Hugging Face's logo

rbelanec
/
train_copa_1745950331

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files
xet
Community
rbelanec commited on
Commit
963b83d
·
verified ·
1 Parent(s): 72c0458

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
+ "k_proj",
28
+ "down_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 sha256:9f26e3323cbd4b8d0354e82190bce6e6afae5dc2ef3e4865c409e66b84c2141f
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": 0.3536, "lr": 4.999999876629946e-05, "epoch": 0.05555555555555555, "percentage": 0.01, "elapsed_time": "0:00:03", "remaining_time": "7:12:04", "throughput": 429.5, "total_tokens": 1392}
2
+ {"current_steps": 10, "total_steps": 40000, "loss": 0.1388, "lr": 4.999999375439123e-05, "epoch": 0.1111111111111111, "percentage": 0.03, "elapsed_time": "0:00:05", "remaining_time": "5:47:10", "throughput": 537.53, "total_tokens": 2800}
3
+ {"current_steps": 15, "total_steps": 40000, "loss": 0.247, "lr": 4.9999984887169785e-05, "epoch": 0.16666666666666666, "percentage": 0.04, "elapsed_time": "0:00:07", "remaining_time": "5:17:27", "throughput": 591.15, "total_tokens": 4224}
4
+ {"current_steps": 20, "total_steps": 40000, "loss": 0.2303, "lr": 4.9999972164636506e-05, "epoch": 0.2222222222222222, "percentage": 0.05, "elapsed_time": "0:00:09", "remaining_time": "5:02:43", "throughput": 621.6, "total_tokens": 5648}
5
+ {"current_steps": 25, "total_steps": 40000, "loss": 0.0298, "lr": 4.999995558679334e-05, "epoch": 0.2777777777777778, "percentage": 0.06, "elapsed_time": "0:00:11", "remaining_time": "4:54:03", "throughput": 638.02, "total_tokens": 7040}
6
+ {"current_steps": 30, "total_steps": 40000, "loss": 0.1076, "lr": 4.999993515364287e-05, "epoch": 0.3333333333333333, "percentage": 0.07, "elapsed_time": "0:00:12", "remaining_time": "4:48:00", "throughput": 650.11, "total_tokens": 8432}
7
+ {"current_steps": 35, "total_steps": 40000, "loss": 0.1874, "lr": 4.999991086518822e-05, "epoch": 0.3888888888888889, "percentage": 0.09, "elapsed_time": "0:00:14", "remaining_time": "4:43:59", "throughput": 659.4, "total_tokens": 9840}
8
+ {"current_steps": 40, "total_steps": 40000, "loss": 0.0114, "lr": 4.999988272143315e-05, "epoch": 0.4444444444444444, "percentage": 0.1, "elapsed_time": "0:00:16", "remaining_time": "4:41:08", "throughput": 663.29, "total_tokens": 11200}
9
+ {"current_steps": 45, "total_steps": 40000, "loss": 0.4715, "lr": 4.999985072238199e-05, "epoch": 0.5, "percentage": 0.11, "elapsed_time": "0:00:18", "remaining_time": "4:38:35", "throughput": 671.41, "total_tokens": 12640}
10
+ {"current_steps": 50, "total_steps": 40000, "loss": 0.4279, "lr": 4.999981486803969e-05, "epoch": 0.5555555555555556, "percentage": 0.12, "elapsed_time": "0:00:20", "remaining_time": "4:36:38", "throughput": 676.99, "total_tokens": 14064}
11
+ {"current_steps": 55, "total_steps": 40000, "loss": 0.0883, "lr": 4.999977515841176e-05, "epoch": 0.6111111111111112, "percentage": 0.14, "elapsed_time": "0:00:22", "remaining_time": "4:34:53", "throughput": 681.99, "total_tokens": 15488}
12
+ {"current_steps": 60, "total_steps": 40000, "loss": 0.1077, "lr": 4.9999731593504344e-05, "epoch": 0.6666666666666666, "percentage": 0.15, "elapsed_time": "0:00:24", "remaining_time": "4:33:28", "throughput": 685.43, "total_tokens": 16896}
13
+ {"current_steps": 65, "total_steps": 40000, "loss": 0.1558, "lr": 4.999968417332415e-05, "epoch": 0.7222222222222222, "percentage": 0.16, "elapsed_time": "0:00:26", "remaining_time": "4:32:19", "throughput": 689.46, "total_tokens": 18336}
14
+ {"current_steps": 70, "total_steps": 40000, "loss": 0.0742, "lr": 4.999963289787848e-05, "epoch": 0.7777777777777778, "percentage": 0.18, "elapsed_time": "0:00:28", "remaining_time": "4:31:19", "throughput": 692.4, "total_tokens": 19760}
15
+ {"current_steps": 75, "total_steps": 40000, "loss": 0.1122, "lr": 4.999957776717526e-05, "epoch": 0.8333333333333334, "percentage": 0.19, "elapsed_time": "0:00:30", "remaining_time": "4:30:32", "throughput": 693.16, "total_tokens": 21136}
16
+ {"current_steps": 80, "total_steps": 40000, "loss": 0.2608, "lr": 4.9999518781222984e-05, "epoch": 0.8888888888888888, "percentage": 0.2, "elapsed_time": "0:00:32", "remaining_time": "4:29:41", "throughput": 695.71, "total_tokens": 22560}
17
+ {"current_steps": 85, "total_steps": 40000, "loss": 0.0559, "lr": 4.9999455940030746e-05, "epoch": 0.9444444444444444, "percentage": 0.21, "elapsed_time": "0:00:34", "remaining_time": "4:28:55", "throughput": 696.59, "total_tokens": 23936}
18
+ {"current_steps": 90, "total_steps": 40000, "loss": 0.2861, "lr": 4.999938924360824e-05, "epoch": 1.0, "percentage": 0.22, "elapsed_time": "0:00:36", "remaining_time": "4:29:10", "throughput": 694.56, "total_tokens": 25296}
19
+ {"current_steps": 95, "total_steps": 40000, "loss": 0.0234, "lr": 4.999931869196575e-05, "epoch": 1.0555555555555556, "percentage": 0.24, "elapsed_time": "0:00:38", "remaining_time": "4:30:33", "throughput": 690.97, "total_tokens": 26704}
20
+ {"current_steps": 100, "total_steps": 40000, "loss": 0.0059, "lr": 4.999924428511416e-05, "epoch": 1.1111111111111112, "percentage": 0.25, "elapsed_time": "0:00:40", "remaining_time": "4:29:56", "throughput": 691.76, "total_tokens": 28080}
21
+ {"current_steps": 105, "total_steps": 40000, "loss": 0.0055, "lr": 4.999916602306494e-05, "epoch": 1.1666666666666667, "percentage": 0.26, "elapsed_time": "0:00:42", "remaining_time": "4:29:18", "throughput": 692.99, "total_tokens": 29472}
22
+ {"current_steps": 110, "total_steps": 40000, "loss": 0.0002, "lr": 4.999908390583016e-05, "epoch": 1.2222222222222223, "percentage": 0.27, "elapsed_time": "0:00:44", "remaining_time": "4:28:44", "throughput": 694.49, "total_tokens": 30880}
23
+ {"current_steps": 115, "total_steps": 40000, "loss": 0.0032, "lr": 4.999899793342247e-05, "epoch": 1.2777777777777777, "percentage": 0.29, "elapsed_time": "0:00:46", "remaining_time": "4:28:20", "throughput": 695.2, "total_tokens": 32272}
24
+ {"current_steps": 120, "total_steps": 40000, "loss": 0.0001, "lr": 4.999890810585516e-05, "epoch": 1.3333333333333333, "percentage": 0.3, "elapsed_time": "0:00:48", "remaining_time": "4:27:56", "throughput": 695.24, "total_tokens": 33632}
25
+ {"current_steps": 125, "total_steps": 40000, "loss": 0.0, "lr": 4.999881442314206e-05, "epoch": 1.3888888888888888, "percentage": 0.31, "elapsed_time": "0:00:50", "remaining_time": "4:27:30", "throughput": 697.05, "total_tokens": 35072}
26
+ {"current_steps": 130, "total_steps": 40000, "loss": 0.049, "lr": 4.9998716885297617e-05, "epoch": 1.4444444444444444, "percentage": 0.33, "elapsed_time": "0:00:52", "remaining_time": "4:27:05", "throughput": 699.07, "total_tokens": 36528}
27
+ {"current_steps": 135, "total_steps": 40000, "loss": 0.0001, "lr": 4.999861549233688e-05, "epoch": 1.5, "percentage": 0.34, "elapsed_time": "0:00:54", "remaining_time": "4:26:44", "throughput": 699.93, "total_tokens": 37936}
28
+ {"current_steps": 140, "total_steps": 40000, "loss": 0.0001, "lr": 4.999851024427548e-05, "epoch": 1.5555555555555556, "percentage": 0.35, "elapsed_time": "0:00:56", "remaining_time": "4:26:25", "throughput": 700.48, "total_tokens": 39328}
29
+ {"current_steps": 145, "total_steps": 40000, "loss": 0.1647, "lr": 4.999840114112965e-05, "epoch": 1.6111111111111112, "percentage": 0.36, "elapsed_time": "0:00:58", "remaining_time": "4:26:03", "throughput": 701.65, "total_tokens": 40752}
30
+ {"current_steps": 150, "total_steps": 40000, "loss": 0.0839, "lr": 4.999828818291621e-05, "epoch": 1.6666666666666665, "percentage": 0.38, "elapsed_time": "0:01:00", "remaining_time": "4:25:47", "throughput": 701.54, "total_tokens": 42112}
31
+ {"current_steps": 155, "total_steps": 40000, "loss": 0.0029, "lr": 4.999817136965259e-05, "epoch": 1.7222222222222223, "percentage": 0.39, "elapsed_time": "0:01:01", "remaining_time": "4:25:30", "throughput": 702.0, "total_tokens": 43504}
32
+ {"current_steps": 160, "total_steps": 40000, "loss": 0.0006, "lr": 4.9998050701356794e-05, "epoch": 1.7777777777777777, "percentage": 0.4, "elapsed_time": "0:01:03", "remaining_time": "4:25:16", "throughput": 701.86, "total_tokens": 44864}
33
+ {"current_steps": 165, "total_steps": 40000, "loss": 0.0036, "lr": 4.999792617804744e-05, "epoch": 1.8333333333333335, "percentage": 0.41, "elapsed_time": "0:01:05", "remaining_time": "4:25:00", "throughput": 701.86, "total_tokens": 46224}
34
+ {"current_steps": 170, "total_steps": 40000, "loss": 0.0004, "lr": 4.9997797799743724e-05, "epoch": 1.8888888888888888, "percentage": 0.43, "elapsed_time": "0:01:07", "remaining_time": "4:24:44", "throughput": 701.86, "total_tokens": 47584}
35
+ {"current_steps": 175, "total_steps": 40000, "loss": 0.0768, "lr": 4.999766556646545e-05, "epoch": 1.9444444444444444, "percentage": 0.44, "elapsed_time": "0:01:09", "remaining_time": "4:24:28", "throughput": 702.83, "total_tokens": 49008}
36
+ {"current_steps": 180, "total_steps": 40000, "loss": 0.0416, "lr": 4.9997529478232996e-05, "epoch": 2.0, "percentage": 0.45, "elapsed_time": "0:01:11", "remaining_time": "4:24:49", "throughput": 701.9, "total_tokens": 50416}
37
+ {"current_steps": 185, "total_steps": 40000, "loss": 0.0001, "lr": 4.9997389535067365e-05, "epoch": 2.0555555555555554, "percentage": 0.46, "elapsed_time": "0:01:14", "remaining_time": "4:25:32", "throughput": 700.25, "total_tokens": 51840}
38
+ {"current_steps": 190, "total_steps": 40000, "loss": 0.045, "lr": 4.999724573699012e-05, "epoch": 2.111111111111111, "percentage": 0.47, "elapsed_time": "0:01:16", "remaining_time": "4:25:24", "throughput": 700.21, "total_tokens": 53216}
39
+ {"current_steps": 195, "total_steps": 40000, "loss": 0.0001, "lr": 4.9997098084023457e-05, "epoch": 2.1666666666666665, "percentage": 0.49, "elapsed_time": "0:01:17", "remaining_time": "4:25:10", "throughput": 700.81, "total_tokens": 54624}
40
+ {"current_steps": 200, "total_steps": 40000, "loss": 0.0001, "lr": 4.999694657619013e-05, "epoch": 2.2222222222222223, "percentage": 0.5, "elapsed_time": "0:01:19", "remaining_time": "4:24:55", "throughput": 701.88, "total_tokens": 56064}
41
+ {"current_steps": 200, "total_steps": 40000, "eval_loss": 0.11372174322605133, "epoch": 2.2222222222222223, "percentage": 0.5, "elapsed_time": "0:01:21", "remaining_time": "4:29:16", "throughput": 690.52, "total_tokens": 56064}
42
+ {"current_steps": 205, "total_steps": 40000, "loss": 0.0012, "lr": 4.999679121351352e-05, "epoch": 2.2777777777777777, "percentage": 0.51, "elapsed_time": "0:01:24", "remaining_time": "4:32:46", "throughput": 681.66, "total_tokens": 57472}
43
+ {"current_steps": 210, "total_steps": 40000, "loss": 0.0, "lr": 4.9996631996017565e-05, "epoch": 2.3333333333333335, "percentage": 0.53, "elapsed_time": "0:01:26", "remaining_time": "4:32:34", "throughput": 681.25, "total_tokens": 58800}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beddd419e27f527e30e4f16dc67adde958e95794e04c178b5cd04b552ff01993
3
+ size 5752