Training in progress, step 2200, 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 250422888
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3532bf018606364bf4f24db3d4392489b67f9bfab6d086b4632bb11a3e5e9c14
|
| 3 |
size 250422888
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 126034975
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e35764b8a4413dd05e7ec8f4adb7fdf5c7b4feae48a1b1eb74b7541667cf8d4c
|
| 3 |
size 126034975
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c47bc107fbed13e50bc54c3efa2183299d8e616284ebd773ece8e4c6b0de84a
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f10a983aa914555fea6e5c0db8d7ddbaebbe7e28546c78ee0e93ac76cbc28436
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 5.
|
| 5 |
"eval_steps": 200,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -137,13 +137,26 @@
|
|
| 137 |
"eval_samples_per_second": 2.751,
|
| 138 |
"eval_steps_per_second": 0.176,
|
| 139 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 140 |
}
|
| 141 |
],
|
| 142 |
"logging_steps": 200,
|
| 143 |
"max_steps": 2232,
|
| 144 |
"num_train_epochs": 6,
|
| 145 |
"save_steps": 200,
|
| 146 |
-
"total_flos":
|
| 147 |
"trial_name": null,
|
| 148 |
"trial_params": null
|
| 149 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.913978494623656,
|
| 5 |
"eval_steps": 200,
|
| 6 |
+
"global_step": 2200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 137 |
"eval_samples_per_second": 2.751,
|
| 138 |
"eval_steps_per_second": 0.176,
|
| 139 |
"step": 2000
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 5.91,
|
| 143 |
+
"learning_rate": 0.0002,
|
| 144 |
+
"loss": 0.0259,
|
| 145 |
+
"step": 2200
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 5.91,
|
| 149 |
+
"eval_runtime": 113.6789,
|
| 150 |
+
"eval_samples_per_second": 2.753,
|
| 151 |
+
"eval_steps_per_second": 0.176,
|
| 152 |
+
"step": 2200
|
| 153 |
}
|
| 154 |
],
|
| 155 |
"logging_steps": 200,
|
| 156 |
"max_steps": 2232,
|
| 157 |
"num_train_epochs": 6,
|
| 158 |
"save_steps": 200,
|
| 159 |
+
"total_flos": 1.048086317730816e+18,
|
| 160 |
"trial_name": null,
|
| 161 |
"trial_params": null
|
| 162 |
}
|