Training in progress, step 9260, 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 sha256:003ce190c4deafe6575695714fe5a89f83274f0831eac3b63804eee0c4050922
|
| 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:c57a8fff28fbdc1570a681ae28bf29fa65238ea7d106ca8437a55fbe65a41584
|
| 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 sha256:40091b875cf1a924bca90a9e2883d3506a56af798786e8eedba7e4bb34b00822
|
| 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": 71.
|
| 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,
|
|
@@ -16658,6 +16658,24 @@
|
|
| 16658 |
"mean_token_accuracy": 0.657853615283966,
|
| 16659 |
"num_tokens": 33734029.0,
|
| 16660 |
"step": 9250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16661 |
}
|
| 16662 |
],
|
| 16663 |
"logging_steps": 5,
|
|
@@ -16677,7 +16695,7 @@
|
|
| 16677 |
"attributes": {}
|
| 16678 |
}
|
| 16679 |
},
|
| 16680 |
-
"total_flos": 1.
|
| 16681 |
"train_batch_size": 4,
|
| 16682 |
"trial_name": null,
|
| 16683 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 71.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9260,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16658 |
"mean_token_accuracy": 0.657853615283966,
|
| 16659 |
"num_tokens": 33734029.0,
|
| 16660 |
"step": 9250
|
| 16661 |
+
},
|
| 16662 |
+
{
|
| 16663 |
+
"epoch": 71.1923076923077,
|
| 16664 |
+
"grad_norm": 0.0,
|
| 16665 |
+
"learning_rate": 3.7300000000000003e-06,
|
| 16666 |
+
"loss": 1.7182,
|
| 16667 |
+
"mean_token_accuracy": 0.653509646654129,
|
| 16668 |
+
"num_tokens": 33752377.0,
|
| 16669 |
+
"step": 9255
|
| 16670 |
+
},
|
| 16671 |
+
{
|
| 16672 |
+
"epoch": 71.23076923076923,
|
| 16673 |
+
"grad_norm": 0.0,
|
| 16674 |
+
"learning_rate": 3.705e-06,
|
| 16675 |
+
"loss": 1.7218,
|
| 16676 |
+
"mean_token_accuracy": 0.6558929115533829,
|
| 16677 |
+
"num_tokens": 33770568.0,
|
| 16678 |
+
"step": 9260
|
| 16679 |
}
|
| 16680 |
],
|
| 16681 |
"logging_steps": 5,
|
|
|
|
| 16695 |
"attributes": {}
|
| 16696 |
}
|
| 16697 |
},
|
| 16698 |
+
"total_flos": 1.712432457081815e+18,
|
| 16699 |
"train_batch_size": 4,
|
| 16700 |
"trial_name": null,
|
| 16701 |
"trial_params": null
|