Training in progress, step 4100, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67abef3040ebedf604da50a24ed03285a45a9d7eb7ac8c410646fd74522733e4
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09eac62166d6bc29c4117a3983eef70a68dd7fba132d72e552169f93e3fef6dc
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2bc0e78b487ec09b26f5e38995aebc28bf2ea524c98bef42a35f5b7a2fa0585
|
| 3 |
size 14645
|
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:be8178c5ebdaf6e1bce8cdbe0782794f33579fb4f40826cc2ecce542d68e0093
|
| 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": 0.
|
| 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,
|
|
@@ -4108,6 +4108,16 @@
|
|
| 4108 |
"mean_token_accuracy": 0.7718042567372322,
|
| 4109 |
"num_tokens": 19073552.0,
|
| 4110 |
"step": 4090
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4111 |
}
|
| 4112 |
],
|
| 4113 |
"logging_steps": 10,
|
|
@@ -4127,7 +4137,7 @@
|
|
| 4127 |
"attributes": {}
|
| 4128 |
}
|
| 4129 |
},
|
| 4130 |
-
"total_flos": 9.
|
| 4131 |
"train_batch_size": 4,
|
| 4132 |
"trial_name": null,
|
| 4133 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8746666666666667,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4100,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4108 |
"mean_token_accuracy": 0.7718042567372322,
|
| 4109 |
"num_tokens": 19073552.0,
|
| 4110 |
"step": 4090
|
| 4111 |
+
},
|
| 4112 |
+
{
|
| 4113 |
+
"entropy": 0.8700525127351284,
|
| 4114 |
+
"epoch": 0.8746666666666667,
|
| 4115 |
+
"grad_norm": 0.26574060320854187,
|
| 4116 |
+
"learning_rate": 6.265095251578796e-05,
|
| 4117 |
+
"loss": 0.9732645988464356,
|
| 4118 |
+
"mean_token_accuracy": 0.7781016409397126,
|
| 4119 |
+
"num_tokens": 19112840.0,
|
| 4120 |
+
"step": 4100
|
| 4121 |
}
|
| 4122 |
],
|
| 4123 |
"logging_steps": 10,
|
|
|
|
| 4137 |
"attributes": {}
|
| 4138 |
}
|
| 4139 |
},
|
| 4140 |
+
"total_flos": 9.045065692627046e+16,
|
| 4141 |
"train_batch_size": 4,
|
| 4142 |
"trial_name": null,
|
| 4143 |
"trial_params": null
|