Training in progress, step 5710, 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 sha256:5c979b57df4e42171d2ec3f24de868f8f089a04e32880c24034fb6b04e60c0f2
|
| 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 sha256:1d1ddf2f3203b27907a50da699de386fd801cbabe0f9b19fa215a30562c970df
|
| 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:fc9f72fbd2e4f02ae4645b3b56f534795ff8f8cd9cfe3196b047173c9ef40a9c
|
| 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": 43.
|
| 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,
|
|
@@ -10268,6 +10268,24 @@
|
|
| 10268 |
"mean_token_accuracy": 0.6409453451633453,
|
| 10269 |
"num_tokens": 20789218.0,
|
| 10270 |
"step": 5700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10271 |
}
|
| 10272 |
],
|
| 10273 |
"logging_steps": 5,
|
|
@@ -10287,7 +10305,7 @@
|
|
| 10287 |
"attributes": {}
|
| 10288 |
}
|
| 10289 |
},
|
| 10290 |
-
"total_flos": 1.
|
| 10291 |
"train_batch_size": 4,
|
| 10292 |
"trial_name": null,
|
| 10293 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 43.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5710,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10268 |
"mean_token_accuracy": 0.6409453451633453,
|
| 10269 |
"num_tokens": 20789218.0,
|
| 10270 |
"step": 5700
|
| 10271 |
+
},
|
| 10272 |
+
{
|
| 10273 |
+
"epoch": 43.88461538461539,
|
| 10274 |
+
"grad_norm": 0.0,
|
| 10275 |
+
"learning_rate": 2.148e-05,
|
| 10276 |
+
"loss": 1.7477,
|
| 10277 |
+
"mean_token_accuracy": 0.6445836216211319,
|
| 10278 |
+
"num_tokens": 20807034.0,
|
| 10279 |
+
"step": 5705
|
| 10280 |
+
},
|
| 10281 |
+
{
|
| 10282 |
+
"epoch": 43.92307692307692,
|
| 10283 |
+
"grad_norm": 0.0,
|
| 10284 |
+
"learning_rate": 2.1455e-05,
|
| 10285 |
+
"loss": 1.7596,
|
| 10286 |
+
"mean_token_accuracy": 0.6507911443710327,
|
| 10287 |
+
"num_tokens": 20824903.0,
|
| 10288 |
+
"step": 5710
|
| 10289 |
}
|
| 10290 |
],
|
| 10291 |
"logging_steps": 5,
|
|
|
|
| 10305 |
"attributes": {}
|
| 10306 |
}
|
| 10307 |
},
|
| 10308 |
+
"total_flos": 1.055294474771497e+18,
|
| 10309 |
"train_batch_size": 4,
|
| 10310 |
"trial_name": null,
|
| 10311 |
"trial_params": null
|