Training in progress, step 3940, 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:b322d572d078d4977fbf8e974cc6a34fa87c916ca40bb20005950901871c2f16
|
| 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 sha256:52e5ac2c311bdec5fd6b0ee75864c0a5b2152d538e7a8e5f7649dc07dedd2f7b
|
| 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:f2181f7218a65e4b84375e883cea34cc0d40b785e3c6f6b40a1985c1833d8ba4
|
| 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": 30.
|
| 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,
|
|
@@ -7082,6 +7082,24 @@
|
|
| 7082 |
"mean_token_accuracy": 0.6538343548774719,
|
| 7083 |
"num_tokens": 14332966.0,
|
| 7084 |
"step": 3930
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7085 |
}
|
| 7086 |
],
|
| 7087 |
"logging_steps": 5,
|
|
@@ -7101,7 +7119,7 @@
|
|
| 7101 |
"attributes": {}
|
| 7102 |
}
|
| 7103 |
},
|
| 7104 |
-
"total_flos": 7.
|
| 7105 |
"train_batch_size": 4,
|
| 7106 |
"trial_name": null,
|
| 7107 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 30.307692307692307,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3940,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7082 |
"mean_token_accuracy": 0.6538343548774719,
|
| 7083 |
"num_tokens": 14332966.0,
|
| 7084 |
"step": 3930
|
| 7085 |
+
},
|
| 7086 |
+
{
|
| 7087 |
+
"epoch": 30.26923076923077,
|
| 7088 |
+
"grad_norm": 0.0,
|
| 7089 |
+
"learning_rate": 3.0330000000000003e-05,
|
| 7090 |
+
"loss": 1.7853,
|
| 7091 |
+
"mean_token_accuracy": 0.6408940821886062,
|
| 7092 |
+
"num_tokens": 14350343.0,
|
| 7093 |
+
"step": 3935
|
| 7094 |
+
},
|
| 7095 |
+
{
|
| 7096 |
+
"epoch": 30.307692307692307,
|
| 7097 |
+
"grad_norm": 0.0,
|
| 7098 |
+
"learning_rate": 3.0305e-05,
|
| 7099 |
+
"loss": 1.6214,
|
| 7100 |
+
"mean_token_accuracy": 0.6724200338125229,
|
| 7101 |
+
"num_tokens": 14369664.0,
|
| 7102 |
+
"step": 3940
|
| 7103 |
}
|
| 7104 |
],
|
| 7105 |
"logging_steps": 5,
|
|
|
|
| 7119 |
"attributes": {}
|
| 7120 |
}
|
| 7121 |
},
|
| 7122 |
+
"total_flos": 7.282249938734285e+17,
|
| 7123 |
"train_batch_size": 4,
|
| 7124 |
"trial_name": null,
|
| 7125 |
"trial_params": null
|