Training in progress, step 13800, 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 sha256:3b87d46a2e2a0561c425ac1321bec92dc869744dc471283bd66f76190315efca
|
| 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:e4ce8f845aaf00b2f8c19f2f795ae13fd8cdc08b38dc6dffbd3507bd332109c3
|
| 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 sha256:51f45a3d0cbfbd54bc9359bd8d79af463bc039ee70fae38f63f04594c8d59a15
|
| 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:ed9f3418d9cafadae95fa310d7d4a7366525ee46fc64989d71134ba1f7ac7c71
|
| 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": 27.
|
| 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,
|
|
@@ -1182,6 +1182,13 @@
|
|
| 1182 |
"learning_rate": 8.666666666666668e-06,
|
| 1183 |
"loss": 1.2178,
|
| 1184 |
"step": 13700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1185 |
}
|
| 1186 |
],
|
| 1187 |
"logging_steps": 100,
|
|
@@ -1201,7 +1208,7 @@
|
|
| 1201 |
"attributes": {}
|
| 1202 |
}
|
| 1203 |
},
|
| 1204 |
-
"total_flos": 2.
|
| 1205 |
"train_batch_size": 8,
|
| 1206 |
"trial_name": null,
|
| 1207 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 27.595688173722856,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 13800,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1182 |
"learning_rate": 8.666666666666668e-06,
|
| 1183 |
"loss": 1.2178,
|
| 1184 |
"step": 13700
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 27.595688173722856,
|
| 1188 |
+
"grad_norm": 0.24631735682487488,
|
| 1189 |
+
"learning_rate": 8.000000000000001e-06,
|
| 1190 |
+
"loss": 1.2223,
|
| 1191 |
+
"step": 13800
|
| 1192 |
}
|
| 1193 |
],
|
| 1194 |
"logging_steps": 100,
|
|
|
|
| 1208 |
"attributes": {}
|
| 1209 |
}
|
| 1210 |
},
|
| 1211 |
+
"total_flos": 2.153809878846957e+19,
|
| 1212 |
"train_batch_size": 8,
|
| 1213 |
"trial_name": null,
|
| 1214 |
"trial_params": null
|