End of training
Browse files- README.md +5 -0
- all_results.json +16 -0
- eval_results.json +10 -0
- runs/May05_14-44-01_41efdc5d42b0/events.out.tfevents.1746468922.41efdc5d42b0.95320.1 +3 -0
- train_results.json +9 -0
- trainer_state.json +1443 -0
README.md
CHANGED
|
@@ -3,6 +3,8 @@ library_name: transformers
|
|
| 3 |
base_model: castorini/afriberta_small
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: afriberta-ti-finetuned
|
| 8 |
results: []
|
|
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
# afriberta-ti-finetuned
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [castorini/afriberta_small](https://huggingface.co/castorini/afriberta_small) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 3 |
base_model: castorini/afriberta_small
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
model-index:
|
| 9 |
- name: afriberta-ti-finetuned
|
| 10 |
results: []
|
|
|
|
| 16 |
# afriberta-ti-finetuned
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [castorini/afriberta_small](https://huggingface.co/castorini/afriberta_small) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: nan
|
| 21 |
+
- Accuracy: 0.4430
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.4121545049831776,
|
| 3 |
+
"eval_accuracy": 0.44298179472842897,
|
| 4 |
+
"eval_loss": NaN,
|
| 5 |
+
"eval_runtime": 641.3922,
|
| 6 |
+
"eval_samples": 141626,
|
| 7 |
+
"eval_samples_per_second": 220.81,
|
| 8 |
+
"eval_steps_per_second": 55.203,
|
| 9 |
+
"perplexity": NaN,
|
| 10 |
+
"total_flos": 1.1173396591784448e+16,
|
| 11 |
+
"train_loss": 3.454826737060547,
|
| 12 |
+
"train_runtime": 11942.9392,
|
| 13 |
+
"train_samples": 1133010,
|
| 14 |
+
"train_samples_per_second": 133.97,
|
| 15 |
+
"train_steps_per_second": 8.373
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.4121545049831776,
|
| 3 |
+
"eval_accuracy": 0.44298179472842897,
|
| 4 |
+
"eval_loss": NaN,
|
| 5 |
+
"eval_runtime": 641.3922,
|
| 6 |
+
"eval_samples": 141626,
|
| 7 |
+
"eval_samples_per_second": 220.81,
|
| 8 |
+
"eval_steps_per_second": 55.203,
|
| 9 |
+
"perplexity": NaN
|
| 10 |
+
}
|
runs/May05_14-44-01_41efdc5d42b0/events.out.tfevents.1746468922.41efdc5d42b0.95320.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e03a71e3362fc2ad537a8974b30a144c61a6874a67b933e8ccba1ebbd13cec95
|
| 3 |
+
size 417
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.4121545049831776,
|
| 3 |
+
"total_flos": 1.1173396591784448e+16,
|
| 4 |
+
"train_loss": 3.454826737060547,
|
| 5 |
+
"train_runtime": 11942.9392,
|
| 6 |
+
"train_samples": 1133010,
|
| 7 |
+
"train_samples_per_second": 133.97,
|
| 8 |
+
"train_steps_per_second": 8.373
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1443 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.4121545049831776,
|
| 6 |
+
"eval_steps": 10000,
|
| 7 |
+
"global_step": 100000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.007060825481106996,
|
| 14 |
+
"grad_norm": 17.72658920288086,
|
| 15 |
+
"learning_rate": 9.920000000000002e-06,
|
| 16 |
+
"loss": 4.3846,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.014121650962213992,
|
| 21 |
+
"grad_norm": 20.74139976501465,
|
| 22 |
+
"learning_rate": 1.9920000000000002e-05,
|
| 23 |
+
"loss": 4.206,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.02118247644332099,
|
| 28 |
+
"grad_norm": 16.99892234802246,
|
| 29 |
+
"learning_rate": 1.989979797979798e-05,
|
| 30 |
+
"loss": 4.2092,
|
| 31 |
+
"step": 1500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.028243301924427984,
|
| 35 |
+
"grad_norm": 25.406461715698242,
|
| 36 |
+
"learning_rate": 1.979878787878788e-05,
|
| 37 |
+
"loss": 4.0983,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.03530412740553498,
|
| 42 |
+
"grad_norm": 18.238832473754883,
|
| 43 |
+
"learning_rate": 1.969777777777778e-05,
|
| 44 |
+
"loss": 4.0354,
|
| 45 |
+
"step": 2500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.04236495288664198,
|
| 49 |
+
"grad_norm": 16.974328994750977,
|
| 50 |
+
"learning_rate": 1.9596969696969698e-05,
|
| 51 |
+
"loss": 4.0445,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.049425778367748974,
|
| 56 |
+
"grad_norm": 15.910529136657715,
|
| 57 |
+
"learning_rate": 1.9495959595959597e-05,
|
| 58 |
+
"loss": 4.0171,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.05648660384885597,
|
| 63 |
+
"grad_norm": 14.3439359664917,
|
| 64 |
+
"learning_rate": 1.9394949494949497e-05,
|
| 65 |
+
"loss": 3.9674,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.06354742932996296,
|
| 70 |
+
"grad_norm": 23.51453399658203,
|
| 71 |
+
"learning_rate": 1.9293939393939396e-05,
|
| 72 |
+
"loss": 3.949,
|
| 73 |
+
"step": 4500
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.07060825481106996,
|
| 77 |
+
"grad_norm": 18.576505661010742,
|
| 78 |
+
"learning_rate": 1.9193131313131315e-05,
|
| 79 |
+
"loss": 3.9888,
|
| 80 |
+
"step": 5000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.07766908029217696,
|
| 84 |
+
"grad_norm": 14.903977394104004,
|
| 85 |
+
"learning_rate": 1.909212121212121e-05,
|
| 86 |
+
"loss": 3.9265,
|
| 87 |
+
"step": 5500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.08472990577328396,
|
| 91 |
+
"grad_norm": 16.43514633178711,
|
| 92 |
+
"learning_rate": 1.8991111111111114e-05,
|
| 93 |
+
"loss": 3.8921,
|
| 94 |
+
"step": 6000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.09179073125439095,
|
| 98 |
+
"grad_norm": 23.28466796875,
|
| 99 |
+
"learning_rate": 1.889010101010101e-05,
|
| 100 |
+
"loss": 3.9371,
|
| 101 |
+
"step": 6500
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.09885155673549795,
|
| 105 |
+
"grad_norm": 20.507205963134766,
|
| 106 |
+
"learning_rate": 1.878909090909091e-05,
|
| 107 |
+
"loss": 3.8411,
|
| 108 |
+
"step": 7000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.10591238221660494,
|
| 112 |
+
"grad_norm": 16.7827205657959,
|
| 113 |
+
"learning_rate": 1.868808080808081e-05,
|
| 114 |
+
"loss": 3.8232,
|
| 115 |
+
"step": 7500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.11297320769771194,
|
| 119 |
+
"grad_norm": 15.237981796264648,
|
| 120 |
+
"learning_rate": 1.858707070707071e-05,
|
| 121 |
+
"loss": 3.8742,
|
| 122 |
+
"step": 8000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.12003403317881893,
|
| 126 |
+
"grad_norm": 19.958890914916992,
|
| 127 |
+
"learning_rate": 1.8486262626262628e-05,
|
| 128 |
+
"loss": 3.8373,
|
| 129 |
+
"step": 8500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.12709485865992592,
|
| 133 |
+
"grad_norm": 17.775405883789062,
|
| 134 |
+
"learning_rate": 1.8385252525252527e-05,
|
| 135 |
+
"loss": 3.7978,
|
| 136 |
+
"step": 9000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.13415568414103293,
|
| 140 |
+
"grad_norm": 16.42775535583496,
|
| 141 |
+
"learning_rate": 1.8284242424242427e-05,
|
| 142 |
+
"loss": 3.8275,
|
| 143 |
+
"step": 9500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.1412165096221399,
|
| 147 |
+
"grad_norm": 15.955525398254395,
|
| 148 |
+
"learning_rate": 1.8183232323232326e-05,
|
| 149 |
+
"loss": 3.7711,
|
| 150 |
+
"step": 10000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.14827733510324692,
|
| 154 |
+
"grad_norm": 23.253620147705078,
|
| 155 |
+
"learning_rate": 1.8082222222222222e-05,
|
| 156 |
+
"loss": 3.7913,
|
| 157 |
+
"step": 10500
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.15533816058435393,
|
| 161 |
+
"grad_norm": 17.985246658325195,
|
| 162 |
+
"learning_rate": 1.7981212121212125e-05,
|
| 163 |
+
"loss": 3.8015,
|
| 164 |
+
"step": 11000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.1623989860654609,
|
| 168 |
+
"grad_norm": 18.045351028442383,
|
| 169 |
+
"learning_rate": 1.788020202020202e-05,
|
| 170 |
+
"loss": 3.7623,
|
| 171 |
+
"step": 11500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.16945981154656792,
|
| 175 |
+
"grad_norm": 14.922831535339355,
|
| 176 |
+
"learning_rate": 1.777919191919192e-05,
|
| 177 |
+
"loss": 3.7497,
|
| 178 |
+
"step": 12000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.1765206370276749,
|
| 182 |
+
"grad_norm": 13.136314392089844,
|
| 183 |
+
"learning_rate": 1.767838383838384e-05,
|
| 184 |
+
"loss": 3.7319,
|
| 185 |
+
"step": 12500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.1835814625087819,
|
| 189 |
+
"grad_norm": 18.23394775390625,
|
| 190 |
+
"learning_rate": 1.757737373737374e-05,
|
| 191 |
+
"loss": 3.7274,
|
| 192 |
+
"step": 13000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.1906422879898889,
|
| 196 |
+
"grad_norm": 17.231151580810547,
|
| 197 |
+
"learning_rate": 1.747636363636364e-05,
|
| 198 |
+
"loss": 3.6995,
|
| 199 |
+
"step": 13500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.1977031134709959,
|
| 203 |
+
"grad_norm": 20.387908935546875,
|
| 204 |
+
"learning_rate": 1.7375555555555558e-05,
|
| 205 |
+
"loss": 3.7243,
|
| 206 |
+
"step": 14000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.2047639389521029,
|
| 210 |
+
"grad_norm": 18.140853881835938,
|
| 211 |
+
"learning_rate": 1.7274545454545454e-05,
|
| 212 |
+
"loss": 3.7182,
|
| 213 |
+
"step": 14500
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.21182476443320988,
|
| 217 |
+
"grad_norm": 13.923667907714844,
|
| 218 |
+
"learning_rate": 1.7173535353535357e-05,
|
| 219 |
+
"loss": 3.7216,
|
| 220 |
+
"step": 15000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.2188855899143169,
|
| 224 |
+
"grad_norm": 19.91632843017578,
|
| 225 |
+
"learning_rate": 1.7072525252525253e-05,
|
| 226 |
+
"loss": 3.7033,
|
| 227 |
+
"step": 15500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.22594641539542387,
|
| 231 |
+
"grad_norm": 15.506410598754883,
|
| 232 |
+
"learning_rate": 1.6971515151515152e-05,
|
| 233 |
+
"loss": 3.6777,
|
| 234 |
+
"step": 16000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.23300724087653088,
|
| 238 |
+
"grad_norm": 16.471162796020508,
|
| 239 |
+
"learning_rate": 1.6870505050505052e-05,
|
| 240 |
+
"loss": 3.6762,
|
| 241 |
+
"step": 16500
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.24006806635763786,
|
| 245 |
+
"grad_norm": 13.96306324005127,
|
| 246 |
+
"learning_rate": 1.676949494949495e-05,
|
| 247 |
+
"loss": 3.6377,
|
| 248 |
+
"step": 17000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.24712889183874487,
|
| 252 |
+
"grad_norm": 18.485990524291992,
|
| 253 |
+
"learning_rate": 1.666848484848485e-05,
|
| 254 |
+
"loss": 3.6504,
|
| 255 |
+
"step": 17500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.25418971731985185,
|
| 259 |
+
"grad_norm": 14.49156665802002,
|
| 260 |
+
"learning_rate": 1.6567676767676767e-05,
|
| 261 |
+
"loss": 3.6563,
|
| 262 |
+
"step": 18000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.2612505428009589,
|
| 266 |
+
"grad_norm": 25.981748580932617,
|
| 267 |
+
"learning_rate": 1.646666666666667e-05,
|
| 268 |
+
"loss": 3.6884,
|
| 269 |
+
"step": 18500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.26831136828206587,
|
| 273 |
+
"grad_norm": 17.442602157592773,
|
| 274 |
+
"learning_rate": 1.6365656565656565e-05,
|
| 275 |
+
"loss": 3.6264,
|
| 276 |
+
"step": 19000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.27537219376317285,
|
| 280 |
+
"grad_norm": 17.210800170898438,
|
| 281 |
+
"learning_rate": 1.6264646464646465e-05,
|
| 282 |
+
"loss": 3.6124,
|
| 283 |
+
"step": 19500
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.2824330192442798,
|
| 287 |
+
"grad_norm": 15.370673179626465,
|
| 288 |
+
"learning_rate": 1.6163838383838387e-05,
|
| 289 |
+
"loss": 3.6067,
|
| 290 |
+
"step": 20000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.28949384472538686,
|
| 294 |
+
"grad_norm": 18.17014503479004,
|
| 295 |
+
"learning_rate": 1.6062828282828284e-05,
|
| 296 |
+
"loss": 3.5987,
|
| 297 |
+
"step": 20500
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.29655467020649384,
|
| 301 |
+
"grad_norm": 15.005146026611328,
|
| 302 |
+
"learning_rate": 1.5961818181818183e-05,
|
| 303 |
+
"loss": 3.6615,
|
| 304 |
+
"step": 21000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.3036154956876008,
|
| 308 |
+
"grad_norm": 18.63738441467285,
|
| 309 |
+
"learning_rate": 1.5860808080808082e-05,
|
| 310 |
+
"loss": 3.5629,
|
| 311 |
+
"step": 21500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.31067632116870786,
|
| 315 |
+
"grad_norm": 20.25809097290039,
|
| 316 |
+
"learning_rate": 1.576e-05,
|
| 317 |
+
"loss": 3.5566,
|
| 318 |
+
"step": 22000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.31773714664981484,
|
| 322 |
+
"grad_norm": 15.953923225402832,
|
| 323 |
+
"learning_rate": 1.56589898989899e-05,
|
| 324 |
+
"loss": 3.574,
|
| 325 |
+
"step": 22500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.3247979721309218,
|
| 329 |
+
"grad_norm": 16.332191467285156,
|
| 330 |
+
"learning_rate": 1.5557979797979797e-05,
|
| 331 |
+
"loss": 3.5761,
|
| 332 |
+
"step": 23000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.3318587976120288,
|
| 336 |
+
"grad_norm": 12.492526054382324,
|
| 337 |
+
"learning_rate": 1.54569696969697e-05,
|
| 338 |
+
"loss": 3.573,
|
| 339 |
+
"step": 23500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.33891962309313584,
|
| 343 |
+
"grad_norm": 15.54623031616211,
|
| 344 |
+
"learning_rate": 1.5355959595959596e-05,
|
| 345 |
+
"loss": 3.5607,
|
| 346 |
+
"step": 24000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.3459804485742428,
|
| 350 |
+
"grad_norm": 20.771549224853516,
|
| 351 |
+
"learning_rate": 1.5255151515151517e-05,
|
| 352 |
+
"loss": 3.5742,
|
| 353 |
+
"step": 24500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.3530412740553498,
|
| 357 |
+
"grad_norm": 13.80363655090332,
|
| 358 |
+
"learning_rate": 1.5154141414141415e-05,
|
| 359 |
+
"loss": 3.587,
|
| 360 |
+
"step": 25000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.36010209953645683,
|
| 364 |
+
"grad_norm": 22.49805450439453,
|
| 365 |
+
"learning_rate": 1.5053131313131316e-05,
|
| 366 |
+
"loss": 3.5951,
|
| 367 |
+
"step": 25500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.3671629250175638,
|
| 371 |
+
"grad_norm": 18.43703269958496,
|
| 372 |
+
"learning_rate": 1.4952121212121214e-05,
|
| 373 |
+
"loss": 3.549,
|
| 374 |
+
"step": 26000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.3742237504986708,
|
| 378 |
+
"grad_norm": 26.025529861450195,
|
| 379 |
+
"learning_rate": 1.4851313131313133e-05,
|
| 380 |
+
"loss": 3.5285,
|
| 381 |
+
"step": 26500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.3812845759797778,
|
| 385 |
+
"grad_norm": 17.635419845581055,
|
| 386 |
+
"learning_rate": 1.4750303030303032e-05,
|
| 387 |
+
"loss": 3.5189,
|
| 388 |
+
"step": 27000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.3883454014608848,
|
| 392 |
+
"grad_norm": 16.968599319458008,
|
| 393 |
+
"learning_rate": 1.4649292929292932e-05,
|
| 394 |
+
"loss": 3.5697,
|
| 395 |
+
"step": 27500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.3954062269419918,
|
| 399 |
+
"grad_norm": 19.92640495300293,
|
| 400 |
+
"learning_rate": 1.454828282828283e-05,
|
| 401 |
+
"loss": 3.5111,
|
| 402 |
+
"step": 28000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.40246705242309877,
|
| 406 |
+
"grad_norm": 15.327055931091309,
|
| 407 |
+
"learning_rate": 1.4447676767676768e-05,
|
| 408 |
+
"loss": 3.5431,
|
| 409 |
+
"step": 28500
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.4095278779042058,
|
| 413 |
+
"grad_norm": 20.179370880126953,
|
| 414 |
+
"learning_rate": 1.434666666666667e-05,
|
| 415 |
+
"loss": 3.512,
|
| 416 |
+
"step": 29000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.4165887033853128,
|
| 420 |
+
"grad_norm": 19.772951126098633,
|
| 421 |
+
"learning_rate": 1.4245656565656567e-05,
|
| 422 |
+
"loss": 3.5076,
|
| 423 |
+
"step": 29500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.42364952886641977,
|
| 427 |
+
"grad_norm": 14.148645401000977,
|
| 428 |
+
"learning_rate": 1.4144646464646465e-05,
|
| 429 |
+
"loss": 3.5435,
|
| 430 |
+
"step": 30000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.43071035434752675,
|
| 434 |
+
"grad_norm": 18.644636154174805,
|
| 435 |
+
"learning_rate": 1.4043636363636364e-05,
|
| 436 |
+
"loss": 3.4785,
|
| 437 |
+
"step": 30500
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.4377711798286338,
|
| 441 |
+
"grad_norm": 17.168704986572266,
|
| 442 |
+
"learning_rate": 1.3942828282828285e-05,
|
| 443 |
+
"loss": 3.4956,
|
| 444 |
+
"step": 31000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.44483200530974076,
|
| 448 |
+
"grad_norm": 19.559444427490234,
|
| 449 |
+
"learning_rate": 1.3841818181818183e-05,
|
| 450 |
+
"loss": 3.4984,
|
| 451 |
+
"step": 31500
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.45189283079084774,
|
| 455 |
+
"grad_norm": 13.651810646057129,
|
| 456 |
+
"learning_rate": 1.374080808080808e-05,
|
| 457 |
+
"loss": 3.5154,
|
| 458 |
+
"step": 32000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.4589536562719548,
|
| 462 |
+
"grad_norm": 14.946928977966309,
|
| 463 |
+
"learning_rate": 1.3639797979797982e-05,
|
| 464 |
+
"loss": 3.5427,
|
| 465 |
+
"step": 32500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.46601448175306176,
|
| 469 |
+
"grad_norm": 17.958921432495117,
|
| 470 |
+
"learning_rate": 1.353878787878788e-05,
|
| 471 |
+
"loss": 3.4956,
|
| 472 |
+
"step": 33000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.47307530723416874,
|
| 476 |
+
"grad_norm": 17.883209228515625,
|
| 477 |
+
"learning_rate": 1.343777777777778e-05,
|
| 478 |
+
"loss": 3.5101,
|
| 479 |
+
"step": 33500
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.4801361327152757,
|
| 483 |
+
"grad_norm": 14.099715232849121,
|
| 484 |
+
"learning_rate": 1.3336767676767677e-05,
|
| 485 |
+
"loss": 3.4633,
|
| 486 |
+
"step": 34000
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.48719695819638276,
|
| 490 |
+
"grad_norm": 18.380918502807617,
|
| 491 |
+
"learning_rate": 1.3235757575757578e-05,
|
| 492 |
+
"loss": 3.4568,
|
| 493 |
+
"step": 34500
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.49425778367748974,
|
| 497 |
+
"grad_norm": 15.116865158081055,
|
| 498 |
+
"learning_rate": 1.3134949494949496e-05,
|
| 499 |
+
"loss": 3.4707,
|
| 500 |
+
"step": 35000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.5013186091585967,
|
| 504 |
+
"grad_norm": 15.808046340942383,
|
| 505 |
+
"learning_rate": 1.3033939393939395e-05,
|
| 506 |
+
"loss": 3.4796,
|
| 507 |
+
"step": 35500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.5083794346397037,
|
| 511 |
+
"grad_norm": 13.205853462219238,
|
| 512 |
+
"learning_rate": 1.2932929292929294e-05,
|
| 513 |
+
"loss": 3.447,
|
| 514 |
+
"step": 36000
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.5154402601208107,
|
| 518 |
+
"grad_norm": 18.99825096130371,
|
| 519 |
+
"learning_rate": 1.2831919191919194e-05,
|
| 520 |
+
"loss": 3.462,
|
| 521 |
+
"step": 36500
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.5225010856019178,
|
| 525 |
+
"grad_norm": 15.703340530395508,
|
| 526 |
+
"learning_rate": 1.2731111111111111e-05,
|
| 527 |
+
"loss": 3.5031,
|
| 528 |
+
"step": 37000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.5295619110830248,
|
| 532 |
+
"grad_norm": 21.517732620239258,
|
| 533 |
+
"learning_rate": 1.2630101010101011e-05,
|
| 534 |
+
"loss": 3.4986,
|
| 535 |
+
"step": 37500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.5366227365641317,
|
| 539 |
+
"grad_norm": 16.335920333862305,
|
| 540 |
+
"learning_rate": 1.252909090909091e-05,
|
| 541 |
+
"loss": 3.4656,
|
| 542 |
+
"step": 38000
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.5436835620452387,
|
| 546 |
+
"grad_norm": 16.09105110168457,
|
| 547 |
+
"learning_rate": 1.242808080808081e-05,
|
| 548 |
+
"loss": 3.462,
|
| 549 |
+
"step": 38500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.5507443875263457,
|
| 553 |
+
"grad_norm": 18.461313247680664,
|
| 554 |
+
"learning_rate": 1.2327272727272727e-05,
|
| 555 |
+
"loss": 3.4566,
|
| 556 |
+
"step": 39000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.5578052130074527,
|
| 560 |
+
"grad_norm": 16.069425582885742,
|
| 561 |
+
"learning_rate": 1.2226464646464646e-05,
|
| 562 |
+
"loss": 3.4643,
|
| 563 |
+
"step": 39500
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.5648660384885597,
|
| 567 |
+
"grad_norm": 19.436756134033203,
|
| 568 |
+
"learning_rate": 1.2125454545454547e-05,
|
| 569 |
+
"loss": 3.4813,
|
| 570 |
+
"step": 40000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.5719268639696667,
|
| 574 |
+
"grad_norm": 17.705595016479492,
|
| 575 |
+
"learning_rate": 1.2024444444444445e-05,
|
| 576 |
+
"loss": 3.4515,
|
| 577 |
+
"step": 40500
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.5789876894507737,
|
| 581 |
+
"grad_norm": 16.269590377807617,
|
| 582 |
+
"learning_rate": 1.1923434343434343e-05,
|
| 583 |
+
"loss": 3.4066,
|
| 584 |
+
"step": 41000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.5860485149318807,
|
| 588 |
+
"grad_norm": 15.331748008728027,
|
| 589 |
+
"learning_rate": 1.1822626262626264e-05,
|
| 590 |
+
"loss": 3.4035,
|
| 591 |
+
"step": 41500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.5931093404129877,
|
| 595 |
+
"grad_norm": 14.219168663024902,
|
| 596 |
+
"learning_rate": 1.1721616161616163e-05,
|
| 597 |
+
"loss": 3.4631,
|
| 598 |
+
"step": 42000
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.6001701658940947,
|
| 602 |
+
"grad_norm": 15.630831718444824,
|
| 603 |
+
"learning_rate": 1.1620606060606061e-05,
|
| 604 |
+
"loss": 3.385,
|
| 605 |
+
"step": 42500
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.6072309913752016,
|
| 609 |
+
"grad_norm": 15.31431770324707,
|
| 610 |
+
"learning_rate": 1.1519595959595959e-05,
|
| 611 |
+
"loss": 3.4145,
|
| 612 |
+
"step": 43000
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.6142918168563086,
|
| 616 |
+
"grad_norm": 22.632341384887695,
|
| 617 |
+
"learning_rate": 1.141858585858586e-05,
|
| 618 |
+
"loss": 3.428,
|
| 619 |
+
"step": 43500
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.6213526423374157,
|
| 623 |
+
"grad_norm": 18.16883659362793,
|
| 624 |
+
"learning_rate": 1.1317575757575758e-05,
|
| 625 |
+
"loss": 3.4082,
|
| 626 |
+
"step": 44000
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.6284134678185227,
|
| 630 |
+
"grad_norm": 13.323620796203613,
|
| 631 |
+
"learning_rate": 1.1216565656565657e-05,
|
| 632 |
+
"loss": 3.4373,
|
| 633 |
+
"step": 44500
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.6354742932996297,
|
| 637 |
+
"grad_norm": 15.68764591217041,
|
| 638 |
+
"learning_rate": 1.1115555555555557e-05,
|
| 639 |
+
"loss": 3.4315,
|
| 640 |
+
"step": 45000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.6425351187807367,
|
| 644 |
+
"grad_norm": 18.161067962646484,
|
| 645 |
+
"learning_rate": 1.1014747474747476e-05,
|
| 646 |
+
"loss": 3.4019,
|
| 647 |
+
"step": 45500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.6495959442618436,
|
| 651 |
+
"grad_norm": 16.415048599243164,
|
| 652 |
+
"learning_rate": 1.0913737373737374e-05,
|
| 653 |
+
"loss": 3.4094,
|
| 654 |
+
"step": 46000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.6566567697429506,
|
| 658 |
+
"grad_norm": 15.824934959411621,
|
| 659 |
+
"learning_rate": 1.0812727272727273e-05,
|
| 660 |
+
"loss": 3.4408,
|
| 661 |
+
"step": 46500
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.6637175952240576,
|
| 665 |
+
"grad_norm": 14.806204795837402,
|
| 666 |
+
"learning_rate": 1.0711717171717173e-05,
|
| 667 |
+
"loss": 3.4002,
|
| 668 |
+
"step": 47000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.6707784207051647,
|
| 672 |
+
"grad_norm": 22.690622329711914,
|
| 673 |
+
"learning_rate": 1.0610707070707072e-05,
|
| 674 |
+
"loss": 3.4085,
|
| 675 |
+
"step": 47500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.6778392461862717,
|
| 679 |
+
"grad_norm": 13.887063026428223,
|
| 680 |
+
"learning_rate": 1.050969696969697e-05,
|
| 681 |
+
"loss": 3.3532,
|
| 682 |
+
"step": 48000
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.6849000716673787,
|
| 686 |
+
"grad_norm": 14.655476570129395,
|
| 687 |
+
"learning_rate": 1.0408686868686871e-05,
|
| 688 |
+
"loss": 3.3489,
|
| 689 |
+
"step": 48500
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.6919608971484856,
|
| 693 |
+
"grad_norm": 16.351926803588867,
|
| 694 |
+
"learning_rate": 1.0307676767676769e-05,
|
| 695 |
+
"loss": 3.3768,
|
| 696 |
+
"step": 49000
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.6990217226295926,
|
| 700 |
+
"grad_norm": 23.84049415588379,
|
| 701 |
+
"learning_rate": 1.0206868686868688e-05,
|
| 702 |
+
"loss": 3.3656,
|
| 703 |
+
"step": 49500
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.7060825481106996,
|
| 707 |
+
"grad_norm": 20.276376724243164,
|
| 708 |
+
"learning_rate": 1.0105858585858586e-05,
|
| 709 |
+
"loss": 3.3996,
|
| 710 |
+
"step": 50000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.7131433735918066,
|
| 714 |
+
"grad_norm": 19.38592529296875,
|
| 715 |
+
"learning_rate": 1.0004848484848487e-05,
|
| 716 |
+
"loss": 3.4112,
|
| 717 |
+
"step": 50500
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.7202041990729137,
|
| 721 |
+
"grad_norm": 17.104467391967773,
|
| 722 |
+
"learning_rate": 9.903838383838385e-06,
|
| 723 |
+
"loss": 3.3521,
|
| 724 |
+
"step": 51000
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.7272650245540206,
|
| 728 |
+
"grad_norm": 18.661767959594727,
|
| 729 |
+
"learning_rate": 9.802828282828284e-06,
|
| 730 |
+
"loss": 3.4185,
|
| 731 |
+
"step": 51500
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.7343258500351276,
|
| 735 |
+
"grad_norm": 17.60913848876953,
|
| 736 |
+
"learning_rate": 9.702020202020203e-06,
|
| 737 |
+
"loss": 3.3682,
|
| 738 |
+
"step": 52000
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.7413866755162346,
|
| 742 |
+
"grad_norm": 22.111852645874023,
|
| 743 |
+
"learning_rate": 9.601010101010103e-06,
|
| 744 |
+
"loss": 3.334,
|
| 745 |
+
"step": 52500
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.7484475009973416,
|
| 749 |
+
"grad_norm": 12.673060417175293,
|
| 750 |
+
"learning_rate": 9.5e-06,
|
| 751 |
+
"loss": 3.3648,
|
| 752 |
+
"step": 53000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.7555083264784486,
|
| 756 |
+
"grad_norm": 15.114596366882324,
|
| 757 |
+
"learning_rate": 9.3989898989899e-06,
|
| 758 |
+
"loss": 3.3536,
|
| 759 |
+
"step": 53500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.7625691519595555,
|
| 763 |
+
"grad_norm": 15.487835884094238,
|
| 764 |
+
"learning_rate": 9.298181818181819e-06,
|
| 765 |
+
"loss": 3.3503,
|
| 766 |
+
"step": 54000
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.7696299774406626,
|
| 770 |
+
"grad_norm": 18.261688232421875,
|
| 771 |
+
"learning_rate": 9.197171717171719e-06,
|
| 772 |
+
"loss": 3.3773,
|
| 773 |
+
"step": 54500
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.7766908029217696,
|
| 777 |
+
"grad_norm": 23.699548721313477,
|
| 778 |
+
"learning_rate": 9.096161616161618e-06,
|
| 779 |
+
"loss": 3.3165,
|
| 780 |
+
"step": 55000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.7837516284028766,
|
| 784 |
+
"grad_norm": 15.470009803771973,
|
| 785 |
+
"learning_rate": 8.995151515151516e-06,
|
| 786 |
+
"loss": 3.3609,
|
| 787 |
+
"step": 55500
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.7908124538839836,
|
| 791 |
+
"grad_norm": 16.061735153198242,
|
| 792 |
+
"learning_rate": 8.894141414141415e-06,
|
| 793 |
+
"loss": 3.3722,
|
| 794 |
+
"step": 56000
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.7978732793650906,
|
| 798 |
+
"grad_norm": 18.046903610229492,
|
| 799 |
+
"learning_rate": 8.793333333333334e-06,
|
| 800 |
+
"loss": 3.3175,
|
| 801 |
+
"step": 56500
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.8049341048461975,
|
| 805 |
+
"grad_norm": 15.547821998596191,
|
| 806 |
+
"learning_rate": 8.692323232323234e-06,
|
| 807 |
+
"loss": 3.3002,
|
| 808 |
+
"step": 57000
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.8119949303273045,
|
| 812 |
+
"grad_norm": 15.785500526428223,
|
| 813 |
+
"learning_rate": 8.591313131313132e-06,
|
| 814 |
+
"loss": 3.3243,
|
| 815 |
+
"step": 57500
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.8190557558084116,
|
| 819 |
+
"grad_norm": 19.183290481567383,
|
| 820 |
+
"learning_rate": 8.490303030303031e-06,
|
| 821 |
+
"loss": 3.3658,
|
| 822 |
+
"step": 58000
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.8261165812895186,
|
| 826 |
+
"grad_norm": 17.534652709960938,
|
| 827 |
+
"learning_rate": 8.38969696969697e-06,
|
| 828 |
+
"loss": 3.3541,
|
| 829 |
+
"step": 58500
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.8331774067706256,
|
| 833 |
+
"grad_norm": 14.905038833618164,
|
| 834 |
+
"learning_rate": 8.28868686868687e-06,
|
| 835 |
+
"loss": 3.3344,
|
| 836 |
+
"step": 59000
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.8402382322517326,
|
| 840 |
+
"grad_norm": 18.182802200317383,
|
| 841 |
+
"learning_rate": 8.187676767676769e-06,
|
| 842 |
+
"loss": 3.3364,
|
| 843 |
+
"step": 59500
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.8472990577328395,
|
| 847 |
+
"grad_norm": 18.967235565185547,
|
| 848 |
+
"learning_rate": 8.086666666666667e-06,
|
| 849 |
+
"loss": 3.3446,
|
| 850 |
+
"step": 60000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.8543598832139465,
|
| 854 |
+
"grad_norm": 18.88031768798828,
|
| 855 |
+
"learning_rate": 7.985656565656566e-06,
|
| 856 |
+
"loss": 3.3677,
|
| 857 |
+
"step": 60500
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.8614207086950535,
|
| 861 |
+
"grad_norm": 15.02967643737793,
|
| 862 |
+
"learning_rate": 7.884646464646466e-06,
|
| 863 |
+
"loss": 3.3527,
|
| 864 |
+
"step": 61000
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.8684815341761606,
|
| 868 |
+
"grad_norm": 13.849907875061035,
|
| 869 |
+
"learning_rate": 7.783636363636365e-06,
|
| 870 |
+
"loss": 3.3243,
|
| 871 |
+
"step": 61500
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.8755423596572676,
|
| 875 |
+
"grad_norm": 15.146381378173828,
|
| 876 |
+
"learning_rate": 7.682828282828282e-06,
|
| 877 |
+
"loss": 3.3019,
|
| 878 |
+
"step": 62000
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.8826031851383745,
|
| 882 |
+
"grad_norm": 20.377721786499023,
|
| 883 |
+
"learning_rate": 7.581818181818183e-06,
|
| 884 |
+
"loss": 3.3191,
|
| 885 |
+
"step": 62500
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.8896640106194815,
|
| 889 |
+
"grad_norm": 17.49558448791504,
|
| 890 |
+
"learning_rate": 7.480808080808082e-06,
|
| 891 |
+
"loss": 3.3441,
|
| 892 |
+
"step": 63000
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.8967248361005885,
|
| 896 |
+
"grad_norm": 16.852956771850586,
|
| 897 |
+
"learning_rate": 7.37979797979798e-06,
|
| 898 |
+
"loss": 3.2858,
|
| 899 |
+
"step": 63500
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.9037856615816955,
|
| 903 |
+
"grad_norm": 23.284814834594727,
|
| 904 |
+
"learning_rate": 7.2787878787878795e-06,
|
| 905 |
+
"loss": 3.2968,
|
| 906 |
+
"step": 64000
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.9108464870628025,
|
| 910 |
+
"grad_norm": 18.788135528564453,
|
| 911 |
+
"learning_rate": 7.177777777777778e-06,
|
| 912 |
+
"loss": 3.3394,
|
| 913 |
+
"step": 64500
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.9179073125439096,
|
| 917 |
+
"grad_norm": 15.641369819641113,
|
| 918 |
+
"learning_rate": 7.076767676767678e-06,
|
| 919 |
+
"loss": 3.3051,
|
| 920 |
+
"step": 65000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.9249681380250165,
|
| 924 |
+
"grad_norm": 37.24586486816406,
|
| 925 |
+
"learning_rate": 6.975757575757577e-06,
|
| 926 |
+
"loss": 3.3256,
|
| 927 |
+
"step": 65500
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.9320289635061235,
|
| 931 |
+
"grad_norm": 20.65641975402832,
|
| 932 |
+
"learning_rate": 6.874747474747475e-06,
|
| 933 |
+
"loss": 3.3239,
|
| 934 |
+
"step": 66000
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.9390897889872305,
|
| 938 |
+
"grad_norm": 16.292463302612305,
|
| 939 |
+
"learning_rate": 6.773939393939395e-06,
|
| 940 |
+
"loss": 3.2797,
|
| 941 |
+
"step": 66500
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.9461506144683375,
|
| 945 |
+
"grad_norm": 14.888529777526855,
|
| 946 |
+
"learning_rate": 6.673131313131314e-06,
|
| 947 |
+
"loss": 3.2913,
|
| 948 |
+
"step": 67000
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.9532114399494445,
|
| 952 |
+
"grad_norm": 17.32676887512207,
|
| 953 |
+
"learning_rate": 6.572121212121213e-06,
|
| 954 |
+
"loss": 3.2906,
|
| 955 |
+
"step": 67500
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.9602722654305514,
|
| 959 |
+
"grad_norm": 21.099210739135742,
|
| 960 |
+
"learning_rate": 6.471111111111111e-06,
|
| 961 |
+
"loss": 3.3143,
|
| 962 |
+
"step": 68000
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.9673330909116585,
|
| 966 |
+
"grad_norm": 20.450485229492188,
|
| 967 |
+
"learning_rate": 6.370101010101011e-06,
|
| 968 |
+
"loss": 3.2968,
|
| 969 |
+
"step": 68500
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.9743939163927655,
|
| 973 |
+
"grad_norm": 17.318950653076172,
|
| 974 |
+
"learning_rate": 6.269090909090909e-06,
|
| 975 |
+
"loss": 3.2946,
|
| 976 |
+
"step": 69000
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.9814547418738725,
|
| 980 |
+
"grad_norm": 18.73086929321289,
|
| 981 |
+
"learning_rate": 6.168080808080809e-06,
|
| 982 |
+
"loss": 3.303,
|
| 983 |
+
"step": 69500
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.9885155673549795,
|
| 987 |
+
"grad_norm": 18.808128356933594,
|
| 988 |
+
"learning_rate": 6.067070707070708e-06,
|
| 989 |
+
"loss": 3.2916,
|
| 990 |
+
"step": 70000
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.9955763928360865,
|
| 994 |
+
"grad_norm": 19.83098793029785,
|
| 995 |
+
"learning_rate": 5.966060606060606e-06,
|
| 996 |
+
"loss": 3.2576,
|
| 997 |
+
"step": 70500
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.0026266270789719,
|
| 1001 |
+
"grad_norm": 22.168275833129883,
|
| 1002 |
+
"learning_rate": 5.865252525252526e-06,
|
| 1003 |
+
"loss": 3.3076,
|
| 1004 |
+
"step": 71000
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.0096874525600787,
|
| 1008 |
+
"grad_norm": 14.332313537597656,
|
| 1009 |
+
"learning_rate": 5.764242424242425e-06,
|
| 1010 |
+
"loss": 3.2915,
|
| 1011 |
+
"step": 71500
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.0167482780411858,
|
| 1015 |
+
"grad_norm": 16.781579971313477,
|
| 1016 |
+
"learning_rate": 5.663232323232324e-06,
|
| 1017 |
+
"loss": 3.2836,
|
| 1018 |
+
"step": 72000
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.0238091035222927,
|
| 1022 |
+
"grad_norm": 18.176483154296875,
|
| 1023 |
+
"learning_rate": 5.562222222222222e-06,
|
| 1024 |
+
"loss": 3.2945,
|
| 1025 |
+
"step": 72500
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.0308699290033998,
|
| 1029 |
+
"grad_norm": 16.951435089111328,
|
| 1030 |
+
"learning_rate": 5.461414141414142e-06,
|
| 1031 |
+
"loss": 3.3042,
|
| 1032 |
+
"step": 73000
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.037930754484507,
|
| 1036 |
+
"grad_norm": 17.18007469177246,
|
| 1037 |
+
"learning_rate": 5.360404040404041e-06,
|
| 1038 |
+
"loss": 3.2748,
|
| 1039 |
+
"step": 73500
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.0449915799656138,
|
| 1043 |
+
"grad_norm": 15.710241317749023,
|
| 1044 |
+
"learning_rate": 5.25939393939394e-06,
|
| 1045 |
+
"loss": 3.2725,
|
| 1046 |
+
"step": 74000
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.0520524054467209,
|
| 1050 |
+
"grad_norm": 16.880611419677734,
|
| 1051 |
+
"learning_rate": 5.15858585858586e-06,
|
| 1052 |
+
"loss": 3.2747,
|
| 1053 |
+
"step": 74500
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.0591132309278277,
|
| 1057 |
+
"grad_norm": 14.415606498718262,
|
| 1058 |
+
"learning_rate": 5.057575757575758e-06,
|
| 1059 |
+
"loss": 3.2699,
|
| 1060 |
+
"step": 75000
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.0661740564089348,
|
| 1064 |
+
"grad_norm": 16.14620590209961,
|
| 1065 |
+
"learning_rate": 4.956565656565657e-06,
|
| 1066 |
+
"loss": 3.266,
|
| 1067 |
+
"step": 75500
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.0732348818900417,
|
| 1071 |
+
"grad_norm": 15.977879524230957,
|
| 1072 |
+
"learning_rate": 4.855555555555556e-06,
|
| 1073 |
+
"loss": 3.2763,
|
| 1074 |
+
"step": 76000
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.0802957073711488,
|
| 1078 |
+
"grad_norm": 21.809913635253906,
|
| 1079 |
+
"learning_rate": 4.754545454545455e-06,
|
| 1080 |
+
"loss": 3.3093,
|
| 1081 |
+
"step": 76500
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.0873565328522559,
|
| 1085 |
+
"grad_norm": 19.541011810302734,
|
| 1086 |
+
"learning_rate": 4.653535353535354e-06,
|
| 1087 |
+
"loss": 3.2863,
|
| 1088 |
+
"step": 77000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.0944173583333627,
|
| 1092 |
+
"grad_norm": 20.050395965576172,
|
| 1093 |
+
"learning_rate": 4.5525252525252525e-06,
|
| 1094 |
+
"loss": 3.2623,
|
| 1095 |
+
"step": 77500
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.1014781838144698,
|
| 1099 |
+
"grad_norm": 15.69351577758789,
|
| 1100 |
+
"learning_rate": 4.451515151515152e-06,
|
| 1101 |
+
"loss": 3.2633,
|
| 1102 |
+
"step": 78000
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.1085390092955767,
|
| 1106 |
+
"grad_norm": 17.333478927612305,
|
| 1107 |
+
"learning_rate": 4.350707070707071e-06,
|
| 1108 |
+
"loss": 3.2609,
|
| 1109 |
+
"step": 78500
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.1155998347766838,
|
| 1113 |
+
"grad_norm": 21.0096435546875,
|
| 1114 |
+
"learning_rate": 4.24989898989899e-06,
|
| 1115 |
+
"loss": 3.2834,
|
| 1116 |
+
"step": 79000
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.1226606602577907,
|
| 1120 |
+
"grad_norm": 18.113319396972656,
|
| 1121 |
+
"learning_rate": 4.148888888888889e-06,
|
| 1122 |
+
"loss": 3.2634,
|
| 1123 |
+
"step": 79500
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.1297214857388977,
|
| 1127 |
+
"grad_norm": 11.683279037475586,
|
| 1128 |
+
"learning_rate": 4.047878787878788e-06,
|
| 1129 |
+
"loss": 3.2916,
|
| 1130 |
+
"step": 80000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.1367823112200046,
|
| 1134 |
+
"grad_norm": 16.4996280670166,
|
| 1135 |
+
"learning_rate": 3.946868686868687e-06,
|
| 1136 |
+
"loss": 3.2395,
|
| 1137 |
+
"step": 80500
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.1438431367011117,
|
| 1141 |
+
"grad_norm": 16.545175552368164,
|
| 1142 |
+
"learning_rate": 3.845858585858586e-06,
|
| 1143 |
+
"loss": 3.2636,
|
| 1144 |
+
"step": 81000
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.1509039621822188,
|
| 1148 |
+
"grad_norm": 18.139225006103516,
|
| 1149 |
+
"learning_rate": 3.744848484848485e-06,
|
| 1150 |
+
"loss": 3.2226,
|
| 1151 |
+
"step": 81500
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.1579647876633257,
|
| 1155 |
+
"grad_norm": 18.051326751708984,
|
| 1156 |
+
"learning_rate": 3.643838383838384e-06,
|
| 1157 |
+
"loss": 3.2456,
|
| 1158 |
+
"step": 82000
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.1650256131444328,
|
| 1162 |
+
"grad_norm": 13.863969802856445,
|
| 1163 |
+
"learning_rate": 3.543030303030303e-06,
|
| 1164 |
+
"loss": 3.2267,
|
| 1165 |
+
"step": 82500
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.1720864386255396,
|
| 1169 |
+
"grad_norm": 18.651126861572266,
|
| 1170 |
+
"learning_rate": 3.442020202020202e-06,
|
| 1171 |
+
"loss": 3.2624,
|
| 1172 |
+
"step": 83000
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.1791472641066467,
|
| 1176 |
+
"grad_norm": 20.253204345703125,
|
| 1177 |
+
"learning_rate": 3.3410101010101017e-06,
|
| 1178 |
+
"loss": 3.2335,
|
| 1179 |
+
"step": 83500
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.1862080895877538,
|
| 1183 |
+
"grad_norm": 15.840412139892578,
|
| 1184 |
+
"learning_rate": 3.2400000000000003e-06,
|
| 1185 |
+
"loss": 3.2268,
|
| 1186 |
+
"step": 84000
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.1932689150688607,
|
| 1190 |
+
"grad_norm": 16.637964248657227,
|
| 1191 |
+
"learning_rate": 3.1389898989898994e-06,
|
| 1192 |
+
"loss": 3.2617,
|
| 1193 |
+
"step": 84500
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.2003297405499678,
|
| 1197 |
+
"grad_norm": 13.255701065063477,
|
| 1198 |
+
"learning_rate": 3.037979797979798e-06,
|
| 1199 |
+
"loss": 3.2882,
|
| 1200 |
+
"step": 85000
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.2073905660310746,
|
| 1204 |
+
"grad_norm": 18.700159072875977,
|
| 1205 |
+
"learning_rate": 2.936969696969697e-06,
|
| 1206 |
+
"loss": 3.245,
|
| 1207 |
+
"step": 85500
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.2144513915121817,
|
| 1211 |
+
"grad_norm": 15.274190902709961,
|
| 1212 |
+
"learning_rate": 2.8359595959595965e-06,
|
| 1213 |
+
"loss": 3.279,
|
| 1214 |
+
"step": 86000
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.2215122169932886,
|
| 1218 |
+
"grad_norm": 16.90398597717285,
|
| 1219 |
+
"learning_rate": 2.735151515151515e-06,
|
| 1220 |
+
"loss": 3.221,
|
| 1221 |
+
"step": 86500
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.2285730424743957,
|
| 1225 |
+
"grad_norm": 15.663399696350098,
|
| 1226 |
+
"learning_rate": 2.6343434343434343e-06,
|
| 1227 |
+
"loss": 3.2685,
|
| 1228 |
+
"step": 87000
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.2356338679555026,
|
| 1232 |
+
"grad_norm": 15.966713905334473,
|
| 1233 |
+
"learning_rate": 2.5333333333333338e-06,
|
| 1234 |
+
"loss": 3.2385,
|
| 1235 |
+
"step": 87500
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.2426946934366097,
|
| 1239 |
+
"grad_norm": 18.072582244873047,
|
| 1240 |
+
"learning_rate": 2.432323232323233e-06,
|
| 1241 |
+
"loss": 3.2613,
|
| 1242 |
+
"step": 88000
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.2497555189177167,
|
| 1246 |
+
"grad_norm": 13.807425498962402,
|
| 1247 |
+
"learning_rate": 2.3313131313131315e-06,
|
| 1248 |
+
"loss": 3.2489,
|
| 1249 |
+
"step": 88500
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.2568163443988236,
|
| 1253 |
+
"grad_norm": 22.68337059020996,
|
| 1254 |
+
"learning_rate": 2.2303030303030305e-06,
|
| 1255 |
+
"loss": 3.2249,
|
| 1256 |
+
"step": 89000
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.2638771698799307,
|
| 1260 |
+
"grad_norm": 17.15445327758789,
|
| 1261 |
+
"learning_rate": 2.1292929292929296e-06,
|
| 1262 |
+
"loss": 3.255,
|
| 1263 |
+
"step": 89500
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.2709379953610376,
|
| 1267 |
+
"grad_norm": 21.880109786987305,
|
| 1268 |
+
"learning_rate": 2.0282828282828286e-06,
|
| 1269 |
+
"loss": 3.2334,
|
| 1270 |
+
"step": 90000
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.2779988208421447,
|
| 1274 |
+
"grad_norm": 19.8821964263916,
|
| 1275 |
+
"learning_rate": 1.9272727272727273e-06,
|
| 1276 |
+
"loss": 3.2677,
|
| 1277 |
+
"step": 90500
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.2850596463232518,
|
| 1281 |
+
"grad_norm": 16.566150665283203,
|
| 1282 |
+
"learning_rate": 1.8264646464646466e-06,
|
| 1283 |
+
"loss": 3.2446,
|
| 1284 |
+
"step": 91000
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.2921204718043586,
|
| 1288 |
+
"grad_norm": 18.1463680267334,
|
| 1289 |
+
"learning_rate": 1.7254545454545456e-06,
|
| 1290 |
+
"loss": 3.2346,
|
| 1291 |
+
"step": 91500
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.2991812972854657,
|
| 1295 |
+
"grad_norm": 15.523479461669922,
|
| 1296 |
+
"learning_rate": 1.6244444444444447e-06,
|
| 1297 |
+
"loss": 3.261,
|
| 1298 |
+
"step": 92000
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.3062421227665726,
|
| 1302 |
+
"grad_norm": 16.982173919677734,
|
| 1303 |
+
"learning_rate": 1.5234343434343435e-06,
|
| 1304 |
+
"loss": 3.253,
|
| 1305 |
+
"step": 92500
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.3133029482476797,
|
| 1309 |
+
"grad_norm": 14.034078598022461,
|
| 1310 |
+
"learning_rate": 1.4226262626262626e-06,
|
| 1311 |
+
"loss": 3.2074,
|
| 1312 |
+
"step": 93000
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.3203637737287865,
|
| 1316 |
+
"grad_norm": 20.547330856323242,
|
| 1317 |
+
"learning_rate": 1.3216161616161619e-06,
|
| 1318 |
+
"loss": 3.2563,
|
| 1319 |
+
"step": 93500
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.3274245992098936,
|
| 1323 |
+
"grad_norm": 16.003023147583008,
|
| 1324 |
+
"learning_rate": 1.2206060606060607e-06,
|
| 1325 |
+
"loss": 3.2645,
|
| 1326 |
+
"step": 94000
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.3344854246910005,
|
| 1330 |
+
"grad_norm": 22.99709701538086,
|
| 1331 |
+
"learning_rate": 1.1195959595959596e-06,
|
| 1332 |
+
"loss": 3.2235,
|
| 1333 |
+
"step": 94500
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.3415462501721076,
|
| 1337 |
+
"grad_norm": 15.624763488769531,
|
| 1338 |
+
"learning_rate": 1.0187878787878789e-06,
|
| 1339 |
+
"loss": 3.2188,
|
| 1340 |
+
"step": 95000
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.3486070756532147,
|
| 1344 |
+
"grad_norm": 13.590816497802734,
|
| 1345 |
+
"learning_rate": 9.177777777777778e-07,
|
| 1346 |
+
"loss": 3.2178,
|
| 1347 |
+
"step": 95500
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.3556679011343216,
|
| 1351 |
+
"grad_norm": 16.545881271362305,
|
| 1352 |
+
"learning_rate": 8.167676767676769e-07,
|
| 1353 |
+
"loss": 3.2647,
|
| 1354 |
+
"step": 96000
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.3627287266154287,
|
| 1358 |
+
"grad_norm": 16.860748291015625,
|
| 1359 |
+
"learning_rate": 7.157575757575757e-07,
|
| 1360 |
+
"loss": 3.271,
|
| 1361 |
+
"step": 96500
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.3697895520965355,
|
| 1365 |
+
"grad_norm": 19.71615219116211,
|
| 1366 |
+
"learning_rate": 6.14949494949495e-07,
|
| 1367 |
+
"loss": 3.2211,
|
| 1368 |
+
"step": 97000
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.3768503775776426,
|
| 1372 |
+
"grad_norm": 14.094860076904297,
|
| 1373 |
+
"learning_rate": 5.13939393939394e-07,
|
| 1374 |
+
"loss": 3.2333,
|
| 1375 |
+
"step": 97500
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.3839112030587497,
|
| 1379 |
+
"grad_norm": 16.053531646728516,
|
| 1380 |
+
"learning_rate": 4.131313131313132e-07,
|
| 1381 |
+
"loss": 3.1983,
|
| 1382 |
+
"step": 98000
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.3909720285398566,
|
| 1386 |
+
"grad_norm": 19.86145782470703,
|
| 1387 |
+
"learning_rate": 3.1212121212121213e-07,
|
| 1388 |
+
"loss": 3.2367,
|
| 1389 |
+
"step": 98500
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.3980328540209637,
|
| 1393 |
+
"grad_norm": 16.2021427154541,
|
| 1394 |
+
"learning_rate": 2.1111111111111113e-07,
|
| 1395 |
+
"loss": 3.2032,
|
| 1396 |
+
"step": 99000
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.4050936795020705,
|
| 1400 |
+
"grad_norm": 16.72536849975586,
|
| 1401 |
+
"learning_rate": 1.101010101010101e-07,
|
| 1402 |
+
"loss": 3.2313,
|
| 1403 |
+
"step": 99500
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.4121545049831776,
|
| 1407 |
+
"grad_norm": 17.82211685180664,
|
| 1408 |
+
"learning_rate": 9.090909090909092e-09,
|
| 1409 |
+
"loss": 3.2355,
|
| 1410 |
+
"step": 100000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.4121545049831776,
|
| 1414 |
+
"step": 100000,
|
| 1415 |
+
"total_flos": 1.1173396591784448e+16,
|
| 1416 |
+
"train_loss": 3.454826737060547,
|
| 1417 |
+
"train_runtime": 11942.9392,
|
| 1418 |
+
"train_samples_per_second": 133.97,
|
| 1419 |
+
"train_steps_per_second": 8.373
|
| 1420 |
+
}
|
| 1421 |
+
],
|
| 1422 |
+
"logging_steps": 500,
|
| 1423 |
+
"max_steps": 100000,
|
| 1424 |
+
"num_input_tokens_seen": 0,
|
| 1425 |
+
"num_train_epochs": 2,
|
| 1426 |
+
"save_steps": 10000,
|
| 1427 |
+
"stateful_callbacks": {
|
| 1428 |
+
"TrainerControl": {
|
| 1429 |
+
"args": {
|
| 1430 |
+
"should_epoch_stop": false,
|
| 1431 |
+
"should_evaluate": false,
|
| 1432 |
+
"should_log": false,
|
| 1433 |
+
"should_save": true,
|
| 1434 |
+
"should_training_stop": true
|
| 1435 |
+
},
|
| 1436 |
+
"attributes": {}
|
| 1437 |
+
}
|
| 1438 |
+
},
|
| 1439 |
+
"total_flos": 1.1173396591784448e+16,
|
| 1440 |
+
"train_batch_size": 4,
|
| 1441 |
+
"trial_name": null,
|
| 1442 |
+
"trial_params": null
|
| 1443 |
+
}
|