MohamedAhmedAE
commited on
Commit
•
b75a263
1
Parent(s):
5dc0d5e
Training in progress, step 5000, 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:d3898deded357ae3f624f6da11d5a240cdabb03ebb6c20aaa1514ff2afc28f42
|
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 sha256:8b6589201aabf4474a11e89f074f30710b9c14f130975414126d44fac37ab285
|
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 sha256:6c2a46d21812f033b59f8253d10c55fd001488b63093ce2c9a28dd3b2087601c
|
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:dadb6c8212cca45778812f2e418e14e8bb1e227cbf578c8c3f0b8b32adfef7b7
|
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,
|
@@ -175,6 +175,13 @@
|
|
175 |
"learning_rate": 1.9999974953119e-05,
|
176 |
"loss": 1.597,
|
177 |
"step": 4800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
178 |
}
|
179 |
],
|
180 |
"logging_steps": 200,
|
@@ -182,7 +189,7 @@
|
|
182 |
"num_input_tokens_seen": 0,
|
183 |
"num_train_epochs": 5,
|
184 |
"save_steps": 200,
|
185 |
-
"total_flos": 6.
|
186 |
"train_batch_size": 1,
|
187 |
"trial_name": null,
|
188 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0037183153057012927,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 5000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
175 |
"learning_rate": 1.9999974953119e-05,
|
176 |
"loss": 1.597,
|
177 |
"step": 4800
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.0,
|
181 |
+
"grad_norm": 2.4163918495178223,
|
182 |
+
"learning_rate": 1.999997281785647e-05,
|
183 |
+
"loss": 1.5405,
|
184 |
+
"step": 5000
|
185 |
}
|
186 |
],
|
187 |
"logging_steps": 200,
|
|
|
189 |
"num_input_tokens_seen": 0,
|
190 |
"num_train_epochs": 5,
|
191 |
"save_steps": 200,
|
192 |
+
"total_flos": 6.541947938699674e+16,
|
193 |
"train_batch_size": 1,
|
194 |
"trial_name": null,
|
195 |
"trial_params": null
|