Hugging Face's logo

rbelanec
/
train_multirc_1745950269

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files
xet
 Community
rbelanec commited on
Commit
c68e931
·
verified ·
1 Parent(s): 1e5298b

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 +41 -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:a8436255a71eb685fdb72319f4faa25d2978a09bcc0cf7b4aa972ec2c5513b26
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 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 5, "total_steps": 40000, "loss": 1.0725, "lr": 4.999999876629946e-05, "epoch": 0.0008157272208173587, "percentage": 0.01, "elapsed_time": "0:00:05", "remaining_time": "11:44:01", "throughput": 1663.36, "total_tokens": 8784}
2
+ {"current_steps": 10, "total_steps": 40000, "loss": 0.276, "lr": 4.999999375439123e-05, "epoch": 0.0016314544416347174, "percentage": 0.03, "elapsed_time": "0:00:08", "remaining_time": "9:45:07", "throughput": 2110.48, "total_tokens": 18528}
3
+ {"current_steps": 15, "total_steps": 40000, "loss": 0.4044, "lr": 4.9999984887169785e-05, "epoch": 0.002447181662452076, "percentage": 0.04, "elapsed_time": "0:00:12", "remaining_time": "9:19:52", "throughput": 2314.54, "total_tokens": 29168}
4
+ {"current_steps": 20, "total_steps": 40000, "loss": 0.2984, "lr": 4.9999972164636506e-05, "epoch": 0.0032629088832694347, "percentage": 0.05, "elapsed_time": "0:00:16", "remaining_time": "9:15:07", "throughput": 2438.14, "total_tokens": 40624}
5
+ {"current_steps": 25, "total_steps": 40000, "loss": 0.3014, "lr": 4.999995558679334e-05, "epoch": 0.004078636104086793, "percentage": 0.06, "elapsed_time": "0:00:19", "remaining_time": "8:52:41", "throughput": 2499.86, "total_tokens": 49968}
6
+ {"current_steps": 30, "total_steps": 40000, "loss": 0.2144, "lr": 4.999993515364287e-05, "epoch": 0.004894363324904152, "percentage": 0.07, "elapsed_time": "0:00:23", "remaining_time": "8:48:14", "throughput": 2550.44, "total_tokens": 60672}
7
+ {"current_steps": 35, "total_steps": 40000, "loss": 0.7108, "lr": 4.999991086518822e-05, "epoch": 0.005710090545721511, "percentage": 0.09, "elapsed_time": "0:00:27", "remaining_time": "8:44:34", "throughput": 2590.57, "total_tokens": 71408}
8
+ {"current_steps": 40, "total_steps": 40000, "loss": 0.3382, "lr": 4.999988272143315e-05, "epoch": 0.0065258177665388694, "percentage": 0.1, "elapsed_time": "0:00:31", "remaining_time": "8:46:30", "throughput": 2616.9, "total_tokens": 82752}
9
+ {"current_steps": 45, "total_steps": 40000, "loss": 0.1571, "lr": 4.999985072238199e-05, "epoch": 0.007341544987356228, "percentage": 0.11, "elapsed_time": "0:00:35", "remaining_time": "8:42:54", "throughput": 2640.21, "total_tokens": 93296}
10
+ {"current_steps": 50, "total_steps": 40000, "loss": 0.2644, "lr": 4.999981486803969e-05, "epoch": 0.008157272208173586, "percentage": 0.12, "elapsed_time": "0:00:39", "remaining_time": "8:43:39", "throughput": 2659.78, "total_tokens": 104592}
11
+ {"current_steps": 55, "total_steps": 40000, "loss": 0.3158, "lr": 4.999977515841176e-05, "epoch": 0.008972999428990946, "percentage": 0.14, "elapsed_time": "0:00:43", "remaining_time": "8:40:47", "throughput": 2672.31, "total_tokens": 114976}
12
+ {"current_steps": 60, "total_steps": 40000, "loss": 0.2687, "lr": 4.9999731593504344e-05, "epoch": 0.009788726649808304, "percentage": 0.15, "elapsed_time": "0:00:46", "remaining_time": "8:36:37", "throughput": 2683.15, "total_tokens": 124944}
13
+ {"current_steps": 65, "total_steps": 40000, "loss": 0.2159, "lr": 4.999968417332415e-05, "epoch": 0.010604453870625663, "percentage": 0.16, "elapsed_time": "0:00:50", "remaining_time": "8:32:51", "throughput": 2686.62, "total_tokens": 134560}
14
+ {"current_steps": 70, "total_steps": 40000, "loss": 0.1389, "lr": 4.999963289787848e-05, "epoch": 0.011420181091443021, "percentage": 0.18, "elapsed_time": "0:00:53", "remaining_time": "8:30:29", "throughput": 2691.59, "total_tokens": 144528}
15
+ {"current_steps": 75, "total_steps": 40000, "loss": 0.3824, "lr": 4.999957776717526e-05, "epoch": 0.012235908312260381, "percentage": 0.19, "elapsed_time": "0:00:57", "remaining_time": "8:29:08", "throughput": 2701.94, "total_tokens": 155056}
16
+ {"current_steps": 80, "total_steps": 40000, "loss": 0.5722, "lr": 4.9999518781222984e-05, "epoch": 0.013051635533077739, "percentage": 0.2, "elapsed_time": "0:01:00", "remaining_time": "8:25:45", "throughput": 2704.41, "total_tokens": 164464}
17
+ {"current_steps": 85, "total_steps": 40000, "loss": 0.183, "lr": 4.9999455940030746e-05, "epoch": 0.013867362753895097, "percentage": 0.21, "elapsed_time": "0:01:04", "remaining_time": "8:24:23", "throughput": 2709.37, "total_tokens": 174608}
18
+ {"current_steps": 90, "total_steps": 40000, "loss": 0.0859, "lr": 4.999938924360824e-05, "epoch": 0.014683089974712456, "percentage": 0.22, "elapsed_time": "0:01:08", "remaining_time": "8:24:54", "throughput": 2717.02, "total_tokens": 185616}
19
+ {"current_steps": 95, "total_steps": 40000, "loss": 0.422, "lr": 4.999931869196575e-05, "epoch": 0.015498817195529814, "percentage": 0.24, "elapsed_time": "0:01:11", "remaining_time": "8:22:22", "throughput": 2722.43, "total_tokens": 195360}
20
+ {"current_steps": 100, "total_steps": 40000, "loss": 0.3293, "lr": 4.999924428511416e-05, "epoch": 0.016314544416347172, "percentage": 0.25, "elapsed_time": "0:01:15", "remaining_time": "8:24:47", "throughput": 2729.0, "total_tokens": 207152}
21
+ {"current_steps": 105, "total_steps": 40000, "loss": 0.1805, "lr": 4.999916602306494e-05, "epoch": 0.017130271637164532, "percentage": 0.26, "elapsed_time": "0:01:19", "remaining_time": "8:25:06", "throughput": 2733.3, "total_tokens": 218016}
22
+ {"current_steps": 110, "total_steps": 40000, "loss": 0.36, "lr": 4.999908390583016e-05, "epoch": 0.01794599885798189, "percentage": 0.27, "elapsed_time": "0:01:23", "remaining_time": "8:26:40", "throughput": 2739.81, "total_tokens": 229680}
23
+ {"current_steps": 115, "total_steps": 40000, "loss": 0.1829, "lr": 4.999899793342247e-05, "epoch": 0.01876172607879925, "percentage": 0.29, "elapsed_time": "0:01:27", "remaining_time": "8:23:22", "throughput": 2740.21, "total_tokens": 238624}
24
+ {"current_steps": 120, "total_steps": 40000, "loss": 0.1772, "lr": 4.999890810585516e-05, "epoch": 0.019577453299616607, "percentage": 0.3, "elapsed_time": "0:01:30", "remaining_time": "8:22:07", "throughput": 2742.18, "total_tokens": 248592}
25
+ {"current_steps": 125, "total_steps": 40000, "loss": 0.0489, "lr": 4.999881442314206e-05, "epoch": 0.020393180520433967, "percentage": 0.31, "elapsed_time": "0:01:34", "remaining_time": "8:22:15", "throughput": 2745.76, "total_tokens": 259392}
26
+ {"current_steps": 130, "total_steps": 40000, "loss": 0.1477, "lr": 4.9998716885297617e-05, "epoch": 0.021208907741251327, "percentage": 0.33, "elapsed_time": "0:01:38", "remaining_time": "8:21:50", "throughput": 2746.65, "total_tokens": 269664}
27
+ {"current_steps": 135, "total_steps": 40000, "loss": 0.2348, "lr": 4.999861549233688e-05, "epoch": 0.022024634962068683, "percentage": 0.34, "elapsed_time": "0:01:42", "remaining_time": "8:22:30", "throughput": 2750.21, "total_tokens": 280800}
28
+ {"current_steps": 140, "total_steps": 40000, "loss": 0.1346, "lr": 4.999851024427548e-05, "epoch": 0.022840362182886043, "percentage": 0.35, "elapsed_time": "0:01:45", "remaining_time": "8:21:27", "throughput": 2751.17, "total_tokens": 290736}
29
+ {"current_steps": 145, "total_steps": 40000, "loss": 0.1868, "lr": 4.999840114112965e-05, "epoch": 0.023656089403703402, "percentage": 0.36, "elapsed_time": "0:01:49", "remaining_time": "8:21:07", "throughput": 2752.98, "total_tokens": 301152}
30
+ {"current_steps": 150, "total_steps": 40000, "loss": 0.2076, "lr": 4.999828818291621e-05, "epoch": 0.024471816624520762, "percentage": 0.38, "elapsed_time": "0:01:52", "remaining_time": "8:20:12", "throughput": 2753.25, "total_tokens": 311040}
31
+ {"current_steps": 155, "total_steps": 40000, "loss": 0.4532, "lr": 4.999817136965259e-05, "epoch": 0.025287543845338118, "percentage": 0.39, "elapsed_time": "0:01:56", "remaining_time": "8:21:07", "throughput": 2757.35, "total_tokens": 322512}
32
+ {"current_steps": 160, "total_steps": 40000, "loss": 0.6416, "lr": 4.9998050701356794e-05, "epoch": 0.026103271066155478, "percentage": 0.4, "elapsed_time": "0:02:00", "remaining_time": "8:21:51", "throughput": 2759.12, "total_tokens": 333664}
33
+ {"current_steps": 165, "total_steps": 40000, "loss": 0.2153, "lr": 4.999792617804744e-05, "epoch": 0.026918998286972837, "percentage": 0.41, "elapsed_time": "0:02:04", "remaining_time": "8:22:50", "throughput": 2761.54, "total_tokens": 345104}
34
+ {"current_steps": 170, "total_steps": 40000, "loss": 0.2257, "lr": 4.9997797799743724e-05, "epoch": 0.027734725507790194, "percentage": 0.43, "elapsed_time": "0:02:08", "remaining_time": "8:23:24", "throughput": 2763.68, "total_tokens": 356288}
35
+ {"current_steps": 175, "total_steps": 40000, "loss": 0.3166, "lr": 4.999766556646545e-05, "epoch": 0.028550452728607553, "percentage": 0.44, "elapsed_time": "0:02:12", "remaining_time": "8:22:16", "throughput": 2761.86, "total_tokens": 365744}
36
+ {"current_steps": 180, "total_steps": 40000, "loss": 0.274, "lr": 4.9997529478232996e-05, "epoch": 0.029366179949424913, "percentage": 0.45, "elapsed_time": "0:02:16", "remaining_time": "8:21:56", "throughput": 2762.55, "total_tokens": 376080}
37
+ {"current_steps": 185, "total_steps": 40000, "loss": 0.1925, "lr": 4.9997389535067365e-05, "epoch": 0.030181907170242273, "percentage": 0.46, "elapsed_time": "0:02:19", "remaining_time": "8:21:52", "throughput": 2764.34, "total_tokens": 386784}
38
+ {"current_steps": 190, "total_steps": 40000, "loss": 0.2189, "lr": 4.999724573699012e-05, "epoch": 0.03099763439105963, "percentage": 0.47, "elapsed_time": "0:02:23", "remaining_time": "8:21:12", "throughput": 2765.66, "total_tokens": 396944}
39
+ {"current_steps": 195, "total_steps": 40000, "loss": 0.1831, "lr": 4.9997098084023457e-05, "epoch": 0.031813361611876985, "percentage": 0.49, "elapsed_time": "0:02:27", "remaining_time": "8:21:35", "throughput": 2767.03, "total_tokens": 407952}
40
+ {"current_steps": 200, "total_steps": 40000, "loss": 0.0113, "lr": 4.999694657619013e-05, "epoch": 0.032629088832694345, "percentage": 0.5, "elapsed_time": "0:02:31", "remaining_time": "8:21:03", "throughput": 2768.11, "total_tokens": 418192}
41
+ {"current_steps": 200, "total_steps": 40000, "eval_loss": 0.2798120677471161, "epoch": 0.032629088832694345, "percentage": 0.5, "elapsed_time": "0:04:59", "remaining_time": "16:33:35", "throughput": 1395.95, "total_tokens": 418192}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63e27cfac114bc47a634c7d0d13d642baae1eb391d39fe2221282d41d59a55f0
3
+ size 5752