Hugging Face's logo

rbelanec
/
train_boolq_1745950280

PEFT
Safetensors
llama-factory
prompt-tuning
Generated from Trainer
Model card Files
xet
Community
rbelanec commited on
Commit
4d41a27
路
verified 路
1 Parent(s): 0dadb9c

Training in progress, step 200

Browse files
Files changed (8) hide show
  1. adapter_config.json +17 -0
  2. adapter_model.safetensors +3 -0
  3. special_tokens_map.json +24 -0
  4. tokenizer.json +0 -0
  5. tokenizer.model +3 -0
  6. tokenizer_config.json +0 -0
  7. trainer_log.jsonl +42 -0
  8. training_args.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
4
+ "inference_mode": true,
5
+ "num_attention_heads": 32,
6
+ "num_layers": 32,
7
+ "num_transformer_submodules": 1,
8
+ "num_virtual_tokens": 100,
9
+ "peft_type": "PROMPT_TUNING",
10
+ "prompt_tuning_init": "RANDOM",
11
+ "prompt_tuning_init_text": null,
12
+ "revision": null,
13
+ "task_type": "CAUSAL_LM",
14
+ "token_dim": 4096,
15
+ "tokenizer_kwargs": null,
16
+ "tokenizer_name_or_path": null
17
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:552a85fba160c229fb19f38da4d72eb89312ec4da2246677707b76205152bbf8
3
+ size 1638528
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
trainer_log.jsonl ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 5, "total_steps": 40000, "loss": 8.8046, "lr": 0.29999999259779675, "epoch": 0.0023573785950023575, "percentage": 0.01, "elapsed_time": "0:00:03", "remaining_time": "7:18:58", "throughput": 1389.71, "total_tokens": 4576}
2
+ {"current_steps": 10, "total_steps": 40000, "loss": 7.1753, "lr": 0.29999996252634736, "epoch": 0.004714757190004715, "percentage": 0.03, "elapsed_time": "0:00:04", "remaining_time": "5:23:15", "throughput": 1857.24, "total_tokens": 9008}
3
+ {"current_steps": 15, "total_steps": 40000, "loss": 2.2257, "lr": 0.2999999093230187, "epoch": 0.007072135785007072, "percentage": 0.04, "elapsed_time": "0:00:06", "remaining_time": "4:48:42", "throughput": 2092.79, "total_tokens": 13600}
4
+ {"current_steps": 20, "total_steps": 40000, "loss": 1.0727, "lr": 0.299999832987819, "epoch": 0.00942951438000943, "percentage": 0.05, "elapsed_time": "0:00:08", "remaining_time": "4:31:36", "throughput": 2284.43, "total_tokens": 18624}
5
+ {"current_steps": 25, "total_steps": 40000, "loss": 0.745, "lr": 0.29999973352076004, "epoch": 0.011786892975011787, "percentage": 0.06, "elapsed_time": "0:00:09", "remaining_time": "4:21:03", "throughput": 2386.36, "total_tokens": 23376}
6
+ {"current_steps": 30, "total_steps": 40000, "loss": 0.4143, "lr": 0.2999996109218572, "epoch": 0.014144271570014143, "percentage": 0.07, "elapsed_time": "0:00:11", "remaining_time": "4:12:28", "throughput": 2447.22, "total_tokens": 27824}
7
+ {"current_steps": 35, "total_steps": 40000, "loss": 0.3913, "lr": 0.2999994651911293, "epoch": 0.0165016501650165, "percentage": 0.09, "elapsed_time": "0:00:12", "remaining_time": "4:05:45", "throughput": 2450.78, "total_tokens": 31648}
8
+ {"current_steps": 40, "total_steps": 40000, "loss": 0.3601, "lr": 0.2999992963285989, "epoch": 0.01885902876001886, "percentage": 0.1, "elapsed_time": "0:00:14", "remaining_time": "4:00:46", "throughput": 2484.0, "total_tokens": 35920}
9
+ {"current_steps": 45, "total_steps": 40000, "loss": 0.3877, "lr": 0.29999910433429194, "epoch": 0.021216407355021217, "percentage": 0.11, "elapsed_time": "0:00:16", "remaining_time": "3:57:06", "throughput": 2511.36, "total_tokens": 40240}
10
+ {"current_steps": 50, "total_steps": 40000, "loss": 0.355, "lr": 0.29999888920823814, "epoch": 0.023573785950023574, "percentage": 0.12, "elapsed_time": "0:00:17", "remaining_time": "3:54:18", "throughput": 2539.74, "total_tokens": 44688}
11
+ {"current_steps": 55, "total_steps": 40000, "loss": 0.3313, "lr": 0.29999865095047057, "epoch": 0.02593116454502593, "percentage": 0.14, "elapsed_time": "0:00:19", "remaining_time": "3:52:28", "throughput": 2579.21, "total_tokens": 49536}
12
+ {"current_steps": 60, "total_steps": 40000, "loss": 0.4659, "lr": 0.29999838956102604, "epoch": 0.028288543140028287, "percentage": 0.15, "elapsed_time": "0:00:20", "remaining_time": "3:51:39", "throughput": 2616.06, "total_tokens": 54624}
13
+ {"current_steps": 65, "total_steps": 40000, "loss": 0.3227, "lr": 0.29999810503994484, "epoch": 0.030645921735030647, "percentage": 0.16, "elapsed_time": "0:00:22", "remaining_time": "3:50:14", "throughput": 2644.2, "total_tokens": 59456}
14
+ {"current_steps": 70, "total_steps": 40000, "loss": 0.3334, "lr": 0.29999779738727084, "epoch": 0.033003300330033, "percentage": 0.18, "elapsed_time": "0:00:24", "remaining_time": "3:49:54", "throughput": 2678.28, "total_tokens": 64768}
15
+ {"current_steps": 75, "total_steps": 40000, "loss": 0.3523, "lr": 0.29999746660305154, "epoch": 0.03536067892503536, "percentage": 0.19, "elapsed_time": "0:00:25", "remaining_time": "3:47:45", "throughput": 2680.73, "total_tokens": 68816}
16
+ {"current_steps": 80, "total_steps": 40000, "loss": 0.2922, "lr": 0.2999971126873379, "epoch": 0.03771805752003772, "percentage": 0.2, "elapsed_time": "0:00:27", "remaining_time": "3:47:32", "throughput": 2690.09, "total_tokens": 73600}
17
+ {"current_steps": 85, "total_steps": 40000, "loss": 0.3558, "lr": 0.2999967356401845, "epoch": 0.040075436115040074, "percentage": 0.21, "elapsed_time": "0:00:28", "remaining_time": "3:46:18", "throughput": 2689.75, "total_tokens": 77776}
18
+ {"current_steps": 90, "total_steps": 40000, "loss": 0.3124, "lr": 0.29999633546164944, "epoch": 0.042432814710042434, "percentage": 0.22, "elapsed_time": "0:00:30", "remaining_time": "3:45:16", "throughput": 2684.89, "total_tokens": 81840}
19
+ {"current_steps": 95, "total_steps": 40000, "loss": 0.3471, "lr": 0.29999591215179444, "epoch": 0.04479019330504479, "percentage": 0.24, "elapsed_time": "0:00:32", "remaining_time": "3:44:25", "throughput": 2682.24, "total_tokens": 85984}
20
+ {"current_steps": 100, "total_steps": 40000, "loss": 0.3614, "lr": 0.2999954657106849, "epoch": 0.04714757190004715, "percentage": 0.25, "elapsed_time": "0:00:33", "remaining_time": "3:43:39", "throughput": 2698.88, "total_tokens": 90768}
21
+ {"current_steps": 105, "total_steps": 40000, "loss": 0.3597, "lr": 0.2999949961383896, "epoch": 0.04950495049504951, "percentage": 0.26, "elapsed_time": "0:00:35", "remaining_time": "3:42:44", "throughput": 2702.84, "total_tokens": 95072}
22
+ {"current_steps": 110, "total_steps": 40000, "loss": 0.3442, "lr": 0.2999945034349809, "epoch": 0.05186232909005186, "percentage": 0.27, "elapsed_time": "0:00:36", "remaining_time": "3:42:12", "throughput": 2715.59, "total_tokens": 99840}
23
+ {"current_steps": 115, "total_steps": 40000, "loss": 0.2426, "lr": 0.2999939876005348, "epoch": 0.05421970768505422, "percentage": 0.29, "elapsed_time": "0:00:38", "remaining_time": "3:42:15", "throughput": 2733.95, "total_tokens": 105120}
24
+ {"current_steps": 120, "total_steps": 40000, "loss": 0.4444, "lr": 0.29999344863513094, "epoch": 0.056577086280056574, "percentage": 0.3, "elapsed_time": "0:00:40", "remaining_time": "3:42:28", "throughput": 2746.18, "total_tokens": 110304}
25
+ {"current_steps": 125, "total_steps": 40000, "loss": 0.3722, "lr": 0.2999928865388523, "epoch": 0.058934464875058934, "percentage": 0.31, "elapsed_time": "0:00:41", "remaining_time": "3:43:14", "throughput": 2766.08, "total_tokens": 116144}
26
+ {"current_steps": 130, "total_steps": 40000, "loss": 0.3274, "lr": 0.29999230131178567, "epoch": 0.061291843470061294, "percentage": 0.33, "elapsed_time": "0:00:43", "remaining_time": "3:43:22", "throughput": 2777.37, "total_tokens": 121376}
27
+ {"current_steps": 135, "total_steps": 40000, "loss": 0.3677, "lr": 0.2999916929540212, "epoch": 0.06364922206506365, "percentage": 0.34, "elapsed_time": "0:00:45", "remaining_time": "3:43:29", "throughput": 2784.13, "total_tokens": 126432}
28
+ {"current_steps": 140, "total_steps": 40000, "loss": 0.3516, "lr": 0.29999106146565285, "epoch": 0.066006600660066, "percentage": 0.35, "elapsed_time": "0:00:46", "remaining_time": "3:43:01", "throughput": 2788.49, "total_tokens": 131056}
29
+ {"current_steps": 145, "total_steps": 40000, "loss": 0.333, "lr": 0.29999040684677786, "epoch": 0.06836397925506836, "percentage": 0.36, "elapsed_time": "0:00:48", "remaining_time": "3:42:40", "throughput": 2789.27, "total_tokens": 135584}
30
+ {"current_steps": 150, "total_steps": 40000, "loss": 0.3167, "lr": 0.2999897290974972, "epoch": 0.07072135785007072, "percentage": 0.38, "elapsed_time": "0:00:50", "remaining_time": "3:42:19", "throughput": 2789.39, "total_tokens": 140064}
31
+ {"current_steps": 155, "total_steps": 40000, "loss": 0.3075, "lr": 0.2999890282179155, "epoch": 0.07307873644507308, "percentage": 0.39, "elapsed_time": "0:00:51", "remaining_time": "3:42:21", "throughput": 2794.95, "total_tokens": 145056}
32
+ {"current_steps": 160, "total_steps": 40000, "loss": 0.2841, "lr": 0.29998830420814077, "epoch": 0.07543611504007544, "percentage": 0.4, "elapsed_time": "0:00:53", "remaining_time": "3:41:46", "throughput": 2796.96, "total_tokens": 149472}
33
+ {"current_steps": 165, "total_steps": 40000, "loss": 0.3112, "lr": 0.2999875570682846, "epoch": 0.07779349363507779, "percentage": 0.41, "elapsed_time": "0:00:55", "remaining_time": "3:41:53", "throughput": 2805.69, "total_tokens": 154720}
34
+ {"current_steps": 170, "total_steps": 40000, "loss": 0.3448, "lr": 0.2999867867984623, "epoch": 0.08015087223008015, "percentage": 0.43, "elapsed_time": "0:00:56", "remaining_time": "3:41:40", "throughput": 2813.11, "total_tokens": 159696}
35
+ {"current_steps": 175, "total_steps": 40000, "loss": 0.3663, "lr": 0.29998599339879267, "epoch": 0.08250825082508251, "percentage": 0.44, "elapsed_time": "0:00:58", "remaining_time": "3:41:30", "throughput": 2821.62, "total_tokens": 164784}
36
+ {"current_steps": 180, "total_steps": 40000, "loss": 0.3636, "lr": 0.29998517686939796, "epoch": 0.08486562942008487, "percentage": 0.45, "elapsed_time": "0:00:59", "remaining_time": "3:40:59", "throughput": 2815.64, "total_tokens": 168768}
37
+ {"current_steps": 185, "total_steps": 40000, "loss": 0.3527, "lr": 0.29998433721040413, "epoch": 0.08722300801508723, "percentage": 0.46, "elapsed_time": "0:01:01", "remaining_time": "3:40:44", "throughput": 2823.15, "total_tokens": 173744}
38
+ {"current_steps": 190, "total_steps": 40000, "loss": 0.356, "lr": 0.29998347442194073, "epoch": 0.08958038661008957, "percentage": 0.47, "elapsed_time": "0:01:03", "remaining_time": "3:40:07", "throughput": 2819.55, "total_tokens": 177728}
39
+ {"current_steps": 195, "total_steps": 40000, "loss": 0.3564, "lr": 0.2999825885041407, "epoch": 0.09193776520509193, "percentage": 0.49, "elapsed_time": "0:01:04", "remaining_time": "3:39:43", "throughput": 2819.91, "total_tokens": 182128}
40
+ {"current_steps": 200, "total_steps": 40000, "loss": 0.3571, "lr": 0.29998167945714077, "epoch": 0.0942951438000943, "percentage": 0.5, "elapsed_time": "0:01:06", "remaining_time": "3:39:33", "throughput": 2821.3, "total_tokens": 186768}
41
+ {"current_steps": 200, "total_steps": 40000, "eval_loss": 0.33534181118011475, "epoch": 0.0942951438000943, "percentage": 0.5, "elapsed_time": "0:01:39", "remaining_time": "5:30:35", "throughput": 1873.74, "total_tokens": 186768}
42
+ {"current_steps": 205, "total_steps": 40000, "loss": 0.3325, "lr": 0.2999807472810811, "epoch": 0.09665252239509665, "percentage": 0.51, "elapsed_time": "0:01:41", "remaining_time": "5:29:53", "throughput": 1880.05, "total_tokens": 191696}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e686347a2bbdd9ebb7560a2caefe4fd2a26957e3ef1f1176e2fad59f3374991d
3
+ size 5752