Hugging Face's logo

rbelanec
/
train_multirc_1745950270

PEFT
Safetensors
llama-factory
lntuning
Generated from Trainer
Model card Files
xet
Community
rbelanec commited on
Commit
53bcfb5
路
verified 路
1 Parent(s): 6740eed

Training in progress, step 200

Browse files
Files changed (8) hide show
  1. adapter_config.json +15 -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 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
4
+ "exclude_modules": null,
5
+ "inference_mode": true,
6
+ "modules_to_save": null,
7
+ "peft_type": "LN_TUNING",
8
+ "revision": null,
9
+ "target_modules": [
10
+ "post_attention_layernorm",
11
+ "input_layernorm",
12
+ "norm"
13
+ ],
14
+ "task_type": "CAUSAL_LM"
15
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:271975ce6fb002f1d76f3565956bf93c4f3022aa7a683e8f61c8889b5c8b11f2
3
+ size 541712
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": 2.3824, "lr": 4.999999876629946e-05, "epoch": 0.0008157272208173587, "percentage": 0.01, "elapsed_time": "0:00:04", "remaining_time": "10:45:38", "throughput": 1813.77, "total_tokens": 8784}
2
+ {"current_steps": 10, "total_steps": 40000, "loss": 2.2428, "lr": 4.999999375439123e-05, "epoch": 0.0016314544416347174, "percentage": 0.03, "elapsed_time": "0:00:07", "remaining_time": "8:39:00", "throughput": 2379.29, "total_tokens": 18528}
3
+ {"current_steps": 15, "total_steps": 40000, "loss": 3.4286, "lr": 4.9999984887169785e-05, "epoch": 0.002447181662452076, "percentage": 0.04, "elapsed_time": "0:00:11", "remaining_time": "8:10:05", "throughput": 2644.13, "total_tokens": 29168}
4
+ {"current_steps": 20, "total_steps": 40000, "loss": 2.5567, "lr": 4.9999972164636506e-05, "epoch": 0.0032629088832694347, "percentage": 0.05, "elapsed_time": "0:00:14", "remaining_time": "8:02:23", "throughput": 2805.73, "total_tokens": 40624}
5
+ {"current_steps": 25, "total_steps": 40000, "loss": 2.8244, "lr": 4.999995558679334e-05, "epoch": 0.004078636104086793, "percentage": 0.06, "elapsed_time": "0:00:17", "remaining_time": "7:40:30", "throughput": 2891.72, "total_tokens": 49968}
6
+ {"current_steps": 30, "total_steps": 40000, "loss": 1.5947, "lr": 4.999993515364287e-05, "epoch": 0.004894363324904152, "percentage": 0.07, "elapsed_time": "0:00:20", "remaining_time": "7:35:10", "throughput": 2959.89, "total_tokens": 60672}
7
+ {"current_steps": 35, "total_steps": 40000, "loss": 3.8766, "lr": 4.999991086518822e-05, "epoch": 0.005710090545721511, "percentage": 0.09, "elapsed_time": "0:00:23", "remaining_time": "7:30:51", "throughput": 3014.2, "total_tokens": 71408}
8
+ {"current_steps": 40, "total_steps": 40000, "loss": 2.6206, "lr": 4.999988272143315e-05, "epoch": 0.0065258177665388694, "percentage": 0.1, "elapsed_time": "0:00:27", "remaining_time": "7:31:42", "throughput": 3050.28, "total_tokens": 82752}
9
+ {"current_steps": 45, "total_steps": 40000, "loss": 2.6362, "lr": 4.999985072238199e-05, "epoch": 0.007341544987356228, "percentage": 0.11, "elapsed_time": "0:00:30", "remaining_time": "7:27:54", "throughput": 3082.31, "total_tokens": 93296}
10
+ {"current_steps": 50, "total_steps": 40000, "loss": 2.9237, "lr": 4.999981486803969e-05, "epoch": 0.008157272208173586, "percentage": 0.12, "elapsed_time": "0:00:33", "remaining_time": "7:28:10", "throughput": 3107.8, "total_tokens": 104592}
11
+ {"current_steps": 55, "total_steps": 40000, "loss": 2.3438, "lr": 4.999977515841176e-05, "epoch": 0.008972999428990946, "percentage": 0.14, "elapsed_time": "0:00:36", "remaining_time": "7:25:22", "throughput": 3124.87, "total_tokens": 114976}
12
+ {"current_steps": 60, "total_steps": 40000, "loss": 3.9838, "lr": 4.9999731593504344e-05, "epoch": 0.009788726649808304, "percentage": 0.15, "elapsed_time": "0:00:39", "remaining_time": "7:21:19", "throughput": 3140.97, "total_tokens": 124944}
13
+ {"current_steps": 65, "total_steps": 40000, "loss": 2.651, "lr": 4.999968417332415e-05, "epoch": 0.010604453870625663, "percentage": 0.16, "elapsed_time": "0:00:42", "remaining_time": "7:17:50", "throughput": 3146.94, "total_tokens": 134560}
14
+ {"current_steps": 70, "total_steps": 40000, "loss": 1.7442, "lr": 4.999963289787848e-05, "epoch": 0.011420181091443021, "percentage": 0.18, "elapsed_time": "0:00:45", "remaining_time": "7:15:33", "throughput": 3154.63, "total_tokens": 144528}
15
+ {"current_steps": 75, "total_steps": 40000, "loss": 2.3111, "lr": 4.999957776717526e-05, "epoch": 0.012235908312260381, "percentage": 0.19, "elapsed_time": "0:00:48", "remaining_time": "7:14:10", "throughput": 3168.49, "total_tokens": 155056}
16
+ {"current_steps": 80, "total_steps": 40000, "loss": 2.7145, "lr": 4.9999518781222984e-05, "epoch": 0.013051635533077739, "percentage": 0.2, "elapsed_time": "0:00:51", "remaining_time": "7:11:07", "throughput": 3172.66, "total_tokens": 164464}
17
+ {"current_steps": 85, "total_steps": 40000, "loss": 3.3305, "lr": 4.9999455940030746e-05, "epoch": 0.013867362753895097, "percentage": 0.21, "elapsed_time": "0:00:54", "remaining_time": "7:09:52", "throughput": 3179.0, "total_tokens": 174608}
18
+ {"current_steps": 90, "total_steps": 40000, "loss": 1.7676, "lr": 4.999938924360824e-05, "epoch": 0.014683089974712456, "percentage": 0.22, "elapsed_time": "0:00:58", "remaining_time": "7:10:10", "throughput": 3189.08, "total_tokens": 185616}
19
+ {"current_steps": 95, "total_steps": 40000, "loss": 2.6622, "lr": 4.999931869196575e-05, "epoch": 0.015498817195529814, "percentage": 0.24, "elapsed_time": "0:01:01", "remaining_time": "7:07:48", "throughput": 3196.94, "total_tokens": 195360}
20
+ {"current_steps": 100, "total_steps": 40000, "loss": 1.9336, "lr": 4.999924428511416e-05, "epoch": 0.016314544416347172, "percentage": 0.25, "elapsed_time": "0:01:04", "remaining_time": "7:09:49", "throughput": 3204.87, "total_tokens": 207152}
21
+ {"current_steps": 105, "total_steps": 40000, "loss": 2.0811, "lr": 4.999916602306494e-05, "epoch": 0.017130271637164532, "percentage": 0.26, "elapsed_time": "0:01:07", "remaining_time": "7:10:01", "throughput": 3210.56, "total_tokens": 218016}
22
+ {"current_steps": 110, "total_steps": 40000, "loss": 2.7338, "lr": 4.999908390583016e-05, "epoch": 0.01794599885798189, "percentage": 0.27, "elapsed_time": "0:01:11", "remaining_time": "7:11:15", "throughput": 3218.9, "total_tokens": 229680}
23
+ {"current_steps": 115, "total_steps": 40000, "loss": 2.3528, "lr": 4.999899793342247e-05, "epoch": 0.01876172607879925, "percentage": 0.29, "elapsed_time": "0:01:14", "remaining_time": "7:08:22", "throughput": 3220.01, "total_tokens": 238624}
24
+ {"current_steps": 120, "total_steps": 40000, "loss": 3.1091, "lr": 4.999890810585516e-05, "epoch": 0.019577453299616607, "percentage": 0.3, "elapsed_time": "0:01:17", "remaining_time": "7:07:15", "throughput": 3222.75, "total_tokens": 248592}
25
+ {"current_steps": 125, "total_steps": 40000, "loss": 1.8262, "lr": 4.999881442314206e-05, "epoch": 0.020393180520433967, "percentage": 0.31, "elapsed_time": "0:01:20", "remaining_time": "7:07:18", "throughput": 3227.38, "total_tokens": 259392}
26
+ {"current_steps": 130, "total_steps": 40000, "loss": 4.0175, "lr": 4.9998716885297617e-05, "epoch": 0.021208907741251327, "percentage": 0.33, "elapsed_time": "0:01:23", "remaining_time": "7:06:53", "throughput": 3228.9, "total_tokens": 269664}
27
+ {"current_steps": 135, "total_steps": 40000, "loss": 2.6776, "lr": 4.999861549233688e-05, "epoch": 0.022024634962068683, "percentage": 0.34, "elapsed_time": "0:01:26", "remaining_time": "7:07:25", "throughput": 3233.3, "total_tokens": 280800}
28
+ {"current_steps": 140, "total_steps": 40000, "loss": 1.98, "lr": 4.999851024427548e-05, "epoch": 0.022840362182886043, "percentage": 0.35, "elapsed_time": "0:01:29", "remaining_time": "7:06:29", "throughput": 3234.83, "total_tokens": 290736}
29
+ {"current_steps": 145, "total_steps": 40000, "loss": 1.8577, "lr": 4.999840114112965e-05, "epoch": 0.023656089403703402, "percentage": 0.36, "elapsed_time": "0:01:33", "remaining_time": "7:06:09", "throughput": 3237.2, "total_tokens": 301152}
30
+ {"current_steps": 150, "total_steps": 40000, "loss": 1.5681, "lr": 4.999828818291621e-05, "epoch": 0.024471816624520762, "percentage": 0.38, "elapsed_time": "0:01:36", "remaining_time": "7:05:24", "throughput": 3237.46, "total_tokens": 311040}
31
+ {"current_steps": 155, "total_steps": 40000, "loss": 2.5782, "lr": 4.999817136965259e-05, "epoch": 0.025287543845338118, "percentage": 0.39, "elapsed_time": "0:01:39", "remaining_time": "7:06:06", "throughput": 3242.74, "total_tokens": 322512}
32
+ {"current_steps": 160, "total_steps": 40000, "loss": 2.9134, "lr": 4.9998050701356794e-05, "epoch": 0.026103271066155478, "percentage": 0.4, "elapsed_time": "0:01:42", "remaining_time": "7:06:42", "throughput": 3245.07, "total_tokens": 333664}
33
+ {"current_steps": 165, "total_steps": 40000, "loss": 2.7584, "lr": 4.999792617804744e-05, "epoch": 0.026918998286972837, "percentage": 0.41, "elapsed_time": "0:01:46", "remaining_time": "7:07:31", "throughput": 3248.07, "total_tokens": 345104}
34
+ {"current_steps": 170, "total_steps": 40000, "loss": 2.09, "lr": 4.9997797799743724e-05, "epoch": 0.027734725507790194, "percentage": 0.43, "elapsed_time": "0:01:49", "remaining_time": "7:07:57", "throughput": 3250.91, "total_tokens": 356288}
35
+ {"current_steps": 175, "total_steps": 40000, "loss": 2.6638, "lr": 4.999766556646545e-05, "epoch": 0.028550452728607553, "percentage": 0.44, "elapsed_time": "0:01:52", "remaining_time": "7:06:58", "throughput": 3248.87, "total_tokens": 365744}
36
+ {"current_steps": 180, "total_steps": 40000, "loss": 3.0835, "lr": 4.9997529478232996e-05, "epoch": 0.029366179949424913, "percentage": 0.45, "elapsed_time": "0:01:55", "remaining_time": "7:06:39", "throughput": 3249.97, "total_tokens": 376080}
37
+ {"current_steps": 185, "total_steps": 40000, "loss": 2.6222, "lr": 4.9997389535067365e-05, "epoch": 0.030181907170242273, "percentage": 0.46, "elapsed_time": "0:01:58", "remaining_time": "7:06:33", "throughput": 3252.41, "total_tokens": 386784}
38
+ {"current_steps": 190, "total_steps": 40000, "loss": 3.8699, "lr": 4.999724573699012e-05, "epoch": 0.03099763439105963, "percentage": 0.47, "elapsed_time": "0:02:01", "remaining_time": "7:05:56", "throughput": 3254.36, "total_tokens": 396944}
39
+ {"current_steps": 195, "total_steps": 40000, "loss": 2.9014, "lr": 4.9997098084023457e-05, "epoch": 0.031813361611876985, "percentage": 0.49, "elapsed_time": "0:02:05", "remaining_time": "7:06:16", "throughput": 3255.89, "total_tokens": 407952}
40
+ {"current_steps": 200, "total_steps": 40000, "loss": 1.8061, "lr": 4.999694657619013e-05, "epoch": 0.032629088832694345, "percentage": 0.5, "elapsed_time": "0:02:08", "remaining_time": "7:05:47", "throughput": 3257.42, "total_tokens": 418192}
41
+ {"current_steps": 200, "total_steps": 40000, "eval_loss": 2.6757116317749023, "epoch": 0.032629088832694345, "percentage": 0.5, "elapsed_time": "0:04:22", "remaining_time": "14:31:45", "throughput": 1591.05, "total_tokens": 418192}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d0c2c0bb46eb1c352b499eb915f25cd739a9a6e20d93074f8f7816c9b08778f
3
+ size 5752