Training in progress, step 7000, 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:b0cdabf2905a125795aa75ccbee5385f047126fe39c93a73365b6620aa6e9c98
|
| 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:f5a31a0b9bef1e654a4e0cbff6090c8a36b452166541c4e100431fc039dbb45d
|
| 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 sha256:84c370977d7f17f0c6f42fdb3b965fea329af5497e6ede6bc7b3010a68f01c56
|
| 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": 53.
|
| 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,
|
|
@@ -12590,6 +12590,24 @@
|
|
| 12590 |
"mean_token_accuracy": 0.6455465704202652,
|
| 12591 |
"num_tokens": 25492111.0,
|
| 12592 |
"step": 6990
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12593 |
}
|
| 12594 |
],
|
| 12595 |
"logging_steps": 5,
|
|
@@ -12609,7 +12627,7 @@
|
|
| 12609 |
"attributes": {}
|
| 12610 |
}
|
| 12611 |
},
|
| 12612 |
-
"total_flos": 1.
|
| 12613 |
"train_batch_size": 4,
|
| 12614 |
"trial_name": null,
|
| 12615 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 53.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12590 |
"mean_token_accuracy": 0.6455465704202652,
|
| 12591 |
"num_tokens": 25492111.0,
|
| 12592 |
"step": 6990
|
| 12593 |
+
},
|
| 12594 |
+
{
|
| 12595 |
+
"epoch": 53.80769230769231,
|
| 12596 |
+
"grad_norm": 0.0,
|
| 12597 |
+
"learning_rate": 1.503e-05,
|
| 12598 |
+
"loss": 1.7091,
|
| 12599 |
+
"mean_token_accuracy": 0.6587622851133347,
|
| 12600 |
+
"num_tokens": 25510592.0,
|
| 12601 |
+
"step": 6995
|
| 12602 |
+
},
|
| 12603 |
+
{
|
| 12604 |
+
"epoch": 53.84615384615385,
|
| 12605 |
+
"grad_norm": 0.0,
|
| 12606 |
+
"learning_rate": 1.5005e-05,
|
| 12607 |
+
"loss": 1.7738,
|
| 12608 |
+
"mean_token_accuracy": 0.646448740363121,
|
| 12609 |
+
"num_tokens": 25528517.0,
|
| 12610 |
+
"step": 7000
|
| 12611 |
}
|
| 12612 |
],
|
| 12613 |
"logging_steps": 5,
|
|
|
|
| 12627 |
"attributes": {}
|
| 12628 |
}
|
| 12629 |
},
|
| 12630 |
+
"total_flos": 1.2943793498053018e+18,
|
| 12631 |
"train_batch_size": 4,
|
| 12632 |
"trial_name": null,
|
| 12633 |
"trial_params": null
|