Training in progress, step 3480, 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 sha256:42ea2d788fb9b424d3fcd3acc64d6358e2448d7bcb92e0889c40acd07c9cd14a
|
| 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 sha256:73f7a585ff8139cab4792e91f4c0fe41662e4984d00f01121aef0a324a1a82d9
|
| 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 sha256:0262962bfafecc157466f39b1e756138ccb324eddd0e35ad243aa1963d5b5409
|
| 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": 26.
|
| 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,
|
|
@@ -6254,6 +6254,24 @@
|
|
| 6254 |
"mean_token_accuracy": 0.6622325748205184,
|
| 6255 |
"num_tokens": 12656523.0,
|
| 6256 |
"step": 3470
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6257 |
}
|
| 6258 |
],
|
| 6259 |
"logging_steps": 5,
|
|
@@ -6273,7 +6291,7 @@
|
|
| 6273 |
"attributes": {}
|
| 6274 |
}
|
| 6275 |
},
|
| 6276 |
-
"total_flos": 6.
|
| 6277 |
"train_batch_size": 4,
|
| 6278 |
"trial_name": null,
|
| 6279 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 26.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3480,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6254 |
"mean_token_accuracy": 0.6622325748205184,
|
| 6255 |
"num_tokens": 12656523.0,
|
| 6256 |
"step": 3470
|
| 6257 |
+
},
|
| 6258 |
+
{
|
| 6259 |
+
"epoch": 26.73076923076923,
|
| 6260 |
+
"grad_norm": 0.0,
|
| 6261 |
+
"learning_rate": 3.263e-05,
|
| 6262 |
+
"loss": 1.7123,
|
| 6263 |
+
"mean_token_accuracy": 0.654995933175087,
|
| 6264 |
+
"num_tokens": 12675577.0,
|
| 6265 |
+
"step": 3475
|
| 6266 |
+
},
|
| 6267 |
+
{
|
| 6268 |
+
"epoch": 26.76923076923077,
|
| 6269 |
+
"grad_norm": 0.0,
|
| 6270 |
+
"learning_rate": 3.2605000000000004e-05,
|
| 6271 |
+
"loss": 1.7554,
|
| 6272 |
+
"mean_token_accuracy": 0.6486168265342712,
|
| 6273 |
+
"num_tokens": 12693239.0,
|
| 6274 |
+
"step": 3480
|
| 6275 |
}
|
| 6276 |
],
|
| 6277 |
"logging_steps": 5,
|
|
|
|
| 6291 |
"attributes": {}
|
| 6292 |
}
|
| 6293 |
},
|
| 6294 |
+
"total_flos": 6.431300096915866e+17,
|
| 6295 |
"train_batch_size": 4,
|
| 6296 |
"trial_name": null,
|
| 6297 |
"trial_params": null
|