Femboyuwu2000
commited on
Training in progress, step 60, 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 12803224
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a36d600cb075593139b01f4d1f27775faa37b77eacaf43dd2393c880d628c4e
|
3 |
size 12803224
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6472698
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e8d270f06b401efc87dfffdef9e44213731951a0be1e0698c2b5564562d00f9
|
3 |
size 6472698
|
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 sha256:1300bb8ffdcaac24edcc93c280d512ef74e120d1952b429e8e1905153ce6021f
|
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 sha256:79897bc37c77685183e620e5ff5489b797fe11af9975c9cb5639933de38b4cff
|
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": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -21,6 +21,13 @@
|
|
21 |
"learning_rate": 3.3333333333333333e-06,
|
22 |
"loss": 3.7271,
|
23 |
"step": 40
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
}
|
25 |
],
|
26 |
"logging_steps": 20,
|
@@ -28,7 +35,7 @@
|
|
28 |
"num_input_tokens_seen": 0,
|
29 |
"num_train_epochs": 1,
|
30 |
"save_steps": 20,
|
31 |
-
"total_flos":
|
32 |
"train_batch_size": 1,
|
33 |
"trial_name": null,
|
34 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.00018678060283439565,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 60,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
21 |
"learning_rate": 3.3333333333333333e-06,
|
22 |
"loss": 3.7271,
|
23 |
"step": 40
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.0,
|
27 |
+
"grad_norm": 47.56499481201172,
|
28 |
+
"learning_rate": 5e-06,
|
29 |
+
"loss": 3.5867,
|
30 |
+
"step": 60
|
31 |
}
|
32 |
],
|
33 |
"logging_steps": 20,
|
|
|
35 |
"num_input_tokens_seen": 0,
|
36 |
"num_train_epochs": 1,
|
37 |
"save_steps": 20,
|
38 |
+
"total_flos": 139848644812800.0,
|
39 |
"train_batch_size": 1,
|
40 |
"trial_name": null,
|
41 |
"trial_params": null
|