Femboyuwu2000
commited on
Commit
•
69af666
1
Parent(s):
50857db
Training in progress, step 140, 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 4725640
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e959f2bedd4d1c06f7560c91048e25cb09d9cd0bf6f1c8ec525e1b2a50b2be5
|
3 |
size 4725640
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2423738
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ea726ba9fc9c9eb1066b46bde05b501eb2ebeaedc9625cd740c2148848db790
|
3 |
size 2423738
|
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 sha256:840146a001ff48fd14f9176d2551e18a68e4936bbf1b797f6c21c89adb36c9a6
|
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 sha256:7d82c151815973da3ac2e374434a38a206899c333d88de9e900733b7877b8460
|
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":
|
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,
|
@@ -49,6 +49,13 @@
|
|
49 |
"learning_rate": 1.9833333333333335e-05,
|
50 |
"loss": 3.1903,
|
51 |
"step": 120
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
52 |
}
|
53 |
],
|
54 |
"logging_steps": 20,
|
@@ -56,7 +63,7 @@
|
|
56 |
"num_input_tokens_seen": 0,
|
57 |
"num_train_epochs": 1,
|
58 |
"save_steps": 20,
|
59 |
-
"total_flos":
|
60 |
"train_batch_size": 1,
|
61 |
"trial_name": null,
|
62 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.00010895535165339746,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 140,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
49 |
"learning_rate": 1.9833333333333335e-05,
|
50 |
"loss": 3.1903,
|
51 |
"step": 120
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.0,
|
55 |
+
"grad_norm": 3.08722186088562,
|
56 |
+
"learning_rate": 2.3166666666666666e-05,
|
57 |
+
"loss": 3.5379,
|
58 |
+
"step": 140
|
59 |
}
|
60 |
],
|
61 |
"logging_steps": 20,
|
|
|
63 |
"num_input_tokens_seen": 0,
|
64 |
"num_train_epochs": 1,
|
65 |
"save_steps": 20,
|
66 |
+
"total_flos": 721108975951872.0,
|
67 |
"train_batch_size": 1,
|
68 |
"trial_name": null,
|
69 |
"trial_params": null
|