MohamedAhmedAE
commited on
Commit
•
77b925b
1
Parent(s):
413ec54
Training in progress, step 4800, 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 sha256:8136d419b8890434688f361ff9055f226cad86b60136d37a16ab511ecdb95732
|
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 sha256:8ae7ca943292c1885fd2fa8fc4a0d7048e58e847fa6978c2dee6a1669f1d7daf
|
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 sha256:450d4161861142b0c607b082cb7975db64bce31f3c9c4ed471faa6a87cc3c651
|
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:cf6116349e1acbc51c06feeb07eabf38596d13779c8b6455b06cf034d85b895b
|
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,
|
@@ -168,6 +168,13 @@
|
|
168 |
"learning_rate": 1.9999977001049872e-05,
|
169 |
"loss": 1.5586,
|
170 |
"step": 4600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
171 |
}
|
172 |
],
|
173 |
"logging_steps": 200,
|
@@ -175,7 +182,7 @@
|
|
175 |
"num_input_tokens_seen": 0,
|
176 |
"num_train_epochs": 5,
|
177 |
"save_steps": 200,
|
178 |
-
"total_flos": 6.
|
179 |
"train_batch_size": 1,
|
180 |
"trial_name": null,
|
181 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.003569582693473241,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 4800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
168 |
"learning_rate": 1.9999977001049872e-05,
|
169 |
"loss": 1.5586,
|
170 |
"step": 4600
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.0,
|
174 |
+
"grad_norm": 2.3270204067230225,
|
175 |
+
"learning_rate": 1.9999974953119e-05,
|
176 |
+
"loss": 1.597,
|
177 |
+
"step": 4800
|
178 |
}
|
179 |
],
|
180 |
"logging_steps": 200,
|
|
|
182 |
"num_input_tokens_seen": 0,
|
183 |
"num_train_epochs": 5,
|
184 |
"save_steps": 200,
|
185 |
+
"total_flos": 6.297651302741606e+16,
|
186 |
"train_batch_size": 1,
|
187 |
"trial_name": null,
|
188 |
"trial_params": null
|