devvanshhh
commited on
Commit
•
4085f9e
1
Parent(s):
3b3a4a2
Training in progress, step 175, checkpoint
Browse files
last-checkpoint/adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 369214349
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53401ac585809d05460d65a1c9bda64d9fed4e7464a57c8369d10aa36361265b
|
3 |
size 369214349
|
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 369142184
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1863412909c6254531f93a09eaeec490fbcec6b0c6b49eba7eb5de3c432daa91
|
3 |
size 369142184
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 738393541
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd65da376d1d23b8cea5bb205442aa0a6e033fcfe39a504ce942a9433e98e7de
|
3 |
size 738393541
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d94693b29beaeb0eb97f84f6c7e5646a39d3c2014bceab5a56d58a3a176dc534
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85894d497f856bc538fc126c6d71dd8363d6b361c3bcd580d80973fd6ad8f277
|
3 |
size 627
|
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,
|
@@ -43,13 +43,19 @@
|
|
43 |
"learning_rate": 0.0002,
|
44 |
"loss": 0.7958,
|
45 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
46 |
}
|
47 |
],
|
48 |
"logging_steps": 25,
|
49 |
"max_steps": 728,
|
50 |
"num_train_epochs": 1,
|
51 |
"save_steps": 25,
|
52 |
-
"total_flos":
|
53 |
"trial_name": null,
|
54 |
"trial_params": null
|
55 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2403846153846154,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 175,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
43 |
"learning_rate": 0.0002,
|
44 |
"loss": 0.7958,
|
45 |
"step": 150
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.24,
|
49 |
+
"learning_rate": 0.0002,
|
50 |
+
"loss": 1.1292,
|
51 |
+
"step": 175
|
52 |
}
|
53 |
],
|
54 |
"logging_steps": 25,
|
55 |
"max_steps": 728,
|
56 |
"num_train_epochs": 1,
|
57 |
"save_steps": 25,
|
58 |
+
"total_flos": 1754634913382400.0,
|
59 |
"trial_name": null,
|
60 |
"trial_params": null
|
61 |
}
|