Training in progress, step 7250, 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 sha256:1696bf6285e9eca9a636a5337d23cf8d1a40ec1406722b9a354be1d847c480dd
|
| 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:b695f7e28b68177b3dc7c0aa0480c114f9cd58647856c673a429076933cc0fde
|
| 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 sha256:756d3fb3b0cb84cefe79818d6331eef375512cea36a705bedd3ab43de2a5de78
|
| 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": 55.
|
| 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,
|
|
@@ -13040,6 +13040,24 @@
|
|
| 13040 |
"mean_token_accuracy": 0.6492596924304962,
|
| 13041 |
"num_tokens": 26403619.0,
|
| 13042 |
"step": 7240
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13043 |
}
|
| 13044 |
],
|
| 13045 |
"logging_steps": 5,
|
|
@@ -13059,7 +13077,7 @@
|
|
| 13059 |
"attributes": {}
|
| 13060 |
}
|
| 13061 |
},
|
| 13062 |
-
"total_flos": 1.
|
| 13063 |
"train_batch_size": 4,
|
| 13064 |
"trial_name": null,
|
| 13065 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 55.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7250,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13040 |
"mean_token_accuracy": 0.6492596924304962,
|
| 13041 |
"num_tokens": 26403619.0,
|
| 13042 |
"step": 7240
|
| 13043 |
+
},
|
| 13044 |
+
{
|
| 13045 |
+
"epoch": 55.73076923076923,
|
| 13046 |
+
"grad_norm": 0.0,
|
| 13047 |
+
"learning_rate": 1.3780000000000002e-05,
|
| 13048 |
+
"loss": 1.6343,
|
| 13049 |
+
"mean_token_accuracy": 0.6683441162109375,
|
| 13050 |
+
"num_tokens": 26423343.0,
|
| 13051 |
+
"step": 7245
|
| 13052 |
+
},
|
| 13053 |
+
{
|
| 13054 |
+
"epoch": 55.76923076923077,
|
| 13055 |
+
"grad_norm": 0.0,
|
| 13056 |
+
"learning_rate": 1.3755000000000001e-05,
|
| 13057 |
+
"loss": 1.8149,
|
| 13058 |
+
"mean_token_accuracy": 0.6388367056846619,
|
| 13059 |
+
"num_tokens": 26440984.0,
|
| 13060 |
+
"step": 7250
|
| 13061 |
}
|
| 13062 |
],
|
| 13063 |
"logging_steps": 5,
|
|
|
|
| 13077 |
"attributes": {}
|
| 13078 |
}
|
| 13079 |
},
|
| 13080 |
+
"total_flos": 1.340662994596823e+18,
|
| 13081 |
"train_batch_size": 4,
|
| 13082 |
"trial_name": null,
|
| 13083 |
"trial_params": null
|