Training in progress, step 6710, 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 sha256:4358c961087f4891f3c857fe584783278533198a54607cb7fbb980488f786dd4
|
| 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 sha256:58378f098863e560d5e0fe9e4a3d7699852df720153956f6b20dc4f53d3c6aab
|
| 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 sha256:995d6895abdbfc6785a053ba4e4717209c1c9ea5b71e4b0acb4375335af92602
|
| 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": 51.
|
| 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,
|
|
@@ -12068,6 +12068,24 @@
|
|
| 12068 |
"mean_token_accuracy": 0.6506275236606598,
|
| 12069 |
"num_tokens": 24435235.0,
|
| 12070 |
"step": 6700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12071 |
}
|
| 12072 |
],
|
| 12073 |
"logging_steps": 5,
|
|
@@ -12087,7 +12105,7 @@
|
|
| 12087 |
"attributes": {}
|
| 12088 |
}
|
| 12089 |
},
|
| 12090 |
-
"total_flos": 1.
|
| 12091 |
"train_batch_size": 4,
|
| 12092 |
"trial_name": null,
|
| 12093 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 51.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6710,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12068 |
"mean_token_accuracy": 0.6506275236606598,
|
| 12069 |
"num_tokens": 24435235.0,
|
| 12070 |
"step": 6700
|
| 12071 |
+
},
|
| 12072 |
+
{
|
| 12073 |
+
"epoch": 51.57692307692308,
|
| 12074 |
+
"grad_norm": 0.0,
|
| 12075 |
+
"learning_rate": 1.648e-05,
|
| 12076 |
+
"loss": 1.7543,
|
| 12077 |
+
"mean_token_accuracy": 0.6435793161392211,
|
| 12078 |
+
"num_tokens": 24453138.0,
|
| 12079 |
+
"step": 6705
|
| 12080 |
+
},
|
| 12081 |
+
{
|
| 12082 |
+
"epoch": 51.61538461538461,
|
| 12083 |
+
"grad_norm": 0.0,
|
| 12084 |
+
"learning_rate": 1.6455e-05,
|
| 12085 |
+
"loss": 1.7537,
|
| 12086 |
+
"mean_token_accuracy": 0.644529914855957,
|
| 12087 |
+
"num_tokens": 24471067.0,
|
| 12088 |
+
"step": 6710
|
| 12089 |
}
|
| 12090 |
],
|
| 12091 |
"logging_steps": 5,
|
|
|
|
| 12105 |
"attributes": {}
|
| 12106 |
}
|
| 12107 |
},
|
| 12108 |
+
"total_flos": 1.2406087919311258e+18,
|
| 12109 |
"train_batch_size": 4,
|
| 12110 |
"trial_name": null,
|
| 12111 |
"trial_params": null
|