kdearsty commited on
Commit
630f718
·
verified ·
1 Parent(s): cbc0047

Upload my model weights

Browse files
adapter_config.json CHANGED
@@ -19,8 +19,6 @@
19
  "megatron_config": null,
20
  "megatron_core": "megatron.core",
21
  "modules_to_save": [
22
- "classifier",
23
- "score",
24
  "classifier",
25
  "score"
26
  ],
 
19
  "megatron_config": null,
20
  "megatron_core": "megatron.core",
21
  "modules_to_save": [
 
 
22
  "classifier",
23
  "score"
24
  ],
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11885c5bae22527575502d179ca99d1c7ea058a6a7345031d3b4e6fb813cb893
3
  size 17640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c252e5768fd0cf41e616c057edcc7c3ddc5c0abb9aa2d32544340c132dabadf9
3
  size 17640
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f350e0fe2ddf4d59a914f3147157110064257b6c972b598a9198df54910668f
3
- size 2338
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b144970d43b1e33bb9eb8e370289d0ae0fe867582e50711f325294b892e6724f
3
+ size 41027
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef19ffcd56004336b9f135564a902e1a7a7d8c546c184bdeed5ab4417799b240
3
  size 13990
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60ee1ac7c2476b9ff76394ef5da7cd1f347e5f322ff7c25e327029b246355e51
3
  size 13990
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f64c53201a4c4c373e851f4cc152b657fbb64e463ffca42b4a9cf2efb71d6834
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8bf3b39aba999c7ce84889c1f825bc67f8c308b05e6789287fefa2acaa63533
3
  size 1064
trainer_state.json CHANGED
@@ -1,72 +1,30 @@
1
  {
2
- "best_global_step": 315,
3
- "best_metric": 0.2992021276595745,
4
- "best_model_checkpoint": "/home/kat/git-repos/icse/results/rsa/19-05-2025:14-19-25/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": 2.3694920539855957,
15
- "learning_rate": 1.688888888888889e-05,
16
- "loss": 0.6988,
17
- "step": 50
18
- },
19
- {
20
- "epoch": 0.31746031746031744,
21
- "grad_norm": 3.2288453578948975,
22
- "learning_rate": 1.3714285714285716e-05,
23
- "loss": 0.7359,
24
- "step": 100
25
- },
26
- {
27
- "epoch": 0.47619047619047616,
28
- "grad_norm": 2.3709213733673096,
29
- "learning_rate": 1.053968253968254e-05,
30
- "loss": 0.6617,
31
- "step": 150
32
- },
33
- {
34
- "epoch": 0.6349206349206349,
35
- "grad_norm": 2.37154483795166,
36
- "learning_rate": 7.3650793650793666e-06,
37
- "loss": 0.6803,
38
- "step": 200
39
- },
40
- {
41
- "epoch": 0.7936507936507936,
42
- "grad_norm": 2.3702969551086426,
43
- "learning_rate": 4.190476190476191e-06,
44
- "loss": 0.7116,
45
- "step": 250
46
- },
47
- {
48
- "epoch": 0.9523809523809523,
49
- "grad_norm": 2.3685238361358643,
50
- "learning_rate": 1.015873015873016e-06,
51
- "loss": 0.6928,
52
- "step": 300
53
- },
54
  {
55
  "epoch": 1.0,
56
- "eval_accuracy": 0.46875,
57
  "eval_balanced_accuracy": 0.0,
58
- "eval_f1_score": 0.2992021276595745,
59
- "eval_loss": 0.714898407459259,
60
- "eval_precision": 0.2197265625,
61
- "eval_recall": 0.46875,
62
- "eval_runtime": 2.4579,
63
- "eval_samples_per_second": 26.038,
64
- "eval_steps_per_second": 26.038,
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,
@@ -82,7 +40,7 @@
82
  "attributes": {}
83
  }
84
  },
85
- "total_flos": 47016456480.0,
86
  "train_batch_size": 1,
87
  "trial_name": null,
88
  "trial_params": null
 
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
  "attributes": {}
41
  }
42
  },
43
+ "total_flos": 3432947616.0,
44
  "train_batch_size": 1,
45
  "trial_name": null,
46
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7f57b363998fd8043b0e49393dea8ee301853ebc3ba8c4ce67488f412f44c6a
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43c733536ead1eb0f98c59332edc3ab89c9e8ef698aad77a80930e90c7bb781a
3
  size 5432