MohamedAhmedAE
commited on
Commit
•
7a0ca95
1
Parent(s):
820e03f
Training in progress, step 4200, 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:bafc3f6442e5ba84431ff078caa6e69b3a936652a78ec4e062738afe5c219732
|
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:e921e944e51dba181ad318d41576f8ac3157dc39c4bff064cdc6b4b895ad6d05
|
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:de92704bc3b6ffc2d27e74d056f93cc6b41e535e9e0201f0fa7c3b78e6075e90
|
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 sha256:8ae6e4af65e99b8816fc6ca644da9b1cf355b8cdc1d577590a1d02007539bd66
|
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,
|
@@ -147,6 +147,13 @@
|
|
147 |
"learning_rate": 1.999998261213993e-05,
|
148 |
"loss": 1.6025,
|
149 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
150 |
}
|
151 |
],
|
152 |
"logging_steps": 200,
|
@@ -154,7 +161,7 @@
|
|
154 |
"num_input_tokens_seen": 0,
|
155 |
"num_train_epochs": 5,
|
156 |
"save_steps": 200,
|
157 |
-
"total_flos": 5.
|
158 |
"train_batch_size": 1,
|
159 |
"trial_name": null,
|
160 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.003123384856789086,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 4200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
147 |
"learning_rate": 1.999998261213993e-05,
|
148 |
"loss": 1.6025,
|
149 |
"step": 4000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.0,
|
153 |
+
"grad_norm": 2.5482230186462402,
|
154 |
+
"learning_rate": 1.9999980825767474e-05,
|
155 |
+
"loss": 1.5963,
|
156 |
+
"step": 4200
|
157 |
}
|
158 |
],
|
159 |
"logging_steps": 200,
|
|
|
161 |
"num_input_tokens_seen": 0,
|
162 |
"num_train_epochs": 5,
|
163 |
"save_steps": 200,
|
164 |
+
"total_flos": 5.526240672691814e+16,
|
165 |
"train_batch_size": 1,
|
166 |
"trial_name": null,
|
167 |
"trial_params": null
|