Hugging Face's logo

kdearsty
/
llama-testing

PEFT
PyTorch
Safetensors
llama
Model card Files
xet
Community
1
kdearsty commited on
Commit
e2ed871
·
verified ·
1 Parent(s): 630f718

Upload my model weights

Browse files
Files changed (7) hide show
  1. adapter_config.json +2 -2
  2. adapter_model.safetensors +1 -1
  3. optimizer.pt +1 -1
  4. rng_state.pth +1 -1
  5. scheduler.pt +1 -1
  6. trainer_state.json +57 -15
  7. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -27,8 +27,8 @@
27
  "rank_pattern": {},
28
  "revision": null,
29
  "target_modules": [
30
- "v_proj",
31
- "q_proj"
32
  ],
33
  "task_type": "SEQ_CLS",
34
  "trainable_token_indices": null,
 
27
  "rank_pattern": {},
28
  "revision": null,
29
  "target_modules": [
30
+ "q_proj",
31
+ "v_proj"
32
  ],
33
  "task_type": "SEQ_CLS",
34
  "trainable_token_indices": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c252e5768fd0cf41e616c057edcc7c3ddc5c0abb9aa2d32544340c132dabadf9
3
  size 17640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3f2dc857ece2ff26d331ff634f8de10cfcfa950f3dcb2e34546a1cba03a0618
3
  size 17640
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b144970d43b1e33bb9eb8e370289d0ae0fe867582e50711f325294b892e6724f
3
  size 41027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:423fac003844c02895c0874e0f5b2ef407026dff7a4d214b1ae5bbaa3e0cc68f
3
  size 41027
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60ee1ac7c2476b9ff76394ef5da7cd1f347e5f322ff7c25e327029b246355e51
3
  size 13990
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef19ffcd56004336b9f135564a902e1a7a7d8c546c184bdeed5ab4417799b240
3
  size 13990
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8bf3b39aba999c7ce84889c1f825bc67f8c308b05e6789287fefa2acaa63533
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f64c53201a4c4c373e851f4cc152b657fbb64e463ffca42b4a9cf2efb71d6834
3
  size 1064
trainer_state.json CHANGED
@@ -1,30 +1,72 @@
1
  {
2
- "best_global_step": 23,
3
- "best_metric": 0.002150537634408602,
4
- "best_model_checkpoint": "/home/kat/git-repos/icse/results/tracing/19-05-2025:16-45-07/checkpoint-23",
5
  "epoch": 1.0,
6
  "eval_steps": 500,
7
- "global_step": 23,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  {
13
  "epoch": 1.0,
14
- "eval_accuracy": 0.03333333333333333,
15
  "eval_balanced_accuracy": 0.0,
16
- "eval_f1_score": 0.002150537634408602,
17
- "eval_loss": 0.7450189590454102,
18
- "eval_precision": 0.0011111111111111111,
19
- "eval_recall": 0.03333333333333333,
20
- "eval_runtime": 3.122,
21
- "eval_samples_per_second": 28.828,
22
- "eval_steps_per_second": 28.828,
23
- "step": 23
24
  }
25
  ],
26
  "logging_steps": 50,
27
- "max_steps": 23,
28
  "num_input_tokens_seen": 0,
29
  "num_train_epochs": 1,
30
  "save_steps": 500,
@@ -40,7 +82,7 @@
40
  "attributes": {}
41
  }
42
  },
43
- "total_flos": 3432947616.0,
44
  "train_batch_size": 1,
45
  "trial_name": null,
46
  "trial_params": null
 
1
  {
2
+ "best_global_step": 315,
3
+ "best_metric": 0.36862244897959184,
4
+ "best_model_checkpoint": "/home/kat/git-repos/icse/results/rsa/19-05-2025:16-53-56/checkpoint-315",
5
  "epoch": 1.0,
6
  "eval_steps": 500,
7
+ "global_step": 315,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
12
+ {
13
+ "epoch": 0.15873015873015872,
14
+ "grad_norm": 2.652902364730835,
15
+ "learning_rate": 1.688888888888889e-05,
16
+ "loss": 0.7018,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.31746031746031744,
21
+ "grad_norm": 2.970874786376953,
22
+ "learning_rate": 1.3714285714285716e-05,
23
+ "loss": 0.6905,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.47619047619047616,
28
+ "grad_norm": 2.647416114807129,
29
+ "learning_rate": 1.053968253968254e-05,
30
+ "loss": 0.6973,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.6349206349206349,
35
+ "grad_norm": 2.643963575363159,
36
+ "learning_rate": 7.3650793650793666e-06,
37
+ "loss": 0.6904,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.7936507936507936,
42
+ "grad_norm": 2.978494882583618,
43
+ "learning_rate": 4.190476190476191e-06,
44
+ "loss": 0.6785,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.9523809523809523,
49
+ "grad_norm": 2.981330633163452,
50
+ "learning_rate": 1.015873015873016e-06,
51
+ "loss": 0.6877,
52
+ "step": 300
53
+ },
54
  {
55
  "epoch": 1.0,
56
+ "eval_accuracy": 0.53125,
57
  "eval_balanced_accuracy": 0.0,
58
+ "eval_f1_score": 0.36862244897959184,
59
+ "eval_loss": 0.691247820854187,
60
+ "eval_precision": 0.2822265625,
61
+ "eval_recall": 0.53125,
62
+ "eval_runtime": 2.2767,
63
+ "eval_samples_per_second": 28.111,
64
+ "eval_steps_per_second": 28.111,
65
+ "step": 315
66
  }
67
  ],
68
  "logging_steps": 50,
69
+ "max_steps": 315,
70
  "num_input_tokens_seen": 0,
71
  "num_train_epochs": 1,
72
  "save_steps": 500,
 
82
  "attributes": {}
83
  }
84
  },
85
+ "total_flos": 47016456480.0,
86
  "train_batch_size": 1,
87
  "trial_name": null,
88
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43c733536ead1eb0f98c59332edc3ab89c9e8ef698aad77a80930e90c7bb781a
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5199e916690144873725b290cf2696ac54eb2bebad6f29ab35e3e59d203073b4
3
  size 5432