Training in progress, step 2800, 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 sha256:9dc2f178242b7550632df0df2c55f6420a674d51d6c09e421e0b4faf984b3402
|
| 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 sha256:2c32acf9f365e8764eb9dbf929e62f257e5badae056f82b4ddf195a6c1d8f23b
|
| 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 sha256:76ba8b738578f295e0a532463bd8e85b447498e4475e9410d6b141ead2ba5753
|
| 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:b5849322fb77b87af1a977898ab484962b1650e0f7a5019e778b3234f5454c07
|
| 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.
|
| 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,
|
|
@@ -236,6 +236,13 @@
|
|
| 236 |
"learning_rate": 8.2e-05,
|
| 237 |
"loss": 1.2805,
|
| 238 |
"step": 2700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 239 |
}
|
| 240 |
],
|
| 241 |
"logging_steps": 100,
|
|
@@ -255,7 +262,7 @@
|
|
| 255 |
"attributes": {}
|
| 256 |
}
|
| 257 |
},
|
| 258 |
-
"total_flos": 4.
|
| 259 |
"train_batch_size": 8,
|
| 260 |
"trial_name": null,
|
| 261 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.599125136697391,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 2800,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 236 |
"learning_rate": 8.2e-05,
|
| 237 |
"loss": 1.2805,
|
| 238 |
"step": 2700
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 5.599125136697391,
|
| 242 |
+
"grad_norm": 0.15919053554534912,
|
| 243 |
+
"learning_rate": 8.133333333333334e-05,
|
| 244 |
+
"loss": 1.279,
|
| 245 |
+
"step": 2800
|
| 246 |
}
|
| 247 |
],
|
| 248 |
"logging_steps": 100,
|
|
|
|
| 262 |
"attributes": {}
|
| 263 |
}
|
| 264 |
},
|
| 265 |
+
"total_flos": 4.370053408917291e+18,
|
| 266 |
"train_batch_size": 8,
|
| 267 |
"trial_name": null,
|
| 268 |
"trial_params": null
|