Training in progress, step 7930, 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 sha256:8e8565f6cd9548816173243b5749b52e73c2d9fd46b60e1452791542ea563a48
|
| 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 sha256:8561f0d3c2396c95fd259b6109d17ed600e3461ac46a8a1c4bed8478c1ba5d81
|
| 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:f376794072f7b4056eb4d3e8e8325ec11b267daa511aa04dbfcc863b9b660880
|
| 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":
|
| 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,
|
|
@@ -14264,6 +14264,24 @@
|
|
| 14264 |
"mean_token_accuracy": 0.6469286412000657,
|
| 14265 |
"num_tokens": 28882849.0,
|
| 14266 |
"step": 7920
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14267 |
}
|
| 14268 |
],
|
| 14269 |
"logging_steps": 5,
|
|
@@ -14283,7 +14301,7 @@
|
|
| 14283 |
"attributes": {}
|
| 14284 |
}
|
| 14285 |
},
|
| 14286 |
-
"total_flos": 1.
|
| 14287 |
"train_batch_size": 4,
|
| 14288 |
"trial_name": null,
|
| 14289 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 61.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7930,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14264 |
"mean_token_accuracy": 0.6469286412000657,
|
| 14265 |
"num_tokens": 28882849.0,
|
| 14266 |
"step": 7920
|
| 14267 |
+
},
|
| 14268 |
+
{
|
| 14269 |
+
"epoch": 60.96153846153846,
|
| 14270 |
+
"grad_norm": 0.0,
|
| 14271 |
+
"learning_rate": 1.038e-05,
|
| 14272 |
+
"loss": 1.6918,
|
| 14273 |
+
"mean_token_accuracy": 0.6562754690647126,
|
| 14274 |
+
"num_tokens": 28902085.0,
|
| 14275 |
+
"step": 7925
|
| 14276 |
+
},
|
| 14277 |
+
{
|
| 14278 |
+
"epoch": 61.0,
|
| 14279 |
+
"grad_norm": 0.0,
|
| 14280 |
+
"learning_rate": 1.0355000000000002e-05,
|
| 14281 |
+
"loss": 1.7195,
|
| 14282 |
+
"mean_token_accuracy": 0.6521394342184067,
|
| 14283 |
+
"num_tokens": 28920405.0,
|
| 14284 |
+
"step": 7930
|
| 14285 |
}
|
| 14286 |
],
|
| 14287 |
"logging_steps": 5,
|
|
|
|
| 14301 |
"attributes": {}
|
| 14302 |
}
|
| 14303 |
},
|
| 14304 |
+
"total_flos": 1.4663659042086912e+18,
|
| 14305 |
"train_batch_size": 4,
|
| 14306 |
"trial_name": null,
|
| 14307 |
"trial_params": null
|