Training in progress, step 40, 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:c05b93acda6a7b2f81f0afd85f5badfd9cfa3a6e9e1606092480a0fbff648c88
|
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:b1a8fd6c5ca33512dfe3433cf2f0529599bf80a58b48b2d72c40c244f1ff4d38
|
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 sha256:87627699ac0553b87adb61769764b7859db5e6139e1fca8eca54989ab707ce0d
|
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:ba9088914de78dc99d767c21058d110a360c0bb50564c9ed4886490601d97b6d
|
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,
|
@@ -14,6 +14,13 @@
|
|
14 |
"learning_rate": 1.6666666666666667e-06,
|
15 |
"loss": 3.7393,
|
16 |
"step": 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
}
|
18 |
],
|
19 |
"logging_steps": 20,
|
@@ -21,7 +28,7 @@
|
|
21 |
"num_input_tokens_seen": 0,
|
22 |
"num_train_epochs": 1,
|
23 |
"save_steps": 20,
|
24 |
-
"total_flos":
|
25 |
"train_batch_size": 1,
|
26 |
"trial_name": null,
|
27 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.1130100472399276e-05,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 40,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
14 |
"learning_rate": 1.6666666666666667e-06,
|
15 |
"loss": 3.7393,
|
16 |
"step": 20
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0,
|
20 |
+
"grad_norm": 1.908144235610962,
|
21 |
+
"learning_rate": 3.2500000000000002e-06,
|
22 |
+
"loss": 3.6056,
|
23 |
+
"step": 40
|
24 |
}
|
25 |
],
|
26 |
"logging_steps": 20,
|
|
|
28 |
"num_input_tokens_seen": 0,
|
29 |
"num_train_epochs": 1,
|
30 |
"save_steps": 20,
|
31 |
+
"total_flos": 24304518549504.0,
|
32 |
"train_batch_size": 1,
|
33 |
"trial_name": null,
|
34 |
"trial_params": null
|