Training in progress, step 3450, 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 sha256:61bc1959a9a1f903067826ad58e74477c245bf8b56e155bdcf448f5abe7dcd79
|
| 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 sha256:775072dcab59f7603563b3340d0117e470bd939d48c34b3de2a95ad2c47c61bd
|
| 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 sha256:2bab52e846b3fa70a3646cbc886e4b01c84d9c53cdb5816eb8fb530216b33c98
|
| 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,
|
|
@@ -6200,6 +6200,24 @@
|
|
| 6200 |
"mean_token_accuracy": 0.6444113343954087,
|
| 6201 |
"num_tokens": 12546721.0,
|
| 6202 |
"step": 3440
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6203 |
}
|
| 6204 |
],
|
| 6205 |
"logging_steps": 5,
|
|
@@ -6219,7 +6237,7 @@
|
|
| 6219 |
"attributes": {}
|
| 6220 |
}
|
| 6221 |
},
|
| 6222 |
-
"total_flos": 6.
|
| 6223 |
"train_batch_size": 4,
|
| 6224 |
"trial_name": null,
|
| 6225 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 26.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3450,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6200 |
"mean_token_accuracy": 0.6444113343954087,
|
| 6201 |
"num_tokens": 12546721.0,
|
| 6202 |
"step": 3440
|
| 6203 |
+
},
|
| 6204 |
+
{
|
| 6205 |
+
"epoch": 26.5,
|
| 6206 |
+
"grad_norm": 0.0,
|
| 6207 |
+
"learning_rate": 3.278e-05,
|
| 6208 |
+
"loss": 1.7363,
|
| 6209 |
+
"mean_token_accuracy": 0.6494855612516404,
|
| 6210 |
+
"num_tokens": 12564745.0,
|
| 6211 |
+
"step": 3445
|
| 6212 |
+
},
|
| 6213 |
+
{
|
| 6214 |
+
"epoch": 26.53846153846154,
|
| 6215 |
+
"grad_norm": 0.0,
|
| 6216 |
+
"learning_rate": 3.2755e-05,
|
| 6217 |
+
"loss": 1.7475,
|
| 6218 |
+
"mean_token_accuracy": 0.6525735288858414,
|
| 6219 |
+
"num_tokens": 12583018.0,
|
| 6220 |
+
"step": 3450
|
| 6221 |
}
|
| 6222 |
],
|
| 6223 |
"logging_steps": 5,
|
|
|
|
| 6237 |
"attributes": {}
|
| 6238 |
}
|
| 6239 |
},
|
| 6240 |
+
"total_flos": 6.374615941708186e+17,
|
| 6241 |
"train_batch_size": 4,
|
| 6242 |
"trial_name": null,
|
| 6243 |
"trial_params": null
|