
|
| 195 |
+
0,
|
| 196 |
+
0,
|
| 197 |
+
61
|
| 198 |
+
]
|
| 199 |
+
],
|
| 200 |
+
"eval_f1": 0.8222676260809794,
|
| 201 |
+
"eval_loss": 0.7625077366828918,
|
| 202 |
+
"eval_precision": 0.8229409839103053,
|
| 203 |
+
"eval_recall": 0.8241758241758241,
|
| 204 |
+
"eval_runtime": 3.757,
|
| 205 |
+
"eval_samples_per_second": 72.664,
|
| 206 |
+
"eval_steps_per_second": 0.799,
|
| 207 |
+
"step": 600
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 9.489051094890511,
|
| 211 |
+
"grad_norm": 0.18371808528900146,
|
| 212 |
+
"learning_rate": 0.0002826943279204283,
|
| 213 |
+
"loss": 0.4842,
|
| 214 |
+
"step": 650
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 10.218978102189782,
|
| 218 |
+
"grad_norm": 11.426072120666504,
|
| 219 |
+
"learning_rate": 0.0002779362400958168,
|
| 220 |
+
"loss": 0.4352,
|
| 221 |
+
"step": 700
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 10.94890510948905,
|
| 225 |
+
"grad_norm": 8.062601089477539,
|
| 226 |
+
"learning_rate": 0.0002726515757469423,
|
| 227 |
+
"loss": 0.4447,
|
| 228 |
+
"step": 750
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 11.678832116788321,
|
| 232 |
+
"grad_norm": 0.3985881805419922,
|
| 233 |
+
"learning_rate": 0.00026686208617885055,
|
| 234 |
+
"loss": 0.442,
|
| 235 |
+
"step": 800
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 11.678832116788321,
|
| 239 |
+
"eval_accuracy": 0.7985347985347986,
|
| 240 |
+
"eval_confusion_matrix": [
|
| 241 |
+
[
|
| 242 |
+
66,
|
| 243 |
+
6,
|
| 244 |
+
1,
|
| 245 |
+
2
|
| 246 |
+
],
|
| 247 |
+
[
|
| 248 |
+
15,
|
| 249 |
+
32,
|
| 250 |
+
26,
|
| 251 |
+
2
|
| 252 |
+
],
|
| 253 |
+
[
|
| 254 |
+
2,
|
| 255 |
+
1,
|
| 256 |
+
59,
|
| 257 |
+
0
|
| 258 |
+
],
|
| 259 |
+
[
|
| 260 |
+
0,
|
| 261 |
+
0,
|
| 262 |
+
0,
|
| 263 |
+
61
|
| 264 |
+
]
|
| 265 |
+
],
|
| 266 |
+
"eval_f1": 0.781170020153555,
|
| 267 |
+
"eval_loss": 0.9623217582702637,
|
| 268 |
+
"eval_precision": 0.8093701586901577,
|
| 269 |
+
"eval_recall": 0.7985347985347986,
|
| 270 |
+
"eval_runtime": 3.774,
|
| 271 |
+
"eval_samples_per_second": 72.337,
|
| 272 |
+
"eval_steps_per_second": 0.795,
|
| 273 |
+
"step": 800
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 12.408759124087592,
|
| 277 |
+
"grad_norm": 38.726985931396484,
|
| 278 |
+
"learning_rate": 0.0002605916005215186,
|
| 279 |
+
"loss": 0.4504,
|
| 280 |
+
"step": 850
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 13.138686131386862,
|
| 284 |
+
"grad_norm": 0.026563748717308044,
|
| 285 |
+
"learning_rate": 0.0002538659276508397,
|
| 286 |
+
"loss": 0.3903,
|
| 287 |
+
"step": 900
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 13.86861313868613,
|
| 291 |
+
"grad_norm": 0.06770322471857071,
|
| 292 |
+
"learning_rate": 0.0002467127499611136,
|
| 293 |
+
"loss": 0.4094,
|
| 294 |
+
"step": 950
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 14.598540145985401,
|
| 298 |
+
"grad_norm": 1.2612749338150024,
|
| 299 |
+
"learning_rate": 0.00023916150942626798,
|
| 300 |
+
"loss": 0.4188,
|
| 301 |
+
"step": 1000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 14.598540145985401,
|
| 305 |
+
"eval_accuracy": 0.8315018315018315,
|
| 306 |
+
"eval_confusion_matrix": [
|
| 307 |
+
[
|
| 308 |
+
60,
|
| 309 |
+
9,
|
| 310 |
+
2,
|
| 311 |
+
4
|
| 312 |
+
],
|
| 313 |
+
[
|
| 314 |
+
8,
|
| 315 |
+
56,
|
| 316 |
+
11,
|
| 317 |
+
0
|
| 318 |
+
],
|
| 319 |
+
[
|
| 320 |
+
1,
|
| 321 |
+
11,
|
| 322 |
+
50,
|
| 323 |
+
0
|
| 324 |
+
],
|
| 325 |
+
[
|
| 326 |
+
0,
|
| 327 |
+
0,
|
| 328 |
+
0,
|
| 329 |
+
61
|
| 330 |
+
]
|
| 331 |
+
],
|
| 332 |
+
"eval_f1": 0.8307422385946511,
|
| 333 |
+
"eval_loss": 0.8534455299377441,
|
| 334 |
+
"eval_precision": 0.8312566016541674,
|
| 335 |
+
"eval_recall": 0.8315018315018315,
|
| 336 |
+
"eval_runtime": 3.796,
|
| 337 |
+
"eval_samples_per_second": 71.917,
|
| 338 |
+
"eval_steps_per_second": 0.79,
|
| 339 |
+
"step": 1000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 15.328467153284672,
|
| 343 |
+
"grad_norm": 28.980899810791016,
|
| 344 |
+
"learning_rate": 0.0002312432864187738,
|
| 345 |
+
"loss": 0.3798,
|
| 346 |
+
"step": 1050
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 16.05839416058394,
|
| 350 |
+
"grad_norm": 0.022609323263168335,
|
| 351 |
+
"learning_rate": 0.0002229906717850284,
|
| 352 |
+
"loss": 0.3672,
|
| 353 |
+
"step": 1100
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 16.78832116788321,
|
| 357 |
+
"grad_norm": 0.02360348217189312,
|
| 358 |
+
"learning_rate": 0.00021443763270373483,
|
| 359 |
+
"loss": 0.3715,
|
| 360 |
+
"step": 1150
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 17.51824817518248,
|
| 364 |
+
"grad_norm": 0.014020542614161968,
|
| 365 |
+
"learning_rate": 0.0002056193728793941,
|
| 366 |
+
"loss": 0.349,
|
| 367 |
+
"step": 1200
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 17.51824817518248,
|
| 371 |
+
"eval_accuracy": 0.8351648351648352,
|
| 372 |
+
"eval_confusion_matrix": [
|
| 373 |
+
[
|
| 374 |
+
62,
|
| 375 |
+
10,
|
| 376 |
+
1,
|
| 377 |
+
2
|
| 378 |
+
],
|
| 379 |
+
[
|
| 380 |
+
9,
|
| 381 |
+
57,
|
| 382 |
+
9,
|
| 383 |
+
0
|
| 384 |
+
],
|
| 385 |
+
[
|
| 386 |
+
2,
|
| 387 |
+
12,
|
| 388 |
+
48,
|
| 389 |
+
0
|
| 390 |
+
],
|
| 391 |
+
[
|
| 392 |
+
0,
|
| 393 |
+
0,
|
| 394 |
+
0,
|
| 395 |
+
61
|
| 396 |
+
]
|
| 397 |
+
],
|
| 398 |
+
"eval_f1": 0.8350675728555914,
|
| 399 |
+
"eval_loss": 0.8131950497627258,
|
| 400 |
+
"eval_precision": 0.8358475863688551,
|
| 401 |
+
"eval_recall": 0.8351648351648352,
|
| 402 |
+
"eval_runtime": 3.7788,
|
| 403 |
+
"eval_samples_per_second": 72.246,
|
| 404 |
+
"eval_steps_per_second": 0.794,
|
| 405 |
+
"step": 1200
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 18.248175182481752,
|
| 409 |
+
"grad_norm": 0.006028232164680958,
|
| 410 |
+
"learning_rate": 0.0001965721876463452,
|
| 411 |
+
"loss": 0.3491,
|
| 412 |
+
"step": 1250
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 18.978102189781023,
|
| 416 |
+
"grad_norm": 0.008285734802484512,
|
| 417 |
+
"learning_rate": 0.00018733331457973358,
|
| 418 |
+
"loss": 0.3489,
|
| 419 |
+
"step": 1300
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 19.708029197080293,
|
| 423 |
+
"grad_norm": 0.008053851313889027,
|
| 424 |
+
"learning_rate": 0.00017794078022828275,
|
| 425 |
+
"loss": 0.3497,
|
| 426 |
+
"step": 1350
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 20.437956204379564,
|
| 430 |
+
"grad_norm": 0.003234422067180276,
|
| 431 |
+
"learning_rate": 0.00016843324359970712,
|
| 432 |
+
"loss": 0.3488,
|
| 433 |
+
"step": 1400
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 20.437956204379564,
|
| 437 |
+
"eval_accuracy": 0.8461538461538461,
|
| 438 |
+
"eval_confusion_matrix": [
|
| 439 |
+
[
|
| 440 |
+
61,
|
| 441 |
+
11,
|
| 442 |
+
1,
|
| 443 |
+
2
|
| 444 |
+
],
|
| 445 |
+
[
|
| 446 |
+
8,
|
| 447 |
+
57,
|
| 448 |
+
10,
|
| 449 |
+
0
|
| 450 |
+
],
|
| 451 |
+
[
|
| 452 |
+
0,
|
| 453 |
+
10,
|
| 454 |
+
52,
|
| 455 |
+
0
|
| 456 |
+
],
|
| 457 |
+
[
|
| 458 |
+
0,
|
| 459 |
+
0,
|
| 460 |
+
0,
|
| 461 |
+
61
|
| 462 |
+
]
|
| 463 |
+
],
|
| 464 |
+
"eval_f1": 0.8462423027109934,
|
| 465 |
+
"eval_loss": 0.7859560251235962,
|
| 466 |
+
"eval_precision": 0.8474363933035696,
|
| 467 |
+
"eval_recall": 0.8461538461538461,
|
| 468 |
+
"eval_runtime": 3.7947,
|
| 469 |
+
"eval_samples_per_second": 71.942,
|
| 470 |
+
"eval_steps_per_second": 0.791,
|
| 471 |
+
"step": 1400
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 21.16788321167883,
|
| 475 |
+
"grad_norm": 0.004595920909196138,
|
| 476 |
+
"learning_rate": 0.00015884983704296757,
|
| 477 |
+
"loss": 0.3488,
|
| 478 |
+
"step": 1450
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 21.8978102189781,
|
| 482 |
+
"grad_norm": 0.002511706668883562,
|
| 483 |
+
"learning_rate": 0.00014923000518228847,
|
| 484 |
+
"loss": 0.3488,
|
| 485 |
+
"step": 1500
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 22.62773722627737,
|
| 489 |
+
"grad_norm": 0.002340014325454831,
|
| 490 |
+
"learning_rate": 0.00013961334256587125,
|
| 491 |
+
"loss": 0.3488,
|
| 492 |
+
"step": 1550
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 23.357664233576642,
|
| 496 |
+
"grad_norm": 0.0028287076856940985,
|
| 497 |
+
"learning_rate": 0.00013003943069753198,
|
| 498 |
+
"loss": 0.3488,
|
| 499 |
+
"step": 1600
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 23.357664233576642,
|
| 503 |
+
"eval_accuracy": 0.8461538461538461,
|
| 504 |
+
"eval_confusion_matrix": [
|
| 505 |
+
[
|
| 506 |
+
61,
|
| 507 |
+
11,
|
| 508 |
+
1,
|
| 509 |
+
2
|
| 510 |
+
],
|
| 511 |
+
[
|
| 512 |
+
8,
|
| 513 |
+
57,
|
| 514 |
+
10,
|
| 515 |
+
0
|
| 516 |
+
],
|
| 517 |
+
[
|
| 518 |
+
0,
|
| 519 |
+
10,
|
| 520 |
+
52,
|
| 521 |
+
0
|
| 522 |
+
],
|
| 523 |
+
[
|
| 524 |
+
0,
|
| 525 |
+
0,
|
| 526 |
+
0,
|
| 527 |
+
61
|
| 528 |
+
]
|
| 529 |
+
],
|
| 530 |
+
"eval_f1": 0.8462423027109934,
|
| 531 |
+
"eval_loss": 0.7856015563011169,
|
| 532 |
+
"eval_precision": 0.8474363933035696,
|
| 533 |
+
"eval_recall": 0.8461538461538461,
|
| 534 |
+
"eval_runtime": 3.7861,
|
| 535 |
+
"eval_samples_per_second": 72.105,
|
| 536 |
+
"eval_steps_per_second": 0.792,
|
| 537 |
+
"step": 1600
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 24.087591240875913,
|
| 541 |
+
"grad_norm": 0.0027960864827036858,
|
| 542 |
+
"learning_rate": 0.00012054767512202832,
|
| 543 |
+
"loss": 0.3488,
|
| 544 |
+
"step": 1650
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 24.817518248175183,
|
| 548 |
+
"grad_norm": 0.0033820979297161102,
|
| 549 |
+
"learning_rate": 0.00011117714323462186,
|
| 550 |
+
"loss": 0.3488,
|
| 551 |
+
"step": 1700
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 25.547445255474454,
|
| 555 |
+
"grad_norm": 0.0034969367552548647,
|
| 556 |
+
"learning_rate": 0.00010196640348243974,
|
| 557 |
+
"loss": 0.3488,
|
| 558 |
+
"step": 1750
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 26.277372262773724,
|
| 562 |
+
"grad_norm": 0.0014958898536860943,
|
| 563 |
+
"learning_rate": 9.295336661947115e-05,
|
| 564 |
+
"loss": 0.3488,
|
| 565 |
+
"step": 1800
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 26.277372262773724,
|
| 569 |
+
"eval_accuracy": 0.8534798534798534,
|
| 570 |
+
"eval_confusion_matrix": [
|
| 571 |
+
[
|
| 572 |
+
61,
|
| 573 |
+
11,
|
| 574 |
+
1,
|
| 575 |
+
2
|
| 576 |
+
],
|
| 577 |
+
[
|
| 578 |
+
7,
|
| 579 |
+
58,
|
| 580 |
+
10,
|
| 581 |
+
0
|
| 582 |
+
],
|
| 583 |
+
[
|
| 584 |
+
0,
|
| 585 |
+
9,
|
| 586 |
+
53,
|
| 587 |
+
0
|
| 588 |
+
],
|
| 589 |
+
[
|
| 590 |
+
0,
|
| 591 |
+
0,
|
| 592 |
+
0,
|
| 593 |
+
61
|
| 594 |
+
]
|
| 595 |
+
],
|
| 596 |
+
"eval_f1": 0.8535663673078441,
|
| 597 |
+
"eval_loss": 0.7831193804740906,
|
| 598 |
+
"eval_precision": 0.8551497604301419,
|
| 599 |
+
"eval_recall": 0.8534798534798534,
|
| 600 |
+
"eval_runtime": 3.7976,
|
| 601 |
+
"eval_samples_per_second": 71.888,
|
| 602 |
+
"eval_steps_per_second": 0.79,
|
| 603 |
+
"step": 1800
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 27.00729927007299,
|
| 607 |
+
"grad_norm": 0.004900149069726467,
|
| 608 |
+
"learning_rate": 8.417512966858319e-05,
|
| 609 |
+
"loss": 0.3488,
|
| 610 |
+
"step": 1850
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 27.73722627737226,
|
| 614 |
+
"grad_norm": 0.0018804975552484393,
|
| 615 |
+
"learning_rate": 7.566782323279578e-05,
|
| 616 |
+
"loss": 0.3488,
|
| 617 |
+
"step": 1900
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 28.467153284671532,
|
| 621 |
+
"grad_norm": 0.0019178036600351334,
|
| 622 |
+
"learning_rate": 6.746646278427247e-05,
|
| 623 |
+
"loss": 0.3488,
|
| 624 |
+
"step": 1950
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 29.197080291970803,
|
| 628 |
+
"grad_norm": 0.001025234698317945,
|
| 629 |
+
"learning_rate": 5.960480454311155e-05,
|
| 630 |
+
"loss": 0.3488,
|
| 631 |
+
"step": 2000
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 29.197080291970803,
|
| 635 |
+
"eval_accuracy": 0.8498168498168498,
|
| 636 |
+
"eval_confusion_matrix": [
|
| 637 |
+
[
|
| 638 |
+
61,
|
| 639 |
+
11,
|
| 640 |
+
1,
|
| 641 |
+
2
|
| 642 |
+
],
|
| 643 |
+
[
|
| 644 |
+
8,
|
| 645 |
+
57,
|
| 646 |
+
10,
|
| 647 |
+
0
|
| 648 |
+
],
|
| 649 |
+
[
|
| 650 |
+
0,
|
| 651 |
+
9,
|
| 652 |
+
53,
|
| 653 |
+
0
|
| 654 |
+
],
|
| 655 |
+
[
|
| 656 |
+
0,
|
| 657 |
+
0,
|
| 658 |
+
0,
|
| 659 |
+
61
|
| 660 |
+
]
|
| 661 |
+
],
|
| 662 |
+
"eval_f1": 0.8496942339108237,
|
| 663 |
+
"eval_loss": 0.7866398692131042,
|
| 664 |
+
"eval_precision": 0.8506632615716467,
|
| 665 |
+
"eval_recall": 0.8498168498168498,
|
| 666 |
+
"eval_runtime": 3.7892,
|
| 667 |
+
"eval_samples_per_second": 72.047,
|
| 668 |
+
"eval_steps_per_second": 0.792,
|
| 669 |
+
"step": 2000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 29.927007299270073,
|
| 673 |
+
"grad_norm": 0.0027674695011228323,
|
| 674 |
+
"learning_rate": 5.2115206539129e-05,
|
| 675 |
+
"loss": 0.3488,
|
| 676 |
+
"step": 2050
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 30.656934306569344,
|
| 680 |
+
"grad_norm": 0.0016269112238660455,
|
| 681 |
+
"learning_rate": 4.5028495428494483e-05,
|
| 682 |
+
"loss": 0.3488,
|
| 683 |
+
"step": 2100
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 31.386861313868614,
|
| 687 |
+
"grad_norm": 0.0019462064374238253,
|
| 688 |
+
"learning_rate": 3.837383961339246e-05,
|
| 689 |
+
"loss": 0.3488,
|
| 690 |
+
"step": 2150
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 32.11678832116788,
|
| 694 |
+
"grad_norm": 0.0011992512736469507,
|
| 695 |
+
"learning_rate": 3.21786291869402e-05,
|
| 696 |
+
"loss": 0.3488,
|
| 697 |
+
"step": 2200
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 32.11678832116788,
|
| 701 |
+
"eval_accuracy": 0.8534798534798534,
|
| 702 |
+
"eval_confusion_matrix": [
|
| 703 |
+
[
|
| 704 |
+
61,
|
| 705 |
+
11,
|
| 706 |
+
1,
|
| 707 |
+
2
|
| 708 |
+
],
|
| 709 |
+
[
|
| 710 |
+
8,
|
| 711 |
+
57,
|
| 712 |
+
10,
|
| 713 |
+
0
|
| 714 |
+
],
|
| 715 |
+
[
|
| 716 |
+
0,
|
| 717 |
+
8,
|
| 718 |
+
54,
|
| 719 |
+
0
|
| 720 |
+
],
|
| 721 |
+
[
|
| 722 |
+
0,
|
| 723 |
+
0,
|
| 724 |
+
0,
|
| 725 |
+
61
|
| 726 |
+
]
|
| 727 |
+
],
|
| 728 |
+
"eval_f1": 0.8531308487327289,
|
| 729 |
+
"eval_loss": 0.7856839895248413,
|
| 730 |
+
"eval_precision": 0.8539396783782831,
|
| 731 |
+
"eval_recall": 0.8534798534798534,
|
| 732 |
+
"eval_runtime": 3.787,
|
| 733 |
+
"eval_samples_per_second": 72.088,
|
| 734 |
+
"eval_steps_per_second": 0.792,
|
| 735 |
+
"step": 2200
|
| 736 |
+
}
|
| 737 |
+
],
|
| 738 |
+
"logging_steps": 50,
|
| 739 |
+
"max_steps": 2720,
|
| 740 |
+
"num_input_tokens_seen": 0,
|
| 741 |
+
"num_train_epochs": 40,
|
| 742 |
+
"save_steps": 200,
|
| 743 |
+
"stateful_callbacks": {
|
| 744 |
+
"EarlyStoppingCallback": {
|
| 745 |
+
"args": {
|
| 746 |
+
"early_stopping_patience": 5,
|
| 747 |
+
"early_stopping_threshold": 0.001
|
| 748 |
+
},
|
| 749 |
+
"attributes": {
|
| 750 |
+
"early_stopping_patience_counter": 0
|
| 751 |
+
}
|
| 752 |
+
},
|
| 753 |
+
"TrainerControl": {
|
| 754 |
+
"args": {
|
| 755 |
+
"should_epoch_stop": false,
|
| 756 |
+
"should_evaluate": false,
|
| 757 |
+
"should_log": false,
|
| 758 |
+
"should_save": true,
|
| 759 |
+
"should_training_stop": false
|
| 760 |
+
},
|
| 761 |
+
"attributes": {}
|
| 762 |
+
}
|
| 763 |
+
},
|
| 764 |
+
"total_flos": 7.961612341248e+16,
|
| 765 |
+
"train_batch_size": 8,
|
| 766 |
+
"trial_name": null,
|
| 767 |
+
"trial_params": null
|
| 768 |
+
}
|
checkpoint-2200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1cd6053c9e08edd46715ea6144f2b03c4f4ac31b547b8ae042d0b5e4a21ad64
|
| 3 |
+
size 5240
|
checkpoint-2400/config.json
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ntu-spml/distilhubert",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"apply_spec_augment": false,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"HubertForSequenceClassification"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"classifier_proj_size": 256,
|
| 11 |
+
"conv_bias": false,
|
| 12 |
+
"conv_dim": [
|
| 13 |
+
512,
|
| 14 |
+
512,
|
| 15 |
+
512,
|
| 16 |
+
512,
|
| 17 |
+
512,
|
| 18 |
+
512,
|
| 19 |
+
512
|
| 20 |
+
],
|
| 21 |
+
"conv_kernel": [
|
| 22 |
+
10,
|
| 23 |
+
3,
|
| 24 |
+
3,
|
| 25 |
+
3,
|
| 26 |
+
3,
|
| 27 |
+
2,
|
| 28 |
+
2
|
| 29 |
+
],
|
| 30 |
+
"conv_stride": [
|
| 31 |
+
5,
|
| 32 |
+
2,
|
| 33 |
+
2,
|
| 34 |
+
2,
|
| 35 |
+
2,
|
| 36 |
+
2,
|
| 37 |
+
2
|
| 38 |
+
],
|
| 39 |
+
"ctc_loss_reduction": "sum",
|
| 40 |
+
"ctc_zero_infinity": false,
|
| 41 |
+
"do_stable_layer_norm": false,
|
| 42 |
+
"eos_token_id": 2,
|
| 43 |
+
"feat_extract_activation": "gelu",
|
| 44 |
+
"feat_extract_norm": "group",
|
| 45 |
+
"feat_proj_dropout": 0.0,
|
| 46 |
+
"feat_proj_layer_norm": false,
|
| 47 |
+
"final_dropout": 0.0,
|
| 48 |
+
"finetuning_task": "audio-classification",
|
| 49 |
+
"hidden_act": "gelu",
|
| 50 |
+
"hidden_dropout": 0.1,
|
| 51 |
+
"hidden_size": 768,
|
| 52 |
+
"id2label": {
|
| 53 |
+
"0": "1s_normal",
|
| 54 |
+
"1": "1s_pain",
|
| 55 |
+
"2": "1s_hunger",
|
| 56 |
+
"3": "1s_asphyxia"
|
| 57 |
+
},
|
| 58 |
+
"initializer_range": 0.02,
|
| 59 |
+
"intermediate_size": 3072,
|
| 60 |
+
"label2id": {
|
| 61 |
+
"LABEL_0": 0,
|
| 62 |
+
"LABEL_1": 1,
|
| 63 |
+
"LABEL_2": 2,
|
| 64 |
+
"LABEL_3": 3
|
| 65 |
+
},
|
| 66 |
+
"layer_norm_eps": 1e-05,
|
| 67 |
+
"layerdrop": 0.0,
|
| 68 |
+
"mask_feature_length": 10,
|
| 69 |
+
"mask_feature_min_masks": 0,
|
| 70 |
+
"mask_feature_prob": 0.0,
|
| 71 |
+
"mask_time_length": 10,
|
| 72 |
+
"mask_time_min_masks": 2,
|
| 73 |
+
"mask_time_prob": 0.05,
|
| 74 |
+
"model_type": "hubert",
|
| 75 |
+
"num_attention_heads": 12,
|
| 76 |
+
"num_conv_pos_embedding_groups": 16,
|
| 77 |
+
"num_conv_pos_embeddings": 128,
|
| 78 |
+
"num_feat_extract_layers": 7,
|
| 79 |
+
"num_hidden_layers": 2,
|
| 80 |
+
"pad_token_id": 0,
|
| 81 |
+
"torch_dtype": "float32",
|
| 82 |
+
"transformers_version": "4.44.2",
|
| 83 |
+
"use_weighted_layer_sum": false,
|
| 84 |
+
"vocab_size": 32
|
| 85 |
+
}
|
checkpoint-2400/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f6f9165a112c1c9f627b872ddba5c6f189bc27160f4e0df85281aa54151f930
|
| 3 |
+
size 94765560
|
checkpoint-2400/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f151b348df4c0110eb4960671482caf90d968f80a4844aaea959dec4e29802fa
|
| 3 |
+
size 189556666
|
checkpoint-2400/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7c6c2284c30ed80bf04e4a7222520c39000a8d449d6494c1393520378ed2c60
|
| 3 |
+
size 14308
|
checkpoint-2400/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2488c60c13a7ef6f9d44255069440fc1dd24d07b71e6efb75a3ad44fe512eaf8
|
| 3 |
+
size 1064
|
checkpoint-2400/trainer_state.json
ADDED
|
@@ -0,0 +1,834 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8535663673078441,
|
| 3 |
+
"best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-1800",
|
| 4 |
+
"epoch": 35.03649635036496,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 2400,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.7299270072992701,
|
| 13 |
+
"grad_norm": 2.289438486099243,
|
| 14 |
+
"learning_rate": 5.5147058823529414e-05,
|
| 15 |
+
"loss": 1.2878,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.4598540145985401,
|
| 20 |
+
"grad_norm": 2.5048491954803467,
|
| 21 |
+
"learning_rate": 0.00011029411764705883,
|
| 22 |
+
"loss": 0.8322,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.18978102189781,
|
| 27 |
+
"grad_norm": 11.18371295928955,
|
| 28 |
+
"learning_rate": 0.00016544117647058823,
|
| 29 |
+
"loss": 0.7897,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.9197080291970803,
|
| 34 |
+
"grad_norm": 9.702393531799316,
|
| 35 |
+
"learning_rate": 0.00022058823529411765,
|
| 36 |
+
"loss": 0.7149,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 2.9197080291970803,
|
| 41 |
+
"eval_accuracy": 0.7252747252747253,
|
| 42 |
+
"eval_confusion_matrix": [
|
| 43 |
+
[
|
| 44 |
+
34,
|
| 45 |
+
39,
|
| 46 |
+
0,
|
| 47 |
+
2
|
| 48 |
+
],
|
| 49 |
+
[
|
| 50 |
+
7,
|
| 51 |
+
62,
|
| 52 |
+
6,
|
| 53 |
+
0
|
| 54 |
+
],
|
| 55 |
+
[
|
| 56 |
+
0,
|
| 57 |
+
19,
|
| 58 |
+
43,
|
| 59 |
+
0
|
| 60 |
+
],
|
| 61 |
+
[
|
| 62 |
+
0,
|
| 63 |
+
2,
|
| 64 |
+
0,
|
| 65 |
+
59
|
| 66 |
+
]
|
| 67 |
+
],
|
| 68 |
+
"eval_f1": 0.7260427659517454,
|
| 69 |
+
"eval_loss": 0.9058456420898438,
|
| 70 |
+
"eval_precision": 0.7828499608603893,
|
| 71 |
+
"eval_recall": 0.7252747252747253,
|
| 72 |
+
"eval_runtime": 3.7417,
|
| 73 |
+
"eval_samples_per_second": 72.962,
|
| 74 |
+
"eval_steps_per_second": 0.802,
|
| 75 |
+
"step": 200
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 3.6496350364963503,
|
| 79 |
+
"grad_norm": 8.47255802154541,
|
| 80 |
+
"learning_rate": 0.000275735294117647,
|
| 81 |
+
"loss": 0.6917,
|
| 82 |
+
"step": 250
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 4.37956204379562,
|
| 86 |
+
"grad_norm": 16.689321517944336,
|
| 87 |
+
"learning_rate": 0.0002999031705390845,
|
| 88 |
+
"loss": 0.7264,
|
| 89 |
+
"step": 300
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 5.109489051094891,
|
| 93 |
+
"grad_norm": 1.7369310855865479,
|
| 94 |
+
"learning_rate": 0.00029924913005299595,
|
| 95 |
+
"loss": 0.6895,
|
| 96 |
+
"step": 350
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 5.839416058394161,
|
| 100 |
+
"grad_norm": 2.210369348526001,
|
| 101 |
+
"learning_rate": 0.0002979807906935489,
|
| 102 |
+
"loss": 0.6939,
|
| 103 |
+
"step": 400
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 5.839416058394161,
|
| 107 |
+
"eval_accuracy": 0.7509157509157509,
|
| 108 |
+
"eval_confusion_matrix": [
|
| 109 |
+
[
|
| 110 |
+
66,
|
| 111 |
+
2,
|
| 112 |
+
0,
|
| 113 |
+
7
|
| 114 |
+
],
|
| 115 |
+
[
|
| 116 |
+
29,
|
| 117 |
+
38,
|
| 118 |
+
7,
|
| 119 |
+
1
|
| 120 |
+
],
|
| 121 |
+
[
|
| 122 |
+
2,
|
| 123 |
+
20,
|
| 124 |
+
40,
|
| 125 |
+
0
|
| 126 |
+
],
|
| 127 |
+
[
|
| 128 |
+
0,
|
| 129 |
+
0,
|
| 130 |
+
0,
|
| 131 |
+
61
|
| 132 |
+
]
|
| 133 |
+
],
|
| 134 |
+
"eval_f1": 0.7418721712792054,
|
| 135 |
+
"eval_loss": 0.8107791543006897,
|
| 136 |
+
"eval_precision": 0.7517378077426524,
|
| 137 |
+
"eval_recall": 0.7509157509157509,
|
| 138 |
+
"eval_runtime": 3.7702,
|
| 139 |
+
"eval_samples_per_second": 72.409,
|
| 140 |
+
"eval_steps_per_second": 0.796,
|
| 141 |
+
"step": 400
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 6.569343065693431,
|
| 145 |
+
"grad_norm": 2.1358511447906494,
|
| 146 |
+
"learning_rate": 0.000296103372855926,
|
| 147 |
+
"loss": 0.5986,
|
| 148 |
+
"step": 450
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 7.299270072992701,
|
| 152 |
+
"grad_norm": 13.704009056091309,
|
| 153 |
+
"learning_rate": 0.0002936246038592886,
|
| 154 |
+
"loss": 0.5932,
|
| 155 |
+
"step": 500
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 8.02919708029197,
|
| 159 |
+
"grad_norm": 2.032876968383789,
|
| 160 |
+
"learning_rate": 0.00029055468614167716,
|
| 161 |
+
"loss": 0.5633,
|
| 162 |
+
"step": 550
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 8.75912408759124,
|
| 166 |
+
"grad_norm": 28.525798797607422,
|
| 167 |
+
"learning_rate": 0.00028690625526749705,
|
| 168 |
+
"loss": 0.4941,
|
| 169 |
+
"step": 600
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 8.75912408759124,
|
| 173 |
+
"eval_accuracy": 0.8241758241758241,
|
| 174 |
+
"eval_confusion_matrix": [
|
| 175 |
+
[
|
| 176 |
+
63,
|
| 177 |
+
8,
|
| 178 |
+
1,
|
| 179 |
+
3
|
| 180 |
+
],
|
| 181 |
+
[
|
| 182 |
+
8,
|
| 183 |
+
50,
|
| 184 |
+
17,
|
| 185 |
+
0
|
| 186 |
+
],
|
| 187 |
+
[
|
| 188 |
+
2,
|
| 189 |
+
9,
|
| 190 |
+
51,
|
| 191 |
+
0
|
| 192 |
+
],
|
| 193 |
+
[
|
| 194 |
+
0,
|
| 195 |
+
0,
|
| 196 |
+
0,
|
| 197 |
+
61
|
| 198 |
+
]
|
| 199 |
+
],
|
| 200 |
+
"eval_f1": 0.8222676260809794,
|
| 201 |
+
"eval_loss": 0.7625077366828918,
|
| 202 |
+
"eval_precision": 0.8229409839103053,
|
| 203 |
+
"eval_recall": 0.8241758241758241,
|
| 204 |
+
"eval_runtime": 3.757,
|
| 205 |
+
"eval_samples_per_second": 72.664,
|
| 206 |
+
"eval_steps_per_second": 0.799,
|
| 207 |
+
"step": 600
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 9.489051094890511,
|
| 211 |
+
"grad_norm": 0.18371808528900146,
|
| 212 |
+
"learning_rate": 0.0002826943279204283,
|
| 213 |
+
"loss": 0.4842,
|
| 214 |
+
"step": 650
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 10.218978102189782,
|
| 218 |
+
"grad_norm": 11.426072120666504,
|
| 219 |
+
"learning_rate": 0.0002779362400958168,
|
| 220 |
+
"loss": 0.4352,
|
| 221 |
+
"step": 700
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 10.94890510948905,
|
| 225 |
+
"grad_norm": 8.062601089477539,
|
| 226 |
+
"learning_rate": 0.0002726515757469423,
|
| 227 |
+
"loss": 0.4447,
|
| 228 |
+
"step": 750
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 11.678832116788321,
|
| 232 |
+
"grad_norm": 0.3985881805419922,
|
| 233 |
+
"learning_rate": 0.00026686208617885055,
|
| 234 |
+
"loss": 0.442,
|
| 235 |
+
"step": 800
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 11.678832116788321,
|
| 239 |
+
"eval_accuracy": 0.7985347985347986,
|
| 240 |
+
"eval_confusion_matrix": [
|
| 241 |
+
[
|
| 242 |
+
66,
|
| 243 |
+
6,
|
| 244 |
+
1,
|
| 245 |
+
2
|
| 246 |
+
],
|
| 247 |
+
[
|
| 248 |
+
15,
|
| 249 |
+
32,
|
| 250 |
+
26,
|
| 251 |
+
2
|
| 252 |
+
],
|
| 253 |
+
[
|
| 254 |
+
2,
|
| 255 |
+
1,
|
| 256 |
+
59,
|
| 257 |
+
0
|
| 258 |
+
],
|
| 259 |
+
[
|
| 260 |
+
0,
|
| 261 |
+
0,
|
| 262 |
+
0,
|
| 263 |
+
61
|
| 264 |
+
]
|
| 265 |
+
],
|
| 266 |
+
"eval_f1": 0.781170020153555,
|
| 267 |
+
"eval_loss": 0.9623217582702637,
|
| 268 |
+
"eval_precision": 0.8093701586901577,
|
| 269 |
+
"eval_recall": 0.7985347985347986,
|
| 270 |
+
"eval_runtime": 3.774,
|
| 271 |
+
"eval_samples_per_second": 72.337,
|
| 272 |
+
"eval_steps_per_second": 0.795,
|
| 273 |
+
"step": 800
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 12.408759124087592,
|
| 277 |
+
"grad_norm": 38.726985931396484,
|
| 278 |
+
"learning_rate": 0.0002605916005215186,
|
| 279 |
+
"loss": 0.4504,
|
| 280 |
+
"step": 850
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 13.138686131386862,
|
| 284 |
+
"grad_norm": 0.026563748717308044,
|
| 285 |
+
"learning_rate": 0.0002538659276508397,
|
| 286 |
+
"loss": 0.3903,
|
| 287 |
+
"step": 900
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 13.86861313868613,
|
| 291 |
+
"grad_norm": 0.06770322471857071,
|
| 292 |
+
"learning_rate": 0.0002467127499611136,
|
| 293 |
+
"loss": 0.4094,
|
| 294 |
+
"step": 950
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 14.598540145985401,
|
| 298 |
+
"grad_norm": 1.2612749338150024,
|
| 299 |
+
"learning_rate": 0.00023916150942626798,
|
| 300 |
+
"loss": 0.4188,
|
| 301 |
+
"step": 1000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 14.598540145985401,
|
| 305 |
+
"eval_accuracy": 0.8315018315018315,
|
| 306 |
+
"eval_confusion_matrix": [
|
| 307 |
+
[
|
| 308 |
+
60,
|
| 309 |
+
9,
|
| 310 |
+
2,
|
| 311 |
+
4
|
| 312 |
+
],
|
| 313 |
+
[
|
| 314 |
+
8,
|
| 315 |
+
56,
|
| 316 |
+
11,
|
| 317 |
+
0
|
| 318 |
+
],
|
| 319 |
+
[
|
| 320 |
+
1,
|
| 321 |
+
11,
|
| 322 |
+
50,
|
| 323 |
+
0
|
| 324 |
+
],
|
| 325 |
+
[
|
| 326 |
+
0,
|
| 327 |
+
0,
|
| 328 |
+
0,
|
| 329 |
+
61
|
| 330 |
+
]
|
| 331 |
+
],
|
| 332 |
+
"eval_f1": 0.8307422385946511,
|
| 333 |
+
"eval_loss": 0.8534455299377441,
|
| 334 |
+
"eval_precision": 0.8312566016541674,
|
| 335 |
+
"eval_recall": 0.8315018315018315,
|
| 336 |
+
"eval_runtime": 3.796,
|
| 337 |
+
"eval_samples_per_second": 71.917,
|
| 338 |
+
"eval_steps_per_second": 0.79,
|
| 339 |
+
"step": 1000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 15.328467153284672,
|
| 343 |
+
"grad_norm": 28.980899810791016,
|
| 344 |
+
"learning_rate": 0.0002312432864187738,
|
| 345 |
+
"loss": 0.3798,
|
| 346 |
+
"step": 1050
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 16.05839416058394,
|
| 350 |
+
"grad_norm": 0.022609323263168335,
|
| 351 |
+
"learning_rate": 0.0002229906717850284,
|
| 352 |
+
"loss": 0.3672,
|
| 353 |
+
"step": 1100
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 16.78832116788321,
|
| 357 |
+
"grad_norm": 0.02360348217189312,
|
| 358 |
+
"learning_rate": 0.00021443763270373483,
|
| 359 |
+
"loss": 0.3715,
|
| 360 |
+
"step": 1150
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 17.51824817518248,
|
| 364 |
+
"grad_norm": 0.014020542614161968,
|
| 365 |
+
"learning_rate": 0.0002056193728793941,
|
| 366 |
+
"loss": 0.349,
|
| 367 |
+
"step": 1200
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 17.51824817518248,
|
| 371 |
+
"eval_accuracy": 0.8351648351648352,
|
| 372 |
+
"eval_confusion_matrix": [
|
| 373 |
+
[
|
| 374 |
+
62,
|
| 375 |
+
10,
|
| 376 |
+
1,
|
| 377 |
+
2
|
| 378 |
+
],
|
| 379 |
+
[
|
| 380 |
+
9,
|
| 381 |
+
57,
|
| 382 |
+
9,
|
| 383 |
+
0
|
| 384 |
+
],
|
| 385 |
+
[
|
| 386 |
+
2,
|
| 387 |
+
12,
|
| 388 |
+
48,
|
| 389 |
+
0
|
| 390 |
+
],
|
| 391 |
+
[
|
| 392 |
+
0,
|
| 393 |
+
0,
|
| 394 |
+
0,
|
| 395 |
+
61
|
| 396 |
+
]
|
| 397 |
+
],
|
| 398 |
+
"eval_f1": 0.8350675728555914,
|
| 399 |
+
"eval_loss": 0.8131950497627258,
|
| 400 |
+
"eval_precision": 0.8358475863688551,
|
| 401 |
+
"eval_recall": 0.8351648351648352,
|
| 402 |
+
"eval_runtime": 3.7788,
|
| 403 |
+
"eval_samples_per_second": 72.246,
|
| 404 |
+
"eval_steps_per_second": 0.794,
|
| 405 |
+
"step": 1200
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 18.248175182481752,
|
| 409 |
+
"grad_norm": 0.006028232164680958,
|
| 410 |
+
"learning_rate": 0.0001965721876463452,
|
| 411 |
+
"loss": 0.3491,
|
| 412 |
+
"step": 1250
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 18.978102189781023,
|
| 416 |
+
"grad_norm": 0.008285734802484512,
|
| 417 |
+
"learning_rate": 0.00018733331457973358,
|
| 418 |
+
"loss": 0.3489,
|
| 419 |
+
"step": 1300
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 19.708029197080293,
|
| 423 |
+
"grad_norm": 0.008053851313889027,
|
| 424 |
+
"learning_rate": 0.00017794078022828275,
|
| 425 |
+
"loss": 0.3497,
|
| 426 |
+
"step": 1350
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 20.437956204379564,
|
| 430 |
+
"grad_norm": 0.003234422067180276,
|
| 431 |
+
"learning_rate": 0.00016843324359970712,
|
| 432 |
+
"loss": 0.3488,
|
| 433 |
+
"step": 1400
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 20.437956204379564,
|
| 437 |
+
"eval_accuracy": 0.8461538461538461,
|
| 438 |
+
"eval_confusion_matrix": [
|
| 439 |
+
[
|
| 440 |
+
61,
|
| 441 |
+
11,
|
| 442 |
+
1,
|
| 443 |
+
2
|
| 444 |
+
],
|
| 445 |
+
[
|
| 446 |
+
8,
|
| 447 |
+
57,
|
| 448 |
+
10,
|
| 449 |
+
0
|
| 450 |
+
],
|
| 451 |
+
[
|
| 452 |
+
0,
|
| 453 |
+
10,
|
| 454 |
+
52,
|
| 455 |
+
0
|
| 456 |
+
],
|
| 457 |
+
[
|
| 458 |
+
0,
|
| 459 |
+
0,
|
| 460 |
+
0,
|
| 461 |
+
61
|
| 462 |
+
]
|
| 463 |
+
],
|
| 464 |
+
"eval_f1": 0.8462423027109934,
|
| 465 |
+
"eval_loss": 0.7859560251235962,
|
| 466 |
+
"eval_precision": 0.8474363933035696,
|
| 467 |
+
"eval_recall": 0.8461538461538461,
|
| 468 |
+
"eval_runtime": 3.7947,
|
| 469 |
+
"eval_samples_per_second": 71.942,
|
| 470 |
+
"eval_steps_per_second": 0.791,
|
| 471 |
+
"step": 1400
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 21.16788321167883,
|
| 475 |
+
"grad_norm": 0.004595920909196138,
|
| 476 |
+
"learning_rate": 0.00015884983704296757,
|
| 477 |
+
"loss": 0.3488,
|
| 478 |
+
"step": 1450
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 21.8978102189781,
|
| 482 |
+
"grad_norm": 0.002511706668883562,
|
| 483 |
+
"learning_rate": 0.00014923000518228847,
|
| 484 |
+
"loss": 0.3488,
|
| 485 |
+
"step": 1500
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 22.62773722627737,
|
| 489 |
+
"grad_norm": 0.002340014325454831,
|
| 490 |
+
"learning_rate": 0.00013961334256587125,
|
| 491 |
+
"loss": 0.3488,
|
| 492 |
+
"step": 1550
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 23.357664233576642,
|
| 496 |
+
"grad_norm": 0.0028287076856940985,
|
| 497 |
+
"learning_rate": 0.00013003943069753198,
|
| 498 |
+
"loss": 0.3488,
|
| 499 |
+
"step": 1600
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 23.357664233576642,
|
| 503 |
+
"eval_accuracy": 0.8461538461538461,
|
| 504 |
+
"eval_confusion_matrix": [
|
| 505 |
+
[
|
| 506 |
+
61,
|
| 507 |
+
11,
|
| 508 |
+
1,
|
| 509 |
+
2
|
| 510 |
+
],
|
| 511 |
+
[
|
| 512 |
+
8,
|
| 513 |
+
57,
|
| 514 |
+
10,
|
| 515 |
+
0
|
| 516 |
+
],
|
| 517 |
+
[
|
| 518 |
+
0,
|
| 519 |
+
10,
|
| 520 |
+
52,
|
| 521 |
+
0
|
| 522 |
+
],
|
| 523 |
+
[
|
| 524 |
+
0,
|
| 525 |
+
0,
|
| 526 |
+
0,
|
| 527 |
+
61
|
| 528 |
+
]
|
| 529 |
+
],
|
| 530 |
+
"eval_f1": 0.8462423027109934,
|
| 531 |
+
"eval_loss": 0.7856015563011169,
|
| 532 |
+
"eval_precision": 0.8474363933035696,
|
| 533 |
+
"eval_recall": 0.8461538461538461,
|
| 534 |
+
"eval_runtime": 3.7861,
|
| 535 |
+
"eval_samples_per_second": 72.105,
|
| 536 |
+
"eval_steps_per_second": 0.792,
|
| 537 |
+
"step": 1600
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 24.087591240875913,
|
| 541 |
+
"grad_norm": 0.0027960864827036858,
|
| 542 |
+
"learning_rate": 0.00012054767512202832,
|
| 543 |
+
"loss": 0.3488,
|
| 544 |
+
"step": 1650
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 24.817518248175183,
|
| 548 |
+
"grad_norm": 0.0033820979297161102,
|
| 549 |
+
"learning_rate": 0.00011117714323462186,
|
| 550 |
+
"loss": 0.3488,
|
| 551 |
+
"step": 1700
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 25.547445255474454,
|
| 555 |
+
"grad_norm": 0.0034969367552548647,
|
| 556 |
+
"learning_rate": 0.00010196640348243974,
|
| 557 |
+
"loss": 0.3488,
|
| 558 |
+
"step": 1750
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 26.277372262773724,
|
| 562 |
+
"grad_norm": 0.0014958898536860943,
|
| 563 |
+
"learning_rate": 9.295336661947115e-05,
|
| 564 |
+
"loss": 0.3488,
|
| 565 |
+
"step": 1800
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 26.277372262773724,
|
| 569 |
+
"eval_accuracy": 0.8534798534798534,
|
| 570 |
+
"eval_confusion_matrix": [
|
| 571 |
+
[
|
| 572 |
+
61,
|
| 573 |
+
11,
|
| 574 |
+
1,
|
| 575 |
+
2
|
| 576 |
+
],
|
| 577 |
+
[
|
| 578 |
+
7,
|
| 579 |
+
58,
|
| 580 |
+
10,
|
| 581 |
+
0
|
| 582 |
+
],
|
| 583 |
+
[
|
| 584 |
+
0,
|
| 585 |
+
9,
|
| 586 |
+
53,
|
| 587 |
+
0
|
| 588 |
+
],
|
| 589 |
+
[
|
| 590 |
+
0,
|
| 591 |
+
0,
|
| 592 |
+
0,
|
| 593 |
+
61
|
| 594 |
+
]
|
| 595 |
+
],
|
| 596 |
+
"eval_f1": 0.8535663673078441,
|
| 597 |
+
"eval_loss": 0.7831193804740906,
|
| 598 |
+
"eval_precision": 0.8551497604301419,
|
| 599 |
+
"eval_recall": 0.8534798534798534,
|
| 600 |
+
"eval_runtime": 3.7976,
|
| 601 |
+
"eval_samples_per_second": 71.888,
|
| 602 |
+
"eval_steps_per_second": 0.79,
|
| 603 |
+
"step": 1800
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 27.00729927007299,
|
| 607 |
+
"grad_norm": 0.004900149069726467,
|
| 608 |
+
"learning_rate": 8.417512966858319e-05,
|
| 609 |
+
"loss": 0.3488,
|
| 610 |
+
"step": 1850
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 27.73722627737226,
|
| 614 |
+
"grad_norm": 0.0018804975552484393,
|
| 615 |
+
"learning_rate": 7.566782323279578e-05,
|
| 616 |
+
"loss": 0.3488,
|
| 617 |
+
"step": 1900
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 28.467153284671532,
|
| 621 |
+
"grad_norm": 0.0019178036600351334,
|
| 622 |
+
"learning_rate": 6.746646278427247e-05,
|
| 623 |
+
"loss": 0.3488,
|
| 624 |
+
"step": 1950
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 29.197080291970803,
|
| 628 |
+
"grad_norm": 0.001025234698317945,
|
| 629 |
+
"learning_rate": 5.960480454311155e-05,
|
| 630 |
+
"loss": 0.3488,
|
| 631 |
+
"step": 2000
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 29.197080291970803,
|
| 635 |
+
"eval_accuracy": 0.8498168498168498,
|
| 636 |
+
"eval_confusion_matrix": [
|
| 637 |
+
[
|
| 638 |
+
61,
|
| 639 |
+
11,
|
| 640 |
+
1,
|
| 641 |
+
2
|
| 642 |
+
],
|
| 643 |
+
[
|
| 644 |
+
8,
|
| 645 |
+
57,
|
| 646 |
+
10,
|
| 647 |
+
0
|
| 648 |
+
],
|
| 649 |
+
[
|
| 650 |
+
0,
|
| 651 |
+
9,
|
| 652 |
+
53,
|
| 653 |
+
0
|
| 654 |
+
],
|
| 655 |
+
[
|
| 656 |
+
0,
|
| 657 |
+
0,
|
| 658 |
+
0,
|
| 659 |
+
61
|
| 660 |
+
]
|
| 661 |
+
],
|
| 662 |
+
"eval_f1": 0.8496942339108237,
|
| 663 |
+
"eval_loss": 0.7866398692131042,
|
| 664 |
+
"eval_precision": 0.8506632615716467,
|
| 665 |
+
"eval_recall": 0.8498168498168498,
|
| 666 |
+
"eval_runtime": 3.7892,
|
| 667 |
+
"eval_samples_per_second": 72.047,
|
| 668 |
+
"eval_steps_per_second": 0.792,
|
| 669 |
+
"step": 2000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 29.927007299270073,
|
| 673 |
+
"grad_norm": 0.0027674695011228323,
|
| 674 |
+
"learning_rate": 5.2115206539129e-05,
|
| 675 |
+
"loss": 0.3488,
|
| 676 |
+
"step": 2050
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 30.656934306569344,
|
| 680 |
+
"grad_norm": 0.0016269112238660455,
|
| 681 |
+
"learning_rate": 4.5028495428494483e-05,
|
| 682 |
+
"loss": 0.3488,
|
| 683 |
+
"step": 2100
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 31.386861313868614,
|
| 687 |
+
"grad_norm": 0.0019462064374238253,
|
| 688 |
+
"learning_rate": 3.837383961339246e-05,
|
| 689 |
+
"loss": 0.3488,
|
| 690 |
+
"step": 2150
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 32.11678832116788,
|
| 694 |
+
"grad_norm": 0.0011992512736469507,
|
| 695 |
+
"learning_rate": 3.21786291869402e-05,
|
| 696 |
+
"loss": 0.3488,
|
| 697 |
+
"step": 2200
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 32.11678832116788,
|
| 701 |
+
"eval_accuracy": 0.8534798534798534,
|
| 702 |
+
"eval_confusion_matrix": [
|
| 703 |
+
[
|
| 704 |
+
61,
|
| 705 |
+
11,
|
| 706 |
+
1,
|
| 707 |
+
2
|
| 708 |
+
],
|
| 709 |
+
[
|
| 710 |
+
8,
|
| 711 |
+
57,
|
| 712 |
+
10,
|
| 713 |
+
0
|
| 714 |
+
],
|
| 715 |
+
[
|
| 716 |
+
0,
|
| 717 |
+
8,
|
| 718 |
+
54,
|
| 719 |
+
0
|
| 720 |
+
],
|
| 721 |
+
[
|
| 722 |
+
0,
|
| 723 |
+
0,
|
| 724 |
+
0,
|
| 725 |
+
61
|
| 726 |
+
]
|
| 727 |
+
],
|
| 728 |
+
"eval_f1": 0.8531308487327289,
|
| 729 |
+
"eval_loss": 0.7856839895248413,
|
| 730 |
+
"eval_precision": 0.8539396783782831,
|
| 731 |
+
"eval_recall": 0.8534798534798534,
|
| 732 |
+
"eval_runtime": 3.787,
|
| 733 |
+
"eval_samples_per_second": 72.088,
|
| 734 |
+
"eval_steps_per_second": 0.792,
|
| 735 |
+
"step": 2200
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 32.846715328467155,
|
| 739 |
+
"grad_norm": 0.0029719627927988768,
|
| 740 |
+
"learning_rate": 2.6468363197499458e-05,
|
| 741 |
+
"loss": 0.3488,
|
| 742 |
+
"step": 2250
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 33.57664233576642,
|
| 746 |
+
"grad_norm": 0.0012639207998290658,
|
| 747 |
+
"learning_rate": 2.1266544696395582e-05,
|
| 748 |
+
"loss": 0.3488,
|
| 749 |
+
"step": 2300
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 34.306569343065696,
|
| 753 |
+
"grad_norm": 0.0011322245700284839,
|
| 754 |
+
"learning_rate": 1.659458400101879e-05,
|
| 755 |
+
"loss": 0.3488,
|
| 756 |
+
"step": 2350
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 35.03649635036496,
|
| 760 |
+
"grad_norm": 0.002087602624669671,
|
| 761 |
+
"learning_rate": 1.2471710571470578e-05,
|
| 762 |
+
"loss": 0.3488,
|
| 763 |
+
"step": 2400
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 35.03649635036496,
|
| 767 |
+
"eval_accuracy": 0.8498168498168498,
|
| 768 |
+
"eval_confusion_matrix": [
|
| 769 |
+
[
|
| 770 |
+
61,
|
| 771 |
+
11,
|
| 772 |
+
1,
|
| 773 |
+
2
|
| 774 |
+
],
|
| 775 |
+
[
|
| 776 |
+
8,
|
| 777 |
+
57,
|
| 778 |
+
10,
|
| 779 |
+
0
|
| 780 |
+
],
|
| 781 |
+
[
|
| 782 |
+
0,
|
| 783 |
+
9,
|
| 784 |
+
53,
|
| 785 |
+
0
|
| 786 |
+
],
|
| 787 |
+
[
|
| 788 |
+
0,
|
| 789 |
+
0,
|
| 790 |
+
0,
|
| 791 |
+
61
|
| 792 |
+
]
|
| 793 |
+
],
|
| 794 |
+
"eval_f1": 0.8496942339108237,
|
| 795 |
+
"eval_loss": 0.7856935858726501,
|
| 796 |
+
"eval_precision": 0.8506632615716467,
|
| 797 |
+
"eval_recall": 0.8498168498168498,
|
| 798 |
+
"eval_runtime": 3.788,
|
| 799 |
+
"eval_samples_per_second": 72.069,
|
| 800 |
+
"eval_steps_per_second": 0.792,
|
| 801 |
+
"step": 2400
|
| 802 |
+
}
|
| 803 |
+
],
|
| 804 |
+
"logging_steps": 50,
|
| 805 |
+
"max_steps": 2720,
|
| 806 |
+
"num_input_tokens_seen": 0,
|
| 807 |
+
"num_train_epochs": 40,
|
| 808 |
+
"save_steps": 200,
|
| 809 |
+
"stateful_callbacks": {
|
| 810 |
+
"EarlyStoppingCallback": {
|
| 811 |
+
"args": {
|
| 812 |
+
"early_stopping_patience": 5,
|
| 813 |
+
"early_stopping_threshold": 0.001
|
| 814 |
+
},
|
| 815 |
+
"attributes": {
|
| 816 |
+
"early_stopping_patience_counter": 0
|
| 817 |
+
}
|
| 818 |
+
},
|
| 819 |
+
"TrainerControl": {
|
| 820 |
+
"args": {
|
| 821 |
+
"should_epoch_stop": false,
|
| 822 |
+
"should_evaluate": false,
|
| 823 |
+
"should_log": false,
|
| 824 |
+
"should_save": true,
|
| 825 |
+
"should_training_stop": false
|
| 826 |
+
},
|
| 827 |
+
"attributes": {}
|
| 828 |
+
}
|
| 829 |
+
},
|
| 830 |
+
"total_flos": 8.68527123264e+16,
|
| 831 |
+
"train_batch_size": 8,
|
| 832 |
+
"trial_name": null,
|
| 833 |
+
"trial_params": null
|
| 834 |
+
}
|
checkpoint-2400/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1cd6053c9e08edd46715ea6144f2b03c4f4ac31b547b8ae042d0b5e4a21ad64
|
| 3 |
+
size 5240
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 94765560
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c75935ca7cf6cf2624c007d676c6f4095f4ab57f426f3d85e0a4fe5b16078bb
|
| 3 |
size 94765560
|
runs/Sep14_17-06-50_ubumarcos/events.out.tfevents.1726327100.ubumarcos
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75de08e534bbfb12e3a8fc006cb6ab6612e4998c46526c752f20021f20b7d043
|
| 3 |
+
size 503
|
runs/Sep14_18-07-00_ubumarcos/events.out.tfevents.1726330021.ubumarcos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7aef52f1e01abd8b1f2974e343dfab563bfe7b9dceb1a4e16c6eaea7954c87b
|
| 3 |
+
size 22146
|
runs/Sep14_18-24-29_ubumarcos/events.out.tfevents.1726331070.ubumarcos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:623ee29ee6d95a119d7d22770b2fa5d05167ef523e56637865d7dd27219b6622
|
| 3 |
+
size 6921
|
runs/Sep14_18-24-29_ubumarcos/events.out.tfevents.1726331984.ubumarcos
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4fede9fcdd631a8ec2518ba9c9ab15f1bfc3400996d5c026e5f67af3e9fe841
|
| 3 |
+
size 40
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b8b55b425459f7b65521e542a14dc1670fa162e08d497ee83bde1c914e74cf6
|
| 3 |
size 5240
|