Commit
•
912cab8
1
Parent(s):
57c915b
Training in progress, step 5800, 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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cea91fb1ecf648cc0d9b1c34c231eeb11e493def8af1b24626b09ec699dcc574
|
3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 84581014
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c0cba11636076b32b316427e9e0cc1651d3ec55ea03d8d1f601d48d89153db6
|
3 |
size 84581014
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98af83b6a2d5ccf06ac67101b7d27db5e186113101b0ca8f3d71a5ca34f809f8
|
3 |
size 14244
|
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 sha256:8b9669fdeac6f8ea3f9f111ac5b46d4674ad051ccbc5e8083a6ee1a8eb3361c0
|
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": 0.
|
5 |
"eval_steps": 2000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -203,6 +203,13 @@
|
|
203 |
"learning_rate": 1.999996590028264e-05,
|
204 |
"loss": 1.5651,
|
205 |
"step": 5600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
206 |
}
|
207 |
],
|
208 |
"logging_steps": 200,
|
@@ -210,7 +217,7 @@
|
|
210 |
"num_input_tokens_seen": 0,
|
211 |
"num_train_epochs": 5,
|
212 |
"save_steps": 200,
|
213 |
-
"total_flos": 7.
|
214 |
"train_batch_size": 1,
|
215 |
"trial_name": null,
|
216 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0043132457546134996,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 5800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
203 |
"learning_rate": 1.999996590028264e-05,
|
204 |
"loss": 1.5651,
|
205 |
"step": 5600
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.0,
|
209 |
+
"grad_norm": 4.262922763824463,
|
210 |
+
"learning_rate": 1.9999963416130326e-05,
|
211 |
+
"loss": 1.6067,
|
212 |
+
"step": 5800
|
213 |
}
|
214 |
],
|
215 |
"logging_steps": 200,
|
|
|
217 |
"num_input_tokens_seen": 0,
|
218 |
"num_train_epochs": 5,
|
219 |
"save_steps": 200,
|
220 |
+
"total_flos": 7.611114196832256e+16,
|
221 |
"train_batch_size": 1,
|
222 |
"trial_name": null,
|
223 |
"trial_params": null
|