Hugging Face's logo

rbelanec
/
train_boolq_1745950281

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files
xet
 Community
rbelanec commited on
Commit
c99c35b
·
verified ·
1 Parent(s): 2e8af95

Training in progress, step 200

Browse files
Files changed (8) hide show
  1. adapter_config.json +35 -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 +43 -0
  8. training_args.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 16,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "down_proj",
28
+ "k_proj",
29
+ "v_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "trainable_token_indices": null,
33
+ "use_dora": false,
34
+ "use_rslora": false
35
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b39e48d1a726c903fc1aaf6510217fbc1b6184f9e15cfc95810bb58f874132dd
3
+ size 58745928
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 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 5, "total_steps": 40000, "loss": 1.74, "lr": 4.999999876629946e-05, "epoch": 0.0023573785950023575, "percentage": 0.01, "elapsed_time": "0:00:04", "remaining_time": "10:31:56", "throughput": 965.35, "total_tokens": 4576}
2
+ {"current_steps": 10, "total_steps": 40000, "loss": 0.5827, "lr": 4.999999375439123e-05, "epoch": 0.004714757190004715, "percentage": 0.03, "elapsed_time": "0:00:06", "remaining_time": "7:32:07", "throughput": 1327.89, "total_tokens": 9008}
3
+ {"current_steps": 15, "total_steps": 40000, "loss": 0.3492, "lr": 4.9999984887169785e-05, "epoch": 0.007072135785007072, "percentage": 0.04, "elapsed_time": "0:00:08", "remaining_time": "6:35:32", "throughput": 1527.58, "total_tokens": 13600}
4
+ {"current_steps": 20, "total_steps": 40000, "loss": 0.2893, "lr": 4.9999972164636506e-05, "epoch": 0.00942951438000943, "percentage": 0.05, "elapsed_time": "0:00:11", "remaining_time": "6:10:47", "throughput": 1673.44, "total_tokens": 18624}
5
+ {"current_steps": 25, "total_steps": 40000, "loss": 0.4185, "lr": 4.999995558679334e-05, "epoch": 0.011786892975011787, "percentage": 0.06, "elapsed_time": "0:00:13", "remaining_time": "5:52:45", "throughput": 1765.96, "total_tokens": 23376}
6
+ {"current_steps": 30, "total_steps": 40000, "loss": 0.1953, "lr": 4.999993515364287e-05, "epoch": 0.014144271570014143, "percentage": 0.07, "elapsed_time": "0:00:15", "remaining_time": "5:40:08", "throughput": 1816.43, "total_tokens": 27824}
7
+ {"current_steps": 35, "total_steps": 40000, "loss": 0.1872, "lr": 4.999991086518822e-05, "epoch": 0.0165016501650165, "percentage": 0.09, "elapsed_time": "0:00:17", "remaining_time": "5:30:30", "throughput": 1822.31, "total_tokens": 31648}
8
+ {"current_steps": 40, "total_steps": 40000, "loss": 0.7711, "lr": 4.999988272143315e-05, "epoch": 0.01885902876001886, "percentage": 0.1, "elapsed_time": "0:00:19", "remaining_time": "5:23:34", "throughput": 1848.36, "total_tokens": 35920}
9
+ {"current_steps": 45, "total_steps": 40000, "loss": 0.3739, "lr": 4.999985072238199e-05, "epoch": 0.021216407355021217, "percentage": 0.11, "elapsed_time": "0:00:21", "remaining_time": "5:17:59", "throughput": 1872.58, "total_tokens": 40240}
10
+ {"current_steps": 50, "total_steps": 40000, "loss": 0.0968, "lr": 4.999981486803969e-05, "epoch": 0.023573785950023574, "percentage": 0.12, "elapsed_time": "0:00:23", "remaining_time": "5:13:13", "throughput": 1899.92, "total_tokens": 44688}
11
+ {"current_steps": 55, "total_steps": 40000, "loss": 0.3422, "lr": 4.999977515841176e-05, "epoch": 0.02593116454502593, "percentage": 0.14, "elapsed_time": "0:00:25", "remaining_time": "5:09:54", "throughput": 1934.79, "total_tokens": 49536}
12
+ {"current_steps": 60, "total_steps": 40000, "loss": 0.5786, "lr": 4.9999731593504344e-05, "epoch": 0.028288543140028287, "percentage": 0.15, "elapsed_time": "0:00:27", "remaining_time": "5:08:12", "throughput": 1966.23, "total_tokens": 54624}
13
+ {"current_steps": 65, "total_steps": 40000, "loss": 0.2593, "lr": 4.999968417332415e-05, "epoch": 0.030645921735030647, "percentage": 0.16, "elapsed_time": "0:00:29", "remaining_time": "5:05:53", "throughput": 1990.28, "total_tokens": 59456}
14
+ {"current_steps": 70, "total_steps": 40000, "loss": 0.1173, "lr": 4.999963289787848e-05, "epoch": 0.033003300330033, "percentage": 0.18, "elapsed_time": "0:00:32", "remaining_time": "5:05:48", "throughput": 2013.57, "total_tokens": 64768}
15
+ {"current_steps": 75, "total_steps": 40000, "loss": 0.5754, "lr": 4.999957776717526e-05, "epoch": 0.03536067892503536, "percentage": 0.19, "elapsed_time": "0:00:34", "remaining_time": "5:03:15", "throughput": 2013.29, "total_tokens": 68816}
16
+ {"current_steps": 80, "total_steps": 40000, "loss": 0.2776, "lr": 4.9999518781222984e-05, "epoch": 0.03771805752003772, "percentage": 0.2, "elapsed_time": "0:00:36", "remaining_time": "5:02:42", "throughput": 2022.15, "total_tokens": 73600}
17
+ {"current_steps": 85, "total_steps": 40000, "loss": 0.2467, "lr": 4.9999455940030746e-05, "epoch": 0.040075436115040074, "percentage": 0.21, "elapsed_time": "0:00:38", "remaining_time": "5:01:15", "throughput": 2020.61, "total_tokens": 77776}
18
+ {"current_steps": 90, "total_steps": 40000, "loss": 0.1672, "lr": 4.999938924360824e-05, "epoch": 0.042432814710042434, "percentage": 0.22, "elapsed_time": "0:00:40", "remaining_time": "4:59:35", "throughput": 2018.9, "total_tokens": 81840}
19
+ {"current_steps": 95, "total_steps": 40000, "loss": 0.1434, "lr": 4.999931869196575e-05, "epoch": 0.04479019330504479, "percentage": 0.24, "elapsed_time": "0:00:42", "remaining_time": "4:58:25", "throughput": 2017.14, "total_tokens": 85984}
20
+ {"current_steps": 100, "total_steps": 40000, "loss": 0.1718, "lr": 4.999924428511416e-05, "epoch": 0.04714757190004715, "percentage": 0.25, "elapsed_time": "0:00:44", "remaining_time": "4:57:23", "throughput": 2029.69, "total_tokens": 90768}
21
+ {"current_steps": 105, "total_steps": 40000, "loss": 0.5296, "lr": 4.999916602306494e-05, "epoch": 0.04950495049504951, "percentage": 0.26, "elapsed_time": "0:00:46", "remaining_time": "4:56:15", "throughput": 2032.18, "total_tokens": 95072}
22
+ {"current_steps": 110, "total_steps": 40000, "loss": 0.0757, "lr": 4.999908390583016e-05, "epoch": 0.05186232909005186, "percentage": 0.27, "elapsed_time": "0:00:48", "remaining_time": "4:55:45", "throughput": 2040.32, "total_tokens": 99840}
23
+ {"current_steps": 115, "total_steps": 40000, "loss": 0.2188, "lr": 4.999899793342247e-05, "epoch": 0.05421970768505422, "percentage": 0.29, "elapsed_time": "0:00:51", "remaining_time": "4:55:40", "throughput": 2055.06, "total_tokens": 105120}
24
+ {"current_steps": 120, "total_steps": 40000, "loss": 0.5732, "lr": 4.999890810585516e-05, "epoch": 0.056577086280056574, "percentage": 0.3, "elapsed_time": "0:00:53", "remaining_time": "4:56:14", "throughput": 2062.37, "total_tokens": 110304}
25
+ {"current_steps": 125, "total_steps": 40000, "loss": 0.4961, "lr": 4.999881442314206e-05, "epoch": 0.058934464875058934, "percentage": 0.31, "elapsed_time": "0:00:55", "remaining_time": "4:57:26", "throughput": 2076.0, "total_tokens": 116144}
26
+ {"current_steps": 130, "total_steps": 40000, "loss": 0.2173, "lr": 4.9998716885297617e-05, "epoch": 0.061291843470061294, "percentage": 0.33, "elapsed_time": "0:00:58", "remaining_time": "4:58:00", "throughput": 2081.84, "total_tokens": 121376}
27
+ {"current_steps": 135, "total_steps": 40000, "loss": 0.4265, "lr": 4.999861549233688e-05, "epoch": 0.06364922206506365, "percentage": 0.34, "elapsed_time": "0:01:00", "remaining_time": "4:57:50", "throughput": 2089.23, "total_tokens": 126432}
28
+ {"current_steps": 140, "total_steps": 40000, "loss": 0.1671, "lr": 4.999851024427548e-05, "epoch": 0.066006600660066, "percentage": 0.35, "elapsed_time": "0:01:02", "remaining_time": "4:57:11", "throughput": 2092.55, "total_tokens": 131056}
29
+ {"current_steps": 145, "total_steps": 40000, "loss": 0.388, "lr": 4.999840114112965e-05, "epoch": 0.06836397925506836, "percentage": 0.36, "elapsed_time": "0:01:04", "remaining_time": "4:56:48", "throughput": 2092.6, "total_tokens": 135584}
30
+ {"current_steps": 150, "total_steps": 40000, "loss": 0.1377, "lr": 4.999828818291621e-05, "epoch": 0.07072135785007072, "percentage": 0.38, "elapsed_time": "0:01:06", "remaining_time": "4:56:18", "throughput": 2093.0, "total_tokens": 140064}
31
+ {"current_steps": 155, "total_steps": 40000, "loss": 0.2331, "lr": 4.999817136965259e-05, "epoch": 0.07307873644507308, "percentage": 0.39, "elapsed_time": "0:01:09", "remaining_time": "4:56:21", "throughput": 2097.09, "total_tokens": 145056}
32
+ {"current_steps": 160, "total_steps": 40000, "loss": 0.1581, "lr": 4.9998050701356794e-05, "epoch": 0.07543611504007544, "percentage": 0.4, "elapsed_time": "0:01:11", "remaining_time": "4:55:38", "throughput": 2098.13, "total_tokens": 149472}
33
+ {"current_steps": 165, "total_steps": 40000, "loss": 0.1243, "lr": 4.999792617804744e-05, "epoch": 0.07779349363507779, "percentage": 0.41, "elapsed_time": "0:01:13", "remaining_time": "4:55:29", "throughput": 2106.85, "total_tokens": 154720}
34
+ {"current_steps": 170, "total_steps": 40000, "loss": 0.1248, "lr": 4.9997797799743724e-05, "epoch": 0.08015087223008015, "percentage": 0.43, "elapsed_time": "0:01:15", "remaining_time": "4:55:17", "throughput": 2111.79, "total_tokens": 159696}
35
+ {"current_steps": 175, "total_steps": 40000, "loss": 0.5234, "lr": 4.999766556646545e-05, "epoch": 0.08250825082508251, "percentage": 0.44, "elapsed_time": "0:01:17", "remaining_time": "4:55:00", "throughput": 2118.56, "total_tokens": 164784}
36
+ {"current_steps": 180, "total_steps": 40000, "loss": 0.3183, "lr": 4.9997529478232996e-05, "epoch": 0.08486562942008487, "percentage": 0.45, "elapsed_time": "0:01:19", "remaining_time": "4:54:15", "throughput": 2114.65, "total_tokens": 168768}
37
+ {"current_steps": 185, "total_steps": 40000, "loss": 0.6899, "lr": 4.9997389535067365e-05, "epoch": 0.08722300801508723, "percentage": 0.46, "elapsed_time": "0:01:21", "remaining_time": "4:53:55", "throughput": 2120.3, "total_tokens": 173744}
38
+ {"current_steps": 190, "total_steps": 40000, "loss": 0.1782, "lr": 4.999724573699012e-05, "epoch": 0.08958038661008957, "percentage": 0.47, "elapsed_time": "0:01:23", "remaining_time": "4:53:12", "throughput": 2116.74, "total_tokens": 177728}
39
+ {"current_steps": 195, "total_steps": 40000, "loss": 0.0255, "lr": 4.9997098084023457e-05, "epoch": 0.09193776520509193, "percentage": 0.49, "elapsed_time": "0:01:26", "remaining_time": "4:52:50", "throughput": 2115.89, "total_tokens": 182128}
40
+ {"current_steps": 200, "total_steps": 40000, "loss": 0.142, "lr": 4.999694657619013e-05, "epoch": 0.0942951438000943, "percentage": 0.5, "elapsed_time": "0:01:28", "remaining_time": "4:52:35", "throughput": 2117.06, "total_tokens": 186768}
41
+ {"current_steps": 200, "total_steps": 40000, "eval_loss": 0.3040875494480133, "epoch": 0.0942951438000943, "percentage": 0.5, "elapsed_time": "0:01:55", "remaining_time": "6:24:36", "throughput": 1610.61, "total_tokens": 186768}
42
+ {"current_steps": 205, "total_steps": 40000, "loss": 0.5682, "lr": 4.999679121351352e-05, "epoch": 0.09665252239509665, "percentage": 0.51, "elapsed_time": "0:01:59", "remaining_time": "6:25:55", "throughput": 1607.06, "total_tokens": 191696}
43
+ {"current_steps": 210, "total_steps": 40000, "loss": 0.3566, "lr": 4.9996631996017565e-05, "epoch": 0.09900990099009901, "percentage": 0.53, "elapsed_time": "0:02:01", "remaining_time": "6:23:23", "throughput": 1616.77, "total_tokens": 196288}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1722a265b3b36f8d2fbf5b326190f6913f16638f8a142170e65ef82198000c3
3
+ size 5752