Training in progress, step 2300, 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:f598d525ffdd6b73acaf9cac0bb0a1c9af34406f61fd444575553f4f0caa9278
|
| 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:e71565859861788448040bad3b7258c02a415674df05487dbc8925f7bbb622e7
|
| 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 sha256:2788b9e4a3e02030f83b8e3801e6e323231f28c3256b02d54b3f0741c38af059
|
| 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 sha256:5fff414ace1867b67391b626a8e245a5248361d78f9269e3a675593c0e9e4f5a
|
| 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": 4.
|
| 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,
|
|
@@ -193,6 +193,13 @@
|
|
| 193 |
"learning_rate": 8.533333333333334e-05,
|
| 194 |
"loss": 1.294,
|
| 195 |
"step": 2200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 196 |
}
|
| 197 |
],
|
| 198 |
"logging_steps": 100,
|
|
@@ -212,7 +219,7 @@
|
|
| 212 |
"attributes": {}
|
| 213 |
}
|
| 214 |
},
|
| 215 |
-
"total_flos": 3.
|
| 216 |
"train_batch_size": 8,
|
| 217 |
"trial_name": null,
|
| 218 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.599281362287143,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 2300,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 193 |
"learning_rate": 8.533333333333334e-05,
|
| 194 |
"loss": 1.294,
|
| 195 |
"step": 2200
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 4.599281362287143,
|
| 199 |
+
"grad_norm": 0.16069631278514862,
|
| 200 |
+
"learning_rate": 8.466666666666667e-05,
|
| 201 |
+
"loss": 1.2912,
|
| 202 |
+
"step": 2300
|
| 203 |
}
|
| 204 |
],
|
| 205 |
"logging_steps": 100,
|
|
|
|
| 219 |
"attributes": {}
|
| 220 |
}
|
| 221 |
},
|
| 222 |
+
"total_flos": 3.589687709846733e+18,
|
| 223 |
"train_batch_size": 8,
|
| 224 |
"trial_name": null,
|
| 225 |
"trial_params": null
|