Hugging Face's logo

parth0908
/
peft-starcoder-finetuned

PEFT
TensorBoard
Safetensors
gpt_bigcode
Generated from Trainer
Model card Files
xet
Metrics Community
parth0908 commited on
Commit
64fa1f8
·
verified ·
1 Parent(s): 033fec6

End of training

Browse files
Files changed (7) hide show
  1. README.md +53 -53
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. runs/Nov28_11-07-15_localhost/events.out.tfevents.1732772236.localhost +2 -2
  5. runs/Nov29_03-49-51_localhost/events.out.tfevents.1732832393.localhost +3 -0
  6. runs/Nov29_06-05-36_localhost/events.out.tfevents.1732840538.localhost +3 -0
  7. training_args.bin +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [bigcode/starcoderbase-1b](https://huggingface.co/bigcode/starcoderbase-1b) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.0382
20
 
21
  ## Model description
22
 
@@ -43,63 +43,63 @@ The following hyperparameters were used during training:
43
  - total_train_batch_size: 16
44
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: cosine
46
- - lr_scheduler_warmup_steps: 10
47
- - training_steps: 500
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:------:|:----:|:---------------:|
53
- | 1.276 | 0.0416 | 10 | 1.0832 |
54
- | 1.2151 | 0.0833 | 20 | 1.0789 |
55
- | 1.2213 | 0.1249 | 30 | 1.0736 |
56
- | 1.1694 | 0.1666 | 40 | 1.0718 |
57
- | 1.2627 | 0.2082 | 50 | 1.0696 |
58
- | 1.1801 | 0.2499 | 60 | 1.0690 |
59
- | 1.1013 | 0.2915 | 70 | 1.0637 |
60
- | 1.082 | 0.3332 | 80 | 1.0643 |
61
- | 1.0783 | 0.3748 | 90 | 1.0638 |
62
- | 1.1166 | 0.4164 | 100 | 1.0615 |
63
- | 1.1207 | 0.4581 | 110 | 1.0581 |
64
- | 1.197 | 0.4997 | 120 | 1.0562 |
65
- | 1.012 | 0.5414 | 130 | 1.0583 |
66
- | 1.1291 | 0.5830 | 140 | 1.0515 |
67
- | 1.0695 | 0.6247 | 150 | 1.0520 |
68
- | 1.0924 | 0.6663 | 160 | 1.0514 |
69
- | 1.1287 | 0.7080 | 170 | 1.0536 |
70
- | 1.0514 | 0.7496 | 180 | 1.0508 |
71
- | 1.1101 | 0.7913 | 190 | 1.0491 |
72
- | 1.1474 | 0.8329 | 200 | 1.0489 |
73
- | 1.1451 | 0.8745 | 210 | 1.0476 |
74
- | 1.1688 | 0.9162 | 220 | 1.0434 |
75
- | 1.053 | 0.9578 | 230 | 1.0447 |
76
- | 1.0146 | 0.9995 | 240 | 1.0438 |
77
- | 1.1127 | 1.0411 | 250 | 1.0442 |
78
- | 0.9734 | 1.0828 | 260 | 1.0420 |
79
- | 1.0315 | 1.1244 | 270 | 1.0445 |
80
- | 1.0803 | 1.1661 | 280 | 1.0435 |
81
- | 1.0892 | 1.2077 | 290 | 1.0440 |
82
- | 1.0191 | 1.2493 | 300 | 1.0427 |
83
- | 1.034 | 1.2910 | 310 | 1.0416 |
84
- | 1.1136 | 1.3326 | 320 | 1.0413 |
85
- | 0.9837 | 1.3743 | 330 | 1.0413 |
86
- | 1.0659 | 1.4159 | 340 | 1.0405 |
87
- | 0.9931 | 1.4576 | 350 | 1.0409 |
88
- | 1.1141 | 1.4992 | 360 | 1.0403 |
89
- | 1.0851 | 1.5409 | 370 | 1.0399 |
90
- | 1.053 | 1.5825 | 380 | 1.0390 |
91
- | 1.0652 | 1.6242 | 390 | 1.0395 |
92
- | 1.0998 | 1.6658 | 400 | 1.0396 |
93
- | 0.9909 | 1.7074 | 410 | 1.0390 |
94
- | 1.0946 | 1.7491 | 420 | 1.0386 |
95
- | 1.0471 | 1.7907 | 430 | 1.0382 |
96
- | 0.9719 | 1.8324 | 440 | 1.0382 |
97
- | 1.0641 | 1.8740 | 450 | 1.0382 |
98
- | 1.0003 | 1.9157 | 460 | 1.0383 |
99
- | 1.0128 | 1.9573 | 470 | 1.0383 |
100
- | 1.0637 | 1.9990 | 480 | 1.0384 |
101
- | 1.0583 | 2.0406 | 490 | 1.0383 |
102
- | 0.991 | 2.0822 | 500 | 1.0382 |
103
 
104
 
105
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [bigcode/starcoderbase-1b](https://huggingface.co/bigcode/starcoderbase-1b) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.8901
20
 
21
  ## Model description
22
 
 
43
  - total_train_batch_size: 16
44
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_steps: 20
47
+ - training_steps: 1000
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:------:|:----:|:---------------:|
53
+ | 1.0733 | 0.1631 | 20 | 0.9622 |
54
+ | 1.0649 | 0.3262 | 40 | 0.9528 |
55
+ | 1.0324 | 0.4893 | 60 | 0.9462 |
56
+ | 1.0216 | 0.6524 | 80 | 0.9424 |
57
+ | 1.0067 | 0.8155 | 100 | 0.9368 |
58
+ | 0.9977 | 0.9786 | 120 | 0.9329 |
59
+ | 0.97 | 1.1458 | 140 | 0.9302 |
60
+ | 0.9085 | 1.3089 | 160 | 0.9279 |
61
+ | 0.934 | 1.4720 | 180 | 0.9233 |
62
+ | 1.0061 | 1.6351 | 200 | 0.9184 |
63
+ | 0.9564 | 1.7982 | 220 | 0.9165 |
64
+ | 0.9738 | 1.9613 | 240 | 0.9126 |
65
+ | 0.8864 | 2.1284 | 260 | 0.9114 |
66
+ | 0.9144 | 2.2915 | 280 | 0.9113 |
67
+ | 0.9443 | 2.4546 | 300 | 0.9098 |
68
+ | 0.9444 | 2.6177 | 320 | 0.9083 |
69
+ | 0.887 | 2.7808 | 340 | 0.9058 |
70
+ | 0.9398 | 2.9439 | 360 | 0.9052 |
71
+ | 0.9015 | 3.1111 | 380 | 0.9031 |
72
+ | 0.8536 | 3.2742 | 400 | 0.9024 |
73
+ | 0.8765 | 3.4373 | 420 | 0.9002 |
74
+ | 0.9198 | 3.6004 | 440 | 0.8997 |
75
+ | 0.9468 | 3.7635 | 460 | 0.8989 |
76
+ | 0.8631 | 3.9266 | 480 | 0.8978 |
77
+ | 0.8777 | 4.0938 | 500 | 0.8977 |
78
+ | 0.9006 | 4.2569 | 520 | 0.8959 |
79
+ | 0.8768 | 4.4200 | 540 | 0.8957 |
80
+ | 0.8477 | 4.5831 | 560 | 0.8951 |
81
+ | 0.9061 | 4.7462 | 580 | 0.8937 |
82
+ | 0.8837 | 4.9093 | 600 | 0.8930 |
83
+ | 0.8402 | 5.0765 | 620 | 0.8939 |
84
+ | 0.8608 | 5.2396 | 640 | 0.8931 |
85
+ | 0.879 | 5.4027 | 660 | 0.8928 |
86
+ | 0.8562 | 5.5657 | 680 | 0.8922 |
87
+ | 0.8776 | 5.7288 | 700 | 0.8913 |
88
+ | 0.8464 | 5.8919 | 720 | 0.8910 |
89
+ | 0.8528 | 6.0591 | 740 | 0.8914 |
90
+ | 0.8538 | 6.2222 | 760 | 0.8910 |
91
+ | 0.8844 | 6.3853 | 780 | 0.8905 |
92
+ | 0.8652 | 6.5484 | 800 | 0.8906 |
93
+ | 0.8443 | 6.7115 | 820 | 0.8905 |
94
+ | 0.8546 | 6.8746 | 840 | 0.8899 |
95
+ | 0.8094 | 7.0418 | 860 | 0.8904 |
96
+ | 0.863 | 7.2049 | 880 | 0.8899 |
97
+ | 0.8642 | 7.3680 | 900 | 0.8902 |
98
+ | 0.8413 | 7.5311 | 920 | 0.8901 |
99
+ | 0.8119 | 7.6942 | 940 | 0.8903 |
100
+ | 0.8909 | 7.8573 | 960 | 0.8901 |
101
+ | 0.8516 | 8.0245 | 980 | 0.8900 |
102
+ | 0.8834 | 8.1876 | 1000 | 0.8901 |
103
 
104
 
105
  ### Framework versions
adapter_config.json CHANGED
@@ -20,10 +20,10 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "c_fc",
24
  "c_proj",
25
- "q_attn",
26
- "c_attn"
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "c_attn",
24
  "c_fc",
25
  "c_proj",
26
+ "q_attn"
 
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a07364278dad56148a64a1d6090cece2cfebb54c2b19abda81ec2c23624e004
3
  size 22241240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc0158b656e9ec52b86ca457fa79f91c332e6618c8a24b37f1f483c135cf7e19
3
  size 22241240
runs/Nov28_11-07-15_localhost/events.out.tfevents.1732772236.localhost CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3307e2d2895063fba13f56743ffd53e7cbba468184df79cf89f8c7bd448f627b
3
- size 7806
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e8835ce323b1c98186a2d2a3d23e76f3a71fe6da6f30e2003f069b61e8198da
3
+ size 8981
runs/Nov29_03-49-51_localhost/events.out.tfevents.1732832393.localhost ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fb4bd1982f4a3e39e67bc96304edf322a32de0443dc34dac24180eb17bb4799
3
+ size 14235
runs/Nov29_06-05-36_localhost/events.out.tfevents.1732840538.localhost ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17e2a4f2f826a82638e45c46b974fc20ea0c219f8a0ef8fdc6a8fdcb10192365
3
+ size 29802
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b9059703c87f76bcdacfceb1d2e4b0a2d11afc55e0b8d777466b9c9548bd6ff
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ffd811870fb31121203e9dd263ecdbd436864079d4bfaa819d4f05f9d45fd4e
3
  size 5304