Training in progress, step 2000, 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 sha256:0b4ced2be054748846e09d40604ab0bbfed2d348afbfb2d39d79452259824577
|
| 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:b565966e80ea0b4b7ad1688ae2266dd1a548749ef2561512d00ae453e42bf553
|
| 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 sha256:270ff03fe084f987f8343d2c8f19d38bbe977bf141126fcfe118a31f05d9430f
|
| 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": 15.
|
| 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,
|
|
@@ -3590,6 +3590,24 @@
|
|
| 3590 |
"mean_token_accuracy": 0.6466970533132553,
|
| 3591 |
"num_tokens": 7255192.0,
|
| 3592 |
"step": 1990
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3593 |
}
|
| 3594 |
],
|
| 3595 |
"logging_steps": 5,
|
|
@@ -3609,7 +3627,7 @@
|
|
| 3609 |
"attributes": {}
|
| 3610 |
}
|
| 3611 |
},
|
| 3612 |
-
"total_flos": 3.
|
| 3613 |
"train_batch_size": 4,
|
| 3614 |
"trial_name": null,
|
| 3615 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 15.384615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3590 |
"mean_token_accuracy": 0.6466970533132553,
|
| 3591 |
"num_tokens": 7255192.0,
|
| 3592 |
"step": 1990
|
| 3593 |
+
},
|
| 3594 |
+
{
|
| 3595 |
+
"epoch": 15.346153846153847,
|
| 3596 |
+
"grad_norm": 0.0,
|
| 3597 |
+
"learning_rate": 4.003e-05,
|
| 3598 |
+
"loss": 1.817,
|
| 3599 |
+
"mean_token_accuracy": 0.6392653495073318,
|
| 3600 |
+
"num_tokens": 7272870.0,
|
| 3601 |
+
"step": 1995
|
| 3602 |
+
},
|
| 3603 |
+
{
|
| 3604 |
+
"epoch": 15.384615384615385,
|
| 3605 |
+
"grad_norm": 0.0,
|
| 3606 |
+
"learning_rate": 4.0005e-05,
|
| 3607 |
+
"loss": 1.7256,
|
| 3608 |
+
"mean_token_accuracy": 0.6513147324323654,
|
| 3609 |
+
"num_tokens": 7291754.0,
|
| 3610 |
+
"step": 2000
|
| 3611 |
}
|
| 3612 |
],
|
| 3613 |
"logging_steps": 5,
|
|
|
|
| 3627 |
"attributes": {}
|
| 3628 |
}
|
| 3629 |
},
|
| 3630 |
+
"total_flos": 3.693993661690675e+17,
|
| 3631 |
"train_batch_size": 4,
|
| 3632 |
"trial_name": null,
|
| 3633 |
"trial_params": null
|