End of training
Browse files- README.md +3 -1
- all_results.json +11 -0
- eval_results.json +6 -0
- train_results.json +8 -0
- trainer_state.json +1022 -0
README.md
CHANGED
|
@@ -3,6 +3,8 @@ base_model: google/vit-base-patch16-224-in21k
|
|
| 3 |
library_name: peft
|
| 4 |
license: apache-2.0
|
| 5 |
tags:
|
|
|
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
| 8 |
- name: only-lora-beans-vit-base-patch16-224-in21k
|
|
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# only-lora-beans-vit-base-patch16-224-in21k
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 3 |
library_name: peft
|
| 4 |
license: apache-2.0
|
| 5 |
tags:
|
| 6 |
+
- image-classification
|
| 7 |
+
- vision
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: only-lora-beans-vit-base-patch16-224-in21k
|
|
|
|
| 16 |
|
| 17 |
# only-lora-beans-vit-base-patch16-224-in21k
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the beans dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_runtime": 0.7743,
|
| 4 |
+
"eval_samples_per_second": 171.777,
|
| 5 |
+
"eval_steps_per_second": 21.956,
|
| 6 |
+
"total_flos": 8.400578669044531e+17,
|
| 7 |
+
"train_loss": 0.9780362775692573,
|
| 8 |
+
"train_runtime": 138.3381,
|
| 9 |
+
"train_samples_per_second": 74.744,
|
| 10 |
+
"train_steps_per_second": 9.397
|
| 11 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_runtime": 0.7743,
|
| 4 |
+
"eval_samples_per_second": 171.777,
|
| 5 |
+
"eval_steps_per_second": 21.956
|
| 6 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 8.400578669044531e+17,
|
| 4 |
+
"train_loss": 0.9780362775692573,
|
| 5 |
+
"train_runtime": 138.3381,
|
| 6 |
+
"train_samples_per_second": 74.744,
|
| 7 |
+
"train_steps_per_second": 9.397
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1022 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1300,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.07692307692307693,
|
| 13 |
+
"grad_norm": 2.0707900524139404,
|
| 14 |
+
"learning_rate": 0.004961538461538462,
|
| 15 |
+
"loss": 0.8561,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.15384615384615385,
|
| 20 |
+
"grad_norm": 0.9913710951805115,
|
| 21 |
+
"learning_rate": 0.004923076923076923,
|
| 22 |
+
"loss": 0.6755,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.23076923076923078,
|
| 27 |
+
"grad_norm": 1.5771081447601318,
|
| 28 |
+
"learning_rate": 0.004884615384615385,
|
| 29 |
+
"loss": 0.4032,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.3076923076923077,
|
| 34 |
+
"grad_norm": 1.9519121646881104,
|
| 35 |
+
"learning_rate": 0.004846153846153846,
|
| 36 |
+
"loss": 0.3903,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.38461538461538464,
|
| 41 |
+
"grad_norm": 2.557398796081543,
|
| 42 |
+
"learning_rate": 0.004807692307692308,
|
| 43 |
+
"loss": 0.5472,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.46153846153846156,
|
| 48 |
+
"grad_norm": 2.4644172191619873,
|
| 49 |
+
"learning_rate": 0.0047692307692307695,
|
| 50 |
+
"loss": 0.3894,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.5384615384615384,
|
| 55 |
+
"grad_norm": 1.2416399717330933,
|
| 56 |
+
"learning_rate": 0.004730769230769231,
|
| 57 |
+
"loss": 0.1827,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.6153846153846154,
|
| 62 |
+
"grad_norm": 0.8515920639038086,
|
| 63 |
+
"learning_rate": 0.004692307692307693,
|
| 64 |
+
"loss": 0.3148,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.6923076923076923,
|
| 69 |
+
"grad_norm": 0.227506622672081,
|
| 70 |
+
"learning_rate": 0.004653846153846154,
|
| 71 |
+
"loss": 0.237,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.7692307692307693,
|
| 76 |
+
"grad_norm": 2.7295713424682617,
|
| 77 |
+
"learning_rate": 0.004615384615384616,
|
| 78 |
+
"loss": 0.4501,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.8461538461538461,
|
| 83 |
+
"grad_norm": 1.2349276542663574,
|
| 84 |
+
"learning_rate": 0.0045769230769230765,
|
| 85 |
+
"loss": 0.6825,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.9230769230769231,
|
| 90 |
+
"grad_norm": 3.311713933944702,
|
| 91 |
+
"learning_rate": 0.004538461538461539,
|
| 92 |
+
"loss": 0.4085,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.0,
|
| 97 |
+
"grad_norm": 0.20723728835582733,
|
| 98 |
+
"learning_rate": 0.0045000000000000005,
|
| 99 |
+
"loss": 0.1292,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.0,
|
| 104 |
+
"eval_runtime": 0.7521,
|
| 105 |
+
"eval_samples_per_second": 176.836,
|
| 106 |
+
"eval_steps_per_second": 22.603,
|
| 107 |
+
"step": 130
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.0769230769230769,
|
| 111 |
+
"grad_norm": 1.5258536338806152,
|
| 112 |
+
"learning_rate": 0.004461538461538462,
|
| 113 |
+
"loss": 0.3389,
|
| 114 |
+
"step": 140
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.1538461538461537,
|
| 118 |
+
"grad_norm": 2.0288751125335693,
|
| 119 |
+
"learning_rate": 0.004423076923076923,
|
| 120 |
+
"loss": 0.2397,
|
| 121 |
+
"step": 150
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.2307692307692308,
|
| 125 |
+
"grad_norm": 0.03801692649722099,
|
| 126 |
+
"learning_rate": 0.004384615384615384,
|
| 127 |
+
"loss": 0.162,
|
| 128 |
+
"step": 160
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.3076923076923077,
|
| 132 |
+
"grad_norm": 0.1472761183977127,
|
| 133 |
+
"learning_rate": 0.004346153846153846,
|
| 134 |
+
"loss": 0.2687,
|
| 135 |
+
"step": 170
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.3846153846153846,
|
| 139 |
+
"grad_norm": 4.054047107696533,
|
| 140 |
+
"learning_rate": 0.004307692307692308,
|
| 141 |
+
"loss": 0.6044,
|
| 142 |
+
"step": 180
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.4615384615384617,
|
| 146 |
+
"grad_norm": 1.6007931232452393,
|
| 147 |
+
"learning_rate": 0.004269230769230769,
|
| 148 |
+
"loss": 0.6124,
|
| 149 |
+
"step": 190
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.5384615384615383,
|
| 153 |
+
"grad_norm": 0.15122832357883453,
|
| 154 |
+
"learning_rate": 0.004230769230769231,
|
| 155 |
+
"loss": 0.4298,
|
| 156 |
+
"step": 200
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.6153846153846154,
|
| 160 |
+
"grad_norm": 1.2161375284194946,
|
| 161 |
+
"learning_rate": 0.004192307692307692,
|
| 162 |
+
"loss": 0.5844,
|
| 163 |
+
"step": 210
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.6923076923076923,
|
| 167 |
+
"grad_norm": 7.478526592254639,
|
| 168 |
+
"learning_rate": 0.004153846153846154,
|
| 169 |
+
"loss": 1.2806,
|
| 170 |
+
"step": 220
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.7692307692307692,
|
| 174 |
+
"grad_norm": 1.2232049703598022,
|
| 175 |
+
"learning_rate": 0.004115384615384615,
|
| 176 |
+
"loss": 0.9687,
|
| 177 |
+
"step": 230
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.8461538461538463,
|
| 181 |
+
"grad_norm": 1.4465281963348389,
|
| 182 |
+
"learning_rate": 0.004076923076923077,
|
| 183 |
+
"loss": 0.4883,
|
| 184 |
+
"step": 240
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.9230769230769231,
|
| 188 |
+
"grad_norm": 3.471082925796509,
|
| 189 |
+
"learning_rate": 0.0040384615384615385,
|
| 190 |
+
"loss": 0.6709,
|
| 191 |
+
"step": 250
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.0,
|
| 195 |
+
"grad_norm": 2.699213981628418,
|
| 196 |
+
"learning_rate": 0.004,
|
| 197 |
+
"loss": 0.6404,
|
| 198 |
+
"step": 260
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.0,
|
| 202 |
+
"eval_runtime": 0.7652,
|
| 203 |
+
"eval_samples_per_second": 173.8,
|
| 204 |
+
"eval_steps_per_second": 22.215,
|
| 205 |
+
"step": 260
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 2.076923076923077,
|
| 209 |
+
"grad_norm": 1.1869909763336182,
|
| 210 |
+
"learning_rate": 0.003961538461538462,
|
| 211 |
+
"loss": 0.6565,
|
| 212 |
+
"step": 270
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.1538461538461537,
|
| 216 |
+
"grad_norm": 2.2662851810455322,
|
| 217 |
+
"learning_rate": 0.003923076923076923,
|
| 218 |
+
"loss": 0.3753,
|
| 219 |
+
"step": 280
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.230769230769231,
|
| 223 |
+
"grad_norm": 3.587059736251831,
|
| 224 |
+
"learning_rate": 0.003884615384615385,
|
| 225 |
+
"loss": 0.9706,
|
| 226 |
+
"step": 290
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.3076923076923075,
|
| 230 |
+
"grad_norm": 1.530928611755371,
|
| 231 |
+
"learning_rate": 0.0038461538461538464,
|
| 232 |
+
"loss": 1.2593,
|
| 233 |
+
"step": 300
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.3846153846153846,
|
| 237 |
+
"grad_norm": 1.0865129232406616,
|
| 238 |
+
"learning_rate": 0.0038076923076923075,
|
| 239 |
+
"loss": 0.9166,
|
| 240 |
+
"step": 310
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 2.4615384615384617,
|
| 244 |
+
"grad_norm": 2.3256101608276367,
|
| 245 |
+
"learning_rate": 0.003769230769230769,
|
| 246 |
+
"loss": 1.1882,
|
| 247 |
+
"step": 320
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 2.5384615384615383,
|
| 251 |
+
"grad_norm": 0.5831055045127869,
|
| 252 |
+
"learning_rate": 0.003730769230769231,
|
| 253 |
+
"loss": 1.2764,
|
| 254 |
+
"step": 330
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.6153846153846154,
|
| 258 |
+
"grad_norm": 0.9471529126167297,
|
| 259 |
+
"learning_rate": 0.0036923076923076927,
|
| 260 |
+
"loss": 1.349,
|
| 261 |
+
"step": 340
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.6923076923076925,
|
| 265 |
+
"grad_norm": 0.6033434867858887,
|
| 266 |
+
"learning_rate": 0.003653846153846154,
|
| 267 |
+
"loss": 1.1626,
|
| 268 |
+
"step": 350
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 2.769230769230769,
|
| 272 |
+
"grad_norm": 0.322643518447876,
|
| 273 |
+
"learning_rate": 0.0036153846153846154,
|
| 274 |
+
"loss": 1.1705,
|
| 275 |
+
"step": 360
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 2.8461538461538463,
|
| 279 |
+
"grad_norm": 0.6473853588104248,
|
| 280 |
+
"learning_rate": 0.003576923076923077,
|
| 281 |
+
"loss": 1.1492,
|
| 282 |
+
"step": 370
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 2.9230769230769234,
|
| 286 |
+
"grad_norm": 0.4563555121421814,
|
| 287 |
+
"learning_rate": 0.003538461538461539,
|
| 288 |
+
"loss": 1.1009,
|
| 289 |
+
"step": 380
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 3.0,
|
| 293 |
+
"grad_norm": 0.6773648858070374,
|
| 294 |
+
"learning_rate": 0.0034999999999999996,
|
| 295 |
+
"loss": 1.1322,
|
| 296 |
+
"step": 390
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.0,
|
| 300 |
+
"eval_runtime": 0.7629,
|
| 301 |
+
"eval_samples_per_second": 174.339,
|
| 302 |
+
"eval_steps_per_second": 22.284,
|
| 303 |
+
"step": 390
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 3.076923076923077,
|
| 307 |
+
"grad_norm": 0.499421089887619,
|
| 308 |
+
"learning_rate": 0.0034615384615384616,
|
| 309 |
+
"loss": 1.0926,
|
| 310 |
+
"step": 400
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 3.1538461538461537,
|
| 314 |
+
"grad_norm": 0.20487019419670105,
|
| 315 |
+
"learning_rate": 0.003423076923076923,
|
| 316 |
+
"loss": 1.129,
|
| 317 |
+
"step": 410
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 3.230769230769231,
|
| 321 |
+
"grad_norm": 0.5652111172676086,
|
| 322 |
+
"learning_rate": 0.003384615384615385,
|
| 323 |
+
"loss": 1.0965,
|
| 324 |
+
"step": 420
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 3.3076923076923075,
|
| 328 |
+
"grad_norm": 0.5159160494804382,
|
| 329 |
+
"learning_rate": 0.003346153846153846,
|
| 330 |
+
"loss": 1.0865,
|
| 331 |
+
"step": 430
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 3.3846153846153846,
|
| 335 |
+
"grad_norm": 0.5972450971603394,
|
| 336 |
+
"learning_rate": 0.0033076923076923075,
|
| 337 |
+
"loss": 1.1468,
|
| 338 |
+
"step": 440
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.4615384615384617,
|
| 342 |
+
"grad_norm": 0.4497612714767456,
|
| 343 |
+
"learning_rate": 0.0032692307692307695,
|
| 344 |
+
"loss": 1.0972,
|
| 345 |
+
"step": 450
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 3.5384615384615383,
|
| 349 |
+
"grad_norm": 0.8494599461555481,
|
| 350 |
+
"learning_rate": 0.003230769230769231,
|
| 351 |
+
"loss": 1.1196,
|
| 352 |
+
"step": 460
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 3.6153846153846154,
|
| 356 |
+
"grad_norm": 0.21025516092777252,
|
| 357 |
+
"learning_rate": 0.003192307692307692,
|
| 358 |
+
"loss": 1.1336,
|
| 359 |
+
"step": 470
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 3.6923076923076925,
|
| 363 |
+
"grad_norm": 0.5746878385543823,
|
| 364 |
+
"learning_rate": 0.0031538461538461538,
|
| 365 |
+
"loss": 1.0988,
|
| 366 |
+
"step": 480
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 3.769230769230769,
|
| 370 |
+
"grad_norm": 0.20434798300266266,
|
| 371 |
+
"learning_rate": 0.0031153846153846153,
|
| 372 |
+
"loss": 1.1101,
|
| 373 |
+
"step": 490
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 3.8461538461538463,
|
| 377 |
+
"grad_norm": 0.15725131332874298,
|
| 378 |
+
"learning_rate": 0.0030769230769230774,
|
| 379 |
+
"loss": 1.1133,
|
| 380 |
+
"step": 500
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 3.9230769230769234,
|
| 384 |
+
"grad_norm": 0.12141856551170349,
|
| 385 |
+
"learning_rate": 0.0030384615384615385,
|
| 386 |
+
"loss": 1.0987,
|
| 387 |
+
"step": 510
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 4.0,
|
| 391 |
+
"grad_norm": 1.1281518936157227,
|
| 392 |
+
"learning_rate": 0.003,
|
| 393 |
+
"loss": 1.1021,
|
| 394 |
+
"step": 520
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 4.0,
|
| 398 |
+
"eval_runtime": 0.7744,
|
| 399 |
+
"eval_samples_per_second": 171.736,
|
| 400 |
+
"eval_steps_per_second": 21.951,
|
| 401 |
+
"step": 520
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 4.076923076923077,
|
| 405 |
+
"grad_norm": 0.5692263841629028,
|
| 406 |
+
"learning_rate": 0.0029615384615384616,
|
| 407 |
+
"loss": 1.1032,
|
| 408 |
+
"step": 530
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 4.153846153846154,
|
| 412 |
+
"grad_norm": 0.21811030805110931,
|
| 413 |
+
"learning_rate": 0.002923076923076923,
|
| 414 |
+
"loss": 1.096,
|
| 415 |
+
"step": 540
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 4.230769230769231,
|
| 419 |
+
"grad_norm": 0.44653287529945374,
|
| 420 |
+
"learning_rate": 0.0028846153846153843,
|
| 421 |
+
"loss": 1.0986,
|
| 422 |
+
"step": 550
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 4.3076923076923075,
|
| 426 |
+
"grad_norm": 0.4496428966522217,
|
| 427 |
+
"learning_rate": 0.002846153846153846,
|
| 428 |
+
"loss": 1.1244,
|
| 429 |
+
"step": 560
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 4.384615384615385,
|
| 433 |
+
"grad_norm": 0.34072381258010864,
|
| 434 |
+
"learning_rate": 0.002807692307692308,
|
| 435 |
+
"loss": 1.0982,
|
| 436 |
+
"step": 570
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 4.461538461538462,
|
| 440 |
+
"grad_norm": 0.617884635925293,
|
| 441 |
+
"learning_rate": 0.0027692307692307695,
|
| 442 |
+
"loss": 1.1137,
|
| 443 |
+
"step": 580
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 4.538461538461538,
|
| 447 |
+
"grad_norm": 0.3251841068267822,
|
| 448 |
+
"learning_rate": 0.0027307692307692306,
|
| 449 |
+
"loss": 1.1054,
|
| 450 |
+
"step": 590
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 4.615384615384615,
|
| 454 |
+
"grad_norm": 0.11284901946783066,
|
| 455 |
+
"learning_rate": 0.002692307692307692,
|
| 456 |
+
"loss": 1.0981,
|
| 457 |
+
"step": 600
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 4.6923076923076925,
|
| 461 |
+
"grad_norm": 0.802207887172699,
|
| 462 |
+
"learning_rate": 0.0026538461538461538,
|
| 463 |
+
"loss": 1.1134,
|
| 464 |
+
"step": 610
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 4.769230769230769,
|
| 468 |
+
"grad_norm": 0.22614385187625885,
|
| 469 |
+
"learning_rate": 0.0026153846153846158,
|
| 470 |
+
"loss": 1.1155,
|
| 471 |
+
"step": 620
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 4.846153846153846,
|
| 475 |
+
"grad_norm": 0.3756657838821411,
|
| 476 |
+
"learning_rate": 0.002576923076923077,
|
| 477 |
+
"loss": 1.1113,
|
| 478 |
+
"step": 630
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 4.923076923076923,
|
| 482 |
+
"grad_norm": 0.6828984618186951,
|
| 483 |
+
"learning_rate": 0.0025384615384615385,
|
| 484 |
+
"loss": 1.1249,
|
| 485 |
+
"step": 640
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 5.0,
|
| 489 |
+
"grad_norm": 1.2701197862625122,
|
| 490 |
+
"learning_rate": 0.0025,
|
| 491 |
+
"loss": 1.102,
|
| 492 |
+
"step": 650
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 5.0,
|
| 496 |
+
"eval_runtime": 0.7836,
|
| 497 |
+
"eval_samples_per_second": 169.724,
|
| 498 |
+
"eval_steps_per_second": 21.694,
|
| 499 |
+
"step": 650
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 5.076923076923077,
|
| 503 |
+
"grad_norm": 0.30358830094337463,
|
| 504 |
+
"learning_rate": 0.0024615384615384616,
|
| 505 |
+
"loss": 1.1044,
|
| 506 |
+
"step": 660
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 5.153846153846154,
|
| 510 |
+
"grad_norm": 0.42961689829826355,
|
| 511 |
+
"learning_rate": 0.002423076923076923,
|
| 512 |
+
"loss": 1.0977,
|
| 513 |
+
"step": 670
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 5.230769230769231,
|
| 517 |
+
"grad_norm": 0.24340471625328064,
|
| 518 |
+
"learning_rate": 0.0023846153846153848,
|
| 519 |
+
"loss": 1.1379,
|
| 520 |
+
"step": 680
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 5.3076923076923075,
|
| 524 |
+
"grad_norm": 0.9648124575614929,
|
| 525 |
+
"learning_rate": 0.0023461538461538463,
|
| 526 |
+
"loss": 1.1314,
|
| 527 |
+
"step": 690
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 5.384615384615385,
|
| 531 |
+
"grad_norm": 0.6379570960998535,
|
| 532 |
+
"learning_rate": 0.002307692307692308,
|
| 533 |
+
"loss": 1.1104,
|
| 534 |
+
"step": 700
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 5.461538461538462,
|
| 538 |
+
"grad_norm": 0.32133665680885315,
|
| 539 |
+
"learning_rate": 0.0022692307692307695,
|
| 540 |
+
"loss": 1.1061,
|
| 541 |
+
"step": 710
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 5.538461538461538,
|
| 545 |
+
"grad_norm": 0.314644455909729,
|
| 546 |
+
"learning_rate": 0.002230769230769231,
|
| 547 |
+
"loss": 1.1035,
|
| 548 |
+
"step": 720
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 5.615384615384615,
|
| 552 |
+
"grad_norm": 0.4097970128059387,
|
| 553 |
+
"learning_rate": 0.002192307692307692,
|
| 554 |
+
"loss": 1.1035,
|
| 555 |
+
"step": 730
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 5.6923076923076925,
|
| 559 |
+
"grad_norm": 0.3651571273803711,
|
| 560 |
+
"learning_rate": 0.002153846153846154,
|
| 561 |
+
"loss": 1.1071,
|
| 562 |
+
"step": 740
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 5.769230769230769,
|
| 566 |
+
"grad_norm": 0.30447086691856384,
|
| 567 |
+
"learning_rate": 0.0021153846153846153,
|
| 568 |
+
"loss": 1.1048,
|
| 569 |
+
"step": 750
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 5.846153846153846,
|
| 573 |
+
"grad_norm": 0.35882461071014404,
|
| 574 |
+
"learning_rate": 0.002076923076923077,
|
| 575 |
+
"loss": 1.106,
|
| 576 |
+
"step": 760
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 5.923076923076923,
|
| 580 |
+
"grad_norm": 0.6777219772338867,
|
| 581 |
+
"learning_rate": 0.0020384615384615385,
|
| 582 |
+
"loss": 1.101,
|
| 583 |
+
"step": 770
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 6.0,
|
| 587 |
+
"grad_norm": 1.031847357749939,
|
| 588 |
+
"learning_rate": 0.002,
|
| 589 |
+
"loss": 1.1027,
|
| 590 |
+
"step": 780
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 6.0,
|
| 594 |
+
"eval_runtime": 0.7774,
|
| 595 |
+
"eval_samples_per_second": 171.09,
|
| 596 |
+
"eval_steps_per_second": 21.869,
|
| 597 |
+
"step": 780
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 6.076923076923077,
|
| 601 |
+
"grad_norm": 0.43265023827552795,
|
| 602 |
+
"learning_rate": 0.0019615384615384616,
|
| 603 |
+
"loss": 1.104,
|
| 604 |
+
"step": 790
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 6.153846153846154,
|
| 608 |
+
"grad_norm": 0.4353933334350586,
|
| 609 |
+
"learning_rate": 0.0019230769230769232,
|
| 610 |
+
"loss": 1.099,
|
| 611 |
+
"step": 800
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 6.230769230769231,
|
| 615 |
+
"grad_norm": 0.11455998569726944,
|
| 616 |
+
"learning_rate": 0.0018846153846153845,
|
| 617 |
+
"loss": 1.0985,
|
| 618 |
+
"step": 810
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 6.3076923076923075,
|
| 622 |
+
"grad_norm": 0.1155104711651802,
|
| 623 |
+
"learning_rate": 0.0018461538461538463,
|
| 624 |
+
"loss": 1.1026,
|
| 625 |
+
"step": 820
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 6.384615384615385,
|
| 629 |
+
"grad_norm": 0.44076037406921387,
|
| 630 |
+
"learning_rate": 0.0018076923076923077,
|
| 631 |
+
"loss": 1.0985,
|
| 632 |
+
"step": 830
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 6.461538461538462,
|
| 636 |
+
"grad_norm": 0.5386171936988831,
|
| 637 |
+
"learning_rate": 0.0017692307692307695,
|
| 638 |
+
"loss": 1.1025,
|
| 639 |
+
"step": 840
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 6.538461538461538,
|
| 643 |
+
"grad_norm": 0.611710786819458,
|
| 644 |
+
"learning_rate": 0.0017307692307692308,
|
| 645 |
+
"loss": 1.0992,
|
| 646 |
+
"step": 850
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 6.615384615384615,
|
| 650 |
+
"grad_norm": 0.2715957760810852,
|
| 651 |
+
"learning_rate": 0.0016923076923076924,
|
| 652 |
+
"loss": 1.1008,
|
| 653 |
+
"step": 860
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 6.6923076923076925,
|
| 657 |
+
"grad_norm": 0.4223721921443939,
|
| 658 |
+
"learning_rate": 0.0016538461538461537,
|
| 659 |
+
"loss": 1.089,
|
| 660 |
+
"step": 870
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 6.769230769230769,
|
| 664 |
+
"grad_norm": 0.14638401567935944,
|
| 665 |
+
"learning_rate": 0.0016153846153846155,
|
| 666 |
+
"loss": 1.1237,
|
| 667 |
+
"step": 880
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 6.846153846153846,
|
| 671 |
+
"grad_norm": 0.32549309730529785,
|
| 672 |
+
"learning_rate": 0.0015769230769230769,
|
| 673 |
+
"loss": 1.1031,
|
| 674 |
+
"step": 890
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 6.923076923076923,
|
| 678 |
+
"grad_norm": 0.4604528844356537,
|
| 679 |
+
"learning_rate": 0.0015384615384615387,
|
| 680 |
+
"loss": 1.1001,
|
| 681 |
+
"step": 900
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 7.0,
|
| 685 |
+
"grad_norm": 0.5566179156303406,
|
| 686 |
+
"learning_rate": 0.0015,
|
| 687 |
+
"loss": 1.0954,
|
| 688 |
+
"step": 910
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 7.0,
|
| 692 |
+
"eval_runtime": 0.7823,
|
| 693 |
+
"eval_samples_per_second": 170.021,
|
| 694 |
+
"eval_steps_per_second": 21.732,
|
| 695 |
+
"step": 910
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 7.076923076923077,
|
| 699 |
+
"grad_norm": 0.5109624266624451,
|
| 700 |
+
"learning_rate": 0.0014615384615384616,
|
| 701 |
+
"loss": 1.1043,
|
| 702 |
+
"step": 920
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 7.153846153846154,
|
| 706 |
+
"grad_norm": 0.5437686443328857,
|
| 707 |
+
"learning_rate": 0.001423076923076923,
|
| 708 |
+
"loss": 1.1055,
|
| 709 |
+
"step": 930
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 7.230769230769231,
|
| 713 |
+
"grad_norm": 0.6647012233734131,
|
| 714 |
+
"learning_rate": 0.0013846153846153847,
|
| 715 |
+
"loss": 1.1021,
|
| 716 |
+
"step": 940
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 7.3076923076923075,
|
| 720 |
+
"grad_norm": 0.4888548254966736,
|
| 721 |
+
"learning_rate": 0.001346153846153846,
|
| 722 |
+
"loss": 1.0968,
|
| 723 |
+
"step": 950
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 7.384615384615385,
|
| 727 |
+
"grad_norm": 0.26103150844573975,
|
| 728 |
+
"learning_rate": 0.0013076923076923079,
|
| 729 |
+
"loss": 1.104,
|
| 730 |
+
"step": 960
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 7.461538461538462,
|
| 734 |
+
"grad_norm": 0.2501744031906128,
|
| 735 |
+
"learning_rate": 0.0012692307692307692,
|
| 736 |
+
"loss": 1.1008,
|
| 737 |
+
"step": 970
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 7.538461538461538,
|
| 741 |
+
"grad_norm": 0.37639835476875305,
|
| 742 |
+
"learning_rate": 0.0012307692307692308,
|
| 743 |
+
"loss": 1.0998,
|
| 744 |
+
"step": 980
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 7.615384615384615,
|
| 748 |
+
"grad_norm": 0.23087725043296814,
|
| 749 |
+
"learning_rate": 0.0011923076923076924,
|
| 750 |
+
"loss": 1.0979,
|
| 751 |
+
"step": 990
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 7.6923076923076925,
|
| 755 |
+
"grad_norm": 0.3334718644618988,
|
| 756 |
+
"learning_rate": 0.001153846153846154,
|
| 757 |
+
"loss": 1.1068,
|
| 758 |
+
"step": 1000
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 7.769230769230769,
|
| 762 |
+
"grad_norm": 0.5154008865356445,
|
| 763 |
+
"learning_rate": 0.0011153846153846155,
|
| 764 |
+
"loss": 1.099,
|
| 765 |
+
"step": 1010
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 7.846153846153846,
|
| 769 |
+
"grad_norm": 0.2505805492401123,
|
| 770 |
+
"learning_rate": 0.001076923076923077,
|
| 771 |
+
"loss": 1.0985,
|
| 772 |
+
"step": 1020
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 7.923076923076923,
|
| 776 |
+
"grad_norm": 0.47592583298683167,
|
| 777 |
+
"learning_rate": 0.0010384615384615384,
|
| 778 |
+
"loss": 1.0968,
|
| 779 |
+
"step": 1030
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 8.0,
|
| 783 |
+
"grad_norm": 0.4868021309375763,
|
| 784 |
+
"learning_rate": 0.001,
|
| 785 |
+
"loss": 1.1047,
|
| 786 |
+
"step": 1040
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 8.0,
|
| 790 |
+
"eval_runtime": 0.7757,
|
| 791 |
+
"eval_samples_per_second": 171.462,
|
| 792 |
+
"eval_steps_per_second": 21.916,
|
| 793 |
+
"step": 1040
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 8.076923076923077,
|
| 797 |
+
"grad_norm": 0.12491131573915482,
|
| 798 |
+
"learning_rate": 0.0009615384615384616,
|
| 799 |
+
"loss": 1.0981,
|
| 800 |
+
"step": 1050
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 8.153846153846153,
|
| 804 |
+
"grad_norm": 0.23577113449573517,
|
| 805 |
+
"learning_rate": 0.0009230769230769232,
|
| 806 |
+
"loss": 1.0998,
|
| 807 |
+
"step": 1060
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 8.23076923076923,
|
| 811 |
+
"grad_norm": 0.12919014692306519,
|
| 812 |
+
"learning_rate": 0.0008846153846153847,
|
| 813 |
+
"loss": 1.098,
|
| 814 |
+
"step": 1070
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 8.307692307692308,
|
| 818 |
+
"grad_norm": 0.11554103344678879,
|
| 819 |
+
"learning_rate": 0.0008461538461538462,
|
| 820 |
+
"loss": 1.099,
|
| 821 |
+
"step": 1080
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 8.384615384615385,
|
| 825 |
+
"grad_norm": 0.3568715751171112,
|
| 826 |
+
"learning_rate": 0.0008076923076923078,
|
| 827 |
+
"loss": 1.0935,
|
| 828 |
+
"step": 1090
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 8.461538461538462,
|
| 832 |
+
"grad_norm": 0.4273003041744232,
|
| 833 |
+
"learning_rate": 0.0007692307692307693,
|
| 834 |
+
"loss": 1.1025,
|
| 835 |
+
"step": 1100
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 8.538461538461538,
|
| 839 |
+
"grad_norm": 0.11346741020679474,
|
| 840 |
+
"learning_rate": 0.0007307692307692308,
|
| 841 |
+
"loss": 1.1079,
|
| 842 |
+
"step": 1110
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 8.615384615384615,
|
| 846 |
+
"grad_norm": 0.5924614667892456,
|
| 847 |
+
"learning_rate": 0.0006923076923076924,
|
| 848 |
+
"loss": 1.095,
|
| 849 |
+
"step": 1120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 8.692307692307692,
|
| 853 |
+
"grad_norm": 0.8924316763877869,
|
| 854 |
+
"learning_rate": 0.0006538461538461539,
|
| 855 |
+
"loss": 1.0969,
|
| 856 |
+
"step": 1130
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 8.76923076923077,
|
| 860 |
+
"grad_norm": 0.14277611672878265,
|
| 861 |
+
"learning_rate": 0.0006153846153846154,
|
| 862 |
+
"loss": 1.112,
|
| 863 |
+
"step": 1140
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 8.846153846153847,
|
| 867 |
+
"grad_norm": 0.29049235582351685,
|
| 868 |
+
"learning_rate": 0.000576923076923077,
|
| 869 |
+
"loss": 1.0914,
|
| 870 |
+
"step": 1150
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 8.923076923076923,
|
| 874 |
+
"grad_norm": 0.5114134550094604,
|
| 875 |
+
"learning_rate": 0.0005384615384615385,
|
| 876 |
+
"loss": 1.1061,
|
| 877 |
+
"step": 1160
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 9.0,
|
| 881 |
+
"grad_norm": 1.142321228981018,
|
| 882 |
+
"learning_rate": 0.0005,
|
| 883 |
+
"loss": 1.1105,
|
| 884 |
+
"step": 1170
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 9.0,
|
| 888 |
+
"eval_runtime": 0.781,
|
| 889 |
+
"eval_samples_per_second": 170.284,
|
| 890 |
+
"eval_steps_per_second": 21.766,
|
| 891 |
+
"step": 1170
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 9.076923076923077,
|
| 895 |
+
"grad_norm": 0.12881995737552643,
|
| 896 |
+
"learning_rate": 0.0004615384615384616,
|
| 897 |
+
"loss": 1.0994,
|
| 898 |
+
"step": 1180
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 9.153846153846153,
|
| 902 |
+
"grad_norm": 0.12638165056705475,
|
| 903 |
+
"learning_rate": 0.0004230769230769231,
|
| 904 |
+
"loss": 1.0982,
|
| 905 |
+
"step": 1190
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 9.23076923076923,
|
| 909 |
+
"grad_norm": 0.13503584265708923,
|
| 910 |
+
"learning_rate": 0.00038461538461538467,
|
| 911 |
+
"loss": 1.0996,
|
| 912 |
+
"step": 1200
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 9.307692307692308,
|
| 916 |
+
"grad_norm": 0.23928503692150116,
|
| 917 |
+
"learning_rate": 0.0003461538461538462,
|
| 918 |
+
"loss": 1.1,
|
| 919 |
+
"step": 1210
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 9.384615384615385,
|
| 923 |
+
"grad_norm": 0.14712156355381012,
|
| 924 |
+
"learning_rate": 0.0003076923076923077,
|
| 925 |
+
"loss": 1.1033,
|
| 926 |
+
"step": 1220
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 9.461538461538462,
|
| 930 |
+
"grad_norm": 0.603887140750885,
|
| 931 |
+
"learning_rate": 0.0002692307692307693,
|
| 932 |
+
"loss": 1.0979,
|
| 933 |
+
"step": 1230
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 9.538461538461538,
|
| 937 |
+
"grad_norm": 0.34505996108055115,
|
| 938 |
+
"learning_rate": 0.0002307692307692308,
|
| 939 |
+
"loss": 1.0977,
|
| 940 |
+
"step": 1240
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 9.615384615384615,
|
| 944 |
+
"grad_norm": 0.11722344160079956,
|
| 945 |
+
"learning_rate": 0.00019230769230769233,
|
| 946 |
+
"loss": 1.1001,
|
| 947 |
+
"step": 1250
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 9.692307692307692,
|
| 951 |
+
"grad_norm": 0.33938324451446533,
|
| 952 |
+
"learning_rate": 0.00015384615384615385,
|
| 953 |
+
"loss": 1.0988,
|
| 954 |
+
"step": 1260
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 9.76923076923077,
|
| 958 |
+
"grad_norm": 0.1380094438791275,
|
| 959 |
+
"learning_rate": 0.0001153846153846154,
|
| 960 |
+
"loss": 1.1004,
|
| 961 |
+
"step": 1270
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 9.846153846153847,
|
| 965 |
+
"grad_norm": 0.2527919411659241,
|
| 966 |
+
"learning_rate": 7.692307692307693e-05,
|
| 967 |
+
"loss": 1.0999,
|
| 968 |
+
"step": 1280
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 9.923076923076923,
|
| 972 |
+
"grad_norm": 0.316256582736969,
|
| 973 |
+
"learning_rate": 3.846153846153846e-05,
|
| 974 |
+
"loss": 1.0984,
|
| 975 |
+
"step": 1290
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 10.0,
|
| 979 |
+
"grad_norm": 0.4816994071006775,
|
| 980 |
+
"learning_rate": 0.0,
|
| 981 |
+
"loss": 1.0979,
|
| 982 |
+
"step": 1300
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 10.0,
|
| 986 |
+
"eval_runtime": 0.7911,
|
| 987 |
+
"eval_samples_per_second": 168.13,
|
| 988 |
+
"eval_steps_per_second": 21.49,
|
| 989 |
+
"step": 1300
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 10.0,
|
| 993 |
+
"step": 1300,
|
| 994 |
+
"total_flos": 8.400578669044531e+17,
|
| 995 |
+
"train_loss": 0.9780362775692573,
|
| 996 |
+
"train_runtime": 138.3381,
|
| 997 |
+
"train_samples_per_second": 74.744,
|
| 998 |
+
"train_steps_per_second": 9.397
|
| 999 |
+
}
|
| 1000 |
+
],
|
| 1001 |
+
"logging_steps": 10,
|
| 1002 |
+
"max_steps": 1300,
|
| 1003 |
+
"num_input_tokens_seen": 0,
|
| 1004 |
+
"num_train_epochs": 10,
|
| 1005 |
+
"save_steps": 500,
|
| 1006 |
+
"stateful_callbacks": {
|
| 1007 |
+
"TrainerControl": {
|
| 1008 |
+
"args": {
|
| 1009 |
+
"should_epoch_stop": false,
|
| 1010 |
+
"should_evaluate": false,
|
| 1011 |
+
"should_log": false,
|
| 1012 |
+
"should_save": true,
|
| 1013 |
+
"should_training_stop": true
|
| 1014 |
+
},
|
| 1015 |
+
"attributes": {}
|
| 1016 |
+
}
|
| 1017 |
+
},
|
| 1018 |
+
"total_flos": 8.400578669044531e+17,
|
| 1019 |
+
"train_batch_size": 8,
|
| 1020 |
+
"trial_name": null,
|
| 1021 |
+
"trial_params": null
|
| 1022 |
+
}
|