Training in progress, step 4600, 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:ad72be4b06c2ac1ea24543706c372fb8b4ab90088605ba24e05dec94c940cd7f
|
| 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 sha256:2b8a3b781a7f54e2fb562b3ee36edcf5d6558e4562c360761fdb1477d33220b3
|
| 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 sha256:3cbbcf461546bd701b38c40bd63c1e02e6660007f12ae9c6ac773ca17fbee0f3
|
| 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,
|
|
@@ -8270,6 +8270,24 @@
|
|
| 8270 |
"mean_token_accuracy": 0.6478658020496368,
|
| 8271 |
"num_tokens": 16739999.0,
|
| 8272 |
"step": 4590
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8273 |
}
|
| 8274 |
],
|
| 8275 |
"logging_steps": 5,
|
|
@@ -8289,7 +8307,7 @@
|
|
| 8289 |
"attributes": {}
|
| 8290 |
}
|
| 8291 |
},
|
| 8292 |
-
"total_flos": 8.
|
| 8293 |
"train_batch_size": 4,
|
| 8294 |
"trial_name": null,
|
| 8295 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 35.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4600,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8270 |
"mean_token_accuracy": 0.6478658020496368,
|
| 8271 |
"num_tokens": 16739999.0,
|
| 8272 |
"step": 4590
|
| 8273 |
+
},
|
| 8274 |
+
{
|
| 8275 |
+
"epoch": 35.34615384615385,
|
| 8276 |
+
"grad_norm": 0.0,
|
| 8277 |
+
"learning_rate": 2.703e-05,
|
| 8278 |
+
"loss": 1.7316,
|
| 8279 |
+
"mean_token_accuracy": 0.647733348608017,
|
| 8280 |
+
"num_tokens": 16758454.0,
|
| 8281 |
+
"step": 4595
|
| 8282 |
+
},
|
| 8283 |
+
{
|
| 8284 |
+
"epoch": 35.38461538461539,
|
| 8285 |
+
"grad_norm": 0.0,
|
| 8286 |
+
"learning_rate": 2.7005000000000003e-05,
|
| 8287 |
+
"loss": 1.7179,
|
| 8288 |
+
"mean_token_accuracy": 0.6545091897249222,
|
| 8289 |
+
"num_tokens": 16776775.0,
|
| 8290 |
+
"step": 4600
|
| 8291 |
}
|
| 8292 |
],
|
| 8293 |
"logging_steps": 5,
|
|
|
|
| 8307 |
"attributes": {}
|
| 8308 |
}
|
| 8309 |
},
|
| 8310 |
+
"total_flos": 8.503844292786586e+17,
|
| 8311 |
"train_batch_size": 4,
|
| 8312 |
"trial_name": null,
|
| 8313 |
"trial_params": null
|