Training in progress, step 8080, 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 sha256:9f2e0a6577d630cf1f645d4a119fb302c4313834c56268300bf0034f17834dab
|
| 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 sha256:23c6b762bb51a57599956575a5c5299aee40f2ce204e570a8e033650528c91ff
|
| 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:abcdb9c4ee0e022fe29ba0f6c2367e2b876e5d05c6e7e53f88c7ac1ec337d14a
|
| 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": 62.
|
| 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,
|
|
@@ -14534,6 +14534,24 @@
|
|
| 14534 |
"mean_token_accuracy": 0.6488070756196975,
|
| 14535 |
"num_tokens": 29430324.0,
|
| 14536 |
"step": 8070
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14537 |
}
|
| 14538 |
],
|
| 14539 |
"logging_steps": 5,
|
|
@@ -14553,7 +14571,7 @@
|
|
| 14553 |
"attributes": {}
|
| 14554 |
}
|
| 14555 |
},
|
| 14556 |
-
"total_flos": 1.
|
| 14557 |
"train_batch_size": 4,
|
| 14558 |
"trial_name": null,
|
| 14559 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 62.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8080,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14534 |
"mean_token_accuracy": 0.6488070756196975,
|
| 14535 |
"num_tokens": 29430324.0,
|
| 14536 |
"step": 8070
|
| 14537 |
+
},
|
| 14538 |
+
{
|
| 14539 |
+
"epoch": 62.11538461538461,
|
| 14540 |
+
"grad_norm": 0.0,
|
| 14541 |
+
"learning_rate": 9.630000000000001e-06,
|
| 14542 |
+
"loss": 1.7514,
|
| 14543 |
+
"mean_token_accuracy": 0.6483252078294754,
|
| 14544 |
+
"num_tokens": 29448473.0,
|
| 14545 |
+
"step": 8075
|
| 14546 |
+
},
|
| 14547 |
+
{
|
| 14548 |
+
"epoch": 62.15384615384615,
|
| 14549 |
+
"grad_norm": 0.0,
|
| 14550 |
+
"learning_rate": 9.605e-06,
|
| 14551 |
+
"loss": 1.7805,
|
| 14552 |
+
"mean_token_accuracy": 0.6442840725183487,
|
| 14553 |
+
"num_tokens": 29466357.0,
|
| 14554 |
+
"step": 8080
|
| 14555 |
}
|
| 14556 |
],
|
| 14557 |
"logging_steps": 5,
|
|
|
|
| 14571 |
"attributes": {}
|
| 14572 |
}
|
| 14573 |
},
|
| 14574 |
+
"total_flos": 1.4939256769590067e+18,
|
| 14575 |
"train_batch_size": 4,
|
| 14576 |
"trial_name": null,
|
| 14577 |
"trial_params": null
|