End of training
Browse files- README.md +6 -3
- adapter.bem.safetensors +3 -0
- all_results.json +15 -0
- eval_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +675 -0
README.md
CHANGED
|
@@ -3,6 +3,9 @@ library_name: transformers
|
|
| 3 |
license: cc-by-nc-4.0
|
| 4 |
base_model: facebook/mms-1b-all
|
| 5 |
tags:
|
|
|
|
|
|
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
metrics:
|
| 8 |
- wer
|
|
@@ -16,10 +19,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# mms-1b-all-bem-genbed-m-model
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
-
- Wer: 0.
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 3 |
license: cc-by-nc-4.0
|
| 4 |
base_model: facebook/mms-1b-all
|
| 5 |
tags:
|
| 6 |
+
- automatic-speech-recognition
|
| 7 |
+
- genbed
|
| 8 |
+
- mms
|
| 9 |
- generated_from_trainer
|
| 10 |
metrics:
|
| 11 |
- wer
|
|
|
|
| 19 |
|
| 20 |
# mms-1b-all-bem-genbed-m-model
|
| 21 |
|
| 22 |
+
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the GENBED - BEM dataset.
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 0.2887
|
| 25 |
+
- Wer: 0.4119
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
adapter.bem.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9af2498f856da15427d50889b1f841ab96ae6ca2fab094860c9a8baf67f7a70
|
| 3 |
+
size 8798532
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.379310344827586,
|
| 3 |
+
"eval_loss": 0.288705050945282,
|
| 4 |
+
"eval_runtime": 66.0339,
|
| 5 |
+
"eval_samples": 969,
|
| 6 |
+
"eval_samples_per_second": 14.674,
|
| 7 |
+
"eval_steps_per_second": 1.848,
|
| 8 |
+
"eval_wer": 0.4119247089544119,
|
| 9 |
+
"total_flos": 9.379255341017438e+18,
|
| 10 |
+
"train_loss": 0.6060099772917918,
|
| 11 |
+
"train_runtime": 5080.4448,
|
| 12 |
+
"train_samples": 2900,
|
| 13 |
+
"train_samples_per_second": 17.124,
|
| 14 |
+
"train_steps_per_second": 4.281
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.379310344827586,
|
| 3 |
+
"eval_loss": 0.288705050945282,
|
| 4 |
+
"eval_runtime": 66.0339,
|
| 5 |
+
"eval_samples": 969,
|
| 6 |
+
"eval_samples_per_second": 14.674,
|
| 7 |
+
"eval_steps_per_second": 1.848,
|
| 8 |
+
"eval_wer": 0.4119247089544119
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.379310344827586,
|
| 3 |
+
"total_flos": 9.379255341017438e+18,
|
| 4 |
+
"train_loss": 0.6060099772917918,
|
| 5 |
+
"train_runtime": 5080.4448,
|
| 6 |
+
"train_samples": 2900,
|
| 7 |
+
"train_samples_per_second": 17.124,
|
| 8 |
+
"train_steps_per_second": 4.281
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,675 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.288705050945282,
|
| 3 |
+
"best_model_checkpoint": "/scratch/skscla001/results/mms-1b-all-bem-genbed-m-model/checkpoint-3600",
|
| 4 |
+
"epoch": 5.379310344827586,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 3900,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.13793103448275862,
|
| 13 |
+
"grad_norm": 4.020408630371094,
|
| 14 |
+
"learning_rate": 0.00029099999999999997,
|
| 15 |
+
"loss": 6.6677,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.13793103448275862,
|
| 20 |
+
"eval_loss": 1.1907541751861572,
|
| 21 |
+
"eval_runtime": 66.3884,
|
| 22 |
+
"eval_samples_per_second": 14.596,
|
| 23 |
+
"eval_steps_per_second": 1.838,
|
| 24 |
+
"eval_wer": 0.9661625503209662,
|
| 25 |
+
"step": 100
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.27586206896551724,
|
| 29 |
+
"grad_norm": 2.7590324878692627,
|
| 30 |
+
"learning_rate": 0.00029865588914549653,
|
| 31 |
+
"loss": 0.7337,
|
| 32 |
+
"step": 200
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.27586206896551724,
|
| 36 |
+
"eval_loss": 0.41317346692085266,
|
| 37 |
+
"eval_runtime": 66.0778,
|
| 38 |
+
"eval_samples_per_second": 14.665,
|
| 39 |
+
"eval_steps_per_second": 1.846,
|
| 40 |
+
"eval_wer": 0.5657708628005658,
|
| 41 |
+
"step": 200
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.41379310344827586,
|
| 45 |
+
"grad_norm": 3.6684412956237793,
|
| 46 |
+
"learning_rate": 0.000297270207852194,
|
| 47 |
+
"loss": 0.5661,
|
| 48 |
+
"step": 300
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.41379310344827586,
|
| 52 |
+
"eval_loss": 0.3766968846321106,
|
| 53 |
+
"eval_runtime": 65.3213,
|
| 54 |
+
"eval_samples_per_second": 14.834,
|
| 55 |
+
"eval_steps_per_second": 1.868,
|
| 56 |
+
"eval_wer": 0.5507561745185507,
|
| 57 |
+
"step": 300
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.5517241379310345,
|
| 61 |
+
"grad_norm": 1.821001648902893,
|
| 62 |
+
"learning_rate": 0.00029588452655889143,
|
| 63 |
+
"loss": 0.523,
|
| 64 |
+
"step": 400
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.5517241379310345,
|
| 68 |
+
"eval_loss": 0.3591341972351074,
|
| 69 |
+
"eval_runtime": 66.145,
|
| 70 |
+
"eval_samples_per_second": 14.65,
|
| 71 |
+
"eval_steps_per_second": 1.844,
|
| 72 |
+
"eval_wer": 0.5009248177565009,
|
| 73 |
+
"step": 400
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.6896551724137931,
|
| 77 |
+
"grad_norm": 1.441114068031311,
|
| 78 |
+
"learning_rate": 0.0002944988452655889,
|
| 79 |
+
"loss": 0.5391,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.6896551724137931,
|
| 84 |
+
"eval_loss": 0.3529561161994934,
|
| 85 |
+
"eval_runtime": 66.2528,
|
| 86 |
+
"eval_samples_per_second": 14.626,
|
| 87 |
+
"eval_steps_per_second": 1.841,
|
| 88 |
+
"eval_wer": 0.5053857034055054,
|
| 89 |
+
"step": 500
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.8275862068965517,
|
| 93 |
+
"grad_norm": 2.5801000595092773,
|
| 94 |
+
"learning_rate": 0.00029311316397228633,
|
| 95 |
+
"loss": 0.4978,
|
| 96 |
+
"step": 600
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.8275862068965517,
|
| 100 |
+
"eval_loss": 0.3495703935623169,
|
| 101 |
+
"eval_runtime": 66.263,
|
| 102 |
+
"eval_samples_per_second": 14.624,
|
| 103 |
+
"eval_steps_per_second": 1.841,
|
| 104 |
+
"eval_wer": 0.5096289848765096,
|
| 105 |
+
"step": 600
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.9655172413793104,
|
| 109 |
+
"grad_norm": 2.353003978729248,
|
| 110 |
+
"learning_rate": 0.00029172748267898384,
|
| 111 |
+
"loss": 0.4737,
|
| 112 |
+
"step": 700
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.9655172413793104,
|
| 116 |
+
"eval_loss": 0.3478347957134247,
|
| 117 |
+
"eval_runtime": 66.0122,
|
| 118 |
+
"eval_samples_per_second": 14.679,
|
| 119 |
+
"eval_steps_per_second": 1.848,
|
| 120 |
+
"eval_wer": 0.5078881514525079,
|
| 121 |
+
"step": 700
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.103448275862069,
|
| 125 |
+
"grad_norm": 1.0043631792068481,
|
| 126 |
+
"learning_rate": 0.00029034180138568123,
|
| 127 |
+
"loss": 0.4878,
|
| 128 |
+
"step": 800
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.103448275862069,
|
| 132 |
+
"eval_loss": 0.33903008699417114,
|
| 133 |
+
"eval_runtime": 65.851,
|
| 134 |
+
"eval_samples_per_second": 14.715,
|
| 135 |
+
"eval_steps_per_second": 1.853,
|
| 136 |
+
"eval_wer": 0.4737242955064737,
|
| 137 |
+
"step": 800
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.2413793103448276,
|
| 141 |
+
"grad_norm": 0.7626993656158447,
|
| 142 |
+
"learning_rate": 0.00028895612009237874,
|
| 143 |
+
"loss": 0.4737,
|
| 144 |
+
"step": 900
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.2413793103448276,
|
| 148 |
+
"eval_loss": 0.3304341435432434,
|
| 149 |
+
"eval_runtime": 65.8955,
|
| 150 |
+
"eval_samples_per_second": 14.705,
|
| 151 |
+
"eval_steps_per_second": 1.851,
|
| 152 |
+
"eval_wer": 0.49047981721249045,
|
| 153 |
+
"step": 900
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.3793103448275863,
|
| 157 |
+
"grad_norm": 0.9640819430351257,
|
| 158 |
+
"learning_rate": 0.0002875704387990762,
|
| 159 |
+
"loss": 0.4603,
|
| 160 |
+
"step": 1000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.3793103448275863,
|
| 164 |
+
"eval_loss": 0.33281686902046204,
|
| 165 |
+
"eval_runtime": 66.3,
|
| 166 |
+
"eval_samples_per_second": 14.615,
|
| 167 |
+
"eval_steps_per_second": 1.84,
|
| 168 |
+
"eval_wer": 0.48416929605048414,
|
| 169 |
+
"step": 1000
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.5172413793103448,
|
| 173 |
+
"grad_norm": 2.8595709800720215,
|
| 174 |
+
"learning_rate": 0.0002861986143187067,
|
| 175 |
+
"loss": 0.4793,
|
| 176 |
+
"step": 1100
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.5172413793103448,
|
| 180 |
+
"eval_loss": 0.3252318799495697,
|
| 181 |
+
"eval_runtime": 66.2152,
|
| 182 |
+
"eval_samples_per_second": 14.634,
|
| 183 |
+
"eval_steps_per_second": 1.842,
|
| 184 |
+
"eval_wer": 0.46404090958546407,
|
| 185 |
+
"step": 1100
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.6551724137931034,
|
| 189 |
+
"grad_norm": 0.949995219707489,
|
| 190 |
+
"learning_rate": 0.0002848129330254041,
|
| 191 |
+
"loss": 0.4359,
|
| 192 |
+
"step": 1200
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.6551724137931034,
|
| 196 |
+
"eval_loss": 0.32520735263824463,
|
| 197 |
+
"eval_runtime": 66.7065,
|
| 198 |
+
"eval_samples_per_second": 14.526,
|
| 199 |
+
"eval_steps_per_second": 1.829,
|
| 200 |
+
"eval_wer": 0.4658905450984659,
|
| 201 |
+
"step": 1200
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.793103448275862,
|
| 205 |
+
"grad_norm": 0.6196809411048889,
|
| 206 |
+
"learning_rate": 0.0002834272517321016,
|
| 207 |
+
"loss": 0.457,
|
| 208 |
+
"step": 1300
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.793103448275862,
|
| 212 |
+
"eval_loss": 0.32037919759750366,
|
| 213 |
+
"eval_runtime": 66.2729,
|
| 214 |
+
"eval_samples_per_second": 14.621,
|
| 215 |
+
"eval_steps_per_second": 1.841,
|
| 216 |
+
"eval_wer": 0.4716570558154717,
|
| 217 |
+
"step": 1300
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.9310344827586206,
|
| 221 |
+
"grad_norm": 1.259907603263855,
|
| 222 |
+
"learning_rate": 0.0002820415704387991,
|
| 223 |
+
"loss": 0.469,
|
| 224 |
+
"step": 1400
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.9310344827586206,
|
| 228 |
+
"eval_loss": 0.3184985816478729,
|
| 229 |
+
"eval_runtime": 66.6429,
|
| 230 |
+
"eval_samples_per_second": 14.54,
|
| 231 |
+
"eval_steps_per_second": 1.831,
|
| 232 |
+
"eval_wer": 0.4696986182134697,
|
| 233 |
+
"step": 1400
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.0689655172413794,
|
| 237 |
+
"grad_norm": 2.5777244567871094,
|
| 238 |
+
"learning_rate": 0.00028065588914549653,
|
| 239 |
+
"loss": 0.4894,
|
| 240 |
+
"step": 1500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 2.0689655172413794,
|
| 244 |
+
"eval_loss": 0.31666702032089233,
|
| 245 |
+
"eval_runtime": 66.147,
|
| 246 |
+
"eval_samples_per_second": 14.649,
|
| 247 |
+
"eval_steps_per_second": 1.844,
|
| 248 |
+
"eval_wer": 0.4621912740724622,
|
| 249 |
+
"step": 1500
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.206896551724138,
|
| 253 |
+
"grad_norm": 1.6249274015426636,
|
| 254 |
+
"learning_rate": 0.000279270207852194,
|
| 255 |
+
"loss": 0.4386,
|
| 256 |
+
"step": 1600
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 2.206896551724138,
|
| 260 |
+
"eval_loss": 0.3184942603111267,
|
| 261 |
+
"eval_runtime": 66.4241,
|
| 262 |
+
"eval_samples_per_second": 14.588,
|
| 263 |
+
"eval_steps_per_second": 1.837,
|
| 264 |
+
"eval_wer": 0.4645849200304646,
|
| 265 |
+
"step": 1600
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.344827586206897,
|
| 269 |
+
"grad_norm": 3.3305695056915283,
|
| 270 |
+
"learning_rate": 0.00027788452655889143,
|
| 271 |
+
"loss": 0.4441,
|
| 272 |
+
"step": 1700
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.344827586206897,
|
| 276 |
+
"eval_loss": 0.30993008613586426,
|
| 277 |
+
"eval_runtime": 66.4734,
|
| 278 |
+
"eval_samples_per_second": 14.577,
|
| 279 |
+
"eval_steps_per_second": 1.835,
|
| 280 |
+
"eval_wer": 0.4606680448264607,
|
| 281 |
+
"step": 1700
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.4827586206896552,
|
| 285 |
+
"grad_norm": 8.44198989868164,
|
| 286 |
+
"learning_rate": 0.0002764988452655889,
|
| 287 |
+
"loss": 0.444,
|
| 288 |
+
"step": 1800
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.4827586206896552,
|
| 292 |
+
"eval_loss": 0.315364807844162,
|
| 293 |
+
"eval_runtime": 66.1431,
|
| 294 |
+
"eval_samples_per_second": 14.65,
|
| 295 |
+
"eval_steps_per_second": 1.844,
|
| 296 |
+
"eval_wer": 0.4551191382874551,
|
| 297 |
+
"step": 1800
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.6206896551724137,
|
| 301 |
+
"grad_norm": 2.8819918632507324,
|
| 302 |
+
"learning_rate": 0.00027511316397228633,
|
| 303 |
+
"loss": 0.4065,
|
| 304 |
+
"step": 1900
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 2.6206896551724137,
|
| 308 |
+
"eval_loss": 0.3137612044811249,
|
| 309 |
+
"eval_runtime": 66.3301,
|
| 310 |
+
"eval_samples_per_second": 14.609,
|
| 311 |
+
"eval_steps_per_second": 1.839,
|
| 312 |
+
"eval_wer": 0.4623000761614623,
|
| 313 |
+
"step": 1900
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.7586206896551726,
|
| 317 |
+
"grad_norm": 2.527022123336792,
|
| 318 |
+
"learning_rate": 0.0002737274826789838,
|
| 319 |
+
"loss": 0.4163,
|
| 320 |
+
"step": 2000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.7586206896551726,
|
| 324 |
+
"eval_loss": 0.3087407350540161,
|
| 325 |
+
"eval_runtime": 66.4958,
|
| 326 |
+
"eval_samples_per_second": 14.572,
|
| 327 |
+
"eval_steps_per_second": 1.835,
|
| 328 |
+
"eval_wer": 0.43771080404743773,
|
| 329 |
+
"step": 2000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.896551724137931,
|
| 333 |
+
"grad_norm": 4.25317907333374,
|
| 334 |
+
"learning_rate": 0.0002723418013856813,
|
| 335 |
+
"loss": 0.4518,
|
| 336 |
+
"step": 2100
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 2.896551724137931,
|
| 340 |
+
"eval_loss": 0.3054434657096863,
|
| 341 |
+
"eval_runtime": 66.3758,
|
| 342 |
+
"eval_samples_per_second": 14.599,
|
| 343 |
+
"eval_steps_per_second": 1.838,
|
| 344 |
+
"eval_wer": 0.44946142965944946,
|
| 345 |
+
"step": 2100
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 3.0344827586206895,
|
| 349 |
+
"grad_norm": 1.4464918375015259,
|
| 350 |
+
"learning_rate": 0.00027095612009237874,
|
| 351 |
+
"loss": 0.4208,
|
| 352 |
+
"step": 2200
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 3.0344827586206895,
|
| 356 |
+
"eval_loss": 0.30368348956108093,
|
| 357 |
+
"eval_runtime": 65.8792,
|
| 358 |
+
"eval_samples_per_second": 14.709,
|
| 359 |
+
"eval_steps_per_second": 1.852,
|
| 360 |
+
"eval_wer": 0.4512022630834512,
|
| 361 |
+
"step": 2200
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 3.1724137931034484,
|
| 365 |
+
"grad_norm": 1.0703141689300537,
|
| 366 |
+
"learning_rate": 0.0002695704387990762,
|
| 367 |
+
"loss": 0.381,
|
| 368 |
+
"step": 2300
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 3.1724137931034484,
|
| 372 |
+
"eval_loss": 0.3074105381965637,
|
| 373 |
+
"eval_runtime": 66.1774,
|
| 374 |
+
"eval_samples_per_second": 14.642,
|
| 375 |
+
"eval_steps_per_second": 1.844,
|
| 376 |
+
"eval_wer": 0.43858122075943856,
|
| 377 |
+
"step": 2300
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.310344827586207,
|
| 381 |
+
"grad_norm": 0.6348339319229126,
|
| 382 |
+
"learning_rate": 0.00026818475750577364,
|
| 383 |
+
"loss": 0.4203,
|
| 384 |
+
"step": 2400
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 3.310344827586207,
|
| 388 |
+
"eval_loss": 0.29894039034843445,
|
| 389 |
+
"eval_runtime": 66.3138,
|
| 390 |
+
"eval_samples_per_second": 14.612,
|
| 391 |
+
"eval_steps_per_second": 1.84,
|
| 392 |
+
"eval_wer": 0.42443694918942443,
|
| 393 |
+
"step": 2400
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 3.4482758620689653,
|
| 397 |
+
"grad_norm": 0.7910144925117493,
|
| 398 |
+
"learning_rate": 0.0002668129330254041,
|
| 399 |
+
"loss": 0.4556,
|
| 400 |
+
"step": 2500
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 3.4482758620689653,
|
| 404 |
+
"eval_loss": 0.30804964900016785,
|
| 405 |
+
"eval_runtime": 66.2991,
|
| 406 |
+
"eval_samples_per_second": 14.616,
|
| 407 |
+
"eval_steps_per_second": 1.84,
|
| 408 |
+
"eval_wer": 0.4835164835164835,
|
| 409 |
+
"step": 2500
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 3.586206896551724,
|
| 413 |
+
"grad_norm": 0.7089941501617432,
|
| 414 |
+
"learning_rate": 0.0002654411085450346,
|
| 415 |
+
"loss": 0.4143,
|
| 416 |
+
"step": 2600
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 3.586206896551724,
|
| 420 |
+
"eval_loss": 0.29555052518844604,
|
| 421 |
+
"eval_runtime": 66.1318,
|
| 422 |
+
"eval_samples_per_second": 14.653,
|
| 423 |
+
"eval_steps_per_second": 1.845,
|
| 424 |
+
"eval_wer": 0.42215210532042213,
|
| 425 |
+
"step": 2600
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 3.7241379310344827,
|
| 429 |
+
"grad_norm": 1.1959691047668457,
|
| 430 |
+
"learning_rate": 0.00026405542725173206,
|
| 431 |
+
"loss": 0.4055,
|
| 432 |
+
"step": 2700
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 3.7241379310344827,
|
| 436 |
+
"eval_loss": 0.30229437351226807,
|
| 437 |
+
"eval_runtime": 66.3475,
|
| 438 |
+
"eval_samples_per_second": 14.605,
|
| 439 |
+
"eval_steps_per_second": 1.839,
|
| 440 |
+
"eval_wer": 0.45805679469045807,
|
| 441 |
+
"step": 2700
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 3.862068965517241,
|
| 445 |
+
"grad_norm": 0.894882321357727,
|
| 446 |
+
"learning_rate": 0.00026266974595842956,
|
| 447 |
+
"loss": 0.4102,
|
| 448 |
+
"step": 2800
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 3.862068965517241,
|
| 452 |
+
"eval_loss": 0.2955451011657715,
|
| 453 |
+
"eval_runtime": 66.6438,
|
| 454 |
+
"eval_samples_per_second": 14.54,
|
| 455 |
+
"eval_steps_per_second": 1.831,
|
| 456 |
+
"eval_wer": 0.44119247089544117,
|
| 457 |
+
"step": 2800
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 4.0,
|
| 461 |
+
"grad_norm": 1.242213249206543,
|
| 462 |
+
"learning_rate": 0.000261284064665127,
|
| 463 |
+
"loss": 0.4451,
|
| 464 |
+
"step": 2900
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 4.0,
|
| 468 |
+
"eval_loss": 0.29440462589263916,
|
| 469 |
+
"eval_runtime": 66.0997,
|
| 470 |
+
"eval_samples_per_second": 14.66,
|
| 471 |
+
"eval_steps_per_second": 1.846,
|
| 472 |
+
"eval_wer": 0.4181264280274181,
|
| 473 |
+
"step": 2900
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 4.137931034482759,
|
| 477 |
+
"grad_norm": 4.585179328918457,
|
| 478 |
+
"learning_rate": 0.00025989838337182446,
|
| 479 |
+
"loss": 0.3857,
|
| 480 |
+
"step": 3000
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 4.137931034482759,
|
| 484 |
+
"eval_loss": 0.29851463437080383,
|
| 485 |
+
"eval_runtime": 66.1268,
|
| 486 |
+
"eval_samples_per_second": 14.654,
|
| 487 |
+
"eval_steps_per_second": 1.845,
|
| 488 |
+
"eval_wer": 0.44260689805244263,
|
| 489 |
+
"step": 3000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 4.275862068965517,
|
| 493 |
+
"grad_norm": 2.503293991088867,
|
| 494 |
+
"learning_rate": 0.0002585127020785219,
|
| 495 |
+
"loss": 0.4071,
|
| 496 |
+
"step": 3100
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 4.275862068965517,
|
| 500 |
+
"eval_loss": 0.29181334376335144,
|
| 501 |
+
"eval_runtime": 66.2612,
|
| 502 |
+
"eval_samples_per_second": 14.624,
|
| 503 |
+
"eval_steps_per_second": 1.841,
|
| 504 |
+
"eval_wer": 0.429006636927429,
|
| 505 |
+
"step": 3100
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 4.413793103448276,
|
| 509 |
+
"grad_norm": 219.94293212890625,
|
| 510 |
+
"learning_rate": 0.00025712702078521936,
|
| 511 |
+
"loss": 0.4,
|
| 512 |
+
"step": 3200
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 4.413793103448276,
|
| 516 |
+
"eval_loss": 0.2951139509677887,
|
| 517 |
+
"eval_runtime": 66.077,
|
| 518 |
+
"eval_samples_per_second": 14.665,
|
| 519 |
+
"eval_steps_per_second": 1.846,
|
| 520 |
+
"eval_wer": 0.43205309541943204,
|
| 521 |
+
"step": 3200
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 4.551724137931035,
|
| 525 |
+
"grad_norm": 5.060625076293945,
|
| 526 |
+
"learning_rate": 0.00025574133949191687,
|
| 527 |
+
"loss": 0.4257,
|
| 528 |
+
"step": 3300
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 4.551724137931035,
|
| 532 |
+
"eval_loss": 0.3035087585449219,
|
| 533 |
+
"eval_runtime": 66.4299,
|
| 534 |
+
"eval_samples_per_second": 14.587,
|
| 535 |
+
"eval_steps_per_second": 1.837,
|
| 536 |
+
"eval_wer": 0.4607768469154608,
|
| 537 |
+
"step": 3300
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 4.689655172413794,
|
| 541 |
+
"grad_norm": 4.010824680328369,
|
| 542 |
+
"learning_rate": 0.00025435565819861426,
|
| 543 |
+
"loss": 0.3929,
|
| 544 |
+
"step": 3400
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 4.689655172413794,
|
| 548 |
+
"eval_loss": 0.2965061366558075,
|
| 549 |
+
"eval_runtime": 66.5423,
|
| 550 |
+
"eval_samples_per_second": 14.562,
|
| 551 |
+
"eval_steps_per_second": 1.833,
|
| 552 |
+
"eval_wer": 0.4131215319334131,
|
| 553 |
+
"step": 3400
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 4.827586206896552,
|
| 557 |
+
"grad_norm": 1.3017578125,
|
| 558 |
+
"learning_rate": 0.00025296997690531177,
|
| 559 |
+
"loss": 0.3957,
|
| 560 |
+
"step": 3500
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 4.827586206896552,
|
| 564 |
+
"eval_loss": 0.2937914729118347,
|
| 565 |
+
"eval_runtime": 66.4495,
|
| 566 |
+
"eval_samples_per_second": 14.583,
|
| 567 |
+
"eval_steps_per_second": 1.836,
|
| 568 |
+
"eval_wer": 0.43966924164943966,
|
| 569 |
+
"step": 3500
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 4.9655172413793105,
|
| 573 |
+
"grad_norm": 2.3724756240844727,
|
| 574 |
+
"learning_rate": 0.0002515842956120092,
|
| 575 |
+
"loss": 0.3974,
|
| 576 |
+
"step": 3600
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 4.9655172413793105,
|
| 580 |
+
"eval_loss": 0.288705050945282,
|
| 581 |
+
"eval_runtime": 66.1655,
|
| 582 |
+
"eval_samples_per_second": 14.645,
|
| 583 |
+
"eval_steps_per_second": 1.844,
|
| 584 |
+
"eval_wer": 0.4119247089544119,
|
| 585 |
+
"step": 3600
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 5.103448275862069,
|
| 589 |
+
"grad_norm": 1.0314807891845703,
|
| 590 |
+
"learning_rate": 0.00025019861431870667,
|
| 591 |
+
"loss": 0.3733,
|
| 592 |
+
"step": 3700
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 5.103448275862069,
|
| 596 |
+
"eval_loss": 0.2889891266822815,
|
| 597 |
+
"eval_runtime": 66.2632,
|
| 598 |
+
"eval_samples_per_second": 14.624,
|
| 599 |
+
"eval_steps_per_second": 1.841,
|
| 600 |
+
"eval_wer": 0.404961375258405,
|
| 601 |
+
"step": 3700
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 5.241379310344827,
|
| 605 |
+
"grad_norm": 1.2068380117416382,
|
| 606 |
+
"learning_rate": 0.0002488129330254041,
|
| 607 |
+
"loss": 0.382,
|
| 608 |
+
"step": 3800
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 5.241379310344827,
|
| 612 |
+
"eval_loss": 0.29174748063087463,
|
| 613 |
+
"eval_runtime": 66.0529,
|
| 614 |
+
"eval_samples_per_second": 14.67,
|
| 615 |
+
"eval_steps_per_second": 1.847,
|
| 616 |
+
"eval_wer": 0.42334892829942333,
|
| 617 |
+
"step": 3800
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 5.379310344827586,
|
| 621 |
+
"grad_norm": 1.330348014831543,
|
| 622 |
+
"learning_rate": 0.00024742725173210157,
|
| 623 |
+
"loss": 0.3669,
|
| 624 |
+
"step": 3900
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 5.379310344827586,
|
| 628 |
+
"eval_loss": 0.2899990379810333,
|
| 629 |
+
"eval_runtime": 66.5504,
|
| 630 |
+
"eval_samples_per_second": 14.56,
|
| 631 |
+
"eval_steps_per_second": 1.833,
|
| 632 |
+
"eval_wer": 0.4312914807964313,
|
| 633 |
+
"step": 3900
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 5.379310344827586,
|
| 637 |
+
"step": 3900,
|
| 638 |
+
"total_flos": 9.379255341017438e+18,
|
| 639 |
+
"train_loss": 0.6060099772917918,
|
| 640 |
+
"train_runtime": 5080.4448,
|
| 641 |
+
"train_samples_per_second": 17.124,
|
| 642 |
+
"train_steps_per_second": 4.281
|
| 643 |
+
}
|
| 644 |
+
],
|
| 645 |
+
"logging_steps": 100,
|
| 646 |
+
"max_steps": 21750,
|
| 647 |
+
"num_input_tokens_seen": 0,
|
| 648 |
+
"num_train_epochs": 30,
|
| 649 |
+
"save_steps": 400,
|
| 650 |
+
"stateful_callbacks": {
|
| 651 |
+
"EarlyStoppingCallback": {
|
| 652 |
+
"args": {
|
| 653 |
+
"early_stopping_patience": 3,
|
| 654 |
+
"early_stopping_threshold": 0.0
|
| 655 |
+
},
|
| 656 |
+
"attributes": {
|
| 657 |
+
"early_stopping_patience_counter": 0
|
| 658 |
+
}
|
| 659 |
+
},
|
| 660 |
+
"TrainerControl": {
|
| 661 |
+
"args": {
|
| 662 |
+
"should_epoch_stop": false,
|
| 663 |
+
"should_evaluate": false,
|
| 664 |
+
"should_log": false,
|
| 665 |
+
"should_save": true,
|
| 666 |
+
"should_training_stop": false
|
| 667 |
+
},
|
| 668 |
+
"attributes": {}
|
| 669 |
+
}
|
| 670 |
+
},
|
| 671 |
+
"total_flos": 9.379255341017438e+18,
|
| 672 |
+
"train_batch_size": 4,
|
| 673 |
+
"trial_name": null,
|
| 674 |
+
"trial_params": null
|
| 675 |
+
}
|