Training in progress, step 8460, 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 sha256:7d78f7b0ca9df5b0590bfed0036e49dbdec6be929b299920f586f91b7c3940fb
|
| 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:c22a61367cbdfa0832d02086f594471928670283baa40f9cd694b175695f6ef4
|
| 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 sha256:41c3a8ae106fc237090be854aacd41df0bdca2a99938aa033a9fa5093b4de4b0
|
| 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": 65.
|
| 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,
|
|
@@ -15218,6 +15218,24 @@
|
|
| 15218 |
"mean_token_accuracy": 0.6472322821617127,
|
| 15219 |
"num_tokens": 30816825.0,
|
| 15220 |
"step": 8450
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15221 |
}
|
| 15222 |
],
|
| 15223 |
"logging_steps": 5,
|
|
@@ -15237,7 +15255,7 @@
|
|
| 15237 |
"attributes": {}
|
| 15238 |
}
|
| 15239 |
},
|
| 15240 |
-
"total_flos": 1.
|
| 15241 |
"train_batch_size": 4,
|
| 15242 |
"trial_name": null,
|
| 15243 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 65.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8460,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15218 |
"mean_token_accuracy": 0.6472322821617127,
|
| 15219 |
"num_tokens": 30816825.0,
|
| 15220 |
"step": 8450
|
| 15221 |
+
},
|
| 15222 |
+
{
|
| 15223 |
+
"epoch": 65.03846153846153,
|
| 15224 |
+
"grad_norm": 0.0,
|
| 15225 |
+
"learning_rate": 7.73e-06,
|
| 15226 |
+
"loss": 1.7898,
|
| 15227 |
+
"mean_token_accuracy": 0.6398821353912354,
|
| 15228 |
+
"num_tokens": 30834858.0,
|
| 15229 |
+
"step": 8455
|
| 15230 |
+
},
|
| 15231 |
+
{
|
| 15232 |
+
"epoch": 65.07692307692308,
|
| 15233 |
+
"grad_norm": 0.0,
|
| 15234 |
+
"learning_rate": 7.705e-06,
|
| 15235 |
+
"loss": 1.7869,
|
| 15236 |
+
"mean_token_accuracy": 0.6389808714389801,
|
| 15237 |
+
"num_tokens": 30853070.0,
|
| 15238 |
+
"step": 8460
|
| 15239 |
}
|
| 15240 |
],
|
| 15241 |
"logging_steps": 5,
|
|
|
|
| 15255 |
"attributes": {}
|
| 15256 |
}
|
| 15257 |
},
|
| 15258 |
+
"total_flos": 1.5643704268755763e+18,
|
| 15259 |
"train_batch_size": 4,
|
| 15260 |
"trial_name": null,
|
| 15261 |
"trial_params": null
|