Training in progress, step 5280, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3988d5d0cbc9769761f949e510a344e8e23dc9b36b87c9781d7d44eabd5baaac
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b7c4ba981284725b4ca522af3ecc78c2ba37134106c11c9bb868d4b8080cb6a
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8df12c399806849125e135c7f1c477ecfede8e81af59026c801eeec196a70bd
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 40.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -9494,6 +9494,24 @@
|
|
| 9494 |
"mean_token_accuracy": 0.6603842228651047,
|
| 9495 |
"num_tokens": 19217073.0,
|
| 9496 |
"step": 5270
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9497 |
}
|
| 9498 |
],
|
| 9499 |
"logging_steps": 5,
|
|
@@ -9513,7 +9531,7 @@
|
|
| 9513 |
"attributes": {}
|
| 9514 |
}
|
| 9515 |
},
|
| 9516 |
-
"total_flos": 9.
|
| 9517 |
"train_batch_size": 4,
|
| 9518 |
"trial_name": null,
|
| 9519 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 40.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5280,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9494 |
"mean_token_accuracy": 0.6603842228651047,
|
| 9495 |
"num_tokens": 19217073.0,
|
| 9496 |
"step": 5270
|
| 9497 |
+
},
|
| 9498 |
+
{
|
| 9499 |
+
"epoch": 40.57692307692308,
|
| 9500 |
+
"grad_norm": 0.0,
|
| 9501 |
+
"learning_rate": 2.3630000000000002e-05,
|
| 9502 |
+
"loss": 1.7213,
|
| 9503 |
+
"mean_token_accuracy": 0.6537799417972565,
|
| 9504 |
+
"num_tokens": 19235609.0,
|
| 9505 |
+
"step": 5275
|
| 9506 |
+
},
|
| 9507 |
+
{
|
| 9508 |
+
"epoch": 40.61538461538461,
|
| 9509 |
+
"grad_norm": 0.0,
|
| 9510 |
+
"learning_rate": 2.3605000000000002e-05,
|
| 9511 |
+
"loss": 1.6618,
|
| 9512 |
+
"mean_token_accuracy": 0.664988386631012,
|
| 9513 |
+
"num_tokens": 19254738.0,
|
| 9514 |
+
"step": 5280
|
| 9515 |
}
|
| 9516 |
],
|
| 9517 |
"logging_steps": 5,
|
|
|
|
| 9531 |
"attributes": {}
|
| 9532 |
}
|
| 9533 |
},
|
| 9534 |
+
"total_flos": 9.756884856751718e+17,
|
| 9535 |
"train_batch_size": 4,
|
| 9536 |
"trial_name": null,
|
| 9537 |
"trial_params": null
|