MohamedAhmedAE
commited on
Commit
•
1f8f7aa
1
Parent(s):
b26ddd4
Training in progress, step 6200, 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 sha256:814f9725a2fe2017d81c7865800e3fc5aaa4d89e46fab595b01bbf4f7f20db30
|
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:bfd0fc04c6dd797da3f4131745048e2e54e143452e73d060a7d4b95cdcc46ab1
|
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:d6abe2d849c4fd1f2d539f784dcb3eeec5c7c22dff6a560aa1f6ccd308e25b9e
|
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 sha256:76d8049c15ee2a00e055cffd8620c280fe7aa42e36ed292a62ff445777eff25a
|
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,
|
@@ -217,6 +217,13 @@
|
|
217 |
"learning_rate": 1.999996084464646e-05,
|
218 |
"loss": 1.6252,
|
219 |
"step": 6000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
220 |
}
|
221 |
],
|
222 |
"logging_steps": 200,
|
@@ -224,7 +231,7 @@
|
|
224 |
"num_input_tokens_seen": 0,
|
225 |
"num_train_epochs": 5,
|
226 |
"save_steps": 200,
|
227 |
-
"total_flos":
|
228 |
"train_batch_size": 1,
|
229 |
"trial_name": null,
|
230 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.004610710979069603,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 6200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
217 |
"learning_rate": 1.999996084464646e-05,
|
218 |
"loss": 1.6252,
|
219 |
"step": 6000
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.0,
|
223 |
+
"grad_norm": 1.8496161699295044,
|
224 |
+
"learning_rate": 1.9999958185831053e-05,
|
225 |
+
"loss": 1.5803,
|
226 |
+
"step": 6200
|
227 |
}
|
228 |
],
|
229 |
"logging_steps": 200,
|
|
|
231 |
"num_input_tokens_seen": 0,
|
232 |
"num_train_epochs": 5,
|
233 |
"save_steps": 200,
|
234 |
+
"total_flos": 8.142964605100032e+16,
|
235 |
"train_batch_size": 1,
|
236 |
"trial_name": null,
|
237 |
"trial_params": null
|