Training in progress, step 5720, 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 sha256:64fd94417fa820b775e8e5275398764601ea9e31a6608a5a0160267e4b2d8343
|
| 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:fcf4f0b7d4cd0e0ba2a42768bce8311aea5439a034dc8d3ab5e2cb9abc07f7ab
|
| 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:caf8741d140b5d7a2e19a5283d520291fc2e59d75d7879ce2b2774fe7f5cce3e
|
| 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,
|
|
@@ -10286,6 +10286,24 @@
|
|
| 10286 |
"mean_token_accuracy": 0.6507911443710327,
|
| 10287 |
"num_tokens": 20824903.0,
|
| 10288 |
"step": 5710
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10289 |
}
|
| 10290 |
],
|
| 10291 |
"logging_steps": 5,
|
|
@@ -10305,7 +10323,7 @@
|
|
| 10305 |
"attributes": {}
|
| 10306 |
}
|
| 10307 |
},
|
| 10308 |
-
"total_flos": 1.
|
| 10309 |
"train_batch_size": 4,
|
| 10310 |
"trial_name": null,
|
| 10311 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 44.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5720,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10286 |
"mean_token_accuracy": 0.6507911443710327,
|
| 10287 |
"num_tokens": 20824903.0,
|
| 10288 |
"step": 5710
|
| 10289 |
+
},
|
| 10290 |
+
{
|
| 10291 |
+
"epoch": 43.96153846153846,
|
| 10292 |
+
"grad_norm": 0.0,
|
| 10293 |
+
"learning_rate": 2.143e-05,
|
| 10294 |
+
"loss": 1.7877,
|
| 10295 |
+
"mean_token_accuracy": 0.6402207911014557,
|
| 10296 |
+
"num_tokens": 20842868.0,
|
| 10297 |
+
"step": 5715
|
| 10298 |
+
},
|
| 10299 |
+
{
|
| 10300 |
+
"epoch": 44.0,
|
| 10301 |
+
"grad_norm": 0.0,
|
| 10302 |
+
"learning_rate": 2.1405e-05,
|
| 10303 |
+
"loss": 1.7548,
|
| 10304 |
+
"mean_token_accuracy": 0.6519168674945831,
|
| 10305 |
+
"num_tokens": 20860620.0,
|
| 10306 |
+
"step": 5720
|
| 10307 |
}
|
| 10308 |
],
|
| 10309 |
"logging_steps": 5,
|
|
|
|
| 10323 |
"attributes": {}
|
| 10324 |
}
|
| 10325 |
},
|
| 10326 |
+
"total_flos": 1.0571236105361818e+18,
|
| 10327 |
"train_batch_size": 4,
|
| 10328 |
"trial_name": null,
|
| 10329 |
"trial_params": null
|