Training in progress, step 4590, 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:ee111b2252e9b0a06261e94588d6d40e06874459e991e2919ebd9815a7994462
|
| 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 sha256:4d5af005b7078137c3e72e8bc63fba1984fca5ccdc4f410e423ae39ec48ea958
|
| 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 sha256:7e6a7e537118d3394a55ebd9503d822516efbfb8dc8936ce099a8019c437d93b
|
| 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": 35.
|
| 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,
|
|
@@ -8252,6 +8252,24 @@
|
|
| 8252 |
"mean_token_accuracy": 0.6510407030582428,
|
| 8253 |
"num_tokens": 16704566.0,
|
| 8254 |
"step": 4580
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8255 |
}
|
| 8256 |
],
|
| 8257 |
"logging_steps": 5,
|
|
@@ -8271,7 +8289,7 @@
|
|
| 8271 |
"attributes": {}
|
| 8272 |
}
|
| 8273 |
},
|
| 8274 |
-
"total_flos": 8.
|
| 8275 |
"train_batch_size": 4,
|
| 8276 |
"trial_name": null,
|
| 8277 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 35.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4590,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8252 |
"mean_token_accuracy": 0.6510407030582428,
|
| 8253 |
"num_tokens": 16704566.0,
|
| 8254 |
"step": 4580
|
| 8255 |
+
},
|
| 8256 |
+
{
|
| 8257 |
+
"epoch": 35.26923076923077,
|
| 8258 |
+
"grad_norm": 0.0,
|
| 8259 |
+
"learning_rate": 2.7079999999999998e-05,
|
| 8260 |
+
"loss": 1.7879,
|
| 8261 |
+
"mean_token_accuracy": 0.6449306428432464,
|
| 8262 |
+
"num_tokens": 16721669.0,
|
| 8263 |
+
"step": 4585
|
| 8264 |
+
},
|
| 8265 |
+
{
|
| 8266 |
+
"epoch": 35.30769230769231,
|
| 8267 |
+
"grad_norm": 0.0,
|
| 8268 |
+
"learning_rate": 2.7055e-05,
|
| 8269 |
+
"loss": 1.7399,
|
| 8270 |
+
"mean_token_accuracy": 0.6478658020496368,
|
| 8271 |
+
"num_tokens": 16739999.0,
|
| 8272 |
+
"step": 4590
|
| 8273 |
}
|
| 8274 |
],
|
| 8275 |
"logging_steps": 5,
|
|
|
|
| 8289 |
"attributes": {}
|
| 8290 |
}
|
| 8291 |
},
|
| 8292 |
+
"total_flos": 8.484551038726963e+17,
|
| 8293 |
"train_batch_size": 4,
|
| 8294 |
"trial_name": null,
|
| 8295 |
"trial_params": null
|