Femboyuwu2000
commited on
Commit
•
eaddd5c
1
Parent(s):
85a4373
Training in progress, step 500, 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 13982248
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:313aba40d65f377c286df07926609c388e7a57dab3c6547cc67866d2fa6580e7
|
3 |
size 13982248
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7062522
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdf2e4db48d199e348f95d4a0546bf60cade1749a871623b7819d7780f9cbf26
|
3 |
size 7062522
|
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:e97adf2d219717b72b639009fa1340825517d95c4424c6ddd24efbfb53c1ae67
|
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 sha256:46969ffbcb8cc5047d9170dfd926cf7206d745881d80bf65b9ce06c9c4e5194d
|
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": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -175,6 +175,13 @@
|
|
175 |
"learning_rate": 2.4e-05,
|
176 |
"loss": 3.8934,
|
177 |
"step": 480
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
178 |
}
|
179 |
],
|
180 |
"logging_steps": 20,
|
@@ -182,7 +189,7 @@
|
|
182 |
"num_input_tokens_seen": 0,
|
183 |
"num_train_epochs": 2,
|
184 |
"save_steps": 20,
|
185 |
-
"total_flos":
|
186 |
"train_batch_size": 8,
|
187 |
"trial_name": null,
|
188 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.04,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
175 |
"learning_rate": 2.4e-05,
|
176 |
"loss": 3.8934,
|
177 |
"step": 480
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.04,
|
181 |
+
"grad_norm": 28.714366912841797,
|
182 |
+
"learning_rate": 2.5e-05,
|
183 |
+
"loss": 3.9194,
|
184 |
+
"step": 500
|
185 |
}
|
186 |
],
|
187 |
"logging_steps": 20,
|
|
|
189 |
"num_input_tokens_seen": 0,
|
190 |
"num_train_epochs": 2,
|
191 |
"save_steps": 20,
|
192 |
+
"total_flos": 1194824141930496.0,
|
193 |
"train_batch_size": 8,
|
194 |
"trial_name": null,
|
195 |
"trial_params": null
|