Training in progress, step 7360, 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 sha256:8ac4519510510c3902bc95b8d0e820b31edc3af5f0c8b4afacb720b881e14a7d
|
| 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:f1f81b540c0af1a5701ed34fa2e60aebff9625790750240087aa82557d4d1041
|
| 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:e188b6dc33e7c51694397529bc709b5f8e21f538cd2f81217546d0d3fe858a57
|
| 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": 56.
|
| 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,
|
|
@@ -13238,6 +13238,24 @@
|
|
| 13238 |
"mean_token_accuracy": 0.6520332425832749,
|
| 13239 |
"num_tokens": 26803690.0,
|
| 13240 |
"step": 7350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13241 |
}
|
| 13242 |
],
|
| 13243 |
"logging_steps": 5,
|
|
@@ -13257,7 +13275,7 @@
|
|
| 13257 |
"attributes": {}
|
| 13258 |
}
|
| 13259 |
},
|
| 13260 |
-
"total_flos": 1.
|
| 13261 |
"train_batch_size": 4,
|
| 13262 |
"trial_name": null,
|
| 13263 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 56.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7360,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13238 |
"mean_token_accuracy": 0.6520332425832749,
|
| 13239 |
"num_tokens": 26803690.0,
|
| 13240 |
"step": 7350
|
| 13241 |
+
},
|
| 13242 |
+
{
|
| 13243 |
+
"epoch": 56.57692307692308,
|
| 13244 |
+
"grad_norm": 0.0,
|
| 13245 |
+
"learning_rate": 1.323e-05,
|
| 13246 |
+
"loss": 1.7765,
|
| 13247 |
+
"mean_token_accuracy": 0.6428980946540832,
|
| 13248 |
+
"num_tokens": 26821866.0,
|
| 13249 |
+
"step": 7355
|
| 13250 |
+
},
|
| 13251 |
+
{
|
| 13252 |
+
"epoch": 56.61538461538461,
|
| 13253 |
+
"grad_norm": 0.0,
|
| 13254 |
+
"learning_rate": 1.3205000000000001e-05,
|
| 13255 |
+
"loss": 1.7009,
|
| 13256 |
+
"mean_token_accuracy": 0.6572036474943161,
|
| 13257 |
+
"num_tokens": 26840558.0,
|
| 13258 |
+
"step": 7360
|
| 13259 |
}
|
| 13260 |
],
|
| 13261 |
"logging_steps": 5,
|
|
|
|
| 13275 |
"attributes": {}
|
| 13276 |
}
|
| 13277 |
},
|
| 13278 |
+
"total_flos": 1.3608554149616026e+18,
|
| 13279 |
"train_batch_size": 4,
|
| 13280 |
"trial_name": null,
|
| 13281 |
"trial_params": null
|