End of training
Browse files- README.md +5 -3
- all_results.json +15 -0
- eval_results.json +10 -0
- train_results.json +8 -0
- trainer_state.json +786 -0
README.md
CHANGED
|
@@ -1,4 +1,6 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
| 4 |
metrics:
|
|
@@ -13,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# bert-plus-embedderForMLM-goodwiki-deduped-split_4096-usecache
|
| 15 |
|
| 16 |
-
This model was trained from scratch on the
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 1.
|
| 19 |
-
- Accuracy: 0.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
|
|
|
| 15 |
|
| 16 |
# bert-plus-embedderForMLM-goodwiki-deduped-split_4096-usecache
|
| 17 |
|
| 18 |
+
This model was trained from scratch on the BEE-spoke-data/goodwiki-deduped-split dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.9835
|
| 21 |
+
- Accuracy: 0.6159
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.6158778269993005,
|
| 4 |
+
"eval_loss": 1.9834641218185425,
|
| 5 |
+
"eval_runtime": 40.5481,
|
| 6 |
+
"eval_samples": 300,
|
| 7 |
+
"eval_samples_per_second": 7.399,
|
| 8 |
+
"eval_steps_per_second": 1.85,
|
| 9 |
+
"perplexity": 7.267876236350372,
|
| 10 |
+
"train_loss": 2.32403786500295,
|
| 11 |
+
"train_runtime": 14945.8713,
|
| 12 |
+
"train_samples": 38441,
|
| 13 |
+
"train_samples_per_second": 2.572,
|
| 14 |
+
"train_steps_per_second": 0.04
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.6158778269993005,
|
| 4 |
+
"eval_loss": 1.9834641218185425,
|
| 5 |
+
"eval_runtime": 40.5481,
|
| 6 |
+
"eval_samples": 300,
|
| 7 |
+
"eval_samples_per_second": 7.399,
|
| 8 |
+
"eval_steps_per_second": 1.85,
|
| 9 |
+
"perplexity": 7.267876236350372
|
| 10 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 2.32403786500295,
|
| 4 |
+
"train_runtime": 14945.8713,
|
| 5 |
+
"train_samples": 38441,
|
| 6 |
+
"train_samples_per_second": 2.572,
|
| 7 |
+
"train_steps_per_second": 0.04
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,786 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9988554780980127,
|
| 5 |
+
"eval_steps": 150,
|
| 6 |
+
"global_step": 600,
|
| 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": 5e-06,
|
| 14 |
+
"loss": 8.3066,
|
| 15 |
+
"step": 5
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 1e-05,
|
| 20 |
+
"loss": 7.9763,
|
| 21 |
+
"step": 10
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.02,
|
| 25 |
+
"learning_rate": 1.5e-05,
|
| 26 |
+
"loss": 7.2999,
|
| 27 |
+
"step": 15
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.03,
|
| 31 |
+
"learning_rate": 2e-05,
|
| 32 |
+
"loss": 6.3145,
|
| 33 |
+
"step": 20
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.04,
|
| 37 |
+
"learning_rate": 2.5e-05,
|
| 38 |
+
"loss": 4.8549,
|
| 39 |
+
"step": 25
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.05,
|
| 43 |
+
"learning_rate": 3e-05,
|
| 44 |
+
"loss": 3.7485,
|
| 45 |
+
"step": 30
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06,
|
| 49 |
+
"learning_rate": 3.5e-05,
|
| 50 |
+
"loss": 3.0173,
|
| 51 |
+
"step": 35
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07,
|
| 55 |
+
"learning_rate": 4e-05,
|
| 56 |
+
"loss": 2.6364,
|
| 57 |
+
"step": 40
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.07,
|
| 61 |
+
"learning_rate": 4.5e-05,
|
| 62 |
+
"loss": 2.4726,
|
| 63 |
+
"step": 45
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.08,
|
| 67 |
+
"learning_rate": 5e-05,
|
| 68 |
+
"loss": 2.3895,
|
| 69 |
+
"step": 50
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.09,
|
| 73 |
+
"learning_rate": 5.500000000000001e-05,
|
| 74 |
+
"loss": 2.2992,
|
| 75 |
+
"step": 55
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.1,
|
| 79 |
+
"learning_rate": 6e-05,
|
| 80 |
+
"loss": 2.291,
|
| 81 |
+
"step": 60
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.11,
|
| 85 |
+
"learning_rate": 6.500000000000001e-05,
|
| 86 |
+
"loss": 2.2597,
|
| 87 |
+
"step": 65
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.12,
|
| 91 |
+
"learning_rate": 7e-05,
|
| 92 |
+
"loss": 2.2245,
|
| 93 |
+
"step": 70
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.12,
|
| 97 |
+
"learning_rate": 7.500000000000001e-05,
|
| 98 |
+
"loss": 2.2076,
|
| 99 |
+
"step": 75
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.13,
|
| 103 |
+
"learning_rate": 8e-05,
|
| 104 |
+
"loss": 2.2132,
|
| 105 |
+
"step": 80
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.14,
|
| 109 |
+
"learning_rate": 8.5e-05,
|
| 110 |
+
"loss": 2.1925,
|
| 111 |
+
"step": 85
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.15,
|
| 115 |
+
"learning_rate": 9e-05,
|
| 116 |
+
"loss": 2.1868,
|
| 117 |
+
"step": 90
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.16,
|
| 121 |
+
"learning_rate": 9.5e-05,
|
| 122 |
+
"loss": 2.1916,
|
| 123 |
+
"step": 95
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.17,
|
| 127 |
+
"learning_rate": 0.0001,
|
| 128 |
+
"loss": 2.1774,
|
| 129 |
+
"step": 100
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.17,
|
| 133 |
+
"learning_rate": 9.900000000000001e-05,
|
| 134 |
+
"loss": 2.183,
|
| 135 |
+
"step": 105
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.18,
|
| 139 |
+
"learning_rate": 9.8e-05,
|
| 140 |
+
"loss": 2.1712,
|
| 141 |
+
"step": 110
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.19,
|
| 145 |
+
"learning_rate": 9.7e-05,
|
| 146 |
+
"loss": 2.1713,
|
| 147 |
+
"step": 115
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.2,
|
| 151 |
+
"learning_rate": 9.6e-05,
|
| 152 |
+
"loss": 2.1731,
|
| 153 |
+
"step": 120
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.21,
|
| 157 |
+
"learning_rate": 9.5e-05,
|
| 158 |
+
"loss": 2.1565,
|
| 159 |
+
"step": 125
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.22,
|
| 163 |
+
"learning_rate": 9.4e-05,
|
| 164 |
+
"loss": 2.1575,
|
| 165 |
+
"step": 130
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.22,
|
| 169 |
+
"learning_rate": 9.300000000000001e-05,
|
| 170 |
+
"loss": 2.1414,
|
| 171 |
+
"step": 135
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.23,
|
| 175 |
+
"learning_rate": 9.200000000000001e-05,
|
| 176 |
+
"loss": 2.1384,
|
| 177 |
+
"step": 140
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.24,
|
| 181 |
+
"learning_rate": 9.1e-05,
|
| 182 |
+
"loss": 2.1487,
|
| 183 |
+
"step": 145
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.25,
|
| 187 |
+
"learning_rate": 9e-05,
|
| 188 |
+
"loss": 2.1283,
|
| 189 |
+
"step": 150
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.25,
|
| 193 |
+
"eval_accuracy": 0.6017748783939872,
|
| 194 |
+
"eval_loss": 2.089164972305298,
|
| 195 |
+
"eval_runtime": 58.1804,
|
| 196 |
+
"eval_samples_per_second": 5.156,
|
| 197 |
+
"eval_steps_per_second": 1.289,
|
| 198 |
+
"step": 150
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.26,
|
| 202 |
+
"learning_rate": 8.900000000000001e-05,
|
| 203 |
+
"loss": 2.1224,
|
| 204 |
+
"step": 155
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.27,
|
| 208 |
+
"learning_rate": 8.800000000000001e-05,
|
| 209 |
+
"loss": 2.144,
|
| 210 |
+
"step": 160
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.27,
|
| 214 |
+
"learning_rate": 8.7e-05,
|
| 215 |
+
"loss": 2.1293,
|
| 216 |
+
"step": 165
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.28,
|
| 220 |
+
"learning_rate": 8.6e-05,
|
| 221 |
+
"loss": 2.1417,
|
| 222 |
+
"step": 170
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.29,
|
| 226 |
+
"learning_rate": 8.5e-05,
|
| 227 |
+
"loss": 2.1282,
|
| 228 |
+
"step": 175
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.3,
|
| 232 |
+
"learning_rate": 8.4e-05,
|
| 233 |
+
"loss": 2.1008,
|
| 234 |
+
"step": 180
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.31,
|
| 238 |
+
"learning_rate": 8.3e-05,
|
| 239 |
+
"loss": 2.1218,
|
| 240 |
+
"step": 185
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.32,
|
| 244 |
+
"learning_rate": 8.2e-05,
|
| 245 |
+
"loss": 2.1292,
|
| 246 |
+
"step": 190
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.32,
|
| 250 |
+
"learning_rate": 8.1e-05,
|
| 251 |
+
"loss": 2.114,
|
| 252 |
+
"step": 195
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.33,
|
| 256 |
+
"learning_rate": 8e-05,
|
| 257 |
+
"loss": 2.1135,
|
| 258 |
+
"step": 200
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.34,
|
| 262 |
+
"learning_rate": 7.900000000000001e-05,
|
| 263 |
+
"loss": 2.118,
|
| 264 |
+
"step": 205
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.35,
|
| 268 |
+
"learning_rate": 7.800000000000001e-05,
|
| 269 |
+
"loss": 2.1231,
|
| 270 |
+
"step": 210
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.36,
|
| 274 |
+
"learning_rate": 7.7e-05,
|
| 275 |
+
"loss": 2.0705,
|
| 276 |
+
"step": 215
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.37,
|
| 280 |
+
"learning_rate": 7.6e-05,
|
| 281 |
+
"loss": 2.11,
|
| 282 |
+
"step": 220
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.37,
|
| 286 |
+
"learning_rate": 7.500000000000001e-05,
|
| 287 |
+
"loss": 2.0866,
|
| 288 |
+
"step": 225
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.38,
|
| 292 |
+
"learning_rate": 7.4e-05,
|
| 293 |
+
"loss": 2.1115,
|
| 294 |
+
"step": 230
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.39,
|
| 298 |
+
"learning_rate": 7.3e-05,
|
| 299 |
+
"loss": 2.1069,
|
| 300 |
+
"step": 235
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.4,
|
| 304 |
+
"learning_rate": 7.2e-05,
|
| 305 |
+
"loss": 2.1083,
|
| 306 |
+
"step": 240
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.41,
|
| 310 |
+
"learning_rate": 7.1e-05,
|
| 311 |
+
"loss": 2.1014,
|
| 312 |
+
"step": 245
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.42,
|
| 316 |
+
"learning_rate": 7e-05,
|
| 317 |
+
"loss": 2.1029,
|
| 318 |
+
"step": 250
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.42,
|
| 322 |
+
"learning_rate": 6.9e-05,
|
| 323 |
+
"loss": 2.0846,
|
| 324 |
+
"step": 255
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.43,
|
| 328 |
+
"learning_rate": 6.800000000000001e-05,
|
| 329 |
+
"loss": 2.1059,
|
| 330 |
+
"step": 260
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.44,
|
| 334 |
+
"learning_rate": 6.7e-05,
|
| 335 |
+
"loss": 2.0875,
|
| 336 |
+
"step": 265
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.45,
|
| 340 |
+
"learning_rate": 6.6e-05,
|
| 341 |
+
"loss": 2.0973,
|
| 342 |
+
"step": 270
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.46,
|
| 346 |
+
"learning_rate": 6.500000000000001e-05,
|
| 347 |
+
"loss": 2.0932,
|
| 348 |
+
"step": 275
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.47,
|
| 352 |
+
"learning_rate": 6.400000000000001e-05,
|
| 353 |
+
"loss": 2.0721,
|
| 354 |
+
"step": 280
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.47,
|
| 358 |
+
"learning_rate": 6.3e-05,
|
| 359 |
+
"loss": 2.0892,
|
| 360 |
+
"step": 285
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.48,
|
| 364 |
+
"learning_rate": 6.2e-05,
|
| 365 |
+
"loss": 2.1002,
|
| 366 |
+
"step": 290
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.49,
|
| 370 |
+
"learning_rate": 6.1e-05,
|
| 371 |
+
"loss": 2.0804,
|
| 372 |
+
"step": 295
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 0.5,
|
| 376 |
+
"learning_rate": 6e-05,
|
| 377 |
+
"loss": 2.0999,
|
| 378 |
+
"step": 300
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.5,
|
| 382 |
+
"eval_accuracy": 0.6084190234842455,
|
| 383 |
+
"eval_loss": 2.038738965988159,
|
| 384 |
+
"eval_runtime": 68.8578,
|
| 385 |
+
"eval_samples_per_second": 4.357,
|
| 386 |
+
"eval_steps_per_second": 1.089,
|
| 387 |
+
"step": 300
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.51,
|
| 391 |
+
"learning_rate": 5.9e-05,
|
| 392 |
+
"loss": 2.0905,
|
| 393 |
+
"step": 305
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.52,
|
| 397 |
+
"learning_rate": 5.8e-05,
|
| 398 |
+
"loss": 2.046,
|
| 399 |
+
"step": 310
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.52,
|
| 403 |
+
"learning_rate": 5.6999999999999996e-05,
|
| 404 |
+
"loss": 2.0794,
|
| 405 |
+
"step": 315
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.53,
|
| 409 |
+
"learning_rate": 5.6000000000000006e-05,
|
| 410 |
+
"loss": 2.0714,
|
| 411 |
+
"step": 320
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.54,
|
| 415 |
+
"learning_rate": 5.500000000000001e-05,
|
| 416 |
+
"loss": 2.0711,
|
| 417 |
+
"step": 325
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.55,
|
| 421 |
+
"learning_rate": 5.4000000000000005e-05,
|
| 422 |
+
"loss": 2.0525,
|
| 423 |
+
"step": 330
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.56,
|
| 427 |
+
"learning_rate": 5.300000000000001e-05,
|
| 428 |
+
"loss": 2.0689,
|
| 429 |
+
"step": 335
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.57,
|
| 433 |
+
"learning_rate": 5.2000000000000004e-05,
|
| 434 |
+
"loss": 2.0936,
|
| 435 |
+
"step": 340
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.57,
|
| 439 |
+
"learning_rate": 5.1000000000000006e-05,
|
| 440 |
+
"loss": 2.062,
|
| 441 |
+
"step": 345
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.58,
|
| 445 |
+
"learning_rate": 5e-05,
|
| 446 |
+
"loss": 2.0621,
|
| 447 |
+
"step": 350
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.59,
|
| 451 |
+
"learning_rate": 4.9e-05,
|
| 452 |
+
"loss": 2.0662,
|
| 453 |
+
"step": 355
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.6,
|
| 457 |
+
"learning_rate": 4.8e-05,
|
| 458 |
+
"loss": 2.0779,
|
| 459 |
+
"step": 360
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.61,
|
| 463 |
+
"learning_rate": 4.7e-05,
|
| 464 |
+
"loss": 2.0773,
|
| 465 |
+
"step": 365
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.62,
|
| 469 |
+
"learning_rate": 4.600000000000001e-05,
|
| 470 |
+
"loss": 2.0407,
|
| 471 |
+
"step": 370
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.62,
|
| 475 |
+
"learning_rate": 4.5e-05,
|
| 476 |
+
"loss": 2.0603,
|
| 477 |
+
"step": 375
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.63,
|
| 481 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 482 |
+
"loss": 2.0556,
|
| 483 |
+
"step": 380
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.64,
|
| 487 |
+
"learning_rate": 4.3e-05,
|
| 488 |
+
"loss": 2.0742,
|
| 489 |
+
"step": 385
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.65,
|
| 493 |
+
"learning_rate": 4.2e-05,
|
| 494 |
+
"loss": 2.0444,
|
| 495 |
+
"step": 390
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.66,
|
| 499 |
+
"learning_rate": 4.1e-05,
|
| 500 |
+
"loss": 2.0409,
|
| 501 |
+
"step": 395
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.67,
|
| 505 |
+
"learning_rate": 4e-05,
|
| 506 |
+
"loss": 2.0539,
|
| 507 |
+
"step": 400
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.67,
|
| 511 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 512 |
+
"loss": 2.0696,
|
| 513 |
+
"step": 405
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.68,
|
| 517 |
+
"learning_rate": 3.8e-05,
|
| 518 |
+
"loss": 2.0614,
|
| 519 |
+
"step": 410
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.69,
|
| 523 |
+
"learning_rate": 3.7e-05,
|
| 524 |
+
"loss": 2.0604,
|
| 525 |
+
"step": 415
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.7,
|
| 529 |
+
"learning_rate": 3.6e-05,
|
| 530 |
+
"loss": 2.0608,
|
| 531 |
+
"step": 420
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.71,
|
| 535 |
+
"learning_rate": 3.5e-05,
|
| 536 |
+
"loss": 2.0412,
|
| 537 |
+
"step": 425
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.72,
|
| 541 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 542 |
+
"loss": 2.0558,
|
| 543 |
+
"step": 430
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.72,
|
| 547 |
+
"learning_rate": 3.3e-05,
|
| 548 |
+
"loss": 2.0338,
|
| 549 |
+
"step": 435
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.73,
|
| 553 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 554 |
+
"loss": 2.0322,
|
| 555 |
+
"step": 440
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.74,
|
| 559 |
+
"learning_rate": 3.1e-05,
|
| 560 |
+
"loss": 2.0511,
|
| 561 |
+
"step": 445
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.75,
|
| 565 |
+
"learning_rate": 3e-05,
|
| 566 |
+
"loss": 2.0595,
|
| 567 |
+
"step": 450
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.75,
|
| 571 |
+
"eval_accuracy": 0.6142522292024847,
|
| 572 |
+
"eval_loss": 1.9970886707305908,
|
| 573 |
+
"eval_runtime": 61.0863,
|
| 574 |
+
"eval_samples_per_second": 4.911,
|
| 575 |
+
"eval_steps_per_second": 1.228,
|
| 576 |
+
"step": 450
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.76,
|
| 580 |
+
"learning_rate": 2.9e-05,
|
| 581 |
+
"loss": 2.032,
|
| 582 |
+
"step": 455
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.77,
|
| 586 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 587 |
+
"loss": 2.0421,
|
| 588 |
+
"step": 460
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 0.77,
|
| 592 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 593 |
+
"loss": 2.0255,
|
| 594 |
+
"step": 465
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.78,
|
| 598 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 599 |
+
"loss": 2.0259,
|
| 600 |
+
"step": 470
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.79,
|
| 604 |
+
"learning_rate": 2.5e-05,
|
| 605 |
+
"loss": 2.0361,
|
| 606 |
+
"step": 475
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.8,
|
| 610 |
+
"learning_rate": 2.4e-05,
|
| 611 |
+
"loss": 2.0584,
|
| 612 |
+
"step": 480
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.81,
|
| 616 |
+
"learning_rate": 2.3000000000000003e-05,
|
| 617 |
+
"loss": 2.0589,
|
| 618 |
+
"step": 485
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.82,
|
| 622 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 623 |
+
"loss": 2.0555,
|
| 624 |
+
"step": 490
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.82,
|
| 628 |
+
"learning_rate": 2.1e-05,
|
| 629 |
+
"loss": 2.0413,
|
| 630 |
+
"step": 495
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 0.83,
|
| 634 |
+
"learning_rate": 2e-05,
|
| 635 |
+
"loss": 2.0097,
|
| 636 |
+
"step": 500
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 0.84,
|
| 640 |
+
"learning_rate": 1.9e-05,
|
| 641 |
+
"loss": 2.0466,
|
| 642 |
+
"step": 505
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.85,
|
| 646 |
+
"learning_rate": 1.8e-05,
|
| 647 |
+
"loss": 2.0572,
|
| 648 |
+
"step": 510
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.86,
|
| 652 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 653 |
+
"loss": 2.0376,
|
| 654 |
+
"step": 515
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.87,
|
| 658 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 659 |
+
"loss": 2.0202,
|
| 660 |
+
"step": 520
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.87,
|
| 664 |
+
"learning_rate": 1.5e-05,
|
| 665 |
+
"loss": 2.0643,
|
| 666 |
+
"step": 525
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 0.88,
|
| 670 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 671 |
+
"loss": 2.0201,
|
| 672 |
+
"step": 530
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 0.89,
|
| 676 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 677 |
+
"loss": 2.0356,
|
| 678 |
+
"step": 535
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.9,
|
| 682 |
+
"learning_rate": 1.2e-05,
|
| 683 |
+
"loss": 2.0255,
|
| 684 |
+
"step": 540
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.91,
|
| 688 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 689 |
+
"loss": 2.0374,
|
| 690 |
+
"step": 545
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.92,
|
| 694 |
+
"learning_rate": 1e-05,
|
| 695 |
+
"loss": 2.0385,
|
| 696 |
+
"step": 550
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.92,
|
| 700 |
+
"learning_rate": 9e-06,
|
| 701 |
+
"loss": 2.024,
|
| 702 |
+
"step": 555
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.93,
|
| 706 |
+
"learning_rate": 8.000000000000001e-06,
|
| 707 |
+
"loss": 2.0144,
|
| 708 |
+
"step": 560
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 0.94,
|
| 712 |
+
"learning_rate": 7.000000000000001e-06,
|
| 713 |
+
"loss": 2.04,
|
| 714 |
+
"step": 565
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.95,
|
| 718 |
+
"learning_rate": 6e-06,
|
| 719 |
+
"loss": 2.0372,
|
| 720 |
+
"step": 570
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.96,
|
| 724 |
+
"learning_rate": 5e-06,
|
| 725 |
+
"loss": 2.0122,
|
| 726 |
+
"step": 575
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.97,
|
| 730 |
+
"learning_rate": 4.000000000000001e-06,
|
| 731 |
+
"loss": 2.0182,
|
| 732 |
+
"step": 580
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.97,
|
| 736 |
+
"learning_rate": 3e-06,
|
| 737 |
+
"loss": 2.0323,
|
| 738 |
+
"step": 585
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.98,
|
| 742 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 743 |
+
"loss": 2.0298,
|
| 744 |
+
"step": 590
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.99,
|
| 748 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 749 |
+
"loss": 2.0212,
|
| 750 |
+
"step": 595
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 1.0,
|
| 754 |
+
"learning_rate": 0.0,
|
| 755 |
+
"loss": 2.0481,
|
| 756 |
+
"step": 600
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 1.0,
|
| 760 |
+
"eval_accuracy": 0.6152243190218628,
|
| 761 |
+
"eval_loss": 1.9892692565917969,
|
| 762 |
+
"eval_runtime": 64.3793,
|
| 763 |
+
"eval_samples_per_second": 4.66,
|
| 764 |
+
"eval_steps_per_second": 1.165,
|
| 765 |
+
"step": 600
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.0,
|
| 769 |
+
"step": 600,
|
| 770 |
+
"total_flos": 5.41006975991808e+16,
|
| 771 |
+
"train_loss": 2.32403786500295,
|
| 772 |
+
"train_runtime": 14945.8713,
|
| 773 |
+
"train_samples_per_second": 2.572,
|
| 774 |
+
"train_steps_per_second": 0.04
|
| 775 |
+
}
|
| 776 |
+
],
|
| 777 |
+
"logging_steps": 5,
|
| 778 |
+
"max_steps": 600,
|
| 779 |
+
"num_input_tokens_seen": 0,
|
| 780 |
+
"num_train_epochs": 1,
|
| 781 |
+
"save_steps": 100,
|
| 782 |
+
"total_flos": 5.41006975991808e+16,
|
| 783 |
+
"train_batch_size": 4,
|
| 784 |
+
"trial_name": null,
|
| 785 |
+
"trial_params": null
|
| 786 |
+
}
|