Training in progress, step 4090, 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 sha256:273d24110e3467af0f339aa38709e8dd8dedb1ee6685a2eb076f0dd2fbe223d4
|
| 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:de12d2d68ce09d1aee055baed4e96b61206b33f3d5e65f9fedbfa1b302495ab4
|
| 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 sha256:1a5799904117e4fd9a7eb349a2c4aa7eb38caf017147d18db132f8eb80b37450
|
| 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 sha256:1cd920df1a88a6590e2a21fbefc645f07be482c398eb9b22caf03dcad21ef026
|
| 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,
|
|
@@ -4098,6 +4098,16 @@
|
|
| 4098 |
"mean_token_accuracy": 0.7543898217380047,
|
| 4099 |
"num_tokens": 19027278.0,
|
| 4100 |
"step": 4080
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4101 |
}
|
| 4102 |
],
|
| 4103 |
"logging_steps": 10,
|
|
@@ -4117,7 +4127,7 @@
|
|
| 4117 |
"attributes": {}
|
| 4118 |
}
|
| 4119 |
},
|
| 4120 |
-
"total_flos": 9.
|
| 4121 |
"train_batch_size": 4,
|
| 4122 |
"trial_name": null,
|
| 4123 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8725333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4090,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4098 |
"mean_token_accuracy": 0.7543898217380047,
|
| 4099 |
"num_tokens": 19027278.0,
|
| 4100 |
"step": 4080
|
| 4101 |
+
},
|
| 4102 |
+
{
|
| 4103 |
+
"entropy": 0.889600582420826,
|
| 4104 |
+
"epoch": 0.8725333333333334,
|
| 4105 |
+
"grad_norm": 0.2604535222053528,
|
| 4106 |
+
"learning_rate": 6.281831630592783e-05,
|
| 4107 |
+
"loss": 1.0391739845275878,
|
| 4108 |
+
"mean_token_accuracy": 0.7718042567372322,
|
| 4109 |
+
"num_tokens": 19073552.0,
|
| 4110 |
+
"step": 4090
|
| 4111 |
}
|
| 4112 |
],
|
| 4113 |
"logging_steps": 10,
|
|
|
|
| 4127 |
"attributes": {}
|
| 4128 |
}
|
| 4129 |
},
|
| 4130 |
+
"total_flos": 9.027474524979302e+16,
|
| 4131 |
"train_batch_size": 4,
|
| 4132 |
"trial_name": null,
|
| 4133 |
"trial_params": null
|