Training in progress, step 850, 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:e83263567214655c30e9de674bae203cbfd6d760382de25ffcb86f93ea6c25f7
|
| 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 sha256:4a5e5c91a5da01fde4acb3c24e39adce8f436560182dda0439f2702de9ff20de
|
| 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:aa201faf54332a1cf6e01faad3149abdb4f41ea0aa94449c949cfda9032fd5f9
|
| 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": 6.
|
| 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,
|
|
@@ -1520,6 +1520,24 @@
|
|
| 1520 |
"mean_token_accuracy": 0.653452581167221,
|
| 1521 |
"num_tokens": 3064572.0,
|
| 1522 |
"step": 840
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1523 |
}
|
| 1524 |
],
|
| 1525 |
"logging_steps": 5,
|
|
@@ -1539,7 +1557,7 @@
|
|
| 1539 |
"attributes": {}
|
| 1540 |
}
|
| 1541 |
},
|
| 1542 |
-
"total_flos": 1.
|
| 1543 |
"train_batch_size": 4,
|
| 1544 |
"trial_name": null,
|
| 1545 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 6.538461538461538,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 850,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1520 |
"mean_token_accuracy": 0.653452581167221,
|
| 1521 |
"num_tokens": 3064572.0,
|
| 1522 |
"step": 840
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 6.5,
|
| 1526 |
+
"grad_norm": 0.0,
|
| 1527 |
+
"learning_rate": 4.578e-05,
|
| 1528 |
+
"loss": 1.7867,
|
| 1529 |
+
"mean_token_accuracy": 0.6452230870723724,
|
| 1530 |
+
"num_tokens": 3081959.0,
|
| 1531 |
+
"step": 845
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 6.538461538461538,
|
| 1535 |
+
"grad_norm": 0.0,
|
| 1536 |
+
"learning_rate": 4.5755000000000005e-05,
|
| 1537 |
+
"loss": 1.7674,
|
| 1538 |
+
"mean_token_accuracy": 0.6463764935731888,
|
| 1539 |
+
"num_tokens": 3100123.0,
|
| 1540 |
+
"step": 850
|
| 1541 |
}
|
| 1542 |
],
|
| 1543 |
"logging_steps": 5,
|
|
|
|
| 1557 |
"attributes": {}
|
| 1558 |
}
|
| 1559 |
},
|
| 1560 |
+
"total_flos": 1.5707179408048128e+17,
|
| 1561 |
"train_batch_size": 4,
|
| 1562 |
"trial_name": null,
|
| 1563 |
"trial_params": null
|