MohamedAhmedAE
commited on
Commit
•
53ee68b
1
Parent(s):
c0fee2d
Training in progress, step 6800, 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 sha256:47fb5b2e87c858b356a497af5a368276e3f58a5b8eb72b8afd457002cb20edd9
|
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 sha256:359bfa99d36cf98378251b4b3e7fbc9f02cda5213fa14831cd11bb03b49f087c
|
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 sha256:9b1c9b6d56495163f90ed52427fdb2571b9bad67126fc94f02c5944a1a78d778
|
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 sha256:4052ec18fc2afb5774bb3660c8960b211e377d97915cd96a50052364ba383943
|
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,
|
@@ -238,6 +238,13 @@
|
|
238 |
"learning_rate": 1.9999952606205736e-05,
|
239 |
"loss": 1.6222,
|
240 |
"step": 6600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
241 |
}
|
242 |
],
|
243 |
"logging_steps": 200,
|
@@ -245,7 +252,7 @@
|
|
245 |
"num_input_tokens_seen": 0,
|
246 |
"num_train_epochs": 5,
|
247 |
"save_steps": 200,
|
248 |
-
"total_flos": 8.
|
249 |
"train_batch_size": 1,
|
250 |
"trial_name": null,
|
251 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0050569088157537585,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 6800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
238 |
"learning_rate": 1.9999952606205736e-05,
|
239 |
"loss": 1.6222,
|
240 |
"step": 6600
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.01,
|
244 |
+
"grad_norm": 2.0667927265167236,
|
245 |
+
"learning_rate": 1.999994968539587e-05,
|
246 |
+
"loss": 1.5443,
|
247 |
+
"step": 6800
|
248 |
}
|
249 |
],
|
250 |
"logging_steps": 200,
|
|
|
252 |
"num_input_tokens_seen": 0,
|
253 |
"num_train_epochs": 5,
|
254 |
"save_steps": 200,
|
255 |
+
"total_flos": 8.931527756085658e+16,
|
256 |
"train_batch_size": 1,
|
257 |
"trial_name": null,
|
258 |
"trial_params": null
|