Training in progress, step 3460, 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 sha256:26161e06ca718a1b3995dd02bb9e9fa731da5415cdb0f0a1c94cbeadf111729e
|
| 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 sha256:3d0c39e296c64203704db19a381e7980cadfbba490929525c1f52fe784a3b725
|
| 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:dc07ea8d71e113379fcc36933067f41341ed47c97627302f6b01f60aead0ea4b
|
| 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": 26.
|
| 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,
|
|
@@ -6218,6 +6218,24 @@
|
|
| 6218 |
"mean_token_accuracy": 0.6525735288858414,
|
| 6219 |
"num_tokens": 12583018.0,
|
| 6220 |
"step": 3450
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6221 |
}
|
| 6222 |
],
|
| 6223 |
"logging_steps": 5,
|
|
@@ -6237,7 +6255,7 @@
|
|
| 6237 |
"attributes": {}
|
| 6238 |
}
|
| 6239 |
},
|
| 6240 |
-
"total_flos": 6.
|
| 6241 |
"train_batch_size": 4,
|
| 6242 |
"trial_name": null,
|
| 6243 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 26.615384615384617,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3460,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6218 |
"mean_token_accuracy": 0.6525735288858414,
|
| 6219 |
"num_tokens": 12583018.0,
|
| 6220 |
"step": 3450
|
| 6221 |
+
},
|
| 6222 |
+
{
|
| 6223 |
+
"epoch": 26.576923076923077,
|
| 6224 |
+
"grad_norm": 0.0,
|
| 6225 |
+
"learning_rate": 3.273e-05,
|
| 6226 |
+
"loss": 1.7463,
|
| 6227 |
+
"mean_token_accuracy": 0.6488917529582977,
|
| 6228 |
+
"num_tokens": 12600537.0,
|
| 6229 |
+
"step": 3455
|
| 6230 |
+
},
|
| 6231 |
+
{
|
| 6232 |
+
"epoch": 26.615384615384617,
|
| 6233 |
+
"grad_norm": 0.0,
|
| 6234 |
+
"learning_rate": 3.2705e-05,
|
| 6235 |
+
"loss": 1.7124,
|
| 6236 |
+
"mean_token_accuracy": 0.6540741354227066,
|
| 6237 |
+
"num_tokens": 12619514.0,
|
| 6238 |
+
"step": 3460
|
| 6239 |
}
|
| 6240 |
],
|
| 6241 |
"logging_steps": 5,
|
|
|
|
| 6255 |
"attributes": {}
|
| 6256 |
}
|
| 6257 |
},
|
| 6258 |
+
"total_flos": 6.39359322526679e+17,
|
| 6259 |
"train_batch_size": 4,
|
| 6260 |
"trial_name": null,
|
| 6261 |
"trial_params": null
|