Training in progress, step 3430, 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:ca10ffebcfab0a1c5a75afcfc918c01ae8e9457f20f1b1b12fcb4e2efe495794
|
| 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 sha256:60adf1d4038b98a8f71d44f3f654c264a9afa246f2343dc62090d3fa5d1dee4c
|
| 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 sha256:029f58bdd60e5ebf970a23fd1f62ecd1f26fa2f6026db49ece2e728aae9a68e6
|
| 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,
|
|
@@ -6164,6 +6164,24 @@
|
|
| 6164 |
"mean_token_accuracy": 0.6505888134241105,
|
| 6165 |
"num_tokens": 12472148.0,
|
| 6166 |
"step": 3420
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6167 |
}
|
| 6168 |
],
|
| 6169 |
"logging_steps": 5,
|
|
@@ -6183,7 +6201,7 @@
|
|
| 6183 |
"attributes": {}
|
| 6184 |
}
|
| 6185 |
},
|
| 6186 |
-
"total_flos": 6.
|
| 6187 |
"train_batch_size": 4,
|
| 6188 |
"trial_name": null,
|
| 6189 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 26.384615384615383,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3430,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6164 |
"mean_token_accuracy": 0.6505888134241105,
|
| 6165 |
"num_tokens": 12472148.0,
|
| 6166 |
"step": 3420
|
| 6167 |
+
},
|
| 6168 |
+
{
|
| 6169 |
+
"epoch": 26.346153846153847,
|
| 6170 |
+
"grad_norm": 0.0,
|
| 6171 |
+
"learning_rate": 3.288e-05,
|
| 6172 |
+
"loss": 1.7421,
|
| 6173 |
+
"mean_token_accuracy": 0.6458885490894317,
|
| 6174 |
+
"num_tokens": 12491225.0,
|
| 6175 |
+
"step": 3425
|
| 6176 |
+
},
|
| 6177 |
+
{
|
| 6178 |
+
"epoch": 26.384615384615383,
|
| 6179 |
+
"grad_norm": 0.0,
|
| 6180 |
+
"learning_rate": 3.2855e-05,
|
| 6181 |
+
"loss": 1.7056,
|
| 6182 |
+
"mean_token_accuracy": 0.6600462704896927,
|
| 6183 |
+
"num_tokens": 12510093.0,
|
| 6184 |
+
"step": 3430
|
| 6185 |
}
|
| 6186 |
],
|
| 6187 |
"logging_steps": 5,
|
|
|
|
| 6201 |
"attributes": {}
|
| 6202 |
}
|
| 6203 |
},
|
| 6204 |
+
"total_flos": 6.337931607760896e+17,
|
| 6205 |
"train_batch_size": 4,
|
| 6206 |
"trial_name": null,
|
| 6207 |
"trial_params": null
|