Hugging Face's logo

rbelanec
/
train_record_1745950257

Safetensors
Model card Files
xet
 Community
rbelanec commited on
Commit
531316c
·
verified ·
1 Parent(s): 7d3927e

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 +42 -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
+ "v_proj",
28
+ "down_proj",
29
+ "k_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 sha256:3244842da264ce5699322460bd05e01319a32b64824bf51af37572108b01ff03
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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 5, "total_steps": 40000, "loss": 3.2827, "lr": 4.999999876629946e-05, "epoch": 0.00016004097048844505, "percentage": 0.01, "elapsed_time": "0:00:05", "remaining_time": "11:53:10", "throughput": 1438.64, "total_tokens": 7696}
2
+ {"current_steps": 10, "total_steps": 40000, "loss": 1.1033, "lr": 4.999999375439123e-05, "epoch": 0.0003200819409768901, "percentage": 0.03, "elapsed_time": "0:00:08", "remaining_time": "9:07:07", "throughput": 1859.45, "total_tokens": 15264}
3
+ {"current_steps": 15, "total_steps": 40000, "loss": 0.8497, "lr": 4.9999984887169785e-05, "epoch": 0.0004801229114653351, "percentage": 0.04, "elapsed_time": "0:00:11", "remaining_time": "8:16:47", "throughput": 2071.88, "total_tokens": 23168}
4
+ {"current_steps": 20, "total_steps": 40000, "loss": 0.6246, "lr": 4.9999972164636506e-05, "epoch": 0.0006401638819537802, "percentage": 0.05, "elapsed_time": "0:00:14", "remaining_time": "7:47:15", "throughput": 2205.27, "total_tokens": 30928}
5
+ {"current_steps": 25, "total_steps": 40000, "loss": 0.5606, "lr": 4.999995558679334e-05, "epoch": 0.0008002048524422252, "percentage": 0.06, "elapsed_time": "0:00:16", "remaining_time": "7:29:00", "throughput": 2279.12, "total_tokens": 38400}
6
+ {"current_steps": 30, "total_steps": 40000, "loss": 0.794, "lr": 4.999993515364287e-05, "epoch": 0.0009602458229306702, "percentage": 0.07, "elapsed_time": "0:00:19", "remaining_time": "7:21:43", "throughput": 2342.2, "total_tokens": 46592}
7
+ {"current_steps": 35, "total_steps": 40000, "loss": 0.7539, "lr": 4.999991086518822e-05, "epoch": 0.0011202867934191152, "percentage": 0.09, "elapsed_time": "0:00:22", "remaining_time": "7:12:32", "throughput": 2387.11, "total_tokens": 54256}
8
+ {"current_steps": 40, "total_steps": 40000, "loss": 0.7213, "lr": 4.999988272143315e-05, "epoch": 0.0012803277639075604, "percentage": 0.1, "elapsed_time": "0:00:25", "remaining_time": "7:07:12", "throughput": 2416.38, "total_tokens": 62000}
9
+ {"current_steps": 45, "total_steps": 40000, "loss": 0.4932, "lr": 4.999985072238199e-05, "epoch": 0.0014403687343960054, "percentage": 0.11, "elapsed_time": "0:00:28", "remaining_time": "7:02:13", "throughput": 2443.24, "total_tokens": 69712}
10
+ {"current_steps": 50, "total_steps": 40000, "loss": 0.5297, "lr": 4.999981486803969e-05, "epoch": 0.0016004097048844504, "percentage": 0.12, "elapsed_time": "0:00:31", "remaining_time": "6:57:03", "throughput": 2460.44, "total_tokens": 77056}
11
+ {"current_steps": 55, "total_steps": 40000, "loss": 0.5173, "lr": 4.999977515841176e-05, "epoch": 0.0017604506753728954, "percentage": 0.14, "elapsed_time": "0:00:34", "remaining_time": "6:54:08", "throughput": 2476.71, "total_tokens": 84736}
12
+ {"current_steps": 60, "total_steps": 40000, "loss": 0.7958, "lr": 4.9999731593504344e-05, "epoch": 0.0019204916458613404, "percentage": 0.15, "elapsed_time": "0:00:37", "remaining_time": "6:50:40", "throughput": 2490.6, "total_tokens": 92192}
13
+ {"current_steps": 65, "total_steps": 40000, "loss": 0.5276, "lr": 4.999968417332415e-05, "epoch": 0.0020805326163497854, "percentage": 0.16, "elapsed_time": "0:00:39", "remaining_time": "6:48:31", "throughput": 2504.96, "total_tokens": 99936}
14
+ {"current_steps": 70, "total_steps": 40000, "loss": 0.5819, "lr": 4.999963289787848e-05, "epoch": 0.0022405735868382304, "percentage": 0.18, "elapsed_time": "0:00:42", "remaining_time": "6:48:39", "throughput": 2512.88, "total_tokens": 108016}
15
+ {"current_steps": 75, "total_steps": 40000, "loss": 0.4047, "lr": 4.999957776717526e-05, "epoch": 0.002400614557326676, "percentage": 0.19, "elapsed_time": "0:00:45", "remaining_time": "6:46:00", "throughput": 2521.89, "total_tokens": 115408}
16
+ {"current_steps": 80, "total_steps": 40000, "loss": 0.3575, "lr": 4.9999518781222984e-05, "epoch": 0.002560655527815121, "percentage": 0.2, "elapsed_time": "0:00:48", "remaining_time": "6:43:26", "throughput": 2533.71, "total_tokens": 122912}
17
+ {"current_steps": 85, "total_steps": 40000, "loss": 0.6338, "lr": 4.9999455940030746e-05, "epoch": 0.002720696498303566, "percentage": 0.21, "elapsed_time": "0:00:51", "remaining_time": "6:43:03", "throughput": 2542.94, "total_tokens": 130960}
18
+ {"current_steps": 90, "total_steps": 40000, "loss": 0.7065, "lr": 4.999938924360824e-05, "epoch": 0.002880737468792011, "percentage": 0.22, "elapsed_time": "0:00:54", "remaining_time": "6:42:39", "throughput": 2547.7, "total_tokens": 138800}
19
+ {"current_steps": 95, "total_steps": 40000, "loss": 0.4734, "lr": 4.999931869196575e-05, "epoch": 0.003040778439280456, "percentage": 0.24, "elapsed_time": "0:00:57", "remaining_time": "6:42:30", "throughput": 2553.55, "total_tokens": 146816}
20
+ {"current_steps": 100, "total_steps": 40000, "loss": 0.4703, "lr": 4.999924428511416e-05, "epoch": 0.003200819409768901, "percentage": 0.25, "elapsed_time": "0:01:00", "remaining_time": "6:41:27", "throughput": 2559.72, "total_tokens": 154528}
21
+ {"current_steps": 105, "total_steps": 40000, "loss": 0.4669, "lr": 4.999916602306494e-05, "epoch": 0.003360860380257346, "percentage": 0.26, "elapsed_time": "0:01:03", "remaining_time": "6:40:52", "throughput": 2564.34, "total_tokens": 162336}
22
+ {"current_steps": 110, "total_steps": 40000, "loss": 0.3572, "lr": 4.999908390583016e-05, "epoch": 0.003520901350745791, "percentage": 0.27, "elapsed_time": "0:01:06", "remaining_time": "6:39:38", "throughput": 2570.7, "total_tokens": 169984}
23
+ {"current_steps": 115, "total_steps": 40000, "loss": 0.5895, "lr": 4.999899793342247e-05, "epoch": 0.003680942321234236, "percentage": 0.29, "elapsed_time": "0:01:09", "remaining_time": "6:39:06", "throughput": 2575.75, "total_tokens": 177840}
24
+ {"current_steps": 120, "total_steps": 40000, "loss": 0.6603, "lr": 4.999890810585516e-05, "epoch": 0.003840983291722681, "percentage": 0.3, "elapsed_time": "0:01:11", "remaining_time": "6:37:44", "throughput": 2580.22, "total_tokens": 185280}
25
+ {"current_steps": 125, "total_steps": 40000, "loss": 0.4603, "lr": 4.999881442314206e-05, "epoch": 0.004001024262211126, "percentage": 0.31, "elapsed_time": "0:01:14", "remaining_time": "6:36:37", "throughput": 2582.93, "total_tokens": 192688}
26
+ {"current_steps": 130, "total_steps": 40000, "loss": 0.4333, "lr": 4.9998716885297617e-05, "epoch": 0.004161065232699571, "percentage": 0.33, "elapsed_time": "0:01:17", "remaining_time": "6:35:59", "throughput": 2584.14, "total_tokens": 200192}
27
+ {"current_steps": 135, "total_steps": 40000, "loss": 0.5359, "lr": 4.999861549233688e-05, "epoch": 0.004321106203188016, "percentage": 0.34, "elapsed_time": "0:01:20", "remaining_time": "6:35:11", "throughput": 2587.94, "total_tokens": 207808}
28
+ {"current_steps": 140, "total_steps": 40000, "loss": 0.7227, "lr": 4.999851024427548e-05, "epoch": 0.004481147173676461, "percentage": 0.35, "elapsed_time": "0:01:23", "remaining_time": "6:34:00", "throughput": 2590.45, "total_tokens": 215088}
29
+ {"current_steps": 145, "total_steps": 40000, "loss": 0.5466, "lr": 4.999840114112965e-05, "epoch": 0.004641188144164906, "percentage": 0.36, "elapsed_time": "0:01:25", "remaining_time": "6:32:54", "throughput": 2592.48, "total_tokens": 222352}
30
+ {"current_steps": 150, "total_steps": 40000, "loss": 0.6071, "lr": 4.999828818291621e-05, "epoch": 0.004801229114653352, "percentage": 0.38, "elapsed_time": "0:01:28", "remaining_time": "6:32:15", "throughput": 2595.11, "total_tokens": 229904}
31
+ {"current_steps": 155, "total_steps": 40000, "loss": 0.8637, "lr": 4.999817136965259e-05, "epoch": 0.004961270085141797, "percentage": 0.39, "elapsed_time": "0:01:31", "remaining_time": "6:31:13", "throughput": 2596.41, "total_tokens": 237088}
32
+ {"current_steps": 160, "total_steps": 40000, "loss": 0.6774, "lr": 4.9998050701356794e-05, "epoch": 0.005121311055630242, "percentage": 0.4, "elapsed_time": "0:01:33", "remaining_time": "6:30:01", "throughput": 2599.36, "total_tokens": 244288}
33
+ {"current_steps": 165, "total_steps": 40000, "loss": 0.5144, "lr": 4.999792617804744e-05, "epoch": 0.005281352026118687, "percentage": 0.41, "elapsed_time": "0:01:36", "remaining_time": "6:29:46", "throughput": 2602.25, "total_tokens": 252080}
34
+ {"current_steps": 170, "total_steps": 40000, "loss": 0.5495, "lr": 4.9997797799743724e-05, "epoch": 0.005441392996607132, "percentage": 0.43, "elapsed_time": "0:01:39", "remaining_time": "6:29:19", "throughput": 2603.95, "total_tokens": 259616}
35
+ {"current_steps": 175, "total_steps": 40000, "loss": 0.5613, "lr": 4.999766556646545e-05, "epoch": 0.005601433967095577, "percentage": 0.44, "elapsed_time": "0:01:42", "remaining_time": "6:29:47", "throughput": 2604.78, "total_tokens": 267696}
36
+ {"current_steps": 180, "total_steps": 40000, "loss": 0.5778, "lr": 4.9997529478232996e-05, "epoch": 0.005761474937584022, "percentage": 0.45, "elapsed_time": "0:01:45", "remaining_time": "6:29:32", "throughput": 2606.96, "total_tokens": 275424}
37
+ {"current_steps": 185, "total_steps": 40000, "loss": 0.5244, "lr": 4.9997389535067365e-05, "epoch": 0.005921515908072467, "percentage": 0.46, "elapsed_time": "0:01:48", "remaining_time": "6:29:30", "throughput": 2608.67, "total_tokens": 283280}
38
+ {"current_steps": 190, "total_steps": 40000, "loss": 0.4043, "lr": 4.999724573699012e-05, "epoch": 0.006081556878560912, "percentage": 0.47, "elapsed_time": "0:01:51", "remaining_time": "6:29:14", "throughput": 2611.94, "total_tokens": 291136}
39
+ {"current_steps": 195, "total_steps": 40000, "loss": 0.6142, "lr": 4.9997098084023457e-05, "epoch": 0.006241597849049357, "percentage": 0.49, "elapsed_time": "0:01:54", "remaining_time": "6:28:55", "throughput": 2615.13, "total_tokens": 298960}
40
+ {"current_steps": 200, "total_steps": 40000, "loss": 0.3597, "lr": 4.999694657619013e-05, "epoch": 0.006401638819537802, "percentage": 0.5, "elapsed_time": "0:01:57", "remaining_time": "6:28:48", "throughput": 2615.85, "total_tokens": 306656}
41
+ {"current_steps": 200, "total_steps": 40000, "eval_loss": 0.48493048548698425, "epoch": 0.006401638819537802, "percentage": 0.5, "elapsed_time": "0:11:37", "remaining_time": "1 day, 14:34:20", "throughput": 439.47, "total_tokens": 306656}
42
+ {"current_steps": 205, "total_steps": 40000, "loss": 0.532, "lr": 4.999679121351352e-05, "epoch": 0.006561679790026247, "percentage": 0.51, "elapsed_time": "0:11:41", "remaining_time": "1 day, 13:50:45", "throughput": 447.43, "total_tokens": 314032}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fdcdde83817f1d492a34fbb57cc00580299f325190a3ba622e3e52cf62f57f5
3
+ size 5752