Training in progress, step 4740, 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:b829eca3c6fd8cb634458e2fdbce9b504bb9736ec7ac1d8458ad04741da24bef
|
| 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:e706ec763c2eed231c1bc9374df18e46808ed70394cf23068d3422a489746cf3
|
| 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 sha256:9a45046a17080e0213f42306f0f71f661d824e8f67b5eac246082d522be24bfe
|
| 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": 36.
|
| 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,
|
|
@@ -8522,6 +8522,24 @@
|
|
| 8522 |
"mean_token_accuracy": 0.6517761409282684,
|
| 8523 |
"num_tokens": 17250069.0,
|
| 8524 |
"step": 4730
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8525 |
}
|
| 8526 |
],
|
| 8527 |
"logging_steps": 5,
|
|
@@ -8541,7 +8559,7 @@
|
|
| 8541 |
"attributes": {}
|
| 8542 |
}
|
| 8543 |
},
|
| 8544 |
-
"total_flos": 8.
|
| 8545 |
"train_batch_size": 4,
|
| 8546 |
"trial_name": null,
|
| 8547 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 36.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4740,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8522 |
"mean_token_accuracy": 0.6517761409282684,
|
| 8523 |
"num_tokens": 17250069.0,
|
| 8524 |
"step": 4730
|
| 8525 |
+
},
|
| 8526 |
+
{
|
| 8527 |
+
"epoch": 36.42307692307692,
|
| 8528 |
+
"grad_norm": 0.0,
|
| 8529 |
+
"learning_rate": 2.633e-05,
|
| 8530 |
+
"loss": 1.7795,
|
| 8531 |
+
"mean_token_accuracy": 0.63814417719841,
|
| 8532 |
+
"num_tokens": 17267793.0,
|
| 8533 |
+
"step": 4735
|
| 8534 |
+
},
|
| 8535 |
+
{
|
| 8536 |
+
"epoch": 36.46153846153846,
|
| 8537 |
+
"grad_norm": 0.0,
|
| 8538 |
+
"learning_rate": 2.6305000000000003e-05,
|
| 8539 |
+
"loss": 1.7513,
|
| 8540 |
+
"mean_token_accuracy": 0.6479008972644806,
|
| 8541 |
+
"num_tokens": 17285956.0,
|
| 8542 |
+
"step": 4740
|
| 8543 |
}
|
| 8544 |
],
|
| 8545 |
"logging_steps": 5,
|
|
|
|
| 8559 |
"attributes": {}
|
| 8560 |
}
|
| 8561 |
},
|
| 8562 |
+
"total_flos": 8.760305957584896e+17,
|
| 8563 |
"train_batch_size": 4,
|
| 8564 |
"trial_name": null,
|
| 8565 |
"trial_params": null
|