Training in progress, step 7340, 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 sha256:9f84d34d7afd1fe372ae931b352045251605766d382d0f938bacf023537ae791
|
| 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:c1d0854b153210e3cdd6f5b6e95869a0ea789ef49ed795a6953aa5c4b068735f
|
| 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 sha256:8deae7d8181db4d3ef2509a7dac4a052c4b2a64c5f92cd0cda1887a2d1028b30
|
| 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,
|
|
@@ -13202,6 +13202,24 @@
|
|
| 13202 |
"mean_token_accuracy": 0.6498448342084885,
|
| 13203 |
"num_tokens": 26731833.0,
|
| 13204 |
"step": 7330
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13205 |
}
|
| 13206 |
],
|
| 13207 |
"logging_steps": 5,
|
|
@@ -13221,7 +13239,7 @@
|
|
| 13221 |
"attributes": {}
|
| 13222 |
}
|
| 13223 |
},
|
| 13224 |
-
"total_flos": 1.
|
| 13225 |
"train_batch_size": 4,
|
| 13226 |
"trial_name": null,
|
| 13227 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 56.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7340,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13202 |
"mean_token_accuracy": 0.6498448342084885,
|
| 13203 |
"num_tokens": 26731833.0,
|
| 13204 |
"step": 7330
|
| 13205 |
+
},
|
| 13206 |
+
{
|
| 13207 |
+
"epoch": 56.42307692307692,
|
| 13208 |
+
"grad_norm": 0.0,
|
| 13209 |
+
"learning_rate": 1.3330000000000001e-05,
|
| 13210 |
+
"loss": 1.7544,
|
| 13211 |
+
"mean_token_accuracy": 0.6504902809858322,
|
| 13212 |
+
"num_tokens": 26749542.0,
|
| 13213 |
+
"step": 7335
|
| 13214 |
+
},
|
| 13215 |
+
{
|
| 13216 |
+
"epoch": 56.46153846153846,
|
| 13217 |
+
"grad_norm": 0.0,
|
| 13218 |
+
"learning_rate": 1.3305e-05,
|
| 13219 |
+
"loss": 1.7841,
|
| 13220 |
+
"mean_token_accuracy": 0.6441579282283783,
|
| 13221 |
+
"num_tokens": 26767123.0,
|
| 13222 |
+
"step": 7340
|
| 13223 |
}
|
| 13224 |
],
|
| 13225 |
"logging_steps": 5,
|
|
|
|
| 13239 |
"attributes": {}
|
| 13240 |
}
|
| 13241 |
},
|
| 13242 |
+
"total_flos": 1.3571298210742272e+18,
|
| 13243 |
"train_batch_size": 4,
|
| 13244 |
"trial_name": null,
|
| 13245 |
"trial_params": null
|