Training in progress, step 8320, 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:bee514f744a376bca323a30206615d98244ac340ec8dc26a2826e1f4f7cf9173
|
| 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 sha256:211188e0d16fe700ec6efcc3b75583bff9c11b9a7a5bcf184041932ae00c9a2e
|
| 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:f75bddc38f366b897384540c84983c2220e5662bbde47eee4c95d16239e38f7c
|
| 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":
|
| 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,
|
|
@@ -14966,6 +14966,24 @@
|
|
| 14966 |
"mean_token_accuracy": 0.649156528711319,
|
| 14967 |
"num_tokens": 30305098.0,
|
| 14968 |
"step": 8310
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14969 |
}
|
| 14970 |
],
|
| 14971 |
"logging_steps": 5,
|
|
@@ -14985,7 +15003,7 @@
|
|
| 14985 |
"attributes": {}
|
| 14986 |
}
|
| 14987 |
},
|
| 14988 |
-
"total_flos": 1.
|
| 14989 |
"train_batch_size": 4,
|
| 14990 |
"trial_name": null,
|
| 14991 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 64.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8320,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14966 |
"mean_token_accuracy": 0.649156528711319,
|
| 14967 |
"num_tokens": 30305098.0,
|
| 14968 |
"step": 8310
|
| 14969 |
+
},
|
| 14970 |
+
{
|
| 14971 |
+
"epoch": 63.96153846153846,
|
| 14972 |
+
"grad_norm": 0.0,
|
| 14973 |
+
"learning_rate": 8.43e-06,
|
| 14974 |
+
"loss": 1.6393,
|
| 14975 |
+
"mean_token_accuracy": 0.6654347360134125,
|
| 14976 |
+
"num_tokens": 30324316.0,
|
| 14977 |
+
"step": 8315
|
| 14978 |
+
},
|
| 14979 |
+
{
|
| 14980 |
+
"epoch": 64.0,
|
| 14981 |
+
"grad_norm": 0.0,
|
| 14982 |
+
"learning_rate": 8.405e-06,
|
| 14983 |
+
"loss": 1.7622,
|
| 14984 |
+
"mean_token_accuracy": 0.647731038928032,
|
| 14985 |
+
"num_tokens": 30342720.0,
|
| 14986 |
+
"step": 8320
|
| 14987 |
}
|
| 14988 |
],
|
| 14989 |
"logging_steps": 5,
|
|
|
|
| 15003 |
"attributes": {}
|
| 15004 |
}
|
| 15005 |
},
|
| 15006 |
+
"total_flos": 1.5384470320064102e+18,
|
| 15007 |
"train_batch_size": 4,
|
| 15008 |
"trial_name": null,
|
| 15009 |
"trial_params": null
|