Femboyuwu2000
commited on
Commit
•
dc00cbb
1
Parent(s):
291544f
Training in progress, step 20, checkpoint
Browse files- last-checkpoint/adapter_config.json +0 -1
- last-checkpoint/adapter_model.safetensors +2 -2
- last-checkpoint/optimizer.pt +2 -2
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/tokenizer.json +2 -2
- last-checkpoint/trainer_state.json +7 -42
- last-checkpoint/training_args.bin +1 -1
last-checkpoint/adapter_config.json
CHANGED
@@ -20,7 +20,6 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"word_embeddings",
|
24 |
"query_key_value"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM",
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
23 |
"query_key_value"
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM",
|
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8772894d12f78b8fc6af826e5276f655e373807dd07b22aed0543e66cbef5292
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af22a61da37ba89fb906663ab84e4be41468f2ac1684b76b88311f42c59c536f
|
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:ad35aae38bdb55d17557911fb95298bbafabf6ae7c3c9106d36788ba438d412a
|
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:bd9af3bd0fffafb125626179d8875b2db50ea3974e8522bd88f257772b2ca911
|
3 |
size 1064
|
last-checkpoint/tokenizer.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fe0e32d5e685050c0787e7fa781db4fc73bddea1b6da68659010dedc06005b3
|
3 |
+
size 14500638
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,54 +1,19 @@
|
|
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,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.0,
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate":
|
15 |
-
"loss": 3.
|
16 |
"step": 20
|
17 |
-
},
|
18 |
-
{
|
19 |
-
"epoch": 0.0,
|
20 |
-
"grad_norm": 90.38651275634766,
|
21 |
-
"learning_rate": 5.333333333333334e-06,
|
22 |
-
"loss": 3.7962,
|
23 |
-
"step": 40
|
24 |
-
},
|
25 |
-
{
|
26 |
-
"epoch": 0.0,
|
27 |
-
"grad_norm": 108.40189361572266,
|
28 |
-
"learning_rate": 8.666666666666668e-06,
|
29 |
-
"loss": 3.5164,
|
30 |
-
"step": 60
|
31 |
-
},
|
32 |
-
{
|
33 |
-
"epoch": 0.0,
|
34 |
-
"grad_norm": 109.34711456298828,
|
35 |
-
"learning_rate": 1.2e-05,
|
36 |
-
"loss": 4.0846,
|
37 |
-
"step": 80
|
38 |
-
},
|
39 |
-
{
|
40 |
-
"epoch": 0.0,
|
41 |
-
"grad_norm": 75.66071319580078,
|
42 |
-
"learning_rate": 1.5333333333333334e-05,
|
43 |
-
"loss": 3.594,
|
44 |
-
"step": 100
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 0.0,
|
48 |
-
"grad_norm": 17.74490737915039,
|
49 |
-
"learning_rate": 1.866666666666667e-05,
|
50 |
-
"loss": 3.6379,
|
51 |
-
"step": 120
|
52 |
}
|
53 |
],
|
54 |
"logging_steps": 20,
|
@@ -56,8 +21,8 @@
|
|
56 |
"num_input_tokens_seen": 0,
|
57 |
"num_train_epochs": 1,
|
58 |
"save_steps": 20,
|
59 |
-
"total_flos":
|
60 |
-
"train_batch_size":
|
61 |
"trial_name": null,
|
62 |
"trial_params": null
|
63 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.1130100472399276e-05,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 20,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.0,
|
13 |
+
"grad_norm": 1.776742935180664,
|
14 |
+
"learning_rate": 3.3333333333333333e-06,
|
15 |
+
"loss": 3.5415,
|
16 |
"step": 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
}
|
18 |
],
|
19 |
"logging_steps": 20,
|
|
|
21 |
"num_input_tokens_seen": 0,
|
22 |
"num_train_epochs": 1,
|
23 |
"save_steps": 20,
|
24 |
+
"total_flos": 184619525971968.0,
|
25 |
+
"train_batch_size": 2,
|
26 |
"trial_name": null,
|
27 |
"trial_params": null
|
28 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da5d41afb0ddac16c18350b7a14dbb4a1e14941c08946cda5f16f71c0aaf525c
|
3 |
size 4984
|