MohamedAhmedAE
commited on
Commit
•
6a89fa7
1
Parent(s):
df8d142
Training in progress, step 5200, 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:a32a8472f24ac0ae5777096edb75d3f2a4dcd1c6f71a5a93bc0a5ae4a7fe3dcf
|
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 sha256:3289ab88db5dbcb3be2060676922612848d1ca284d404ff24a82083e0a9f0264
|
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 sha256:49f463b5f7795e26b9e24462f96b39a52b6b97b5adfc046ad7d24a04ed313a17
|
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:ac1bdf201c735a2a3a0e28881f6c25b745bd1b24bb6cddaa05404a7fc4dbfa5a
|
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,
|
@@ -182,6 +182,13 @@
|
|
182 |
"learning_rate": 1.999997281785647e-05,
|
183 |
"loss": 1.5405,
|
184 |
"step": 5000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
185 |
}
|
186 |
],
|
187 |
"logging_steps": 200,
|
@@ -189,7 +196,7 @@
|
|
189 |
"num_input_tokens_seen": 0,
|
190 |
"num_train_epochs": 5,
|
191 |
"save_steps": 200,
|
192 |
-
"total_flos": 6.
|
193 |
"train_batch_size": 1,
|
194 |
"trial_name": null,
|
195 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0038670479179293447,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 5200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
182 |
"learning_rate": 1.999997281785647e-05,
|
183 |
"loss": 1.5405,
|
184 |
"step": 5000
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.0,
|
188 |
+
"grad_norm": 2.7667906284332275,
|
189 |
+
"learning_rate": 1.9999970595262297e-05,
|
190 |
+
"loss": 1.5714,
|
191 |
+
"step": 5200
|
192 |
}
|
193 |
],
|
194 |
"logging_steps": 200,
|
|
|
196 |
"num_input_tokens_seen": 0,
|
197 |
"num_train_epochs": 5,
|
198 |
"save_steps": 200,
|
199 |
+
"total_flos": 6.809650430179738e+16,
|
200 |
"train_batch_size": 1,
|
201 |
"trial_name": null,
|
202 |
"trial_params": null
|