Training in progress, step 7910, 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 sha256:16b63ccc1386e85d06c468a35ec5e50d3890fad1a19f5d0fa449f67c68ac9fb8
|
| 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:fcbb5e9486958d5ed54e9e938358f2335ad61fd58f6a2394088b28d08fca1f99
|
| 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 sha256:11d3640ad723b62008759dd2da028c2e567a9f1fe699bd9f19c087086f50bbeb
|
| 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": 60.
|
| 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,
|
|
@@ -14228,6 +14228,24 @@
|
|
| 14228 |
"mean_token_accuracy": 0.6532931387424469,
|
| 14229 |
"num_tokens": 28810975.0,
|
| 14230 |
"step": 7900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14231 |
}
|
| 14232 |
],
|
| 14233 |
"logging_steps": 5,
|
|
@@ -14247,7 +14265,7 @@
|
|
| 14247 |
"attributes": {}
|
| 14248 |
}
|
| 14249 |
},
|
| 14250 |
-
"total_flos": 1.
|
| 14251 |
"train_batch_size": 4,
|
| 14252 |
"trial_name": null,
|
| 14253 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 60.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7910,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14228 |
"mean_token_accuracy": 0.6532931387424469,
|
| 14229 |
"num_tokens": 28810975.0,
|
| 14230 |
"step": 7900
|
| 14231 |
+
},
|
| 14232 |
+
{
|
| 14233 |
+
"epoch": 60.80769230769231,
|
| 14234 |
+
"grad_norm": 0.0,
|
| 14235 |
+
"learning_rate": 1.0480000000000001e-05,
|
| 14236 |
+
"loss": 1.8055,
|
| 14237 |
+
"mean_token_accuracy": 0.6381255328655243,
|
| 14238 |
+
"num_tokens": 28828534.0,
|
| 14239 |
+
"step": 7905
|
| 14240 |
+
},
|
| 14241 |
+
{
|
| 14242 |
+
"epoch": 60.84615384615385,
|
| 14243 |
+
"grad_norm": 0.0,
|
| 14244 |
+
"learning_rate": 1.0455e-05,
|
| 14245 |
+
"loss": 1.7612,
|
| 14246 |
+
"mean_token_accuracy": 0.6478750109672546,
|
| 14247 |
+
"num_tokens": 28846473.0,
|
| 14248 |
+
"step": 7910
|
| 14249 |
}
|
| 14250 |
],
|
| 14251 |
"logging_steps": 5,
|
|
|
|
| 14265 |
"attributes": {}
|
| 14266 |
}
|
| 14267 |
},
|
| 14268 |
+
"total_flos": 1.4626811165618995e+18,
|
| 14269 |
"train_batch_size": 4,
|
| 14270 |
"trial_name": null,
|
| 14271 |
"trial_params": null
|