Training in progress, step 1180, 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 sha256:288306b57959d43c5e7ef05d35a4ac5251094447045c6996af6cc6d38b00ccff
|
| 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 sha256:8820c070d78955078923565843c3abf166f926d92bb894cc601d44bc4f3806a7
|
| 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 sha256:9a006ad85191b8f87e46f28bfc39eb88dfd5b2c899b63ff0d0859284b2409003
|
| 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": 9.
|
| 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,
|
|
@@ -2114,6 +2114,24 @@
|
|
| 2114 |
"mean_token_accuracy": 0.661212831735611,
|
| 2115 |
"num_tokens": 4266945.0,
|
| 2116 |
"step": 1170
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2117 |
}
|
| 2118 |
],
|
| 2119 |
"logging_steps": 5,
|
|
@@ -2133,7 +2151,7 @@
|
|
| 2133 |
"attributes": {}
|
| 2134 |
}
|
| 2135 |
},
|
| 2136 |
-
"total_flos": 2.
|
| 2137 |
"train_batch_size": 4,
|
| 2138 |
"trial_name": null,
|
| 2139 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 9.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1180,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2114 |
"mean_token_accuracy": 0.661212831735611,
|
| 2115 |
"num_tokens": 4266945.0,
|
| 2116 |
"step": 1170
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 9.038461538461538,
|
| 2120 |
+
"grad_norm": 0.0,
|
| 2121 |
+
"learning_rate": 4.4130000000000006e-05,
|
| 2122 |
+
"loss": 1.6492,
|
| 2123 |
+
"mean_token_accuracy": 0.6669099152088165,
|
| 2124 |
+
"num_tokens": 4285875.0,
|
| 2125 |
+
"step": 1175
|
| 2126 |
+
},
|
| 2127 |
+
{
|
| 2128 |
+
"epoch": 9.076923076923077,
|
| 2129 |
+
"grad_norm": 0.0,
|
| 2130 |
+
"learning_rate": 4.4105e-05,
|
| 2131 |
+
"loss": 1.7311,
|
| 2132 |
+
"mean_token_accuracy": 0.6541598349809646,
|
| 2133 |
+
"num_tokens": 4304365.0,
|
| 2134 |
+
"step": 1180
|
| 2135 |
}
|
| 2136 |
],
|
| 2137 |
"logging_steps": 5,
|
|
|
|
| 2151 |
"attributes": {}
|
| 2152 |
}
|
| 2153 |
},
|
| 2154 |
+
"total_flos": 2.1824415941492736e+17,
|
| 2155 |
"train_batch_size": 4,
|
| 2156 |
"trial_name": null,
|
| 2157 |
"trial_params": null
|