persian whisper small ft
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +92 -0
- added_tokens.json +109 -0
- all_results.json +12 -0
- checkpoint-1000/config.json +41 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/preprocessor_config.json +0 -0
- checkpoint-1000/pytorch_model.bin +3 -0
- checkpoint-1000/rng_state_0.pth +3 -0
- checkpoint-1000/rng_state_1.pth +3 -0
- checkpoint-1000/rng_state_2.pth +3 -0
- checkpoint-1000/rng_state_3.pth +3 -0
- checkpoint-1000/scaler.pt +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/trainer_state.json +274 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-1500/config.json +41 -0
- checkpoint-1500/optimizer.pt +3 -0
- checkpoint-1500/preprocessor_config.json +0 -0
- checkpoint-1500/pytorch_model.bin +3 -0
- checkpoint-1500/rng_state_0.pth +3 -0
- checkpoint-1500/rng_state_1.pth +3 -0
- checkpoint-1500/rng_state_2.pth +3 -0
- checkpoint-1500/rng_state_3.pth +3 -0
- checkpoint-1500/scaler.pt +3 -0
- checkpoint-1500/scheduler.pt +3 -0
- checkpoint-1500/trainer_state.json +403 -0
- checkpoint-1500/training_args.bin +3 -0
- checkpoint-2000/config.json +41 -0
- checkpoint-2000/optimizer.pt +3 -0
- checkpoint-2000/preprocessor_config.json +0 -0
- checkpoint-2000/pytorch_model.bin +3 -0
- checkpoint-2000/rng_state_0.pth +3 -0
- checkpoint-2000/rng_state_1.pth +3 -0
- checkpoint-2000/rng_state_2.pth +3 -0
- checkpoint-2000/rng_state_3.pth +3 -0
- checkpoint-2000/scaler.pt +3 -0
- checkpoint-2000/scheduler.pt +3 -0
- checkpoint-2000/trainer_state.json +532 -0
- checkpoint-2000/training_args.bin +3 -0
- checkpoint-2500/config.json +41 -0
- checkpoint-2500/optimizer.pt +3 -0
- checkpoint-2500/preprocessor_config.json +0 -0
- checkpoint-2500/pytorch_model.bin +3 -0
- checkpoint-2500/rng_state_0.pth +3 -0
- checkpoint-2500/rng_state_1.pth +3 -0
- checkpoint-2500/rng_state_2.pth +3 -0
- checkpoint-2500/rng_state_3.pth +3 -0
- checkpoint-2500/scaler.pt +3 -0
- checkpoint-2500/scheduler.pt +3 -0
- checkpoint-2500/trainer_state.json +661 -0
README.md
ADDED
|
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- fa
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- whisper-event
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
datasets:
|
| 9 |
+
- mozilla-foundation/common_voice_11_0
|
| 10 |
+
metrics:
|
| 11 |
+
- wer
|
| 12 |
+
model-index:
|
| 13 |
+
- name: Whisper small Persian
|
| 14 |
+
results:
|
| 15 |
+
- task:
|
| 16 |
+
name: Automatic Speech Recognition
|
| 17 |
+
type: automatic-speech-recognition
|
| 18 |
+
dataset:
|
| 19 |
+
name: mozilla-foundation/common_voice_11_0 fa
|
| 20 |
+
type: mozilla-foundation/common_voice_11_0
|
| 21 |
+
config: null
|
| 22 |
+
split: None
|
| 23 |
+
metrics:
|
| 24 |
+
- name: Wer
|
| 25 |
+
type: wer
|
| 26 |
+
value: 32.89950864725314
|
| 27 |
+
---
|
| 28 |
+
|
| 29 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 30 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 31 |
+
|
| 32 |
+
# Whisper small Persian
|
| 33 |
+
|
| 34 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the mozilla-foundation/common_voice_11_0 fa dataset.
|
| 35 |
+
It achieves the following results on the evaluation set:
|
| 36 |
+
- Loss: 0.4924
|
| 37 |
+
- Wer: 39.8995
|
| 38 |
+
|
| 39 |
+
## Model description
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Intended uses & limitations
|
| 44 |
+
|
| 45 |
+
More information needed
|
| 46 |
+
|
| 47 |
+
## Training and evaluation data
|
| 48 |
+
|
| 49 |
+
More information needed
|
| 50 |
+
|
| 51 |
+
## Training procedure
|
| 52 |
+
|
| 53 |
+
### Training hyperparameters
|
| 54 |
+
|
| 55 |
+
The following hyperparameters were used during training:
|
| 56 |
+
- learning_rate: 1e-06
|
| 57 |
+
- train_batch_size: 8
|
| 58 |
+
- eval_batch_size: 16
|
| 59 |
+
- seed: 42
|
| 60 |
+
- distributed_type: multi-GPU
|
| 61 |
+
- num_devices: 4
|
| 62 |
+
- gradient_accumulation_steps: 2
|
| 63 |
+
- total_train_batch_size: 64
|
| 64 |
+
- total_eval_batch_size: 64
|
| 65 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 66 |
+
- lr_scheduler_type: linear
|
| 67 |
+
- lr_scheduler_warmup_steps: 500
|
| 68 |
+
- training_steps: 5000
|
| 69 |
+
- mixed_precision_training: Native AMP
|
| 70 |
+
|
| 71 |
+
### Training results
|
| 72 |
+
|
| 73 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 74 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 75 |
+
| 0.5533 | 1.56 | 500 | 0.7044 | 54.5499 |
|
| 76 |
+
| 0.3951 | 3.12 | 1000 | 0.5893 | 47.5210 |
|
| 77 |
+
| 0.3296 | 4.67 | 1500 | 0.5429 | 42.6451 |
|
| 78 |
+
| 0.2662 | 6.23 | 2000 | 0.5223 | 40.6644 |
|
| 79 |
+
| 0.2535 | 7.79 | 2500 | 0.5045 | 38.5304 |
|
| 80 |
+
| 0.224 | 9.35 | 3000 | 0.5002 | 36.8822 |
|
| 81 |
+
| 0.2204 | 10.9 | 3500 | 0.4967 | 35.3076 |
|
| 82 |
+
| 0.2024 | 12.46 | 4000 | 0.4951 | 34.9883 |
|
| 83 |
+
| 0.2099 | 14.02 | 4500 | 0.4921 | 34.9842 |
|
| 84 |
+
| 0.1836 | 15.58 | 5000 | 0.4924 | 34.8995 |
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
### Framework versions
|
| 88 |
+
|
| 89 |
+
- Transformers 4.25.1
|
| 90 |
+
- Pytorch 1.13.0+cu117
|
| 91 |
+
- Datasets 2.7.1
|
| 92 |
+
- Tokenizers 0.13.2
|
added_tokens.json
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|af|>": 50327,
|
| 3 |
+
"<|am|>": 50334,
|
| 4 |
+
"<|ar|>": 50272,
|
| 5 |
+
"<|as|>": 50350,
|
| 6 |
+
"<|az|>": 50304,
|
| 7 |
+
"<|ba|>": 50355,
|
| 8 |
+
"<|be|>": 50330,
|
| 9 |
+
"<|bg|>": 50292,
|
| 10 |
+
"<|bn|>": 50302,
|
| 11 |
+
"<|bo|>": 50347,
|
| 12 |
+
"<|br|>": 50309,
|
| 13 |
+
"<|bs|>": 50315,
|
| 14 |
+
"<|ca|>": 50270,
|
| 15 |
+
"<|cs|>": 50283,
|
| 16 |
+
"<|cy|>": 50297,
|
| 17 |
+
"<|da|>": 50285,
|
| 18 |
+
"<|de|>": 50261,
|
| 19 |
+
"<|el|>": 50281,
|
| 20 |
+
"<|endoftext|>": 50257,
|
| 21 |
+
"<|en|>": 50259,
|
| 22 |
+
"<|es|>": 50262,
|
| 23 |
+
"<|et|>": 50307,
|
| 24 |
+
"<|eu|>": 50310,
|
| 25 |
+
"<|fa|>": 50300,
|
| 26 |
+
"<|fi|>": 50277,
|
| 27 |
+
"<|fo|>": 50338,
|
| 28 |
+
"<|fr|>": 50265,
|
| 29 |
+
"<|gl|>": 50319,
|
| 30 |
+
"<|gu|>": 50333,
|
| 31 |
+
"<|haw|>": 50352,
|
| 32 |
+
"<|ha|>": 50354,
|
| 33 |
+
"<|hi|>": 50276,
|
| 34 |
+
"<|hr|>": 50291,
|
| 35 |
+
"<|ht|>": 50339,
|
| 36 |
+
"<|hu|>": 50286,
|
| 37 |
+
"<|hy|>": 50312,
|
| 38 |
+
"<|id|>": 50275,
|
| 39 |
+
"<|is|>": 50311,
|
| 40 |
+
"<|it|>": 50274,
|
| 41 |
+
"<|iw|>": 50279,
|
| 42 |
+
"<|ja|>": 50266,
|
| 43 |
+
"<|jw|>": 50356,
|
| 44 |
+
"<|ka|>": 50329,
|
| 45 |
+
"<|kk|>": 50316,
|
| 46 |
+
"<|km|>": 50323,
|
| 47 |
+
"<|kn|>": 50306,
|
| 48 |
+
"<|ko|>": 50264,
|
| 49 |
+
"<|la|>": 50294,
|
| 50 |
+
"<|lb|>": 50345,
|
| 51 |
+
"<|ln|>": 50353,
|
| 52 |
+
"<|lo|>": 50336,
|
| 53 |
+
"<|lt|>": 50293,
|
| 54 |
+
"<|lv|>": 50301,
|
| 55 |
+
"<|mg|>": 50349,
|
| 56 |
+
"<|mi|>": 50295,
|
| 57 |
+
"<|mk|>": 50308,
|
| 58 |
+
"<|ml|>": 50296,
|
| 59 |
+
"<|mn|>": 50314,
|
| 60 |
+
"<|mr|>": 50320,
|
| 61 |
+
"<|ms|>": 50282,
|
| 62 |
+
"<|mt|>": 50343,
|
| 63 |
+
"<|my|>": 50346,
|
| 64 |
+
"<|ne|>": 50313,
|
| 65 |
+
"<|nl|>": 50271,
|
| 66 |
+
"<|nn|>": 50342,
|
| 67 |
+
"<|nocaptions|>": 50362,
|
| 68 |
+
"<|notimestamps|>": 50363,
|
| 69 |
+
"<|no|>": 50288,
|
| 70 |
+
"<|oc|>": 50328,
|
| 71 |
+
"<|pa|>": 50321,
|
| 72 |
+
"<|pl|>": 50269,
|
| 73 |
+
"<|ps|>": 50340,
|
| 74 |
+
"<|pt|>": 50267,
|
| 75 |
+
"<|ro|>": 50284,
|
| 76 |
+
"<|ru|>": 50263,
|
| 77 |
+
"<|sa|>": 50344,
|
| 78 |
+
"<|sd|>": 50332,
|
| 79 |
+
"<|si|>": 50322,
|
| 80 |
+
"<|sk|>": 50298,
|
| 81 |
+
"<|sl|>": 50305,
|
| 82 |
+
"<|sn|>": 50324,
|
| 83 |
+
"<|so|>": 50326,
|
| 84 |
+
"<|sq|>": 50317,
|
| 85 |
+
"<|sr|>": 50303,
|
| 86 |
+
"<|startoflm|>": 50360,
|
| 87 |
+
"<|startofprev|>": 50361,
|
| 88 |
+
"<|startoftranscript|>": 50258,
|
| 89 |
+
"<|su|>": 50357,
|
| 90 |
+
"<|sv|>": 50273,
|
| 91 |
+
"<|sw|>": 50318,
|
| 92 |
+
"<|ta|>": 50287,
|
| 93 |
+
"<|te|>": 50299,
|
| 94 |
+
"<|tg|>": 50331,
|
| 95 |
+
"<|th|>": 50289,
|
| 96 |
+
"<|tk|>": 50341,
|
| 97 |
+
"<|tl|>": 50348,
|
| 98 |
+
"<|transcribe|>": 50359,
|
| 99 |
+
"<|translate|>": 50358,
|
| 100 |
+
"<|tr|>": 50268,
|
| 101 |
+
"<|tt|>": 50351,
|
| 102 |
+
"<|uk|>": 50280,
|
| 103 |
+
"<|ur|>": 50290,
|
| 104 |
+
"<|uz|>": 50337,
|
| 105 |
+
"<|vi|>": 50278,
|
| 106 |
+
"<|yi|>": 50335,
|
| 107 |
+
"<|yo|>": 50325,
|
| 108 |
+
"<|zh|>": 50260
|
| 109 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.58,
|
| 3 |
+
"eval_loss": 0.4923795163631439,
|
| 4 |
+
"eval_runtime": 1370.1044,
|
| 5 |
+
"eval_samples_per_second": 7.509,
|
| 6 |
+
"eval_steps_per_second": 0.118,
|
| 7 |
+
"eval_wer": 39.89950864725314,
|
| 8 |
+
"train_loss": 0.3303420036315918,
|
| 9 |
+
"train_runtime": 21571.4866,
|
| 10 |
+
"train_samples_per_second": 14.834,
|
| 11 |
+
"train_steps_per_second": 0.232
|
| 12 |
+
}
|
checkpoint-1000/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/whisper-small",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"WhisperForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"begin_suppress_tokens": [
|
| 10 |
+
220,
|
| 11 |
+
50257
|
| 12 |
+
],
|
| 13 |
+
"bos_token_id": 50257,
|
| 14 |
+
"d_model": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 12,
|
| 19 |
+
"decoder_start_token_id": 50258,
|
| 20 |
+
"dropout": 0.0,
|
| 21 |
+
"encoder_attention_heads": 12,
|
| 22 |
+
"encoder_ffn_dim": 3072,
|
| 23 |
+
"encoder_layerdrop": 0.0,
|
| 24 |
+
"encoder_layers": 12,
|
| 25 |
+
"eos_token_id": 50257,
|
| 26 |
+
"forced_decoder_ids": null,
|
| 27 |
+
"init_std": 0.02,
|
| 28 |
+
"is_encoder_decoder": true,
|
| 29 |
+
"max_length": 448,
|
| 30 |
+
"max_source_positions": 1500,
|
| 31 |
+
"max_target_positions": 448,
|
| 32 |
+
"model_type": "whisper",
|
| 33 |
+
"num_hidden_layers": 12,
|
| 34 |
+
"num_mel_bins": 80,
|
| 35 |
+
"pad_token_id": 50257,
|
| 36 |
+
"scale_embedding": false,
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.25.1",
|
| 39 |
+
"use_cache": false,
|
| 40 |
+
"vocab_size": 51865
|
| 41 |
+
}
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6e47e4300e4e3bd21b0c869c587bdfcea35e8bf36cebb1e53270fe67f5f88ff
|
| 3 |
+
size 1934161093
|
checkpoint-1000/preprocessor_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:effd83aa50562711333009da3acee71cb8d4cc97401631fc6051fb672aa01d45
|
| 3 |
+
size 967102601
|
checkpoint-1000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc55a315e5b7e256395762f330f90c34727ffc733709c8144bb9eb79a2f1f225
|
| 3 |
+
size 14519
|
checkpoint-1000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b943b140f7b35b4e08fe884358b1d5cd34372a8626a75ebdf6d8895e2b886e3
|
| 3 |
+
size 14519
|
checkpoint-1000/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a72f4ae227453cc8ce249882042f38fc236801402867a065febe98ec49fcc3eb
|
| 3 |
+
size 14519
|
checkpoint-1000/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8045f82b260f2c2d7af0513d9c0de4f50e24893816efc96d254dea13220280a
|
| 3 |
+
size 14583
|
checkpoint-1000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6dce1d2ae382ebe376f59073c1e3e94fa0133976fb67ca102a1b392494adc915
|
| 3 |
+
size 557
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f250987d7a2989ae5f1dfe2a3d3533de6b31bfde834549e82ed7a565b251efa
|
| 3 |
+
size 627
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,274 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 47.521028231962916,
|
| 3 |
+
"best_model_checkpoint": "./whisper-small-Persian/checkpoint-1000",
|
| 4 |
+
"epoch": 3.1150855365474337,
|
| 5 |
+
"global_step": 1000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.08,
|
| 12 |
+
"learning_rate": 4.4e-08,
|
| 13 |
+
"loss": 1.4232,
|
| 14 |
+
"step": 25
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.16,
|
| 18 |
+
"learning_rate": 9.4e-08,
|
| 19 |
+
"loss": 1.4027,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.23,
|
| 24 |
+
"learning_rate": 1.44e-07,
|
| 25 |
+
"loss": 1.3731,
|
| 26 |
+
"step": 75
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.31,
|
| 30 |
+
"learning_rate": 1.94e-07,
|
| 31 |
+
"loss": 1.2969,
|
| 32 |
+
"step": 100
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.39,
|
| 36 |
+
"learning_rate": 2.4399999999999996e-07,
|
| 37 |
+
"loss": 1.1964,
|
| 38 |
+
"step": 125
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.47,
|
| 42 |
+
"learning_rate": 2.9399999999999996e-07,
|
| 43 |
+
"loss": 1.0995,
|
| 44 |
+
"step": 150
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.54,
|
| 48 |
+
"learning_rate": 3.4399999999999996e-07,
|
| 49 |
+
"loss": 1.0068,
|
| 50 |
+
"step": 175
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.62,
|
| 54 |
+
"learning_rate": 3.94e-07,
|
| 55 |
+
"loss": 0.8949,
|
| 56 |
+
"step": 200
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.7,
|
| 60 |
+
"learning_rate": 4.44e-07,
|
| 61 |
+
"loss": 0.8521,
|
| 62 |
+
"step": 225
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.78,
|
| 66 |
+
"learning_rate": 4.94e-07,
|
| 67 |
+
"loss": 0.7694,
|
| 68 |
+
"step": 250
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.86,
|
| 72 |
+
"learning_rate": 5.44e-07,
|
| 73 |
+
"loss": 0.7196,
|
| 74 |
+
"step": 275
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.93,
|
| 78 |
+
"learning_rate": 5.939999999999999e-07,
|
| 79 |
+
"loss": 0.6902,
|
| 80 |
+
"step": 300
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.01,
|
| 84 |
+
"learning_rate": 6.44e-07,
|
| 85 |
+
"loss": 0.6748,
|
| 86 |
+
"step": 325
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.09,
|
| 90 |
+
"learning_rate": 6.939999999999999e-07,
|
| 91 |
+
"loss": 0.6247,
|
| 92 |
+
"step": 350
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.17,
|
| 96 |
+
"learning_rate": 7.44e-07,
|
| 97 |
+
"loss": 0.63,
|
| 98 |
+
"step": 375
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.25,
|
| 102 |
+
"learning_rate": 7.94e-07,
|
| 103 |
+
"loss": 0.5899,
|
| 104 |
+
"step": 400
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.32,
|
| 108 |
+
"learning_rate": 8.439999999999999e-07,
|
| 109 |
+
"loss": 0.5628,
|
| 110 |
+
"step": 425
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.4,
|
| 114 |
+
"learning_rate": 8.939999999999999e-07,
|
| 115 |
+
"loss": 0.5634,
|
| 116 |
+
"step": 450
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.48,
|
| 120 |
+
"learning_rate": 9.439999999999999e-07,
|
| 121 |
+
"loss": 0.5549,
|
| 122 |
+
"step": 475
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.56,
|
| 126 |
+
"learning_rate": 9.94e-07,
|
| 127 |
+
"loss": 0.5533,
|
| 128 |
+
"step": 500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.56,
|
| 132 |
+
"eval_loss": 0.7044046521186829,
|
| 133 |
+
"eval_runtime": 1265.1903,
|
| 134 |
+
"eval_samples_per_second": 8.132,
|
| 135 |
+
"eval_steps_per_second": 0.127,
|
| 136 |
+
"eval_wer": 54.54987091580379,
|
| 137 |
+
"step": 500
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.63,
|
| 141 |
+
"learning_rate": 9.95111111111111e-07,
|
| 142 |
+
"loss": 0.5329,
|
| 143 |
+
"step": 525
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.71,
|
| 147 |
+
"learning_rate": 9.895555555555554e-07,
|
| 148 |
+
"loss": 0.5116,
|
| 149 |
+
"step": 550
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.79,
|
| 153 |
+
"learning_rate": 9.84e-07,
|
| 154 |
+
"loss": 0.511,
|
| 155 |
+
"step": 575
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.87,
|
| 159 |
+
"learning_rate": 9.784444444444444e-07,
|
| 160 |
+
"loss": 0.4963,
|
| 161 |
+
"step": 600
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.95,
|
| 165 |
+
"learning_rate": 9.728888888888888e-07,
|
| 166 |
+
"loss": 0.5177,
|
| 167 |
+
"step": 625
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.02,
|
| 171 |
+
"learning_rate": 9.673333333333332e-07,
|
| 172 |
+
"loss": 0.4947,
|
| 173 |
+
"step": 650
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 2.1,
|
| 177 |
+
"learning_rate": 9.617777777777776e-07,
|
| 178 |
+
"loss": 0.4529,
|
| 179 |
+
"step": 675
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 2.18,
|
| 183 |
+
"learning_rate": 9.562222222222223e-07,
|
| 184 |
+
"loss": 0.4543,
|
| 185 |
+
"step": 700
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 2.26,
|
| 189 |
+
"learning_rate": 9.506666666666667e-07,
|
| 190 |
+
"loss": 0.4478,
|
| 191 |
+
"step": 725
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.34,
|
| 195 |
+
"learning_rate": 9.451111111111111e-07,
|
| 196 |
+
"loss": 0.4421,
|
| 197 |
+
"step": 750
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 2.41,
|
| 201 |
+
"learning_rate": 9.395555555555556e-07,
|
| 202 |
+
"loss": 0.4465,
|
| 203 |
+
"step": 775
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 2.49,
|
| 207 |
+
"learning_rate": 9.34e-07,
|
| 208 |
+
"loss": 0.4164,
|
| 209 |
+
"step": 800
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.57,
|
| 213 |
+
"learning_rate": 9.284444444444444e-07,
|
| 214 |
+
"loss": 0.4291,
|
| 215 |
+
"step": 825
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 2.65,
|
| 219 |
+
"learning_rate": 9.228888888888888e-07,
|
| 220 |
+
"loss": 0.4149,
|
| 221 |
+
"step": 850
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 2.72,
|
| 225 |
+
"learning_rate": 9.173333333333333e-07,
|
| 226 |
+
"loss": 0.4242,
|
| 227 |
+
"step": 875
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 2.8,
|
| 231 |
+
"learning_rate": 9.117777777777778e-07,
|
| 232 |
+
"loss": 0.4329,
|
| 233 |
+
"step": 900
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.88,
|
| 237 |
+
"learning_rate": 9.062222222222222e-07,
|
| 238 |
+
"loss": 0.4165,
|
| 239 |
+
"step": 925
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.96,
|
| 243 |
+
"learning_rate": 9.006666666666666e-07,
|
| 244 |
+
"loss": 0.4166,
|
| 245 |
+
"step": 950
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 3.04,
|
| 249 |
+
"learning_rate": 8.95111111111111e-07,
|
| 250 |
+
"loss": 0.409,
|
| 251 |
+
"step": 975
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 3.12,
|
| 255 |
+
"learning_rate": 8.895555555555555e-07,
|
| 256 |
+
"loss": 0.3951,
|
| 257 |
+
"step": 1000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.12,
|
| 261 |
+
"eval_loss": 0.5893104076385498,
|
| 262 |
+
"eval_runtime": 1326.5175,
|
| 263 |
+
"eval_samples_per_second": 7.756,
|
| 264 |
+
"eval_steps_per_second": 0.121,
|
| 265 |
+
"eval_wer": 47.521028231962916,
|
| 266 |
+
"step": 1000
|
| 267 |
+
}
|
| 268 |
+
],
|
| 269 |
+
"max_steps": 5000,
|
| 270 |
+
"num_train_epochs": 16,
|
| 271 |
+
"total_flos": 1.849716994470209e+19,
|
| 272 |
+
"trial_name": null,
|
| 273 |
+
"trial_params": null
|
| 274 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bda70737a84052aee98fe01ec95a00d27783f83ee9889ee9d6ffa0984826347e
|
| 3 |
+
size 3579
|
checkpoint-1500/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/whisper-small",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"WhisperForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"begin_suppress_tokens": [
|
| 10 |
+
220,
|
| 11 |
+
50257
|
| 12 |
+
],
|
| 13 |
+
"bos_token_id": 50257,
|
| 14 |
+
"d_model": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 12,
|
| 19 |
+
"decoder_start_token_id": 50258,
|
| 20 |
+
"dropout": 0.0,
|
| 21 |
+
"encoder_attention_heads": 12,
|
| 22 |
+
"encoder_ffn_dim": 3072,
|
| 23 |
+
"encoder_layerdrop": 0.0,
|
| 24 |
+
"encoder_layers": 12,
|
| 25 |
+
"eos_token_id": 50257,
|
| 26 |
+
"forced_decoder_ids": null,
|
| 27 |
+
"init_std": 0.02,
|
| 28 |
+
"is_encoder_decoder": true,
|
| 29 |
+
"max_length": 448,
|
| 30 |
+
"max_source_positions": 1500,
|
| 31 |
+
"max_target_positions": 448,
|
| 32 |
+
"model_type": "whisper",
|
| 33 |
+
"num_hidden_layers": 12,
|
| 34 |
+
"num_mel_bins": 80,
|
| 35 |
+
"pad_token_id": 50257,
|
| 36 |
+
"scale_embedding": false,
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.25.1",
|
| 39 |
+
"use_cache": false,
|
| 40 |
+
"vocab_size": 51865
|
| 41 |
+
}
|
checkpoint-1500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:847a61d4fd60ee9d944adfb2acfc7039ceb8a4ed184bb09e0dfc78c7bb78a9d0
|
| 3 |
+
size 1934161093
|
checkpoint-1500/preprocessor_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1500/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b773c4e1eb73396fab8cc0254287f1ac0298a07d6af06b9ba6b8ca0a99a6bc5
|
| 3 |
+
size 967102601
|
checkpoint-1500/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c241fb277d290b4db104171998a510d48dd6d96c6d37fdb5ea448dd0b2e6f723
|
| 3 |
+
size 14647
|
checkpoint-1500/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4db9742f4079692a73cad94c5651453235f2bbd8dc05620d82692f1f2189526a
|
| 3 |
+
size 14583
|
checkpoint-1500/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97940afe4e3f5dd75207e0c11d204341b59b0e48f3c15c64a35e306180ab69a0
|
| 3 |
+
size 14583
|
checkpoint-1500/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1143ff2c3189c690c8d13b34f0ede037dd914c70a4495c1c1e60700f6a62dbc5
|
| 3 |
+
size 14519
|
checkpoint-1500/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a1080490c5f23904ed7607a160b86a63d0fbf35f6ea0f13b4c1b02ec4a7646b
|
| 3 |
+
size 557
|
checkpoint-1500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c9b0e7f2e678434af32e69234b2356b6547a35c00d4d4f5a4d4e7b59be2066b
|
| 3 |
+
size 627
|
checkpoint-1500/trainer_state.json
ADDED
|
@@ -0,0 +1,403 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 44.64508786053355,
|
| 3 |
+
"best_model_checkpoint": "./whisper-small-Persian/checkpoint-1500",
|
| 4 |
+
"epoch": 4.671850699844479,
|
| 5 |
+
"global_step": 1500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.08,
|
| 12 |
+
"learning_rate": 4.4e-08,
|
| 13 |
+
"loss": 1.4232,
|
| 14 |
+
"step": 25
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.16,
|
| 18 |
+
"learning_rate": 9.4e-08,
|
| 19 |
+
"loss": 1.4027,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.23,
|
| 24 |
+
"learning_rate": 1.44e-07,
|
| 25 |
+
"loss": 1.3731,
|
| 26 |
+
"step": 75
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.31,
|
| 30 |
+
"learning_rate": 1.94e-07,
|
| 31 |
+
"loss": 1.2969,
|
| 32 |
+
"step": 100
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.39,
|
| 36 |
+
"learning_rate": 2.4399999999999996e-07,
|
| 37 |
+
"loss": 1.1964,
|
| 38 |
+
"step": 125
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.47,
|
| 42 |
+
"learning_rate": 2.9399999999999996e-07,
|
| 43 |
+
"loss": 1.0995,
|
| 44 |
+
"step": 150
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.54,
|
| 48 |
+
"learning_rate": 3.4399999999999996e-07,
|
| 49 |
+
"loss": 1.0068,
|
| 50 |
+
"step": 175
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.62,
|
| 54 |
+
"learning_rate": 3.94e-07,
|
| 55 |
+
"loss": 0.8949,
|
| 56 |
+
"step": 200
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.7,
|
| 60 |
+
"learning_rate": 4.44e-07,
|
| 61 |
+
"loss": 0.8521,
|
| 62 |
+
"step": 225
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.78,
|
| 66 |
+
"learning_rate": 4.94e-07,
|
| 67 |
+
"loss": 0.7694,
|
| 68 |
+
"step": 250
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.86,
|
| 72 |
+
"learning_rate": 5.44e-07,
|
| 73 |
+
"loss": 0.7196,
|
| 74 |
+
"step": 275
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.93,
|
| 78 |
+
"learning_rate": 5.939999999999999e-07,
|
| 79 |
+
"loss": 0.6902,
|
| 80 |
+
"step": 300
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.01,
|
| 84 |
+
"learning_rate": 6.44e-07,
|
| 85 |
+
"loss": 0.6748,
|
| 86 |
+
"step": 325
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.09,
|
| 90 |
+
"learning_rate": 6.939999999999999e-07,
|
| 91 |
+
"loss": 0.6247,
|
| 92 |
+
"step": 350
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.17,
|
| 96 |
+
"learning_rate": 7.44e-07,
|
| 97 |
+
"loss": 0.63,
|
| 98 |
+
"step": 375
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.25,
|
| 102 |
+
"learning_rate": 7.94e-07,
|
| 103 |
+
"loss": 0.5899,
|
| 104 |
+
"step": 400
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.32,
|
| 108 |
+
"learning_rate": 8.439999999999999e-07,
|
| 109 |
+
"loss": 0.5628,
|
| 110 |
+
"step": 425
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.4,
|
| 114 |
+
"learning_rate": 8.939999999999999e-07,
|
| 115 |
+
"loss": 0.5634,
|
| 116 |
+
"step": 450
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.48,
|
| 120 |
+
"learning_rate": 9.439999999999999e-07,
|
| 121 |
+
"loss": 0.5549,
|
| 122 |
+
"step": 475
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.56,
|
| 126 |
+
"learning_rate": 9.94e-07,
|
| 127 |
+
"loss": 0.5533,
|
| 128 |
+
"step": 500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.56,
|
| 132 |
+
"eval_loss": 0.7044046521186829,
|
| 133 |
+
"eval_runtime": 1265.1903,
|
| 134 |
+
"eval_samples_per_second": 8.132,
|
| 135 |
+
"eval_steps_per_second": 0.127,
|
| 136 |
+
"eval_wer": 54.54987091580379,
|
| 137 |
+
"step": 500
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.63,
|
| 141 |
+
"learning_rate": 9.95111111111111e-07,
|
| 142 |
+
"loss": 0.5329,
|
| 143 |
+
"step": 525
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.71,
|
| 147 |
+
"learning_rate": 9.895555555555554e-07,
|
| 148 |
+
"loss": 0.5116,
|
| 149 |
+
"step": 550
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.79,
|
| 153 |
+
"learning_rate": 9.84e-07,
|
| 154 |
+
"loss": 0.511,
|
| 155 |
+
"step": 575
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.87,
|
| 159 |
+
"learning_rate": 9.784444444444444e-07,
|
| 160 |
+
"loss": 0.4963,
|
| 161 |
+
"step": 600
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.95,
|
| 165 |
+
"learning_rate": 9.728888888888888e-07,
|
| 166 |
+
"loss": 0.5177,
|
| 167 |
+
"step": 625
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.02,
|
| 171 |
+
"learning_rate": 9.673333333333332e-07,
|
| 172 |
+
"loss": 0.4947,
|
| 173 |
+
"step": 650
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 2.1,
|
| 177 |
+
"learning_rate": 9.617777777777776e-07,
|
| 178 |
+
"loss": 0.4529,
|
| 179 |
+
"step": 675
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 2.18,
|
| 183 |
+
"learning_rate": 9.562222222222223e-07,
|
| 184 |
+
"loss": 0.4543,
|
| 185 |
+
"step": 700
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 2.26,
|
| 189 |
+
"learning_rate": 9.506666666666667e-07,
|
| 190 |
+
"loss": 0.4478,
|
| 191 |
+
"step": 725
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.34,
|
| 195 |
+
"learning_rate": 9.451111111111111e-07,
|
| 196 |
+
"loss": 0.4421,
|
| 197 |
+
"step": 750
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 2.41,
|
| 201 |
+
"learning_rate": 9.395555555555556e-07,
|
| 202 |
+
"loss": 0.4465,
|
| 203 |
+
"step": 775
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 2.49,
|
| 207 |
+
"learning_rate": 9.34e-07,
|
| 208 |
+
"loss": 0.4164,
|
| 209 |
+
"step": 800
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.57,
|
| 213 |
+
"learning_rate": 9.284444444444444e-07,
|
| 214 |
+
"loss": 0.4291,
|
| 215 |
+
"step": 825
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 2.65,
|
| 219 |
+
"learning_rate": 9.228888888888888e-07,
|
| 220 |
+
"loss": 0.4149,
|
| 221 |
+
"step": 850
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 2.72,
|
| 225 |
+
"learning_rate": 9.173333333333333e-07,
|
| 226 |
+
"loss": 0.4242,
|
| 227 |
+
"step": 875
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 2.8,
|
| 231 |
+
"learning_rate": 9.117777777777778e-07,
|
| 232 |
+
"loss": 0.4329,
|
| 233 |
+
"step": 900
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.88,
|
| 237 |
+
"learning_rate": 9.062222222222222e-07,
|
| 238 |
+
"loss": 0.4165,
|
| 239 |
+
"step": 925
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.96,
|
| 243 |
+
"learning_rate": 9.006666666666666e-07,
|
| 244 |
+
"loss": 0.4166,
|
| 245 |
+
"step": 950
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 3.04,
|
| 249 |
+
"learning_rate": 8.95111111111111e-07,
|
| 250 |
+
"loss": 0.409,
|
| 251 |
+
"step": 975
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 3.12,
|
| 255 |
+
"learning_rate": 8.895555555555555e-07,
|
| 256 |
+
"loss": 0.3951,
|
| 257 |
+
"step": 1000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.12,
|
| 261 |
+
"eval_loss": 0.5893104076385498,
|
| 262 |
+
"eval_runtime": 1326.5175,
|
| 263 |
+
"eval_samples_per_second": 7.756,
|
| 264 |
+
"eval_steps_per_second": 0.121,
|
| 265 |
+
"eval_wer": 47.521028231962916,
|
| 266 |
+
"step": 1000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 3.19,
|
| 270 |
+
"learning_rate": 8.839999999999999e-07,
|
| 271 |
+
"loss": 0.3808,
|
| 272 |
+
"step": 1025
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.27,
|
| 276 |
+
"learning_rate": 8.784444444444444e-07,
|
| 277 |
+
"loss": 0.3786,
|
| 278 |
+
"step": 1050
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 3.35,
|
| 282 |
+
"learning_rate": 8.728888888888889e-07,
|
| 283 |
+
"loss": 0.3811,
|
| 284 |
+
"step": 1075
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.43,
|
| 288 |
+
"learning_rate": 8.673333333333332e-07,
|
| 289 |
+
"loss": 0.3644,
|
| 290 |
+
"step": 1100
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 3.5,
|
| 294 |
+
"learning_rate": 8.617777777777777e-07,
|
| 295 |
+
"loss": 0.3737,
|
| 296 |
+
"step": 1125
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.58,
|
| 300 |
+
"learning_rate": 8.562222222222222e-07,
|
| 301 |
+
"loss": 0.3698,
|
| 302 |
+
"step": 1150
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.66,
|
| 306 |
+
"learning_rate": 8.506666666666667e-07,
|
| 307 |
+
"loss": 0.3601,
|
| 308 |
+
"step": 1175
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 3.74,
|
| 312 |
+
"learning_rate": 8.451111111111111e-07,
|
| 313 |
+
"loss": 0.3675,
|
| 314 |
+
"step": 1200
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 3.81,
|
| 318 |
+
"learning_rate": 8.395555555555556e-07,
|
| 319 |
+
"loss": 0.3588,
|
| 320 |
+
"step": 1225
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 3.89,
|
| 324 |
+
"learning_rate": 8.34e-07,
|
| 325 |
+
"loss": 0.3541,
|
| 326 |
+
"step": 1250
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 3.97,
|
| 330 |
+
"learning_rate": 8.284444444444444e-07,
|
| 331 |
+
"loss": 0.3537,
|
| 332 |
+
"step": 1275
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 4.05,
|
| 336 |
+
"learning_rate": 8.228888888888889e-07,
|
| 337 |
+
"loss": 0.3666,
|
| 338 |
+
"step": 1300
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.13,
|
| 342 |
+
"learning_rate": 8.173333333333333e-07,
|
| 343 |
+
"loss": 0.3242,
|
| 344 |
+
"step": 1325
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 4.21,
|
| 348 |
+
"learning_rate": 8.117777777777778e-07,
|
| 349 |
+
"loss": 0.3212,
|
| 350 |
+
"step": 1350
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 4.28,
|
| 354 |
+
"learning_rate": 8.062222222222221e-07,
|
| 355 |
+
"loss": 0.3374,
|
| 356 |
+
"step": 1375
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 4.36,
|
| 360 |
+
"learning_rate": 8.006666666666666e-07,
|
| 361 |
+
"loss": 0.3259,
|
| 362 |
+
"step": 1400
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 4.44,
|
| 366 |
+
"learning_rate": 7.95111111111111e-07,
|
| 367 |
+
"loss": 0.3361,
|
| 368 |
+
"step": 1425
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 4.52,
|
| 372 |
+
"learning_rate": 7.895555555555555e-07,
|
| 373 |
+
"loss": 0.3355,
|
| 374 |
+
"step": 1450
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.59,
|
| 378 |
+
"learning_rate": 7.84e-07,
|
| 379 |
+
"loss": 0.3254,
|
| 380 |
+
"step": 1475
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 4.67,
|
| 384 |
+
"learning_rate": 7.784444444444444e-07,
|
| 385 |
+
"loss": 0.3296,
|
| 386 |
+
"step": 1500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 4.67,
|
| 390 |
+
"eval_loss": 0.5428555011749268,
|
| 391 |
+
"eval_runtime": 1299.6224,
|
| 392 |
+
"eval_samples_per_second": 7.916,
|
| 393 |
+
"eval_steps_per_second": 0.124,
|
| 394 |
+
"eval_wer": 44.64508786053355,
|
| 395 |
+
"step": 1500
|
| 396 |
+
}
|
| 397 |
+
],
|
| 398 |
+
"max_steps": 5000,
|
| 399 |
+
"num_train_epochs": 16,
|
| 400 |
+
"total_flos": 2.774113755233203e+19,
|
| 401 |
+
"trial_name": null,
|
| 402 |
+
"trial_params": null
|
| 403 |
+
}
|
checkpoint-1500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bda70737a84052aee98fe01ec95a00d27783f83ee9889ee9d6ffa0984826347e
|
| 3 |
+
size 3579
|
checkpoint-2000/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/whisper-small",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"WhisperForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"begin_suppress_tokens": [
|
| 10 |
+
220,
|
| 11 |
+
50257
|
| 12 |
+
],
|
| 13 |
+
"bos_token_id": 50257,
|
| 14 |
+
"d_model": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 12,
|
| 19 |
+
"decoder_start_token_id": 50258,
|
| 20 |
+
"dropout": 0.0,
|
| 21 |
+
"encoder_attention_heads": 12,
|
| 22 |
+
"encoder_ffn_dim": 3072,
|
| 23 |
+
"encoder_layerdrop": 0.0,
|
| 24 |
+
"encoder_layers": 12,
|
| 25 |
+
"eos_token_id": 50257,
|
| 26 |
+
"forced_decoder_ids": null,
|
| 27 |
+
"init_std": 0.02,
|
| 28 |
+
"is_encoder_decoder": true,
|
| 29 |
+
"max_length": 448,
|
| 30 |
+
"max_source_positions": 1500,
|
| 31 |
+
"max_target_positions": 448,
|
| 32 |
+
"model_type": "whisper",
|
| 33 |
+
"num_hidden_layers": 12,
|
| 34 |
+
"num_mel_bins": 80,
|
| 35 |
+
"pad_token_id": 50257,
|
| 36 |
+
"scale_embedding": false,
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.25.1",
|
| 39 |
+
"use_cache": false,
|
| 40 |
+
"vocab_size": 51865
|
| 41 |
+
}
|
checkpoint-2000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55615f6bde936bb1e58c190a081c5e2667f693ae46397930b43e29e8d9523962
|
| 3 |
+
size 1934161093
|
checkpoint-2000/preprocessor_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0c7544da5f411a2cce995c121ea9d8fe855d38a67dd9376d4ff9bdc152e3f95
|
| 3 |
+
size 967102601
|
checkpoint-2000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46b9c72c7eed1fd4c4f798e93fa1ede8521ac20b90fe4cf8875169df39ebe280
|
| 3 |
+
size 14583
|
checkpoint-2000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8080778388d210607de5b81682e40562c65c649583ce16519fb3b8c62009fc41
|
| 3 |
+
size 14583
|
checkpoint-2000/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:073cd8a681f64f906aee66bc4e51e3745829cf0d7a5e40767cb64fd2ad8dcfb2
|
| 3 |
+
size 14519
|
checkpoint-2000/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b8de99171336a8003c52583af34523efe031e9e49849784cd4024882cdb3efb
|
| 3 |
+
size 14583
|
checkpoint-2000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:172321c3064ae4a11267185f654f9636260463be1a922f305c5370008f78b7f2
|
| 3 |
+
size 557
|
checkpoint-2000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07a414e9d8627cd29b61655f515b44908fdbf1b87394717d76f2608595276d9f
|
| 3 |
+
size 627
|
checkpoint-2000/trainer_state.json
ADDED
|
@@ -0,0 +1,532 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 42.664408849901456,
|
| 3 |
+
"best_model_checkpoint": "./whisper-small-Persian/checkpoint-2000",
|
| 4 |
+
"epoch": 6.230171073094867,
|
| 5 |
+
"global_step": 2000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.08,
|
| 12 |
+
"learning_rate": 4.4e-08,
|
| 13 |
+
"loss": 1.4232,
|
| 14 |
+
"step": 25
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.16,
|
| 18 |
+
"learning_rate": 9.4e-08,
|
| 19 |
+
"loss": 1.4027,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.23,
|
| 24 |
+
"learning_rate": 1.44e-07,
|
| 25 |
+
"loss": 1.3731,
|
| 26 |
+
"step": 75
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.31,
|
| 30 |
+
"learning_rate": 1.94e-07,
|
| 31 |
+
"loss": 1.2969,
|
| 32 |
+
"step": 100
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.39,
|
| 36 |
+
"learning_rate": 2.4399999999999996e-07,
|
| 37 |
+
"loss": 1.1964,
|
| 38 |
+
"step": 125
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.47,
|
| 42 |
+
"learning_rate": 2.9399999999999996e-07,
|
| 43 |
+
"loss": 1.0995,
|
| 44 |
+
"step": 150
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.54,
|
| 48 |
+
"learning_rate": 3.4399999999999996e-07,
|
| 49 |
+
"loss": 1.0068,
|
| 50 |
+
"step": 175
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.62,
|
| 54 |
+
"learning_rate": 3.94e-07,
|
| 55 |
+
"loss": 0.8949,
|
| 56 |
+
"step": 200
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.7,
|
| 60 |
+
"learning_rate": 4.44e-07,
|
| 61 |
+
"loss": 0.8521,
|
| 62 |
+
"step": 225
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.78,
|
| 66 |
+
"learning_rate": 4.94e-07,
|
| 67 |
+
"loss": 0.7694,
|
| 68 |
+
"step": 250
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.86,
|
| 72 |
+
"learning_rate": 5.44e-07,
|
| 73 |
+
"loss": 0.7196,
|
| 74 |
+
"step": 275
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.93,
|
| 78 |
+
"learning_rate": 5.939999999999999e-07,
|
| 79 |
+
"loss": 0.6902,
|
| 80 |
+
"step": 300
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.01,
|
| 84 |
+
"learning_rate": 6.44e-07,
|
| 85 |
+
"loss": 0.6748,
|
| 86 |
+
"step": 325
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.09,
|
| 90 |
+
"learning_rate": 6.939999999999999e-07,
|
| 91 |
+
"loss": 0.6247,
|
| 92 |
+
"step": 350
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.17,
|
| 96 |
+
"learning_rate": 7.44e-07,
|
| 97 |
+
"loss": 0.63,
|
| 98 |
+
"step": 375
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.25,
|
| 102 |
+
"learning_rate": 7.94e-07,
|
| 103 |
+
"loss": 0.5899,
|
| 104 |
+
"step": 400
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.32,
|
| 108 |
+
"learning_rate": 8.439999999999999e-07,
|
| 109 |
+
"loss": 0.5628,
|
| 110 |
+
"step": 425
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.4,
|
| 114 |
+
"learning_rate": 8.939999999999999e-07,
|
| 115 |
+
"loss": 0.5634,
|
| 116 |
+
"step": 450
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.48,
|
| 120 |
+
"learning_rate": 9.439999999999999e-07,
|
| 121 |
+
"loss": 0.5549,
|
| 122 |
+
"step": 475
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.56,
|
| 126 |
+
"learning_rate": 9.94e-07,
|
| 127 |
+
"loss": 0.5533,
|
| 128 |
+
"step": 500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.56,
|
| 132 |
+
"eval_loss": 0.7044046521186829,
|
| 133 |
+
"eval_runtime": 1265.1903,
|
| 134 |
+
"eval_samples_per_second": 8.132,
|
| 135 |
+
"eval_steps_per_second": 0.127,
|
| 136 |
+
"eval_wer": 54.54987091580379,
|
| 137 |
+
"step": 500
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.63,
|
| 141 |
+
"learning_rate": 9.95111111111111e-07,
|
| 142 |
+
"loss": 0.5329,
|
| 143 |
+
"step": 525
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.71,
|
| 147 |
+
"learning_rate": 9.895555555555554e-07,
|
| 148 |
+
"loss": 0.5116,
|
| 149 |
+
"step": 550
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.79,
|
| 153 |
+
"learning_rate": 9.84e-07,
|
| 154 |
+
"loss": 0.511,
|
| 155 |
+
"step": 575
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.87,
|
| 159 |
+
"learning_rate": 9.784444444444444e-07,
|
| 160 |
+
"loss": 0.4963,
|
| 161 |
+
"step": 600
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.95,
|
| 165 |
+
"learning_rate": 9.728888888888888e-07,
|
| 166 |
+
"loss": 0.5177,
|
| 167 |
+
"step": 625
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.02,
|
| 171 |
+
"learning_rate": 9.673333333333332e-07,
|
| 172 |
+
"loss": 0.4947,
|
| 173 |
+
"step": 650
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 2.1,
|
| 177 |
+
"learning_rate": 9.617777777777776e-07,
|
| 178 |
+
"loss": 0.4529,
|
| 179 |
+
"step": 675
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 2.18,
|
| 183 |
+
"learning_rate": 9.562222222222223e-07,
|
| 184 |
+
"loss": 0.4543,
|
| 185 |
+
"step": 700
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 2.26,
|
| 189 |
+
"learning_rate": 9.506666666666667e-07,
|
| 190 |
+
"loss": 0.4478,
|
| 191 |
+
"step": 725
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.34,
|
| 195 |
+
"learning_rate": 9.451111111111111e-07,
|
| 196 |
+
"loss": 0.4421,
|
| 197 |
+
"step": 750
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 2.41,
|
| 201 |
+
"learning_rate": 9.395555555555556e-07,
|
| 202 |
+
"loss": 0.4465,
|
| 203 |
+
"step": 775
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 2.49,
|
| 207 |
+
"learning_rate": 9.34e-07,
|
| 208 |
+
"loss": 0.4164,
|
| 209 |
+
"step": 800
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.57,
|
| 213 |
+
"learning_rate": 9.284444444444444e-07,
|
| 214 |
+
"loss": 0.4291,
|
| 215 |
+
"step": 825
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 2.65,
|
| 219 |
+
"learning_rate": 9.228888888888888e-07,
|
| 220 |
+
"loss": 0.4149,
|
| 221 |
+
"step": 850
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 2.72,
|
| 225 |
+
"learning_rate": 9.173333333333333e-07,
|
| 226 |
+
"loss": 0.4242,
|
| 227 |
+
"step": 875
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 2.8,
|
| 231 |
+
"learning_rate": 9.117777777777778e-07,
|
| 232 |
+
"loss": 0.4329,
|
| 233 |
+
"step": 900
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.88,
|
| 237 |
+
"learning_rate": 9.062222222222222e-07,
|
| 238 |
+
"loss": 0.4165,
|
| 239 |
+
"step": 925
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.96,
|
| 243 |
+
"learning_rate": 9.006666666666666e-07,
|
| 244 |
+
"loss": 0.4166,
|
| 245 |
+
"step": 950
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 3.04,
|
| 249 |
+
"learning_rate": 8.95111111111111e-07,
|
| 250 |
+
"loss": 0.409,
|
| 251 |
+
"step": 975
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 3.12,
|
| 255 |
+
"learning_rate": 8.895555555555555e-07,
|
| 256 |
+
"loss": 0.3951,
|
| 257 |
+
"step": 1000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.12,
|
| 261 |
+
"eval_loss": 0.5893104076385498,
|
| 262 |
+
"eval_runtime": 1326.5175,
|
| 263 |
+
"eval_samples_per_second": 7.756,
|
| 264 |
+
"eval_steps_per_second": 0.121,
|
| 265 |
+
"eval_wer": 47.521028231962916,
|
| 266 |
+
"step": 1000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 3.19,
|
| 270 |
+
"learning_rate": 8.839999999999999e-07,
|
| 271 |
+
"loss": 0.3808,
|
| 272 |
+
"step": 1025
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.27,
|
| 276 |
+
"learning_rate": 8.784444444444444e-07,
|
| 277 |
+
"loss": 0.3786,
|
| 278 |
+
"step": 1050
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 3.35,
|
| 282 |
+
"learning_rate": 8.728888888888889e-07,
|
| 283 |
+
"loss": 0.3811,
|
| 284 |
+
"step": 1075
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.43,
|
| 288 |
+
"learning_rate": 8.673333333333332e-07,
|
| 289 |
+
"loss": 0.3644,
|
| 290 |
+
"step": 1100
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 3.5,
|
| 294 |
+
"learning_rate": 8.617777777777777e-07,
|
| 295 |
+
"loss": 0.3737,
|
| 296 |
+
"step": 1125
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.58,
|
| 300 |
+
"learning_rate": 8.562222222222222e-07,
|
| 301 |
+
"loss": 0.3698,
|
| 302 |
+
"step": 1150
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.66,
|
| 306 |
+
"learning_rate": 8.506666666666667e-07,
|
| 307 |
+
"loss": 0.3601,
|
| 308 |
+
"step": 1175
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 3.74,
|
| 312 |
+
"learning_rate": 8.451111111111111e-07,
|
| 313 |
+
"loss": 0.3675,
|
| 314 |
+
"step": 1200
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 3.81,
|
| 318 |
+
"learning_rate": 8.395555555555556e-07,
|
| 319 |
+
"loss": 0.3588,
|
| 320 |
+
"step": 1225
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 3.89,
|
| 324 |
+
"learning_rate": 8.34e-07,
|
| 325 |
+
"loss": 0.3541,
|
| 326 |
+
"step": 1250
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 3.97,
|
| 330 |
+
"learning_rate": 8.284444444444444e-07,
|
| 331 |
+
"loss": 0.3537,
|
| 332 |
+
"step": 1275
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 4.05,
|
| 336 |
+
"learning_rate": 8.228888888888889e-07,
|
| 337 |
+
"loss": 0.3666,
|
| 338 |
+
"step": 1300
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.13,
|
| 342 |
+
"learning_rate": 8.173333333333333e-07,
|
| 343 |
+
"loss": 0.3242,
|
| 344 |
+
"step": 1325
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 4.21,
|
| 348 |
+
"learning_rate": 8.117777777777778e-07,
|
| 349 |
+
"loss": 0.3212,
|
| 350 |
+
"step": 1350
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 4.28,
|
| 354 |
+
"learning_rate": 8.062222222222221e-07,
|
| 355 |
+
"loss": 0.3374,
|
| 356 |
+
"step": 1375
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 4.36,
|
| 360 |
+
"learning_rate": 8.006666666666666e-07,
|
| 361 |
+
"loss": 0.3259,
|
| 362 |
+
"step": 1400
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 4.44,
|
| 366 |
+
"learning_rate": 7.95111111111111e-07,
|
| 367 |
+
"loss": 0.3361,
|
| 368 |
+
"step": 1425
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 4.52,
|
| 372 |
+
"learning_rate": 7.895555555555555e-07,
|
| 373 |
+
"loss": 0.3355,
|
| 374 |
+
"step": 1450
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.59,
|
| 378 |
+
"learning_rate": 7.84e-07,
|
| 379 |
+
"loss": 0.3254,
|
| 380 |
+
"step": 1475
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 4.67,
|
| 384 |
+
"learning_rate": 7.784444444444444e-07,
|
| 385 |
+
"loss": 0.3296,
|
| 386 |
+
"step": 1500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 4.67,
|
| 390 |
+
"eval_loss": 0.5428555011749268,
|
| 391 |
+
"eval_runtime": 1299.6224,
|
| 392 |
+
"eval_samples_per_second": 7.916,
|
| 393 |
+
"eval_steps_per_second": 0.124,
|
| 394 |
+
"eval_wer": 44.64508786053355,
|
| 395 |
+
"step": 1500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 4.75,
|
| 399 |
+
"learning_rate": 7.728888888888888e-07,
|
| 400 |
+
"loss": 0.3229,
|
| 401 |
+
"step": 1525
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 4.83,
|
| 405 |
+
"learning_rate": 7.673333333333332e-07,
|
| 406 |
+
"loss": 0.3372,
|
| 407 |
+
"step": 1550
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 4.91,
|
| 411 |
+
"learning_rate": 7.617777777777778e-07,
|
| 412 |
+
"loss": 0.3297,
|
| 413 |
+
"step": 1575
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 4.98,
|
| 417 |
+
"learning_rate": 7.562222222222222e-07,
|
| 418 |
+
"loss": 0.3239,
|
| 419 |
+
"step": 1600
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 5.06,
|
| 423 |
+
"learning_rate": 7.506666666666667e-07,
|
| 424 |
+
"loss": 0.3113,
|
| 425 |
+
"step": 1625
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 5.14,
|
| 429 |
+
"learning_rate": 7.451111111111111e-07,
|
| 430 |
+
"loss": 0.3142,
|
| 431 |
+
"step": 1650
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 5.22,
|
| 435 |
+
"learning_rate": 7.395555555555555e-07,
|
| 436 |
+
"loss": 0.303,
|
| 437 |
+
"step": 1675
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 5.3,
|
| 441 |
+
"learning_rate": 7.34e-07,
|
| 442 |
+
"loss": 0.2973,
|
| 443 |
+
"step": 1700
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 5.37,
|
| 447 |
+
"learning_rate": 7.284444444444444e-07,
|
| 448 |
+
"loss": 0.2998,
|
| 449 |
+
"step": 1725
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 5.45,
|
| 453 |
+
"learning_rate": 7.228888888888889e-07,
|
| 454 |
+
"loss": 0.2962,
|
| 455 |
+
"step": 1750
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 5.53,
|
| 459 |
+
"learning_rate": 7.173333333333333e-07,
|
| 460 |
+
"loss": 0.3007,
|
| 461 |
+
"step": 1775
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 5.61,
|
| 465 |
+
"learning_rate": 7.117777777777777e-07,
|
| 466 |
+
"loss": 0.2906,
|
| 467 |
+
"step": 1800
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 5.68,
|
| 471 |
+
"learning_rate": 7.062222222222222e-07,
|
| 472 |
+
"loss": 0.295,
|
| 473 |
+
"step": 1825
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 5.76,
|
| 477 |
+
"learning_rate": 7.006666666666666e-07,
|
| 478 |
+
"loss": 0.3083,
|
| 479 |
+
"step": 1850
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 5.84,
|
| 483 |
+
"learning_rate": 6.951111111111111e-07,
|
| 484 |
+
"loss": 0.2869,
|
| 485 |
+
"step": 1875
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 5.92,
|
| 489 |
+
"learning_rate": 6.895555555555555e-07,
|
| 490 |
+
"loss": 0.2936,
|
| 491 |
+
"step": 1900
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 6.0,
|
| 495 |
+
"learning_rate": 6.84e-07,
|
| 496 |
+
"loss": 0.2982,
|
| 497 |
+
"step": 1925
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 6.07,
|
| 501 |
+
"learning_rate": 6.784444444444443e-07,
|
| 502 |
+
"loss": 0.2885,
|
| 503 |
+
"step": 1950
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 6.15,
|
| 507 |
+
"learning_rate": 6.728888888888888e-07,
|
| 508 |
+
"loss": 0.2719,
|
| 509 |
+
"step": 1975
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 6.23,
|
| 513 |
+
"learning_rate": 6.673333333333334e-07,
|
| 514 |
+
"loss": 0.2662,
|
| 515 |
+
"step": 2000
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 6.23,
|
| 519 |
+
"eval_loss": 0.5223153829574585,
|
| 520 |
+
"eval_runtime": 1347.3336,
|
| 521 |
+
"eval_samples_per_second": 7.636,
|
| 522 |
+
"eval_steps_per_second": 0.119,
|
| 523 |
+
"eval_wer": 42.664408849901456,
|
| 524 |
+
"step": 2000
|
| 525 |
+
}
|
| 526 |
+
],
|
| 527 |
+
"max_steps": 5000,
|
| 528 |
+
"num_train_epochs": 16,
|
| 529 |
+
"total_flos": 3.699433988940418e+19,
|
| 530 |
+
"trial_name": null,
|
| 531 |
+
"trial_params": null
|
| 532 |
+
}
|
checkpoint-2000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bda70737a84052aee98fe01ec95a00d27783f83ee9889ee9d6ffa0984826347e
|
| 3 |
+
size 3579
|
checkpoint-2500/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/whisper-small",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"WhisperForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"begin_suppress_tokens": [
|
| 10 |
+
220,
|
| 11 |
+
50257
|
| 12 |
+
],
|
| 13 |
+
"bos_token_id": 50257,
|
| 14 |
+
"d_model": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 12,
|
| 19 |
+
"decoder_start_token_id": 50258,
|
| 20 |
+
"dropout": 0.0,
|
| 21 |
+
"encoder_attention_heads": 12,
|
| 22 |
+
"encoder_ffn_dim": 3072,
|
| 23 |
+
"encoder_layerdrop": 0.0,
|
| 24 |
+
"encoder_layers": 12,
|
| 25 |
+
"eos_token_id": 50257,
|
| 26 |
+
"forced_decoder_ids": null,
|
| 27 |
+
"init_std": 0.02,
|
| 28 |
+
"is_encoder_decoder": true,
|
| 29 |
+
"max_length": 448,
|
| 30 |
+
"max_source_positions": 1500,
|
| 31 |
+
"max_target_positions": 448,
|
| 32 |
+
"model_type": "whisper",
|
| 33 |
+
"num_hidden_layers": 12,
|
| 34 |
+
"num_mel_bins": 80,
|
| 35 |
+
"pad_token_id": 50257,
|
| 36 |
+
"scale_embedding": false,
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.25.1",
|
| 39 |
+
"use_cache": false,
|
| 40 |
+
"vocab_size": 51865
|
| 41 |
+
}
|
checkpoint-2500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b1bac388e9ccb5c85426c16252364dc258a48aebb84a068f2b63513a42ffb4a
|
| 3 |
+
size 1934161093
|
checkpoint-2500/preprocessor_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2500/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63e637219ffc3358d4ca0ea19cad9ea7f996d874a2c7b6a52a1e706fa59302e3
|
| 3 |
+
size 967102601
|
checkpoint-2500/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32d582dbdb4c1e2b98c61b22baf74e479d8d8e8a93b2151bd6293afe2786d2f8
|
| 3 |
+
size 14583
|
checkpoint-2500/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e07f727622efb4a24b1cfc5b9f0ab5af9a6aadd797759821cf175f71466f919b
|
| 3 |
+
size 14647
|
checkpoint-2500/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:105882858c82a984658b5d4f76b92652efc3df674f31929b33a1fae0cf114417
|
| 3 |
+
size 14583
|
checkpoint-2500/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7037146f98830f9a234ab8852ec5401c0cc6283a54ab1a65f2a9bd9059d87a43
|
| 3 |
+
size 14583
|
checkpoint-2500/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:edf730497bda1dd7d810be24acd7ff911a283f9988fb87926ddea4a8506d9615
|
| 3 |
+
size 557
|
checkpoint-2500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a77720265737918b69cda81377c78110d51cb0982308e66f42db7acc9269820
|
| 3 |
+
size 627
|
checkpoint-2500/trainer_state.json
ADDED
|
@@ -0,0 +1,661 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 41.53041112622491,
|
| 3 |
+
"best_model_checkpoint": "./whisper-small-Persian/checkpoint-2500",
|
| 4 |
+
"epoch": 7.786936236391913,
|
| 5 |
+
"global_step": 2500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.08,
|
| 12 |
+
"learning_rate": 4.4e-08,
|
| 13 |
+
"loss": 1.4232,
|
| 14 |
+
"step": 25
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.16,
|
| 18 |
+
"learning_rate": 9.4e-08,
|
| 19 |
+
"loss": 1.4027,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.23,
|
| 24 |
+
"learning_rate": 1.44e-07,
|
| 25 |
+
"loss": 1.3731,
|
| 26 |
+
"step": 75
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.31,
|
| 30 |
+
"learning_rate": 1.94e-07,
|
| 31 |
+
"loss": 1.2969,
|
| 32 |
+
"step": 100
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.39,
|
| 36 |
+
"learning_rate": 2.4399999999999996e-07,
|
| 37 |
+
"loss": 1.1964,
|
| 38 |
+
"step": 125
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.47,
|
| 42 |
+
"learning_rate": 2.9399999999999996e-07,
|
| 43 |
+
"loss": 1.0995,
|
| 44 |
+
"step": 150
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.54,
|
| 48 |
+
"learning_rate": 3.4399999999999996e-07,
|
| 49 |
+
"loss": 1.0068,
|
| 50 |
+
"step": 175
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.62,
|
| 54 |
+
"learning_rate": 3.94e-07,
|
| 55 |
+
"loss": 0.8949,
|
| 56 |
+
"step": 200
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.7,
|
| 60 |
+
"learning_rate": 4.44e-07,
|
| 61 |
+
"loss": 0.8521,
|
| 62 |
+
"step": 225
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.78,
|
| 66 |
+
"learning_rate": 4.94e-07,
|
| 67 |
+
"loss": 0.7694,
|
| 68 |
+
"step": 250
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.86,
|
| 72 |
+
"learning_rate": 5.44e-07,
|
| 73 |
+
"loss": 0.7196,
|
| 74 |
+
"step": 275
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.93,
|
| 78 |
+
"learning_rate": 5.939999999999999e-07,
|
| 79 |
+
"loss": 0.6902,
|
| 80 |
+
"step": 300
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.01,
|
| 84 |
+
"learning_rate": 6.44e-07,
|
| 85 |
+
"loss": 0.6748,
|
| 86 |
+
"step": 325
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.09,
|
| 90 |
+
"learning_rate": 6.939999999999999e-07,
|
| 91 |
+
"loss": 0.6247,
|
| 92 |
+
"step": 350
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.17,
|
| 96 |
+
"learning_rate": 7.44e-07,
|
| 97 |
+
"loss": 0.63,
|
| 98 |
+
"step": 375
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.25,
|
| 102 |
+
"learning_rate": 7.94e-07,
|
| 103 |
+
"loss": 0.5899,
|
| 104 |
+
"step": 400
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.32,
|
| 108 |
+
"learning_rate": 8.439999999999999e-07,
|
| 109 |
+
"loss": 0.5628,
|
| 110 |
+
"step": 425
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.4,
|
| 114 |
+
"learning_rate": 8.939999999999999e-07,
|
| 115 |
+
"loss": 0.5634,
|
| 116 |
+
"step": 450
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.48,
|
| 120 |
+
"learning_rate": 9.439999999999999e-07,
|
| 121 |
+
"loss": 0.5549,
|
| 122 |
+
"step": 475
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.56,
|
| 126 |
+
"learning_rate": 9.94e-07,
|
| 127 |
+
"loss": 0.5533,
|
| 128 |
+
"step": 500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.56,
|
| 132 |
+
"eval_loss": 0.7044046521186829,
|
| 133 |
+
"eval_runtime": 1265.1903,
|
| 134 |
+
"eval_samples_per_second": 8.132,
|
| 135 |
+
"eval_steps_per_second": 0.127,
|
| 136 |
+
"eval_wer": 54.54987091580379,
|
| 137 |
+
"step": 500
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.63,
|
| 141 |
+
"learning_rate": 9.95111111111111e-07,
|
| 142 |
+
"loss": 0.5329,
|
| 143 |
+
"step": 525
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.71,
|
| 147 |
+
"learning_rate": 9.895555555555554e-07,
|
| 148 |
+
"loss": 0.5116,
|
| 149 |
+
"step": 550
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.79,
|
| 153 |
+
"learning_rate": 9.84e-07,
|
| 154 |
+
"loss": 0.511,
|
| 155 |
+
"step": 575
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.87,
|
| 159 |
+
"learning_rate": 9.784444444444444e-07,
|
| 160 |
+
"loss": 0.4963,
|
| 161 |
+
"step": 600
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.95,
|
| 165 |
+
"learning_rate": 9.728888888888888e-07,
|
| 166 |
+
"loss": 0.5177,
|
| 167 |
+
"step": 625
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.02,
|
| 171 |
+
"learning_rate": 9.673333333333332e-07,
|
| 172 |
+
"loss": 0.4947,
|
| 173 |
+
"step": 650
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 2.1,
|
| 177 |
+
"learning_rate": 9.617777777777776e-07,
|
| 178 |
+
"loss": 0.4529,
|
| 179 |
+
"step": 675
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 2.18,
|
| 183 |
+
"learning_rate": 9.562222222222223e-07,
|
| 184 |
+
"loss": 0.4543,
|
| 185 |
+
"step": 700
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 2.26,
|
| 189 |
+
"learning_rate": 9.506666666666667e-07,
|
| 190 |
+
"loss": 0.4478,
|
| 191 |
+
"step": 725
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.34,
|
| 195 |
+
"learning_rate": 9.451111111111111e-07,
|
| 196 |
+
"loss": 0.4421,
|
| 197 |
+
"step": 750
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 2.41,
|
| 201 |
+
"learning_rate": 9.395555555555556e-07,
|
| 202 |
+
"loss": 0.4465,
|
| 203 |
+
"step": 775
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 2.49,
|
| 207 |
+
"learning_rate": 9.34e-07,
|
| 208 |
+
"loss": 0.4164,
|
| 209 |
+
"step": 800
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.57,
|
| 213 |
+
"learning_rate": 9.284444444444444e-07,
|
| 214 |
+
"loss": 0.4291,
|
| 215 |
+
"step": 825
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 2.65,
|
| 219 |
+
"learning_rate": 9.228888888888888e-07,
|
| 220 |
+
"loss": 0.4149,
|
| 221 |
+
"step": 850
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 2.72,
|
| 225 |
+
"learning_rate": 9.173333333333333e-07,
|
| 226 |
+
"loss": 0.4242,
|
| 227 |
+
"step": 875
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 2.8,
|
| 231 |
+
"learning_rate": 9.117777777777778e-07,
|
| 232 |
+
"loss": 0.4329,
|
| 233 |
+
"step": 900
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.88,
|
| 237 |
+
"learning_rate": 9.062222222222222e-07,
|
| 238 |
+
"loss": 0.4165,
|
| 239 |
+
"step": 925
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.96,
|
| 243 |
+
"learning_rate": 9.006666666666666e-07,
|
| 244 |
+
"loss": 0.4166,
|
| 245 |
+
"step": 950
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 3.04,
|
| 249 |
+
"learning_rate": 8.95111111111111e-07,
|
| 250 |
+
"loss": 0.409,
|
| 251 |
+
"step": 975
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 3.12,
|
| 255 |
+
"learning_rate": 8.895555555555555e-07,
|
| 256 |
+
"loss": 0.3951,
|
| 257 |
+
"step": 1000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.12,
|
| 261 |
+
"eval_loss": 0.5893104076385498,
|
| 262 |
+
"eval_runtime": 1326.5175,
|
| 263 |
+
"eval_samples_per_second": 7.756,
|
| 264 |
+
"eval_steps_per_second": 0.121,
|
| 265 |
+
"eval_wer": 47.521028231962916,
|
| 266 |
+
"step": 1000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 3.19,
|
| 270 |
+
"learning_rate": 8.839999999999999e-07,
|
| 271 |
+
"loss": 0.3808,
|
| 272 |
+
"step": 1025
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.27,
|
| 276 |
+
"learning_rate": 8.784444444444444e-07,
|
| 277 |
+
"loss": 0.3786,
|
| 278 |
+
"step": 1050
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 3.35,
|
| 282 |
+
"learning_rate": 8.728888888888889e-07,
|
| 283 |
+
"loss": 0.3811,
|
| 284 |
+
"step": 1075
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.43,
|
| 288 |
+
"learning_rate": 8.673333333333332e-07,
|
| 289 |
+
"loss": 0.3644,
|
| 290 |
+
"step": 1100
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 3.5,
|
| 294 |
+
"learning_rate": 8.617777777777777e-07,
|
| 295 |
+
"loss": 0.3737,
|
| 296 |
+
"step": 1125
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.58,
|
| 300 |
+
"learning_rate": 8.562222222222222e-07,
|
| 301 |
+
"loss": 0.3698,
|
| 302 |
+
"step": 1150
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.66,
|
| 306 |
+
"learning_rate": 8.506666666666667e-07,
|
| 307 |
+
"loss": 0.3601,
|
| 308 |
+
"step": 1175
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 3.74,
|
| 312 |
+
"learning_rate": 8.451111111111111e-07,
|
| 313 |
+
"loss": 0.3675,
|
| 314 |
+
"step": 1200
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 3.81,
|
| 318 |
+
"learning_rate": 8.395555555555556e-07,
|
| 319 |
+
"loss": 0.3588,
|
| 320 |
+
"step": 1225
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 3.89,
|
| 324 |
+
"learning_rate": 8.34e-07,
|
| 325 |
+
"loss": 0.3541,
|
| 326 |
+
"step": 1250
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 3.97,
|
| 330 |
+
"learning_rate": 8.284444444444444e-07,
|
| 331 |
+
"loss": 0.3537,
|
| 332 |
+
"step": 1275
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 4.05,
|
| 336 |
+
"learning_rate": 8.228888888888889e-07,
|
| 337 |
+
"loss": 0.3666,
|
| 338 |
+
"step": 1300
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.13,
|
| 342 |
+
"learning_rate": 8.173333333333333e-07,
|
| 343 |
+
"loss": 0.3242,
|
| 344 |
+
"step": 1325
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 4.21,
|
| 348 |
+
"learning_rate": 8.117777777777778e-07,
|
| 349 |
+
"loss": 0.3212,
|
| 350 |
+
"step": 1350
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 4.28,
|
| 354 |
+
"learning_rate": 8.062222222222221e-07,
|
| 355 |
+
"loss": 0.3374,
|
| 356 |
+
"step": 1375
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 4.36,
|
| 360 |
+
"learning_rate": 8.006666666666666e-07,
|
| 361 |
+
"loss": 0.3259,
|
| 362 |
+
"step": 1400
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 4.44,
|
| 366 |
+
"learning_rate": 7.95111111111111e-07,
|
| 367 |
+
"loss": 0.3361,
|
| 368 |
+
"step": 1425
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 4.52,
|
| 372 |
+
"learning_rate": 7.895555555555555e-07,
|
| 373 |
+
"loss": 0.3355,
|
| 374 |
+
"step": 1450
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.59,
|
| 378 |
+
"learning_rate": 7.84e-07,
|
| 379 |
+
"loss": 0.3254,
|
| 380 |
+
"step": 1475
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 4.67,
|
| 384 |
+
"learning_rate": 7.784444444444444e-07,
|
| 385 |
+
"loss": 0.3296,
|
| 386 |
+
"step": 1500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 4.67,
|
| 390 |
+
"eval_loss": 0.5428555011749268,
|
| 391 |
+
"eval_runtime": 1299.6224,
|
| 392 |
+
"eval_samples_per_second": 7.916,
|
| 393 |
+
"eval_steps_per_second": 0.124,
|
| 394 |
+
"eval_wer": 44.64508786053355,
|
| 395 |
+
"step": 1500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 4.75,
|
| 399 |
+
"learning_rate": 7.728888888888888e-07,
|
| 400 |
+
"loss": 0.3229,
|
| 401 |
+
"step": 1525
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 4.83,
|
| 405 |
+
"learning_rate": 7.673333333333332e-07,
|
| 406 |
+
"loss": 0.3372,
|
| 407 |
+
"step": 1550
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 4.91,
|
| 411 |
+
"learning_rate": 7.617777777777778e-07,
|
| 412 |
+
"loss": 0.3297,
|
| 413 |
+
"step": 1575
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 4.98,
|
| 417 |
+
"learning_rate": 7.562222222222222e-07,
|
| 418 |
+
"loss": 0.3239,
|
| 419 |
+
"step": 1600
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 5.06,
|
| 423 |
+
"learning_rate": 7.506666666666667e-07,
|
| 424 |
+
"loss": 0.3113,
|
| 425 |
+
"step": 1625
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 5.14,
|
| 429 |
+
"learning_rate": 7.451111111111111e-07,
|
| 430 |
+
"loss": 0.3142,
|
| 431 |
+
"step": 1650
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 5.22,
|
| 435 |
+
"learning_rate": 7.395555555555555e-07,
|
| 436 |
+
"loss": 0.303,
|
| 437 |
+
"step": 1675
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 5.3,
|
| 441 |
+
"learning_rate": 7.34e-07,
|
| 442 |
+
"loss": 0.2973,
|
| 443 |
+
"step": 1700
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 5.37,
|
| 447 |
+
"learning_rate": 7.284444444444444e-07,
|
| 448 |
+
"loss": 0.2998,
|
| 449 |
+
"step": 1725
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 5.45,
|
| 453 |
+
"learning_rate": 7.228888888888889e-07,
|
| 454 |
+
"loss": 0.2962,
|
| 455 |
+
"step": 1750
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 5.53,
|
| 459 |
+
"learning_rate": 7.173333333333333e-07,
|
| 460 |
+
"loss": 0.3007,
|
| 461 |
+
"step": 1775
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 5.61,
|
| 465 |
+
"learning_rate": 7.117777777777777e-07,
|
| 466 |
+
"loss": 0.2906,
|
| 467 |
+
"step": 1800
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 5.68,
|
| 471 |
+
"learning_rate": 7.062222222222222e-07,
|
| 472 |
+
"loss": 0.295,
|
| 473 |
+
"step": 1825
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 5.76,
|
| 477 |
+
"learning_rate": 7.006666666666666e-07,
|
| 478 |
+
"loss": 0.3083,
|
| 479 |
+
"step": 1850
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 5.84,
|
| 483 |
+
"learning_rate": 6.951111111111111e-07,
|
| 484 |
+
"loss": 0.2869,
|
| 485 |
+
"step": 1875
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 5.92,
|
| 489 |
+
"learning_rate": 6.895555555555555e-07,
|
| 490 |
+
"loss": 0.2936,
|
| 491 |
+
"step": 1900
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 6.0,
|
| 495 |
+
"learning_rate": 6.84e-07,
|
| 496 |
+
"loss": 0.2982,
|
| 497 |
+
"step": 1925
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 6.07,
|
| 501 |
+
"learning_rate": 6.784444444444443e-07,
|
| 502 |
+
"loss": 0.2885,
|
| 503 |
+
"step": 1950
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 6.15,
|
| 507 |
+
"learning_rate": 6.728888888888888e-07,
|
| 508 |
+
"loss": 0.2719,
|
| 509 |
+
"step": 1975
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 6.23,
|
| 513 |
+
"learning_rate": 6.673333333333334e-07,
|
| 514 |
+
"loss": 0.2662,
|
| 515 |
+
"step": 2000
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 6.23,
|
| 519 |
+
"eval_loss": 0.5223153829574585,
|
| 520 |
+
"eval_runtime": 1347.3336,
|
| 521 |
+
"eval_samples_per_second": 7.636,
|
| 522 |
+
"eval_steps_per_second": 0.119,
|
| 523 |
+
"eval_wer": 42.664408849901456,
|
| 524 |
+
"step": 2000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 6.31,
|
| 528 |
+
"learning_rate": 6.617777777777778e-07,
|
| 529 |
+
"loss": 0.2739,
|
| 530 |
+
"step": 2025
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 6.39,
|
| 534 |
+
"learning_rate": 6.562222222222223e-07,
|
| 535 |
+
"loss": 0.2694,
|
| 536 |
+
"step": 2050
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 6.46,
|
| 540 |
+
"learning_rate": 6.506666666666666e-07,
|
| 541 |
+
"loss": 0.2678,
|
| 542 |
+
"step": 2075
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 6.54,
|
| 546 |
+
"learning_rate": 6.451111111111111e-07,
|
| 547 |
+
"loss": 0.2716,
|
| 548 |
+
"step": 2100
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 6.62,
|
| 552 |
+
"learning_rate": 6.395555555555555e-07,
|
| 553 |
+
"loss": 0.27,
|
| 554 |
+
"step": 2125
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 6.7,
|
| 558 |
+
"learning_rate": 6.34e-07,
|
| 559 |
+
"loss": 0.2715,
|
| 560 |
+
"step": 2150
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 6.77,
|
| 564 |
+
"learning_rate": 6.284444444444445e-07,
|
| 565 |
+
"loss": 0.2705,
|
| 566 |
+
"step": 2175
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 6.85,
|
| 570 |
+
"learning_rate": 6.228888888888889e-07,
|
| 571 |
+
"loss": 0.2771,
|
| 572 |
+
"step": 2200
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 6.93,
|
| 576 |
+
"learning_rate": 6.173333333333333e-07,
|
| 577 |
+
"loss": 0.2814,
|
| 578 |
+
"step": 2225
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 7.01,
|
| 582 |
+
"learning_rate": 6.117777777777777e-07,
|
| 583 |
+
"loss": 0.302,
|
| 584 |
+
"step": 2250
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 7.09,
|
| 588 |
+
"learning_rate": 6.062222222222222e-07,
|
| 589 |
+
"loss": 0.2619,
|
| 590 |
+
"step": 2275
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 7.16,
|
| 594 |
+
"learning_rate": 6.006666666666666e-07,
|
| 595 |
+
"loss": 0.2561,
|
| 596 |
+
"step": 2300
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 7.24,
|
| 600 |
+
"learning_rate": 5.951111111111111e-07,
|
| 601 |
+
"loss": 0.2559,
|
| 602 |
+
"step": 2325
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 7.32,
|
| 606 |
+
"learning_rate": 5.895555555555555e-07,
|
| 607 |
+
"loss": 0.2524,
|
| 608 |
+
"step": 2350
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 7.4,
|
| 612 |
+
"learning_rate": 5.839999999999999e-07,
|
| 613 |
+
"loss": 0.2583,
|
| 614 |
+
"step": 2375
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 7.48,
|
| 618 |
+
"learning_rate": 5.784444444444444e-07,
|
| 619 |
+
"loss": 0.2434,
|
| 620 |
+
"step": 2400
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 7.55,
|
| 624 |
+
"learning_rate": 5.728888888888888e-07,
|
| 625 |
+
"loss": 0.2546,
|
| 626 |
+
"step": 2425
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 7.63,
|
| 630 |
+
"learning_rate": 5.673333333333334e-07,
|
| 631 |
+
"loss": 0.2492,
|
| 632 |
+
"step": 2450
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 7.71,
|
| 636 |
+
"learning_rate": 5.617777777777778e-07,
|
| 637 |
+
"loss": 0.2544,
|
| 638 |
+
"step": 2475
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 7.79,
|
| 642 |
+
"learning_rate": 5.562222222222222e-07,
|
| 643 |
+
"loss": 0.2535,
|
| 644 |
+
"step": 2500
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 7.79,
|
| 648 |
+
"eval_loss": 0.5044606924057007,
|
| 649 |
+
"eval_runtime": 1321.646,
|
| 650 |
+
"eval_samples_per_second": 7.784,
|
| 651 |
+
"eval_steps_per_second": 0.122,
|
| 652 |
+
"eval_wer": 41.53041112622491,
|
| 653 |
+
"step": 2500
|
| 654 |
+
}
|
| 655 |
+
],
|
| 656 |
+
"max_steps": 5000,
|
| 657 |
+
"num_train_epochs": 16,
|
| 658 |
+
"total_flos": 4.623830749703412e+19,
|
| 659 |
+
"trial_name": null,
|
| 660 |
+
"trial_params": null
|
| 661 |
+
}
|