Training in progress, step 9620, 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:ac2fb879c016463506499eee105d80c60767e2058b662ec43823ec82df39a204
|
| 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 sha256:54fa4ddfec2e5ddc1e178c9a355e70c666036e3164392b101a9050bc1c901be6
|
| 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 sha256:5227f156cec315f492dc582944d80803849736ab7c09fe76720254736e08b28c
|
| 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,
|
|
@@ -17306,6 +17306,24 @@
|
|
| 17306 |
"mean_token_accuracy": 0.656490358710289,
|
| 17307 |
"num_tokens": 35046822.0,
|
| 17308 |
"step": 9610
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17309 |
}
|
| 17310 |
],
|
| 17311 |
"logging_steps": 5,
|
|
@@ -17325,7 +17343,7 @@
|
|
| 17325 |
"attributes": {}
|
| 17326 |
}
|
| 17327 |
},
|
| 17328 |
-
"total_flos": 1.
|
| 17329 |
"train_batch_size": 4,
|
| 17330 |
"trial_name": null,
|
| 17331 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 74.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9620,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17306 |
"mean_token_accuracy": 0.656490358710289,
|
| 17307 |
"num_tokens": 35046822.0,
|
| 17308 |
"step": 9610
|
| 17309 |
+
},
|
| 17310 |
+
{
|
| 17311 |
+
"epoch": 73.96153846153847,
|
| 17312 |
+
"grad_norm": 0.0,
|
| 17313 |
+
"learning_rate": 1.93e-06,
|
| 17314 |
+
"loss": 1.7048,
|
| 17315 |
+
"mean_token_accuracy": 0.6573001593351364,
|
| 17316 |
+
"num_tokens": 35065193.0,
|
| 17317 |
+
"step": 9615
|
| 17318 |
+
},
|
| 17319 |
+
{
|
| 17320 |
+
"epoch": 74.0,
|
| 17321 |
+
"grad_norm": 0.0,
|
| 17322 |
+
"learning_rate": 1.9050000000000002e-06,
|
| 17323 |
+
"loss": 1.7038,
|
| 17324 |
+
"mean_token_accuracy": 0.6570831030607224,
|
| 17325 |
+
"num_tokens": 35083770.0,
|
| 17326 |
+
"step": 9620
|
| 17327 |
}
|
| 17328 |
],
|
| 17329 |
"logging_steps": 5,
|
|
|
|
| 17343 |
"attributes": {}
|
| 17344 |
}
|
| 17345 |
},
|
| 17346 |
+
"total_flos": 1.779216236223529e+18,
|
| 17347 |
"train_batch_size": 4,
|
| 17348 |
"trial_name": null,
|
| 17349 |
"trial_params": null
|