Training in progress, epoch 1, checkpoint
Browse files
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86a1ccd9f7066dca55443398dffdd4e76ff6f9b9071f99d8222f75921367ac98
|
| 3 |
size 14244
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "./opt_trained3/checkpoint-
|
| 4 |
"epoch": 1.99898924928788,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 2720,
|
|
@@ -50,6 +50,14 @@
|
|
| 50 |
"learning_rate": 1.6054963006338742e-06,
|
| 51 |
"loss": 0.9047,
|
| 52 |
"step": 2500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
}
|
| 54 |
],
|
| 55 |
"logging_steps": 500,
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9013135433197021,
|
| 3 |
+
"best_model_checkpoint": "./opt_trained3/checkpoint-2720",
|
| 4 |
"epoch": 1.99898924928788,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 2720,
|
|
|
|
| 50 |
"learning_rate": 1.6054963006338742e-06,
|
| 51 |
"loss": 0.9047,
|
| 52 |
"step": 2500
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.99898924928788,
|
| 56 |
+
"eval_loss": 0.9013135433197021,
|
| 57 |
+
"eval_runtime": 765.3687,
|
| 58 |
+
"eval_samples_per_second": 50.557,
|
| 59 |
+
"eval_steps_per_second": 12.64,
|
| 60 |
+
"step": 2720
|
| 61 |
}
|
| 62 |
],
|
| 63 |
"logging_steps": 500,
|