Training in progress, step 1160, 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 sha256:702855286858793cd32804fc395fc1dc069aab53c8fcf3545f60f66b5c53276d
|
| 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:f397658bc736bf189a7af219e1144951c720460c81511208b05206388e679894
|
| 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 sha256:15eb54306a2e8293da282fbee9088062a3dadcdaf26d45e7c916420375c453e7
|
| 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": 8.
|
| 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,
|
|
@@ -2078,6 +2078,24 @@
|
|
| 2078 |
"mean_token_accuracy": 0.6698046773672104,
|
| 2079 |
"num_tokens": 4195030.0,
|
| 2080 |
"step": 1150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2081 |
}
|
| 2082 |
],
|
| 2083 |
"logging_steps": 5,
|
|
@@ -2097,7 +2115,7 @@
|
|
| 2097 |
"attributes": {}
|
| 2098 |
}
|
| 2099 |
},
|
| 2100 |
-
"total_flos": 2.
|
| 2101 |
"train_batch_size": 4,
|
| 2102 |
"trial_name": null,
|
| 2103 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 8.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1160,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2078 |
"mean_token_accuracy": 0.6698046773672104,
|
| 2079 |
"num_tokens": 4195030.0,
|
| 2080 |
"step": 1150
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 8.884615384615385,
|
| 2084 |
+
"grad_norm": 0.0,
|
| 2085 |
+
"learning_rate": 4.423e-05,
|
| 2086 |
+
"loss": 1.7975,
|
| 2087 |
+
"mean_token_accuracy": 0.638244041800499,
|
| 2088 |
+
"num_tokens": 4212955.0,
|
| 2089 |
+
"step": 1155
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 8.923076923076923,
|
| 2093 |
+
"grad_norm": 0.0,
|
| 2094 |
+
"learning_rate": 4.4205e-05,
|
| 2095 |
+
"loss": 1.7643,
|
| 2096 |
+
"mean_token_accuracy": 0.6474886476993561,
|
| 2097 |
+
"num_tokens": 4230913.0,
|
| 2098 |
+
"step": 1160
|
| 2099 |
}
|
| 2100 |
],
|
| 2101 |
"logging_steps": 5,
|
|
|
|
| 2115 |
"attributes": {}
|
| 2116 |
}
|
| 2117 |
},
|
| 2118 |
+
"total_flos": 2.145296800677888e+17,
|
| 2119 |
"train_batch_size": 4,
|
| 2120 |
"trial_name": null,
|
| 2121 |
"trial_params": null
|