Training in progress, step 1600, 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 8137792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a09897170ca4c86ea4ae7f6453538d8d39b54c06e27455ce0e7905841a38af0
|
| 3 |
size 8137792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16386426
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12452e90b4a1fd677e732337508808a3f5243000b967e24178cfe6afd5912c5f
|
| 3 |
size 16386426
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a4d689899d8df9a42c41f1e954507b0244addb8d13cda7a5284587e71310b52
|
| 3 |
size 15006
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8721aea20789d976adf9f26393b2100d4d9a0b80e8c4a8958557bf529935434c
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -136,6 +136,13 @@
|
|
| 136 |
"eval_samples_per_second": 19.868,
|
| 137 |
"eval_steps_per_second": 2.484,
|
| 138 |
"step": 1500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 139 |
}
|
| 140 |
],
|
| 141 |
"logging_steps": 100,
|
|
@@ -155,7 +162,7 @@
|
|
| 155 |
"attributes": {}
|
| 156 |
}
|
| 157 |
},
|
| 158 |
-
"total_flos": 2.
|
| 159 |
"train_batch_size": 8,
|
| 160 |
"trial_name": null,
|
| 161 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.199500078112795,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1600,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 136 |
"eval_samples_per_second": 19.868,
|
| 137 |
"eval_steps_per_second": 2.484,
|
| 138 |
"step": 1500
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 3.199500078112795,
|
| 142 |
+
"grad_norm": 0.1341802030801773,
|
| 143 |
+
"learning_rate": 8.933333333333334e-05,
|
| 144 |
+
"loss": 1.3093,
|
| 145 |
+
"step": 1600
|
| 146 |
}
|
| 147 |
],
|
| 148 |
"logging_steps": 100,
|
|
|
|
| 162 |
"attributes": {}
|
| 163 |
}
|
| 164 |
},
|
| 165 |
+
"total_flos": 2.4971720683998413e+18,
|
| 166 |
"train_batch_size": 8,
|
| 167 |
"trial_name": null,
|
| 168 |
"trial_params": null
|