Hugging Face's logo

rbelanec
/
test

Text Generation
PEFT
Safetensors
Transformers
llama-factory
conversational
Model card Files
xet
 Community
rbelanec commited on
Commit
f331790
·
verified ·
1 Parent(s): bb625a2

Training in progress, step 13

Browse files
Files changed (4) hide show
  1. adapter_config.json +2 -2
  2. adapter_model.safetensors +1 -1
  3. trainer_log.jsonl +7 -61
  4. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -5,8 +5,8 @@
5
  "peft_type": "BITFIT",
6
  "revision": null,
7
  "target_modules": [
8
- "v_proj",
9
- "q_proj"
10
  ],
11
  "task_type": "CAUSAL_LM"
12
  }
 
5
  "peft_type": "BITFIT",
6
  "revision": null,
7
  "target_modules": [
8
+ "q_proj",
9
+ "v_proj"
10
  ],
11
  "task_type": "CAUSAL_LM"
12
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3450a265f20d658447e91f7b1233ffb786dc84527f788f9dcbe3ccadbb87f0c
3
  size 335717200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82b6cb8f1cd3f6a9a41e84b4d818b3351937ccb10dea0e6026ef1c448406a527
3
  size 335717200
trainer_log.jsonl CHANGED
@@ -1,61 +1,7 @@
1
- {"current_steps": 5, "total_steps": 249, "loss": 0.8454, "lr": 8.000000000000001e-06, "epoch": 0.020080321285140562, "percentage": 2.01, "elapsed_time": "0:00:01", "remaining_time": "0:01:09", "throughput": 585.81, "total_tokens": 832}
2
- {"current_steps": 10, "total_steps": 249, "loss": 0.7689, "lr": 1.8e-05, "epoch": 0.040160642570281124, "percentage": 4.02, "elapsed_time": "0:00:01", "remaining_time": "0:00:42", "throughput": 993.61, "total_tokens": 1760}
3
- {"current_steps": 13, "total_steps": 249, "eval_loss": 0.6837943196296692, "epoch": 0.05220883534136546, "percentage": 5.22, "elapsed_time": "0:00:02", "remaining_time": "0:00:48", "throughput": 849.12, "total_tokens": 2288}
4
- {"current_steps": 15, "total_steps": 249, "loss": 0.6956, "lr": 2.8000000000000003e-05, "epoch": 0.060240963855421686, "percentage": 6.02, "elapsed_time": "0:00:04", "remaining_time": "0:01:06", "throughput": 613.77, "total_tokens": 2608}
5
- {"current_steps": 20, "total_steps": 249, "loss": 0.5552, "lr": 3.8e-05, "epoch": 0.08032128514056225, "percentage": 8.03, "elapsed_time": "0:00:04", "remaining_time": "0:00:53", "throughput": 763.27, "total_tokens": 3536}
6
- {"current_steps": 25, "total_steps": 249, "loss": 0.6557, "lr": 4.8e-05, "epoch": 0.10040160642570281, "percentage": 10.04, "elapsed_time": "0:00:04", "remaining_time": "0:00:44", "throughput": 904.28, "total_tokens": 4496}
7
- {"current_steps": 26, "total_steps": 249, "eval_loss": 0.46041956543922424, "epoch": 0.10441767068273092, "percentage": 10.44, "elapsed_time": "0:00:05", "remaining_time": "0:00:49", "throughput": 804.22, "total_tokens": 4656}
8
- {"current_steps": 30, "total_steps": 249, "loss": 0.4952, "lr": 4.996067037544542e-05, "epoch": 0.12048192771084337, "percentage": 12.05, "elapsed_time": "0:00:07", "remaining_time": "0:00:52", "throughput": 752.22, "total_tokens": 5424}
9
- {"current_steps": 35, "total_steps": 249, "loss": 0.3647, "lr": 4.980110583549062e-05, "epoch": 0.14056224899598393, "percentage": 14.06, "elapsed_time": "0:00:07", "remaining_time": "0:00:45", "throughput": 838.57, "total_tokens": 6304}
10
- {"current_steps": 39, "total_steps": 249, "eval_loss": 0.3834764063358307, "epoch": 0.1566265060240964, "percentage": 15.66, "elapsed_time": "0:00:08", "remaining_time": "0:00:46", "throughput": 811.47, "total_tokens": 6944}
11
- {"current_steps": 40, "total_steps": 249, "loss": 0.4023, "lr": 4.951963201008076e-05, "epoch": 0.1606425702811245, "percentage": 16.06, "elapsed_time": "0:00:09", "remaining_time": "0:00:50", "throughput": 727.37, "total_tokens": 7072}
12
- {"current_steps": 45, "total_steps": 249, "loss": 0.3811, "lr": 4.91176324775594e-05, "epoch": 0.18072289156626506, "percentage": 18.07, "elapsed_time": "0:00:10", "remaining_time": "0:00:45", "throughput": 782.97, "total_tokens": 7856}
13
- {"current_steps": 50, "total_steps": 249, "loss": 0.3506, "lr": 4.8597083257709194e-05, "epoch": 0.20080321285140562, "percentage": 20.08, "elapsed_time": "0:00:10", "remaining_time": "0:00:41", "throughput": 856.06, "total_tokens": 8880}
14
- {"current_steps": 52, "total_steps": 249, "eval_loss": 0.38357535004615784, "epoch": 0.20883534136546184, "percentage": 20.88, "elapsed_time": "0:00:11", "remaining_time": "0:00:42", "throughput": 821.02, "total_tokens": 9232}
15
- {"current_steps": 55, "total_steps": 249, "loss": 0.4133, "lr": 4.796054309867053e-05, "epoch": 0.22088353413654618, "percentage": 22.09, "elapsed_time": "0:00:13", "remaining_time": "0:00:46", "throughput": 739.1, "total_tokens": 9680}
16
- {"current_steps": 60, "total_steps": 249, "loss": 0.3351, "lr": 4.721114089947181e-05, "epoch": 0.24096385542168675, "percentage": 24.1, "elapsed_time": "0:00:13", "remaining_time": "0:00:42", "throughput": 788.36, "total_tokens": 10576}
17
- {"current_steps": 65, "total_steps": 249, "loss": 0.3084, "lr": 4.6352560329995686e-05, "epoch": 0.26104417670682734, "percentage": 26.1, "elapsed_time": "0:00:13", "remaining_time": "0:00:38", "throughput": 833.3, "total_tokens": 11424}
18
- {"current_steps": 65, "total_steps": 249, "eval_loss": 0.36912769079208374, "epoch": 0.26104417670682734, "percentage": 26.1, "elapsed_time": "0:00:14", "remaining_time": "0:00:41", "throughput": 785.27, "total_tokens": 11424}
19
- {"current_steps": 70, "total_steps": 249, "loss": 0.374, "lr": 4.538902172398151e-05, "epoch": 0.28112449799196787, "percentage": 28.11, "elapsed_time": "0:00:16", "remaining_time": "0:00:41", "throughput": 761.66, "total_tokens": 12224}
20
- {"current_steps": 75, "total_steps": 249, "loss": 0.3649, "lr": 4.4325261334068426e-05, "epoch": 0.30120481927710846, "percentage": 30.12, "elapsed_time": "0:00:16", "remaining_time": "0:00:37", "throughput": 804.04, "total_tokens": 13168}
21
- {"current_steps": 78, "total_steps": 249, "eval_loss": 0.3668709397315979, "epoch": 0.3132530120481928, "percentage": 31.33, "elapsed_time": "0:00:17", "remaining_time": "0:00:37", "throughput": 794.93, "total_tokens": 13760}
22
- {"current_steps": 80, "total_steps": 249, "loss": 0.3613, "lr": 4.316650805085068e-05, "epoch": 0.321285140562249, "percentage": 32.13, "elapsed_time": "0:00:19", "remaining_time": "0:00:40", "throughput": 740.23, "total_tokens": 14080}
23
- {"current_steps": 85, "total_steps": 249, "loss": 0.3601, "lr": 4.1918457700381855e-05, "epoch": 0.3413654618473896, "percentage": 34.14, "elapsed_time": "0:00:19", "remaining_time": "0:00:37", "throughput": 779.19, "total_tokens": 15056}
24
- {"current_steps": 90, "total_steps": 249, "loss": 0.3612, "lr": 4.058724504646834e-05, "epoch": 0.3614457831325301, "percentage": 36.14, "elapsed_time": "0:00:19", "remaining_time": "0:00:34", "throughput": 809.15, "total_tokens": 15904}
25
- {"current_steps": 91, "total_steps": 249, "eval_loss": 0.36205965280532837, "epoch": 0.3654618473895582, "percentage": 36.55, "elapsed_time": "0:00:20", "remaining_time": "0:00:35", "throughput": 779.24, "total_tokens": 16048}
26
- {"current_steps": 95, "total_steps": 249, "loss": 0.3307, "lr": 3.9179413635373897e-05, "epoch": 0.3815261044176707, "percentage": 38.15, "elapsed_time": "0:00:22", "remaining_time": "0:00:35", "throughput": 756.44, "total_tokens": 16688}
27
- {"current_steps": 100, "total_steps": 249, "loss": 0.2896, "lr": 3.770188363116324e-05, "epoch": 0.40160642570281124, "percentage": 40.16, "elapsed_time": "0:00:22", "remaining_time": "0:00:33", "throughput": 782.92, "total_tokens": 17552}
28
- {"current_steps": 104, "total_steps": 249, "eval_loss": 0.37523433566093445, "epoch": 0.41767068273092367, "percentage": 41.77, "elapsed_time": "0:00:23", "remaining_time": "0:00:32", "throughput": 780.09, "total_tokens": 18272}
29
- {"current_steps": 105, "total_steps": 249, "loss": 0.3154, "lr": 3.616191779978907e-05, "epoch": 0.42168674698795183, "percentage": 42.17, "elapsed_time": "0:00:25", "remaining_time": "0:00:34", "throughput": 732.06, "total_tokens": 18400}
30
- {"current_steps": 110, "total_steps": 249, "loss": 0.3694, "lr": 3.456708580912725e-05, "epoch": 0.44176706827309237, "percentage": 44.18, "elapsed_time": "0:00:25", "remaining_time": "0:00:32", "throughput": 764.09, "total_tokens": 19456}
31
- {"current_steps": 115, "total_steps": 249, "loss": 0.4278, "lr": 3.292522702044221e-05, "epoch": 0.46184738955823296, "percentage": 46.18, "elapsed_time": "0:00:25", "remaining_time": "0:00:30", "throughput": 785.68, "total_tokens": 20288}
32
- {"current_steps": 117, "total_steps": 249, "eval_loss": 0.3691355884075165, "epoch": 0.46987951807228917, "percentage": 46.99, "elapsed_time": "0:00:26", "remaining_time": "0:00:30", "throughput": 770.43, "total_tokens": 20656}
33
- {"current_steps": 120, "total_steps": 249, "loss": 0.3821, "lr": 3.1244411954180676e-05, "epoch": 0.4819277108433735, "percentage": 48.19, "elapsed_time": "0:00:28", "remaining_time": "0:00:30", "throughput": 757.29, "total_tokens": 21328}
34
- {"current_steps": 125, "total_steps": 249, "loss": 0.3672, "lr": 2.9532902619507462e-05, "epoch": 0.5020080321285141, "percentage": 50.2, "elapsed_time": "0:00:28", "remaining_time": "0:00:28", "throughput": 781.97, "total_tokens": 22304}
35
- {"current_steps": 130, "total_steps": 249, "loss": 0.3659, "lr": 2.7799111902582696e-05, "epoch": 0.5220883534136547, "percentage": 52.21, "elapsed_time": "0:00:28", "remaining_time": "0:00:26", "throughput": 798.34, "total_tokens": 23056}
36
- {"current_steps": 130, "total_steps": 249, "eval_loss": 0.3518533706665039, "epoch": 0.5220883534136547, "percentage": 52.21, "elapsed_time": "0:00:29", "remaining_time": "0:00:27", "throughput": 775.59, "total_tokens": 23056}
37
- {"current_steps": 135, "total_steps": 249, "loss": 0.3506, "lr": 2.6051562213206632e-05, "epoch": 0.5421686746987951, "percentage": 54.22, "elapsed_time": "0:00:31", "remaining_time": "0:00:26", "throughput": 754.7, "total_tokens": 23840}
38
- {"current_steps": 140, "total_steps": 249, "loss": 0.3597, "lr": 2.429884359310328e-05, "epoch": 0.5622489959839357, "percentage": 56.22, "elapsed_time": "0:00:31", "remaining_time": "0:00:24", "throughput": 776.42, "total_tokens": 24832}
39
- {"current_steps": 143, "total_steps": 249, "eval_loss": 0.3539418578147888, "epoch": 0.5742971887550201, "percentage": 57.43, "elapsed_time": "0:00:33", "remaining_time": "0:00:24", "throughput": 764.59, "total_tokens": 25312}
40
- {"current_steps": 145, "total_steps": 249, "loss": 0.382, "lr": 2.2549571491760986e-05, "epoch": 0.5823293172690763, "percentage": 58.23, "elapsed_time": "0:00:34", "remaining_time": "0:00:24", "throughput": 748.86, "total_tokens": 25648}
41
- {"current_steps": 150, "total_steps": 249, "loss": 0.3337, "lr": 2.0812344417381595e-05, "epoch": 0.6024096385542169, "percentage": 60.24, "elapsed_time": "0:00:34", "remaining_time": "0:00:22", "throughput": 765.61, "total_tokens": 26496}
42
- {"current_steps": 155, "total_steps": 249, "loss": 0.3846, "lr": 1.909570167110415e-05, "epoch": 0.6224899598393574, "percentage": 62.25, "elapsed_time": "0:00:34", "remaining_time": "0:00:21", "throughput": 784.09, "total_tokens": 27392}
43
- {"current_steps": 156, "total_steps": 249, "eval_loss": 0.35141557455062866, "epoch": 0.6265060240963856, "percentage": 62.65, "elapsed_time": "0:00:35", "remaining_time": "0:00:21", "throughput": 772.32, "total_tokens": 27552}
44
- {"current_steps": 160, "total_steps": 249, "loss": 0.3663, "lr": 1.7408081372259632e-05, "epoch": 0.642570281124498, "percentage": 64.26, "elapsed_time": "0:00:37", "remaining_time": "0:00:21", "throughput": 748.74, "total_tokens": 28272}
45
- {"current_steps": 165, "total_steps": 249, "loss": 0.3281, "lr": 1.5757778980982626e-05, "epoch": 0.6626506024096386, "percentage": 66.27, "elapsed_time": "0:00:38", "remaining_time": "0:00:19", "throughput": 766.77, "total_tokens": 29184}
46
- {"current_steps": 169, "total_steps": 249, "eval_loss": 0.35279974341392517, "epoch": 0.678714859437751, "percentage": 67.87, "elapsed_time": "0:00:39", "remaining_time": "0:00:18", "throughput": 766.99, "total_tokens": 29984}
47
- {"current_steps": 170, "total_steps": 249, "loss": 0.333, "lr": 1.4152906522061048e-05, "epoch": 0.6827309236947792, "percentage": 68.27, "elapsed_time": "0:00:40", "remaining_time": "0:00:18", "throughput": 746.8, "total_tokens": 30128}
48
- {"current_steps": 175, "total_steps": 249, "loss": 0.3335, "lr": 1.2601352710458313e-05, "epoch": 0.7028112449799196, "percentage": 70.28, "elapsed_time": "0:00:40", "remaining_time": "0:00:17", "throughput": 760.02, "total_tokens": 30976}
49
- {"current_steps": 180, "total_steps": 249, "loss": 0.3654, "lr": 1.1110744174509952e-05, "epoch": 0.7228915662650602, "percentage": 72.29, "elapsed_time": "0:00:41", "remaining_time": "0:00:15", "throughput": 773.33, "total_tokens": 31776}
50
- {"current_steps": 182, "total_steps": 249, "eval_loss": 0.3537220358848572, "epoch": 0.7309236947791165, "percentage": 73.09, "elapsed_time": "0:00:41", "remaining_time": "0:00:15", "throughput": 765.23, "total_tokens": 32080}
51
- {"current_steps": 185, "total_steps": 249, "loss": 0.3846, "lr": 9.688407967401248e-06, "epoch": 0.7429718875502008, "percentage": 74.3, "elapsed_time": "0:00:43", "remaining_time": "0:00:15", "throughput": 744.94, "total_tokens": 32608}
52
- {"current_steps": 190, "total_steps": 249, "loss": 0.4085, "lr": 8.341335551199902e-06, "epoch": 0.7630522088353414, "percentage": 76.31, "elapsed_time": "0:00:44", "remaining_time": "0:00:13", "throughput": 756.08, "total_tokens": 33360}
53
- {"current_steps": 195, "total_steps": 249, "loss": 0.3745, "lr": 7.076148430479321e-06, "epoch": 0.7831325301204819, "percentage": 78.31, "elapsed_time": "0:00:44", "remaining_time": "0:00:12", "throughput": 768.47, "total_tokens": 34176}
54
- {"current_steps": 195, "total_steps": 249, "eval_loss": 0.3510403037071228, "epoch": 0.7831325301204819, "percentage": 78.31, "elapsed_time": "0:00:45", "remaining_time": "0:00:12", "throughput": 756.02, "total_tokens": 34176}
55
- {"current_steps": 200, "total_steps": 249, "loss": 0.3619, "lr": 5.899065604459814e-06, "epoch": 0.8032128514056225, "percentage": 80.32, "elapsed_time": "0:00:46", "remaining_time": "0:00:11", "throughput": 749.1, "total_tokens": 34992}
56
- {"current_steps": 205, "total_steps": 249, "loss": 0.3715, "lr": 4.81587299765594e-06, "epoch": 0.8232931726907631, "percentage": 82.33, "elapsed_time": "0:00:47", "remaining_time": "0:00:10", "throughput": 762.9, "total_tokens": 35888}
57
- {"current_steps": 208, "total_steps": 249, "eval_loss": 0.3522191047668457, "epoch": 0.8353413654618473, "percentage": 83.53, "elapsed_time": "0:00:48", "remaining_time": "0:00:09", "throughput": 758.49, "total_tokens": 36512}
58
- {"current_steps": 210, "total_steps": 249, "loss": 0.3618, "lr": 3.831895019292897e-06, "epoch": 0.8433734939759037, "percentage": 84.34, "elapsed_time": "0:00:49", "remaining_time": "0:00:09", "throughput": 737.9, "total_tokens": 36848}
59
- {"current_steps": 215, "total_steps": 249, "loss": 0.3692, "lr": 2.9519683912911266e-06, "epoch": 0.8634538152610441, "percentage": 86.35, "elapsed_time": "0:00:50", "remaining_time": "0:00:07", "throughput": 753.12, "total_tokens": 37888}
60
- {"current_steps": 220, "total_steps": 249, "loss": 0.3653, "lr": 2.1804183734670277e-06, "epoch": 0.8835341365461847, "percentage": 88.35, "elapsed_time": "0:00:50", "remaining_time": "0:00:06", "throughput": 765.54, "total_tokens": 38768}
61
- {"current_steps": 221, "total_steps": 249, "eval_loss": 0.35432901978492737, "epoch": 0.8875502008032129, "percentage": 88.76, "elapsed_time": "0:00:51", "remaining_time": "0:00:06", "throughput": 754.99, "total_tokens": 38912}
 
1
+ {"current_steps": 5, "total_steps": 249, "loss": 0.8454, "lr": 8.000000000000001e-06, "epoch": 0.020080321285140562, "percentage": 2.01, "elapsed_time": "0:00:01", "remaining_time": "0:01:02", "throughput": 648.98, "total_tokens": 832}
2
+ {"current_steps": 10, "total_steps": 249, "loss": 0.7689, "lr": 1.8e-05, "epoch": 0.040160642570281124, "percentage": 4.02, "elapsed_time": "0:00:01", "remaining_time": "0:00:42", "throughput": 991.19, "total_tokens": 1760}
3
+ {"current_steps": 13, "total_steps": 249, "eval_loss": 0.6837943196296692, "epoch": 0.05220883534136546, "percentage": 5.22, "elapsed_time": "0:00:02", "remaining_time": "0:00:54", "throughput": 764.78, "total_tokens": 2288}
4
+ {"current_steps": 15, "total_steps": 249, "loss": 0.6956, "lr": 2.8000000000000003e-05, "epoch": 0.060240963855421686, "percentage": 6.02, "elapsed_time": "0:00:04", "remaining_time": "0:01:14", "throughput": 549.1, "total_tokens": 2608}
5
+ {"current_steps": 20, "total_steps": 249, "loss": 0.5552, "lr": 3.8e-05, "epoch": 0.08032128514056225, "percentage": 8.03, "elapsed_time": "0:00:05", "remaining_time": "0:00:58", "throughput": 696.01, "total_tokens": 3536}
6
+ {"current_steps": 25, "total_steps": 249, "loss": 0.6557, "lr": 4.8e-05, "epoch": 0.10040160642570281, "percentage": 10.04, "elapsed_time": "0:00:05", "remaining_time": "0:00:48", "throughput": 833.1, "total_tokens": 4496}
7
+ {"current_steps": 26, "total_steps": 249, "eval_loss": 0.46041956543922424, "epoch": 0.10441767068273092, "percentage": 10.44, "elapsed_time": "0:00:06", "remaining_time": "0:00:53", "throughput": 749.9, "total_tokens": 4656}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26268eb85c50b67eb87366e2d3ad0a6dc633662f3fff996413359f7f264b2012
3
  size 6097
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d7412620e2abdc5c7b16ad757ec7052dfaba7217e117cef782a1d29f70e5329
3
  size 6097