End of training
Browse files- README.md +16 -4
- all_results.json +16 -0
- eval_results.json +10 -0
- train_results.json +9 -0
- trainer_state.json +921 -0
README.md
CHANGED
|
@@ -2,11 +2,23 @@
|
|
| 2 |
library_name: transformers
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
| 5 |
metrics:
|
| 6 |
- accuracy
|
| 7 |
model-index:
|
| 8 |
- name: bert_base_rand_20_v2
|
| 9 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -14,10 +26,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# bert_base_rand_20_v2
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [](https://huggingface.co/) on
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss:
|
| 20 |
-
- Accuracy: 0.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 2 |
library_name: transformers
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- Hartunka/processed_wikitext-103-raw-v1-rand-20_v2
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
| 9 |
model-index:
|
| 10 |
- name: bert_base_rand_20_v2
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Masked Language Modeling
|
| 14 |
+
type: fill-mask
|
| 15 |
+
dataset:
|
| 16 |
+
name: Hartunka/processed_wikitext-103-raw-v1-rand-20_v2
|
| 17 |
+
type: Hartunka/processed_wikitext-103-raw-v1-rand-20_v2
|
| 18 |
+
metrics:
|
| 19 |
+
- name: Accuracy
|
| 20 |
+
type: accuracy
|
| 21 |
+
value: 0.15350059332090185
|
| 22 |
---
|
| 23 |
|
| 24 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 26 |
|
| 27 |
# bert_base_rand_20_v2
|
| 28 |
|
| 29 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the Hartunka/processed_wikitext-103-raw-v1-rand-20_v2 dataset.
|
| 30 |
It achieves the following results on the evaluation set:
|
| 31 |
+
- Loss: 9.0856
|
| 32 |
+
- Accuracy: 0.1535
|
| 33 |
|
| 34 |
## Model description
|
| 35 |
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 25.0,
|
| 3 |
+
"eval_accuracy": 0.15350059332090185,
|
| 4 |
+
"eval_loss": 9.08564567565918,
|
| 5 |
+
"eval_runtime": 1.0357,
|
| 6 |
+
"eval_samples": 479,
|
| 7 |
+
"eval_samples_per_second": 462.482,
|
| 8 |
+
"eval_steps_per_second": 4.828,
|
| 9 |
+
"perplexity": 8827.663732722915,
|
| 10 |
+
"total_flos": 1.5151126801503744e+18,
|
| 11 |
+
"train_loss": 7.625829259710688,
|
| 12 |
+
"train_runtime": 24701.7833,
|
| 13 |
+
"train_samples": 228639,
|
| 14 |
+
"train_samples_per_second": 231.399,
|
| 15 |
+
"train_steps_per_second": 2.411
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 25.0,
|
| 3 |
+
"eval_accuracy": 0.15350059332090185,
|
| 4 |
+
"eval_loss": 9.08564567565918,
|
| 5 |
+
"eval_runtime": 1.0357,
|
| 6 |
+
"eval_samples": 479,
|
| 7 |
+
"eval_samples_per_second": 462.482,
|
| 8 |
+
"eval_steps_per_second": 4.828,
|
| 9 |
+
"perplexity": 8827.663732722915
|
| 10 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 25.0,
|
| 3 |
+
"total_flos": 1.5151126801503744e+18,
|
| 4 |
+
"train_loss": 7.625829259710688,
|
| 5 |
+
"train_runtime": 24701.7833,
|
| 6 |
+
"train_samples": 228639,
|
| 7 |
+
"train_samples_per_second": 231.399,
|
| 8 |
+
"train_steps_per_second": 2.411
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,921 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 10000,
|
| 3 |
+
"best_metric": 9.065109252929688,
|
| 4 |
+
"best_model_checkpoint": "bert_base_rand_20_v2/checkpoint-10000",
|
| 5 |
+
"epoch": 25.0,
|
| 6 |
+
"eval_steps": 10000,
|
| 7 |
+
"global_step": 59550,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.20990764063811923,
|
| 14 |
+
"grad_norm": 3.0308218002319336,
|
| 15 |
+
"learning_rate": 5e-06,
|
| 16 |
+
"loss": 12.1977,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.41981528127623846,
|
| 21 |
+
"grad_norm": 2.4327733516693115,
|
| 22 |
+
"learning_rate": 1e-05,
|
| 23 |
+
"loss": 10.5454,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.6297229219143576,
|
| 28 |
+
"grad_norm": 1.899172067642212,
|
| 29 |
+
"learning_rate": 1.5e-05,
|
| 30 |
+
"loss": 10.0079,
|
| 31 |
+
"step": 1500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.8396305625524769,
|
| 35 |
+
"grad_norm": 1.7947323322296143,
|
| 36 |
+
"learning_rate": 2e-05,
|
| 37 |
+
"loss": 9.8503,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.0495382031905962,
|
| 42 |
+
"grad_norm": 2.0414254665374756,
|
| 43 |
+
"learning_rate": 2.5e-05,
|
| 44 |
+
"loss": 9.7294,
|
| 45 |
+
"step": 2500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.2594458438287153,
|
| 49 |
+
"grad_norm": 2.25095272064209,
|
| 50 |
+
"learning_rate": 3e-05,
|
| 51 |
+
"loss": 9.6169,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.4693534844668346,
|
| 56 |
+
"grad_norm": 2.219564914703369,
|
| 57 |
+
"learning_rate": 3.5e-05,
|
| 58 |
+
"loss": 9.5259,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.6792611251049538,
|
| 63 |
+
"grad_norm": 1.8111666440963745,
|
| 64 |
+
"learning_rate": 4e-05,
|
| 65 |
+
"loss": 9.4574,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.8891687657430731,
|
| 70 |
+
"grad_norm": 2.3417046070098877,
|
| 71 |
+
"learning_rate": 4.5e-05,
|
| 72 |
+
"loss": 9.3995,
|
| 73 |
+
"step": 4500
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 2.0990764063811924,
|
| 77 |
+
"grad_norm": 2.3426718711853027,
|
| 78 |
+
"learning_rate": 5e-05,
|
| 79 |
+
"loss": 9.3492,
|
| 80 |
+
"step": 5000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.3089840470193117,
|
| 84 |
+
"grad_norm": 2.1550545692443848,
|
| 85 |
+
"learning_rate": 5.500000000000001e-05,
|
| 86 |
+
"loss": 9.3097,
|
| 87 |
+
"step": 5500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 2.5188916876574305,
|
| 91 |
+
"grad_norm": 2.569795846939087,
|
| 92 |
+
"learning_rate": 6e-05,
|
| 93 |
+
"loss": 9.2719,
|
| 94 |
+
"step": 6000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 2.72879932829555,
|
| 98 |
+
"grad_norm": 2.7756941318511963,
|
| 99 |
+
"learning_rate": 6.500000000000001e-05,
|
| 100 |
+
"loss": 9.2391,
|
| 101 |
+
"step": 6500
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 2.938706968933669,
|
| 105 |
+
"grad_norm": 2.712641477584839,
|
| 106 |
+
"learning_rate": 7e-05,
|
| 107 |
+
"loss": 9.209,
|
| 108 |
+
"step": 7000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 3.1486146095717884,
|
| 112 |
+
"grad_norm": 2.3369410037994385,
|
| 113 |
+
"learning_rate": 7.500000000000001e-05,
|
| 114 |
+
"loss": 9.1855,
|
| 115 |
+
"step": 7500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 3.3585222502099077,
|
| 119 |
+
"grad_norm": 2.314936399459839,
|
| 120 |
+
"learning_rate": 8e-05,
|
| 121 |
+
"loss": 9.1649,
|
| 122 |
+
"step": 8000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 3.568429890848027,
|
| 126 |
+
"grad_norm": 3.075246572494507,
|
| 127 |
+
"learning_rate": 8.5e-05,
|
| 128 |
+
"loss": 9.148,
|
| 129 |
+
"step": 8500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.7783375314861463,
|
| 133 |
+
"grad_norm": 3.077697515487671,
|
| 134 |
+
"learning_rate": 9e-05,
|
| 135 |
+
"loss": 9.1222,
|
| 136 |
+
"step": 9000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 3.988245172124265,
|
| 140 |
+
"grad_norm": 2.9913086891174316,
|
| 141 |
+
"learning_rate": 9.5e-05,
|
| 142 |
+
"loss": 9.1057,
|
| 143 |
+
"step": 9500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 4.198152812762385,
|
| 147 |
+
"grad_norm": 3.597776412963867,
|
| 148 |
+
"learning_rate": 0.0001,
|
| 149 |
+
"loss": 9.0594,
|
| 150 |
+
"step": 10000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 4.198152812762385,
|
| 154 |
+
"eval_accuracy": 0.15092239628258994,
|
| 155 |
+
"eval_loss": 9.065109252929688,
|
| 156 |
+
"eval_runtime": 1.0336,
|
| 157 |
+
"eval_samples_per_second": 463.438,
|
| 158 |
+
"eval_steps_per_second": 4.838,
|
| 159 |
+
"step": 10000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 4.408060453400504,
|
| 163 |
+
"grad_norm": 2.595629930496216,
|
| 164 |
+
"learning_rate": 9.899091826437942e-05,
|
| 165 |
+
"loss": 9.0438,
|
| 166 |
+
"step": 10500
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 4.617968094038623,
|
| 170 |
+
"grad_norm": 2.5200111865997314,
|
| 171 |
+
"learning_rate": 9.798183652875883e-05,
|
| 172 |
+
"loss": 9.0326,
|
| 173 |
+
"step": 11000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 4.827875734676742,
|
| 177 |
+
"grad_norm": 3.3044512271881104,
|
| 178 |
+
"learning_rate": 9.697275479313825e-05,
|
| 179 |
+
"loss": 9.0298,
|
| 180 |
+
"step": 11500
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 5.037783375314861,
|
| 184 |
+
"grad_norm": 3.339869499206543,
|
| 185 |
+
"learning_rate": 9.596367305751767e-05,
|
| 186 |
+
"loss": 8.9946,
|
| 187 |
+
"step": 12000
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 5.247691015952981,
|
| 191 |
+
"grad_norm": 3.565800666809082,
|
| 192 |
+
"learning_rate": 9.495459132189707e-05,
|
| 193 |
+
"loss": 8.8959,
|
| 194 |
+
"step": 12500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 5.4575986565911,
|
| 198 |
+
"grad_norm": 3.91796612739563,
|
| 199 |
+
"learning_rate": 9.394550958627649e-05,
|
| 200 |
+
"loss": 8.9122,
|
| 201 |
+
"step": 13000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 5.667506297229219,
|
| 205 |
+
"grad_norm": 3.0361363887786865,
|
| 206 |
+
"learning_rate": 9.293642785065591e-05,
|
| 207 |
+
"loss": 8.9154,
|
| 208 |
+
"step": 13500
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 5.877413937867338,
|
| 212 |
+
"grad_norm": 3.6139206886291504,
|
| 213 |
+
"learning_rate": 9.192734611503532e-05,
|
| 214 |
+
"loss": 8.9138,
|
| 215 |
+
"step": 14000
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 6.087321578505458,
|
| 219 |
+
"grad_norm": 3.5524585247039795,
|
| 220 |
+
"learning_rate": 9.091826437941474e-05,
|
| 221 |
+
"loss": 8.8435,
|
| 222 |
+
"step": 14500
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 6.297229219143577,
|
| 226 |
+
"grad_norm": 2.9967706203460693,
|
| 227 |
+
"learning_rate": 8.990918264379415e-05,
|
| 228 |
+
"loss": 8.7773,
|
| 229 |
+
"step": 15000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 6.507136859781696,
|
| 233 |
+
"grad_norm": 2.7934579849243164,
|
| 234 |
+
"learning_rate": 8.890010090817356e-05,
|
| 235 |
+
"loss": 8.7888,
|
| 236 |
+
"step": 15500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 6.717044500419815,
|
| 240 |
+
"grad_norm": 3.5226430892944336,
|
| 241 |
+
"learning_rate": 8.789101917255298e-05,
|
| 242 |
+
"loss": 8.8033,
|
| 243 |
+
"step": 16000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 6.926952141057934,
|
| 247 |
+
"grad_norm": 4.111179351806641,
|
| 248 |
+
"learning_rate": 8.68819374369324e-05,
|
| 249 |
+
"loss": 8.8123,
|
| 250 |
+
"step": 16500
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 7.136859781696054,
|
| 254 |
+
"grad_norm": 3.3247392177581787,
|
| 255 |
+
"learning_rate": 8.58728557013118e-05,
|
| 256 |
+
"loss": 8.6669,
|
| 257 |
+
"step": 17000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 7.346767422334173,
|
| 261 |
+
"grad_norm": 3.9535279273986816,
|
| 262 |
+
"learning_rate": 8.486377396569122e-05,
|
| 263 |
+
"loss": 8.6189,
|
| 264 |
+
"step": 17500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 7.5566750629722925,
|
| 268 |
+
"grad_norm": 3.8891823291778564,
|
| 269 |
+
"learning_rate": 8.385469223007064e-05,
|
| 270 |
+
"loss": 8.6515,
|
| 271 |
+
"step": 18000
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 7.766582703610411,
|
| 275 |
+
"grad_norm": 3.8274359703063965,
|
| 276 |
+
"learning_rate": 8.284561049445006e-05,
|
| 277 |
+
"loss": 8.6651,
|
| 278 |
+
"step": 18500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 7.97649034424853,
|
| 282 |
+
"grad_norm": 3.6684072017669678,
|
| 283 |
+
"learning_rate": 8.183652875882947e-05,
|
| 284 |
+
"loss": 8.6732,
|
| 285 |
+
"step": 19000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 8.18639798488665,
|
| 289 |
+
"grad_norm": 4.276801109313965,
|
| 290 |
+
"learning_rate": 8.082744702320889e-05,
|
| 291 |
+
"loss": 8.3804,
|
| 292 |
+
"step": 19500
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 8.39630562552477,
|
| 296 |
+
"grad_norm": 4.779017925262451,
|
| 297 |
+
"learning_rate": 7.98183652875883e-05,
|
| 298 |
+
"loss": 8.3784,
|
| 299 |
+
"step": 20000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 8.39630562552477,
|
| 303 |
+
"eval_accuracy": 0.1525295322539914,
|
| 304 |
+
"eval_loss": 9.502010345458984,
|
| 305 |
+
"eval_runtime": 1.0346,
|
| 306 |
+
"eval_samples_per_second": 462.997,
|
| 307 |
+
"eval_steps_per_second": 4.833,
|
| 308 |
+
"step": 20000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 8.606213266162888,
|
| 312 |
+
"grad_norm": 4.9919114112854,
|
| 313 |
+
"learning_rate": 7.880928355196771e-05,
|
| 314 |
+
"loss": 8.3976,
|
| 315 |
+
"step": 20500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 8.816120906801007,
|
| 319 |
+
"grad_norm": 5.021790504455566,
|
| 320 |
+
"learning_rate": 7.780020181634713e-05,
|
| 321 |
+
"loss": 8.4266,
|
| 322 |
+
"step": 21000
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 9.026028547439127,
|
| 326 |
+
"grad_norm": 6.880457401275635,
|
| 327 |
+
"learning_rate": 7.679112008072655e-05,
|
| 328 |
+
"loss": 8.3783,
|
| 329 |
+
"step": 21500
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 9.235936188077247,
|
| 333 |
+
"grad_norm": 6.020832538604736,
|
| 334 |
+
"learning_rate": 7.578203834510595e-05,
|
| 335 |
+
"loss": 8.0255,
|
| 336 |
+
"step": 22000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 9.445843828715365,
|
| 340 |
+
"grad_norm": 6.427469253540039,
|
| 341 |
+
"learning_rate": 7.477295660948537e-05,
|
| 342 |
+
"loss": 8.0499,
|
| 343 |
+
"step": 22500
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 9.655751469353484,
|
| 347 |
+
"grad_norm": 5.471770286560059,
|
| 348 |
+
"learning_rate": 7.376387487386479e-05,
|
| 349 |
+
"loss": 8.0971,
|
| 350 |
+
"step": 23000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 9.865659109991604,
|
| 354 |
+
"grad_norm": 6.466521263122559,
|
| 355 |
+
"learning_rate": 7.27547931382442e-05,
|
| 356 |
+
"loss": 8.0974,
|
| 357 |
+
"step": 23500
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 10.075566750629722,
|
| 361 |
+
"grad_norm": 5.689241409301758,
|
| 362 |
+
"learning_rate": 7.174571140262362e-05,
|
| 363 |
+
"loss": 7.9726,
|
| 364 |
+
"step": 24000
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 10.285474391267842,
|
| 368 |
+
"grad_norm": 5.892643451690674,
|
| 369 |
+
"learning_rate": 7.073662966700304e-05,
|
| 370 |
+
"loss": 7.746,
|
| 371 |
+
"step": 24500
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 10.495382031905962,
|
| 375 |
+
"grad_norm": 7.06170654296875,
|
| 376 |
+
"learning_rate": 6.972754793138244e-05,
|
| 377 |
+
"loss": 7.7692,
|
| 378 |
+
"step": 25000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 10.705289672544081,
|
| 382 |
+
"grad_norm": 7.507574081420898,
|
| 383 |
+
"learning_rate": 6.871846619576186e-05,
|
| 384 |
+
"loss": 7.8097,
|
| 385 |
+
"step": 25500
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 10.9151973131822,
|
| 389 |
+
"grad_norm": 7.282630920410156,
|
| 390 |
+
"learning_rate": 6.770938446014128e-05,
|
| 391 |
+
"loss": 7.8392,
|
| 392 |
+
"step": 26000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 11.125104953820319,
|
| 396 |
+
"grad_norm": 7.8448872566223145,
|
| 397 |
+
"learning_rate": 6.670030272452068e-05,
|
| 398 |
+
"loss": 7.6247,
|
| 399 |
+
"step": 26500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 11.335012594458439,
|
| 403 |
+
"grad_norm": 6.813558578491211,
|
| 404 |
+
"learning_rate": 6.56912209889001e-05,
|
| 405 |
+
"loss": 7.52,
|
| 406 |
+
"step": 27000
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 11.544920235096557,
|
| 410 |
+
"grad_norm": 5.603688716888428,
|
| 411 |
+
"learning_rate": 6.468213925327952e-05,
|
| 412 |
+
"loss": 7.5587,
|
| 413 |
+
"step": 27500
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 11.754827875734676,
|
| 417 |
+
"grad_norm": 8.152605056762695,
|
| 418 |
+
"learning_rate": 6.367305751765893e-05,
|
| 419 |
+
"loss": 7.5688,
|
| 420 |
+
"step": 28000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 11.964735516372796,
|
| 424 |
+
"grad_norm": 6.765694618225098,
|
| 425 |
+
"learning_rate": 6.266397578203835e-05,
|
| 426 |
+
"loss": 7.6036,
|
| 427 |
+
"step": 28500
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 12.174643157010916,
|
| 431 |
+
"grad_norm": 9.186474800109863,
|
| 432 |
+
"learning_rate": 6.165489404641777e-05,
|
| 433 |
+
"loss": 7.3235,
|
| 434 |
+
"step": 29000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 12.384550797649034,
|
| 438 |
+
"grad_norm": 8.772801399230957,
|
| 439 |
+
"learning_rate": 6.064581231079718e-05,
|
| 440 |
+
"loss": 7.2951,
|
| 441 |
+
"step": 29500
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 12.594458438287154,
|
| 445 |
+
"grad_norm": 9.275589942932129,
|
| 446 |
+
"learning_rate": 5.963673057517659e-05,
|
| 447 |
+
"loss": 7.3382,
|
| 448 |
+
"step": 30000
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 12.594458438287154,
|
| 452 |
+
"eval_accuracy": 0.15303466994991186,
|
| 453 |
+
"eval_loss": 10.855603218078613,
|
| 454 |
+
"eval_runtime": 1.0198,
|
| 455 |
+
"eval_samples_per_second": 469.721,
|
| 456 |
+
"eval_steps_per_second": 4.903,
|
| 457 |
+
"step": 30000
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 12.804366078925273,
|
| 461 |
+
"grad_norm": 7.982213020324707,
|
| 462 |
+
"learning_rate": 5.8627648839556e-05,
|
| 463 |
+
"loss": 7.3658,
|
| 464 |
+
"step": 30500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 13.014273719563391,
|
| 468 |
+
"grad_norm": 8.000374794006348,
|
| 469 |
+
"learning_rate": 5.7618567103935416e-05,
|
| 470 |
+
"loss": 7.3535,
|
| 471 |
+
"step": 31000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 13.224181360201511,
|
| 475 |
+
"grad_norm": 9.556083679199219,
|
| 476 |
+
"learning_rate": 5.660948536831484e-05,
|
| 477 |
+
"loss": 7.0701,
|
| 478 |
+
"step": 31500
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 13.43408900083963,
|
| 482 |
+
"grad_norm": 9.914329528808594,
|
| 483 |
+
"learning_rate": 5.5600403632694254e-05,
|
| 484 |
+
"loss": 7.1059,
|
| 485 |
+
"step": 32000
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 13.64399664147775,
|
| 489 |
+
"grad_norm": 7.568287372589111,
|
| 490 |
+
"learning_rate": 5.4591321897073666e-05,
|
| 491 |
+
"loss": 7.1469,
|
| 492 |
+
"step": 32500
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 13.853904282115868,
|
| 496 |
+
"grad_norm": 6.821398735046387,
|
| 497 |
+
"learning_rate": 5.358224016145308e-05,
|
| 498 |
+
"loss": 7.1523,
|
| 499 |
+
"step": 33000
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 14.063811922753988,
|
| 503 |
+
"grad_norm": 7.772975444793701,
|
| 504 |
+
"learning_rate": 5.257315842583249e-05,
|
| 505 |
+
"loss": 7.0788,
|
| 506 |
+
"step": 33500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 14.273719563392108,
|
| 510 |
+
"grad_norm": 9.745587348937988,
|
| 511 |
+
"learning_rate": 5.15640766902119e-05,
|
| 512 |
+
"loss": 6.8992,
|
| 513 |
+
"step": 34000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 14.483627204030226,
|
| 517 |
+
"grad_norm": 7.389908313751221,
|
| 518 |
+
"learning_rate": 5.055499495459133e-05,
|
| 519 |
+
"loss": 6.9267,
|
| 520 |
+
"step": 34500
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 14.693534844668346,
|
| 524 |
+
"grad_norm": 7.512205123901367,
|
| 525 |
+
"learning_rate": 4.954591321897074e-05,
|
| 526 |
+
"loss": 6.9509,
|
| 527 |
+
"step": 35000
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 14.903442485306465,
|
| 531 |
+
"grad_norm": 8.74570083618164,
|
| 532 |
+
"learning_rate": 4.853683148335015e-05,
|
| 533 |
+
"loss": 6.9629,
|
| 534 |
+
"step": 35500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 15.113350125944585,
|
| 538 |
+
"grad_norm": 9.084261894226074,
|
| 539 |
+
"learning_rate": 4.7527749747729566e-05,
|
| 540 |
+
"loss": 6.8317,
|
| 541 |
+
"step": 36000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 15.323257766582703,
|
| 545 |
+
"grad_norm": 8.2465238571167,
|
| 546 |
+
"learning_rate": 4.6518668012108985e-05,
|
| 547 |
+
"loss": 6.7407,
|
| 548 |
+
"step": 36500
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 15.533165407220823,
|
| 552 |
+
"grad_norm": 8.073356628417969,
|
| 553 |
+
"learning_rate": 4.55095862764884e-05,
|
| 554 |
+
"loss": 6.7606,
|
| 555 |
+
"step": 37000
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 15.743073047858942,
|
| 559 |
+
"grad_norm": 7.8887529373168945,
|
| 560 |
+
"learning_rate": 4.450050454086781e-05,
|
| 561 |
+
"loss": 6.7849,
|
| 562 |
+
"step": 37500
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 15.95298068849706,
|
| 566 |
+
"grad_norm": 10.014334678649902,
|
| 567 |
+
"learning_rate": 4.349142280524723e-05,
|
| 568 |
+
"loss": 6.8052,
|
| 569 |
+
"step": 38000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 16.162888329135182,
|
| 573 |
+
"grad_norm": 7.972960948944092,
|
| 574 |
+
"learning_rate": 4.248234106962664e-05,
|
| 575 |
+
"loss": 6.6332,
|
| 576 |
+
"step": 38500
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 16.3727959697733,
|
| 580 |
+
"grad_norm": 7.208271503448486,
|
| 581 |
+
"learning_rate": 4.147325933400605e-05,
|
| 582 |
+
"loss": 6.6161,
|
| 583 |
+
"step": 39000
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 16.582703610411418,
|
| 587 |
+
"grad_norm": 11.550618171691895,
|
| 588 |
+
"learning_rate": 4.046417759838547e-05,
|
| 589 |
+
"loss": 6.6255,
|
| 590 |
+
"step": 39500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 16.79261125104954,
|
| 594 |
+
"grad_norm": 9.207111358642578,
|
| 595 |
+
"learning_rate": 3.9455095862764884e-05,
|
| 596 |
+
"loss": 6.6369,
|
| 597 |
+
"step": 40000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 16.79261125104954,
|
| 601 |
+
"eval_accuracy": 0.1519849725243916,
|
| 602 |
+
"eval_loss": 11.952146530151367,
|
| 603 |
+
"eval_runtime": 1.0125,
|
| 604 |
+
"eval_samples_per_second": 473.089,
|
| 605 |
+
"eval_steps_per_second": 4.938,
|
| 606 |
+
"step": 40000
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 17.002518891687657,
|
| 610 |
+
"grad_norm": 7.137587070465088,
|
| 611 |
+
"learning_rate": 3.84460141271443e-05,
|
| 612 |
+
"loss": 6.6614,
|
| 613 |
+
"step": 40500
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 17.212426532325775,
|
| 617 |
+
"grad_norm": 8.455475807189941,
|
| 618 |
+
"learning_rate": 3.7436932391523715e-05,
|
| 619 |
+
"loss": 6.4812,
|
| 620 |
+
"step": 41000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 17.422334172963897,
|
| 624 |
+
"grad_norm": 9.873649597167969,
|
| 625 |
+
"learning_rate": 3.642785065590313e-05,
|
| 626 |
+
"loss": 6.5059,
|
| 627 |
+
"step": 41500
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 17.632241813602015,
|
| 631 |
+
"grad_norm": 8.446501731872559,
|
| 632 |
+
"learning_rate": 3.541876892028255e-05,
|
| 633 |
+
"loss": 6.5169,
|
| 634 |
+
"step": 42000
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 17.842149454240133,
|
| 638 |
+
"grad_norm": 7.7715606689453125,
|
| 639 |
+
"learning_rate": 3.440968718466196e-05,
|
| 640 |
+
"loss": 6.5316,
|
| 641 |
+
"step": 42500
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 18.052057094878254,
|
| 645 |
+
"grad_norm": 7.825333118438721,
|
| 646 |
+
"learning_rate": 3.340060544904137e-05,
|
| 647 |
+
"loss": 6.498,
|
| 648 |
+
"step": 43000
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 18.261964735516372,
|
| 652 |
+
"grad_norm": 8.917506217956543,
|
| 653 |
+
"learning_rate": 3.239152371342079e-05,
|
| 654 |
+
"loss": 6.4094,
|
| 655 |
+
"step": 43500
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 18.471872376154494,
|
| 659 |
+
"grad_norm": 8.458283424377441,
|
| 660 |
+
"learning_rate": 3.13824419778002e-05,
|
| 661 |
+
"loss": 6.4178,
|
| 662 |
+
"step": 44000
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 18.68178001679261,
|
| 666 |
+
"grad_norm": 8.396074295043945,
|
| 667 |
+
"learning_rate": 3.0373360242179615e-05,
|
| 668 |
+
"loss": 6.4292,
|
| 669 |
+
"step": 44500
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 18.89168765743073,
|
| 673 |
+
"grad_norm": 6.289218902587891,
|
| 674 |
+
"learning_rate": 2.9364278506559034e-05,
|
| 675 |
+
"loss": 6.4439,
|
| 676 |
+
"step": 45000
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 19.10159529806885,
|
| 680 |
+
"grad_norm": 9.249333381652832,
|
| 681 |
+
"learning_rate": 2.8355196770938446e-05,
|
| 682 |
+
"loss": 6.3816,
|
| 683 |
+
"step": 45500
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 19.31150293870697,
|
| 687 |
+
"grad_norm": 5.880438804626465,
|
| 688 |
+
"learning_rate": 2.734611503531786e-05,
|
| 689 |
+
"loss": 6.337,
|
| 690 |
+
"step": 46000
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 19.521410579345087,
|
| 694 |
+
"grad_norm": 9.66485595703125,
|
| 695 |
+
"learning_rate": 2.6337033299697278e-05,
|
| 696 |
+
"loss": 6.3425,
|
| 697 |
+
"step": 46500
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 19.73131821998321,
|
| 701 |
+
"grad_norm": 7.285576343536377,
|
| 702 |
+
"learning_rate": 2.532795156407669e-05,
|
| 703 |
+
"loss": 6.3536,
|
| 704 |
+
"step": 47000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 19.941225860621326,
|
| 708 |
+
"grad_norm": 8.842156410217285,
|
| 709 |
+
"learning_rate": 2.4318869828456106e-05,
|
| 710 |
+
"loss": 6.351,
|
| 711 |
+
"step": 47500
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 20.151133501259444,
|
| 715 |
+
"grad_norm": 8.728751182556152,
|
| 716 |
+
"learning_rate": 2.330978809283552e-05,
|
| 717 |
+
"loss": 6.3055,
|
| 718 |
+
"step": 48000
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 20.361041141897566,
|
| 722 |
+
"grad_norm": 7.451524257659912,
|
| 723 |
+
"learning_rate": 2.2300706357214934e-05,
|
| 724 |
+
"loss": 6.2863,
|
| 725 |
+
"step": 48500
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 20.570948782535684,
|
| 729 |
+
"grad_norm": 5.038097381591797,
|
| 730 |
+
"learning_rate": 2.129162462159435e-05,
|
| 731 |
+
"loss": 6.2799,
|
| 732 |
+
"step": 49000
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 20.7808564231738,
|
| 736 |
+
"grad_norm": 5.486204147338867,
|
| 737 |
+
"learning_rate": 2.0282542885973765e-05,
|
| 738 |
+
"loss": 6.2762,
|
| 739 |
+
"step": 49500
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 20.990764063811923,
|
| 743 |
+
"grad_norm": 7.932175159454346,
|
| 744 |
+
"learning_rate": 1.927346115035318e-05,
|
| 745 |
+
"loss": 6.2858,
|
| 746 |
+
"step": 50000
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 20.990764063811923,
|
| 750 |
+
"eval_accuracy": 0.1512602685956206,
|
| 751 |
+
"eval_loss": 12.46147346496582,
|
| 752 |
+
"eval_runtime": 1.0119,
|
| 753 |
+
"eval_samples_per_second": 473.349,
|
| 754 |
+
"eval_steps_per_second": 4.941,
|
| 755 |
+
"step": 50000
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 21.20067170445004,
|
| 759 |
+
"grad_norm": 7.7092485427856445,
|
| 760 |
+
"learning_rate": 1.8264379414732593e-05,
|
| 761 |
+
"loss": 6.2279,
|
| 762 |
+
"step": 50500
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 21.410579345088163,
|
| 766 |
+
"grad_norm": 9.494937896728516,
|
| 767 |
+
"learning_rate": 1.725529767911201e-05,
|
| 768 |
+
"loss": 6.2366,
|
| 769 |
+
"step": 51000
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 21.62048698572628,
|
| 773 |
+
"grad_norm": 9.652212142944336,
|
| 774 |
+
"learning_rate": 1.6246215943491424e-05,
|
| 775 |
+
"loss": 6.228,
|
| 776 |
+
"step": 51500
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 21.8303946263644,
|
| 780 |
+
"grad_norm": 5.58165979385376,
|
| 781 |
+
"learning_rate": 1.5237134207870837e-05,
|
| 782 |
+
"loss": 6.2309,
|
| 783 |
+
"step": 52000
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 22.04030226700252,
|
| 787 |
+
"grad_norm": 8.985339164733887,
|
| 788 |
+
"learning_rate": 1.4228052472250252e-05,
|
| 789 |
+
"loss": 6.2171,
|
| 790 |
+
"step": 52500
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 22.250209907640638,
|
| 794 |
+
"grad_norm": 7.544305801391602,
|
| 795 |
+
"learning_rate": 1.3218970736629668e-05,
|
| 796 |
+
"loss": 6.1848,
|
| 797 |
+
"step": 53000
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 22.460117548278756,
|
| 801 |
+
"grad_norm": 8.620584487915039,
|
| 802 |
+
"learning_rate": 1.2209889001009082e-05,
|
| 803 |
+
"loss": 6.1863,
|
| 804 |
+
"step": 53500
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 22.670025188916878,
|
| 808 |
+
"grad_norm": 8.475058555603027,
|
| 809 |
+
"learning_rate": 1.1200807265388496e-05,
|
| 810 |
+
"loss": 6.189,
|
| 811 |
+
"step": 54000
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 22.879932829554996,
|
| 815 |
+
"grad_norm": 4.212444305419922,
|
| 816 |
+
"learning_rate": 1.0191725529767912e-05,
|
| 817 |
+
"loss": 6.1791,
|
| 818 |
+
"step": 54500
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 23.089840470193113,
|
| 822 |
+
"grad_norm": 4.587650299072266,
|
| 823 |
+
"learning_rate": 9.182643794147326e-06,
|
| 824 |
+
"loss": 6.1679,
|
| 825 |
+
"step": 55000
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 23.299748110831235,
|
| 829 |
+
"grad_norm": 6.570645809173584,
|
| 830 |
+
"learning_rate": 8.173562058526741e-06,
|
| 831 |
+
"loss": 6.1543,
|
| 832 |
+
"step": 55500
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 23.509655751469353,
|
| 836 |
+
"grad_norm": 7.142970561981201,
|
| 837 |
+
"learning_rate": 7.164480322906156e-06,
|
| 838 |
+
"loss": 6.1603,
|
| 839 |
+
"step": 56000
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 23.719563392107474,
|
| 843 |
+
"grad_norm": 5.22387170791626,
|
| 844 |
+
"learning_rate": 6.155398587285571e-06,
|
| 845 |
+
"loss": 6.1463,
|
| 846 |
+
"step": 56500
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 23.929471032745592,
|
| 850 |
+
"grad_norm": 4.836696147918701,
|
| 851 |
+
"learning_rate": 5.146316851664986e-06,
|
| 852 |
+
"loss": 6.1529,
|
| 853 |
+
"step": 57000
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 24.13937867338371,
|
| 857 |
+
"grad_norm": 5.709256172180176,
|
| 858 |
+
"learning_rate": 4.1372351160444e-06,
|
| 859 |
+
"loss": 6.1382,
|
| 860 |
+
"step": 57500
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 24.349286314021832,
|
| 864 |
+
"grad_norm": 7.1039276123046875,
|
| 865 |
+
"learning_rate": 3.1281533804238145e-06,
|
| 866 |
+
"loss": 6.141,
|
| 867 |
+
"step": 58000
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 24.55919395465995,
|
| 871 |
+
"grad_norm": 4.547121047973633,
|
| 872 |
+
"learning_rate": 2.1190716448032293e-06,
|
| 873 |
+
"loss": 6.1454,
|
| 874 |
+
"step": 58500
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 24.769101595298068,
|
| 878 |
+
"grad_norm": 4.302024841308594,
|
| 879 |
+
"learning_rate": 1.109989909182644e-06,
|
| 880 |
+
"loss": 6.1342,
|
| 881 |
+
"step": 59000
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 24.97900923593619,
|
| 885 |
+
"grad_norm": 5.072787761688232,
|
| 886 |
+
"learning_rate": 1.0090817356205853e-07,
|
| 887 |
+
"loss": 6.1273,
|
| 888 |
+
"step": 59500
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 25.0,
|
| 892 |
+
"step": 59550,
|
| 893 |
+
"total_flos": 1.5151126801503744e+18,
|
| 894 |
+
"train_loss": 7.625829259710688,
|
| 895 |
+
"train_runtime": 24701.7833,
|
| 896 |
+
"train_samples_per_second": 231.399,
|
| 897 |
+
"train_steps_per_second": 2.411
|
| 898 |
+
}
|
| 899 |
+
],
|
| 900 |
+
"logging_steps": 500,
|
| 901 |
+
"max_steps": 59550,
|
| 902 |
+
"num_input_tokens_seen": 0,
|
| 903 |
+
"num_train_epochs": 25,
|
| 904 |
+
"save_steps": 10000,
|
| 905 |
+
"stateful_callbacks": {
|
| 906 |
+
"TrainerControl": {
|
| 907 |
+
"args": {
|
| 908 |
+
"should_epoch_stop": false,
|
| 909 |
+
"should_evaluate": false,
|
| 910 |
+
"should_log": false,
|
| 911 |
+
"should_save": true,
|
| 912 |
+
"should_training_stop": true
|
| 913 |
+
},
|
| 914 |
+
"attributes": {}
|
| 915 |
+
}
|
| 916 |
+
},
|
| 917 |
+
"total_flos": 1.5151126801503744e+18,
|
| 918 |
+
"train_batch_size": 96,
|
| 919 |
+
"trial_name": null,
|
| 920 |
+
"trial_params": null
|
| 921 |
+
}
|