Training in progress, step 750, 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:af9b4e6eb852272992e22fd2308af9343f56d1a30bdd69989c07464914693a4d
|
| 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:f644f33bf6383d5f8565815b141b275c22bceb6671de05815f2f2a15ed19d908
|
| 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:de24cf8a1d7e594bfa212dacbcf7547031ec08e2204676f91882e6a5b5a7330d
|
| 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": 5.
|
| 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,
|
|
@@ -1340,6 +1340,24 @@
|
|
| 1340 |
"mean_token_accuracy": 0.6477038502693176,
|
| 1341 |
"num_tokens": 2698512.0,
|
| 1342 |
"step": 740
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1343 |
}
|
| 1344 |
],
|
| 1345 |
"logging_steps": 5,
|
|
@@ -1359,7 +1377,7 @@
|
|
| 1359 |
"attributes": {}
|
| 1360 |
}
|
| 1361 |
},
|
| 1362 |
-
"total_flos": 1.
|
| 1363 |
"train_batch_size": 4,
|
| 1364 |
"trial_name": null,
|
| 1365 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 5.769230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 750,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1340 |
"mean_token_accuracy": 0.6477038502693176,
|
| 1341 |
"num_tokens": 2698512.0,
|
| 1342 |
"step": 740
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 5.730769230769231,
|
| 1346 |
+
"grad_norm": 0.0,
|
| 1347 |
+
"learning_rate": 4.6280000000000004e-05,
|
| 1348 |
+
"loss": 1.7583,
|
| 1349 |
+
"mean_token_accuracy": 0.6484469920396805,
|
| 1350 |
+
"num_tokens": 2716683.0,
|
| 1351 |
+
"step": 745
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 5.769230769230769,
|
| 1355 |
+
"grad_norm": 0.0,
|
| 1356 |
+
"learning_rate": 4.6255000000000004e-05,
|
| 1357 |
+
"loss": 1.7656,
|
| 1358 |
+
"mean_token_accuracy": 0.6475028216838836,
|
| 1359 |
+
"num_tokens": 2734221.0,
|
| 1360 |
+
"step": 750
|
| 1361 |
}
|
| 1362 |
],
|
| 1363 |
"logging_steps": 5,
|
|
|
|
| 1377 |
"attributes": {}
|
| 1378 |
}
|
| 1379 |
},
|
| 1380 |
+
"total_flos": 1.3862816723238912e+17,
|
| 1381 |
"train_batch_size": 4,
|
| 1382 |
"trial_name": null,
|
| 1383 |
"trial_params": null
|