MohamedAhmedAE
commited on
Commit
•
f541b11
1
Parent(s):
2e4130d
Training in progress, step 6000, 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:df13651e277a0c57568ab8ad1700485f28f93fce313b51d305bf49236a22d848
|
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 sha256:3f6d8560b09a8acbd520a643f2c903a1b4abe534eed07f393b76e7e3b4383130
|
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 sha256:387d439f709c593f39d19f3e24beeef5450e32e99e883dfbed8c69aedc09f310
|
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:db17511cf40c553b235e796d2decd760897da6988ddf690cb68bdac8e17c1364
|
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,
|
@@ -210,6 +210,13 @@
|
|
210 |
"learning_rate": 1.9999963416130326e-05,
|
211 |
"loss": 1.6067,
|
212 |
"step": 5800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
213 |
}
|
214 |
],
|
215 |
"logging_steps": 200,
|
@@ -217,7 +224,7 @@
|
|
217 |
"num_input_tokens_seen": 0,
|
218 |
"num_train_epochs": 5,
|
219 |
"save_steps": 200,
|
220 |
-
"total_flos": 7.
|
221 |
"train_batch_size": 1,
|
222 |
"trial_name": null,
|
223 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.004461978366841551,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 6000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
210 |
"learning_rate": 1.9999963416130326e-05,
|
211 |
"loss": 1.6067,
|
212 |
"step": 5800
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.0,
|
216 |
+
"grad_norm": 2.953801393508911,
|
217 |
+
"learning_rate": 1.999996084464646e-05,
|
218 |
+
"loss": 1.6252,
|
219 |
+
"step": 6000
|
220 |
}
|
221 |
],
|
222 |
"logging_steps": 200,
|
|
|
224 |
"num_input_tokens_seen": 0,
|
225 |
"num_train_epochs": 5,
|
226 |
"save_steps": 200,
|
227 |
+
"total_flos": 7.88654619022295e+16,
|
228 |
"train_batch_size": 1,
|
229 |
"trial_name": null,
|
230 |
"trial_params": null
|