Femboyuwu2000
commited on
Commit
•
353bd36
1
Parent(s):
1fcd4be
Training in progress, step 100, 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 8077608
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79d9c815d4c43548c4c0ce822c3f1c0ee1bdede2f9fab3ab3cfa6a4b4da825c8
|
3 |
size 8077608
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4052500
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3869c96ebfba4f36b625f829a247602f184bab0bda88f860ef66d890bb9851f
|
3 |
size 4052500
|
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:f32c34e49a5be573fa37f12748aab7e78650fd25c6cf007f14b7927a9f8cf3fb
|
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,
|
@@ -35,6 +35,13 @@
|
|
35 |
"learning_rate": 4e-06,
|
36 |
"loss": 4.6765,
|
37 |
"step": 80
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
}
|
39 |
],
|
40 |
"logging_steps": 20,
|
@@ -42,7 +49,7 @@
|
|
42 |
"num_input_tokens_seen": 0,
|
43 |
"num_train_epochs": 1,
|
44 |
"save_steps": 20,
|
45 |
-
"total_flos":
|
46 |
"train_batch_size": 2,
|
47 |
"trial_name": null,
|
48 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.002,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
35 |
"learning_rate": 4e-06,
|
36 |
"loss": 4.6765,
|
37 |
"step": 80
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.0,
|
41 |
+
"grad_norm": 147.12461853027344,
|
42 |
+
"learning_rate": 4.9999999999999996e-06,
|
43 |
+
"loss": 4.7237,
|
44 |
+
"step": 100
|
45 |
}
|
46 |
],
|
47 |
"logging_steps": 20,
|
|
|
49 |
"num_input_tokens_seen": 0,
|
50 |
"num_train_epochs": 1,
|
51 |
"save_steps": 20,
|
52 |
+
"total_flos": 34052722827264.0,
|
53 |
"train_batch_size": 2,
|
54 |
"trial_name": null,
|
55 |
"trial_params": null
|