End of training
Browse files- README.md +12 -9
- all_results.json +12 -0
- eval_results.json +8 -0
- runs/Jan17_15-43-43_knight/events.out.tfevents.1705504331.knight.131338.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +372 -0
README.md
CHANGED
|
@@ -1,39 +1,42 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: openai/whisper-base
|
| 4 |
tags:
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
-
- common_voice_16_0
|
| 8 |
metrics:
|
| 9 |
- wer
|
| 10 |
model-index:
|
| 11 |
-
- name:
|
| 12 |
results:
|
| 13 |
- task:
|
| 14 |
name: Automatic Speech Recognition
|
| 15 |
type: automatic-speech-recognition
|
| 16 |
dataset:
|
| 17 |
-
name: common_voice_16_0
|
| 18 |
-
type: common_voice_16_0
|
| 19 |
config: ml
|
| 20 |
split: test
|
| 21 |
args: ml
|
| 22 |
metrics:
|
| 23 |
- name: Wer
|
| 24 |
type: wer
|
| 25 |
-
value:
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
|
| 31 |
-
#
|
| 32 |
|
| 33 |
-
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the common_voice_16_0 dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Wer:
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- ml
|
| 4 |
license: apache-2.0
|
| 5 |
base_model: openai/whisper-base
|
| 6 |
tags:
|
| 7 |
+
- whisper-event
|
| 8 |
- generated_from_trainer
|
| 9 |
datasets:
|
| 10 |
+
- mozilla-foundation/common_voice_16_0
|
| 11 |
metrics:
|
| 12 |
- wer
|
| 13 |
model-index:
|
| 14 |
+
- name: Breeze DSW Malayalam - base
|
| 15 |
results:
|
| 16 |
- task:
|
| 17 |
name: Automatic Speech Recognition
|
| 18 |
type: automatic-speech-recognition
|
| 19 |
dataset:
|
| 20 |
+
name: mozilla-foundation/common_voice_16_0 ml
|
| 21 |
+
type: mozilla-foundation/common_voice_16_0
|
| 22 |
config: ml
|
| 23 |
split: test
|
| 24 |
args: ml
|
| 25 |
metrics:
|
| 26 |
- name: Wer
|
| 27 |
type: wer
|
| 28 |
+
value: 42.72474513438369
|
| 29 |
---
|
| 30 |
|
| 31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 32 |
should probably proofread and complete it, then remove this comment. -->
|
| 33 |
|
| 34 |
+
# Breeze DSW Malayalam - base
|
| 35 |
|
| 36 |
+
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the mozilla-foundation/common_voice_16_0 ml dataset.
|
| 37 |
It achieves the following results on the evaluation set:
|
| 38 |
+
- Loss: 0.6260
|
| 39 |
+
- Wer: 42.7247
|
| 40 |
|
| 41 |
## Model description
|
| 42 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.02,
|
| 3 |
+
"eval_loss": 0.6259765625,
|
| 4 |
+
"eval_runtime": 1588.6597,
|
| 5 |
+
"eval_samples_per_second": 0.417,
|
| 6 |
+
"eval_steps_per_second": 0.026,
|
| 7 |
+
"eval_wer": 42.72474513438369,
|
| 8 |
+
"train_loss": 0.0,
|
| 9 |
+
"train_runtime": 41.2826,
|
| 10 |
+
"train_samples_per_second": 1550.288,
|
| 11 |
+
"train_steps_per_second": 48.447
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.02,
|
| 3 |
+
"eval_loss": 0.6259765625,
|
| 4 |
+
"eval_runtime": 1588.6597,
|
| 5 |
+
"eval_samples_per_second": 0.417,
|
| 6 |
+
"eval_steps_per_second": 0.026,
|
| 7 |
+
"eval_wer": 42.72474513438369
|
| 8 |
+
}
|
runs/Jan17_15-43-43_knight/events.out.tfevents.1705504331.knight.131338.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5302c52e69f47081b302ccf0e4f7502eda808d15a227720c5ae0444068af08cf
|
| 3 |
+
size 406
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.02,
|
| 3 |
+
"train_loss": 0.0,
|
| 4 |
+
"train_runtime": 41.2826,
|
| 5 |
+
"train_samples_per_second": 1550.288,
|
| 6 |
+
"train_steps_per_second": 48.447
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,372 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 42.72474513438369,
|
| 3 |
+
"best_model_checkpoint": "/cosmos/home/sp-operator/ai/training/models/huggingface/scripts/../breeze-dsw-base-ml/checkpoint-800",
|
| 4 |
+
"epoch": 29.02,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 1200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 5.0453611334320685e-06,
|
| 14 |
+
"loss": 1.6886,
|
| 15 |
+
"step": 25
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.0,
|
| 19 |
+
"learning_rate": 6.229195710491767e-06,
|
| 20 |
+
"loss": 1.2987,
|
| 21 |
+
"step": 50
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 1.02,
|
| 25 |
+
"learning_rate": 6.903829450223392e-06,
|
| 26 |
+
"loss": 1.0959,
|
| 27 |
+
"step": 75
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.01,
|
| 31 |
+
"learning_rate": 7.361221988663844e-06,
|
| 32 |
+
"loss": 0.8535,
|
| 33 |
+
"step": 100
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 3.0,
|
| 37 |
+
"learning_rate": 7.730207550743121e-06,
|
| 38 |
+
"loss": 0.6174,
|
| 39 |
+
"step": 125
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 3.02,
|
| 43 |
+
"learning_rate": 8.03016458599496e-06,
|
| 44 |
+
"loss": 0.4687,
|
| 45 |
+
"step": 150
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 4.01,
|
| 49 |
+
"learning_rate": 8.282894746203441e-06,
|
| 50 |
+
"loss": 0.3515,
|
| 51 |
+
"step": 175
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 4.02,
|
| 55 |
+
"learning_rate": 8.501266121799902e-06,
|
| 56 |
+
"loss": 0.3151,
|
| 57 |
+
"step": 200
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.02,
|
| 61 |
+
"eval_loss": 0.45166015625,
|
| 62 |
+
"eval_runtime": 1605.5021,
|
| 63 |
+
"eval_samples_per_second": 0.413,
|
| 64 |
+
"eval_steps_per_second": 0.026,
|
| 65 |
+
"eval_wer": 54.51343836886006,
|
| 66 |
+
"step": 200
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 5.01,
|
| 70 |
+
"learning_rate": 8.693512601774437e-06,
|
| 71 |
+
"loss": 0.2339,
|
| 72 |
+
"step": 225
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 6.0,
|
| 76 |
+
"learning_rate": 8.865222471593567e-06,
|
| 77 |
+
"loss": 0.1966,
|
| 78 |
+
"step": 250
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 6.02,
|
| 82 |
+
"learning_rate": 9.020362953730323e-06,
|
| 83 |
+
"loss": 0.1695,
|
| 84 |
+
"step": 275
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 7.01,
|
| 88 |
+
"learning_rate": 9.161852281961698e-06,
|
| 89 |
+
"loss": 0.134,
|
| 90 |
+
"step": 300
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 8.0,
|
| 94 |
+
"learning_rate": 9.29189975311636e-06,
|
| 95 |
+
"loss": 0.1164,
|
| 96 |
+
"step": 325
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 8.02,
|
| 100 |
+
"learning_rate": 9.412218256259678e-06,
|
| 101 |
+
"loss": 0.0968,
|
| 102 |
+
"step": 350
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 9.01,
|
| 106 |
+
"learning_rate": 9.524162683365145e-06,
|
| 107 |
+
"loss": 0.0761,
|
| 108 |
+
"step": 375
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 9.02,
|
| 112 |
+
"learning_rate": 9.62882322733502e-06,
|
| 113 |
+
"loss": 0.0703,
|
| 114 |
+
"step": 400
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 9.02,
|
| 118 |
+
"eval_loss": 0.4560546875,
|
| 119 |
+
"eval_runtime": 1612.3575,
|
| 120 |
+
"eval_samples_per_second": 0.411,
|
| 121 |
+
"eval_steps_per_second": 0.026,
|
| 122 |
+
"eval_wer": 46.72845227062095,
|
| 123 |
+
"step": 400
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 10.01,
|
| 127 |
+
"learning_rate": 9.727090137141168e-06,
|
| 128 |
+
"loss": 0.0476,
|
| 129 |
+
"step": 425
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 11.01,
|
| 133 |
+
"learning_rate": 9.819699807237934e-06,
|
| 134 |
+
"loss": 0.0431,
|
| 135 |
+
"step": 450
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 11.02,
|
| 139 |
+
"learning_rate": 9.907268307310855e-06,
|
| 140 |
+
"loss": 0.0363,
|
| 141 |
+
"step": 475
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 12.01,
|
| 145 |
+
"learning_rate": 9.990316248055788e-06,
|
| 146 |
+
"loss": 0.0278,
|
| 147 |
+
"step": 500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 13.0,
|
| 151 |
+
"learning_rate": 9.86e-06,
|
| 152 |
+
"loss": 0.0231,
|
| 153 |
+
"step": 525
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 13.02,
|
| 157 |
+
"learning_rate": 9.693333333333334e-06,
|
| 158 |
+
"loss": 0.0222,
|
| 159 |
+
"step": 550
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 14.01,
|
| 163 |
+
"learning_rate": 9.526666666666668e-06,
|
| 164 |
+
"loss": 0.0161,
|
| 165 |
+
"step": 575
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 14.02,
|
| 169 |
+
"learning_rate": 9.360000000000002e-06,
|
| 170 |
+
"loss": 0.0144,
|
| 171 |
+
"step": 600
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 14.02,
|
| 175 |
+
"eval_loss": 0.5625,
|
| 176 |
+
"eval_runtime": 1602.9774,
|
| 177 |
+
"eval_samples_per_second": 0.414,
|
| 178 |
+
"eval_steps_per_second": 0.026,
|
| 179 |
+
"eval_wer": 43.76274328081557,
|
| 180 |
+
"step": 600
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 15.01,
|
| 184 |
+
"learning_rate": 9.193333333333334e-06,
|
| 185 |
+
"loss": 0.0108,
|
| 186 |
+
"step": 625
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 16.0,
|
| 190 |
+
"learning_rate": 9.026666666666666e-06,
|
| 191 |
+
"loss": 0.01,
|
| 192 |
+
"step": 650
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 16.02,
|
| 196 |
+
"learning_rate": 8.860000000000002e-06,
|
| 197 |
+
"loss": 0.0097,
|
| 198 |
+
"step": 675
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 17.01,
|
| 202 |
+
"learning_rate": 8.693333333333334e-06,
|
| 203 |
+
"loss": 0.0064,
|
| 204 |
+
"step": 700
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 18.0,
|
| 208 |
+
"learning_rate": 8.526666666666667e-06,
|
| 209 |
+
"loss": 0.0087,
|
| 210 |
+
"step": 725
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 18.02,
|
| 214 |
+
"learning_rate": 8.36e-06,
|
| 215 |
+
"loss": 0.008,
|
| 216 |
+
"step": 750
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 19.01,
|
| 220 |
+
"learning_rate": 8.193333333333335e-06,
|
| 221 |
+
"loss": 0.0073,
|
| 222 |
+
"step": 775
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 19.02,
|
| 226 |
+
"learning_rate": 8.026666666666667e-06,
|
| 227 |
+
"loss": 0.006,
|
| 228 |
+
"step": 800
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 19.02,
|
| 232 |
+
"eval_loss": 0.6259765625,
|
| 233 |
+
"eval_runtime": 1596.5675,
|
| 234 |
+
"eval_samples_per_second": 0.415,
|
| 235 |
+
"eval_steps_per_second": 0.026,
|
| 236 |
+
"eval_wer": 42.72474513438369,
|
| 237 |
+
"step": 800
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 20.01,
|
| 241 |
+
"learning_rate": 7.860000000000001e-06,
|
| 242 |
+
"loss": 0.0041,
|
| 243 |
+
"step": 825
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 21.0,
|
| 247 |
+
"learning_rate": 7.693333333333333e-06,
|
| 248 |
+
"loss": 0.0043,
|
| 249 |
+
"step": 850
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 21.02,
|
| 253 |
+
"learning_rate": 7.526666666666668e-06,
|
| 254 |
+
"loss": 0.0043,
|
| 255 |
+
"step": 875
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 22.01,
|
| 259 |
+
"learning_rate": 7.360000000000001e-06,
|
| 260 |
+
"loss": 0.0034,
|
| 261 |
+
"step": 900
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 23.0,
|
| 265 |
+
"learning_rate": 7.1933333333333345e-06,
|
| 266 |
+
"loss": 0.0036,
|
| 267 |
+
"step": 925
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 23.02,
|
| 271 |
+
"learning_rate": 7.0266666666666674e-06,
|
| 272 |
+
"loss": 0.0033,
|
| 273 |
+
"step": 950
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 24.01,
|
| 277 |
+
"learning_rate": 6.860000000000001e-06,
|
| 278 |
+
"loss": 0.0024,
|
| 279 |
+
"step": 975
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 24.02,
|
| 283 |
+
"learning_rate": 6.693333333333334e-06,
|
| 284 |
+
"loss": 0.0024,
|
| 285 |
+
"step": 1000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 24.02,
|
| 289 |
+
"eval_loss": 0.69384765625,
|
| 290 |
+
"eval_runtime": 1597.407,
|
| 291 |
+
"eval_samples_per_second": 0.415,
|
| 292 |
+
"eval_steps_per_second": 0.026,
|
| 293 |
+
"eval_wer": 43.03058387395737,
|
| 294 |
+
"step": 1000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 25.01,
|
| 298 |
+
"learning_rate": 6.526666666666666e-06,
|
| 299 |
+
"loss": 0.003,
|
| 300 |
+
"step": 1025
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 26.0,
|
| 304 |
+
"learning_rate": 6.360000000000001e-06,
|
| 305 |
+
"loss": 0.0026,
|
| 306 |
+
"step": 1050
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 26.02,
|
| 310 |
+
"learning_rate": 6.193333333333333e-06,
|
| 311 |
+
"loss": 0.0022,
|
| 312 |
+
"step": 1075
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 27.01,
|
| 316 |
+
"learning_rate": 6.026666666666668e-06,
|
| 317 |
+
"loss": 0.0017,
|
| 318 |
+
"step": 1100
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 28.0,
|
| 322 |
+
"learning_rate": 5.86e-06,
|
| 323 |
+
"loss": 0.0013,
|
| 324 |
+
"step": 1125
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 28.02,
|
| 328 |
+
"learning_rate": 5.6933333333333344e-06,
|
| 329 |
+
"loss": 0.0011,
|
| 330 |
+
"step": 1150
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 29.01,
|
| 334 |
+
"learning_rate": 5.5266666666666666e-06,
|
| 335 |
+
"loss": 0.0015,
|
| 336 |
+
"step": 1175
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 29.02,
|
| 340 |
+
"learning_rate": 5.36e-06,
|
| 341 |
+
"loss": 0.0012,
|
| 342 |
+
"step": 1200
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 29.02,
|
| 346 |
+
"eval_loss": 0.7353515625,
|
| 347 |
+
"eval_runtime": 1601.8604,
|
| 348 |
+
"eval_samples_per_second": 0.414,
|
| 349 |
+
"eval_steps_per_second": 0.026,
|
| 350 |
+
"eval_wer": 44.21686746987952,
|
| 351 |
+
"step": 1200
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 29.02,
|
| 355 |
+
"step": 1200,
|
| 356 |
+
"total_flos": 2.443924644411998e+18,
|
| 357 |
+
"train_loss": 0.0,
|
| 358 |
+
"train_runtime": 41.2826,
|
| 359 |
+
"train_samples_per_second": 1550.288,
|
| 360 |
+
"train_steps_per_second": 48.447
|
| 361 |
+
}
|
| 362 |
+
],
|
| 363 |
+
"logging_steps": 25,
|
| 364 |
+
"max_steps": 2000,
|
| 365 |
+
"num_input_tokens_seen": 0,
|
| 366 |
+
"num_train_epochs": 9223372036854775807,
|
| 367 |
+
"save_steps": 200,
|
| 368 |
+
"total_flos": 2.443924644411998e+18,
|
| 369 |
+
"train_batch_size": 32,
|
| 370 |
+
"trial_name": null,
|
| 371 |
+
"trial_params": null
|
| 372 |
+
}
|