Training in progress, step 9630, 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:e90df72b0f96a806e06ce4b646f58773fb21695478737bac2c2fba375f56b064
|
| 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 sha256:452216833385b6255a0555ba98c016c8046f54812a763edd80ea2f474b97a191
|
| 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 sha256:3b1579786ef9b5ef8862a41ffc2a0b388282345a1e97f236cffc11990f53ed7d
|
| 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": 74.
|
| 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,
|
|
@@ -17324,6 +17324,24 @@
|
|
| 17324 |
"mean_token_accuracy": 0.6570831030607224,
|
| 17325 |
"num_tokens": 35083770.0,
|
| 17326 |
"step": 9620
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17327 |
}
|
| 17328 |
],
|
| 17329 |
"logging_steps": 5,
|
|
@@ -17343,7 +17361,7 @@
|
|
| 17343 |
"attributes": {}
|
| 17344 |
}
|
| 17345 |
},
|
| 17346 |
-
"total_flos": 1.
|
| 17347 |
"train_batch_size": 4,
|
| 17348 |
"trial_name": null,
|
| 17349 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 74.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9630,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17324 |
"mean_token_accuracy": 0.6570831030607224,
|
| 17325 |
"num_tokens": 35083770.0,
|
| 17326 |
"step": 9620
|
| 17327 |
+
},
|
| 17328 |
+
{
|
| 17329 |
+
"epoch": 74.03846153846153,
|
| 17330 |
+
"grad_norm": 0.0,
|
| 17331 |
+
"learning_rate": 1.8800000000000002e-06,
|
| 17332 |
+
"loss": 1.841,
|
| 17333 |
+
"mean_token_accuracy": 0.6277540296316146,
|
| 17334 |
+
"num_tokens": 35101050.0,
|
| 17335 |
+
"step": 9625
|
| 17336 |
+
},
|
| 17337 |
+
{
|
| 17338 |
+
"epoch": 74.07692307692308,
|
| 17339 |
+
"grad_norm": 0.0,
|
| 17340 |
+
"learning_rate": 1.8550000000000002e-06,
|
| 17341 |
+
"loss": 1.7552,
|
| 17342 |
+
"mean_token_accuracy": 0.6447629004716873,
|
| 17343 |
+
"num_tokens": 35119255.0,
|
| 17344 |
+
"step": 9630
|
| 17345 |
}
|
| 17346 |
],
|
| 17347 |
"logging_steps": 5,
|
|
|
|
| 17361 |
"attributes": {}
|
| 17362 |
}
|
| 17363 |
},
|
| 17364 |
+
"total_flos": 1.7809669350899712e+18,
|
| 17365 |
"train_batch_size": 4,
|
| 17366 |
"trial_name": null,
|
| 17367 |
"trial_params": null
|