rbelanec commited on
Commit
fb2fa50
·
verified ·
1 Parent(s): 0dadb9c

Training in progress, step 200

Browse files
adapter_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
4
+ "exclude_modules": null,
5
+ "fan_in_fan_out": false,
6
+ "feedforward_modules": "down_proj",
7
+ "inference_mode": true,
8
+ "init_ia3_weights": true,
9
+ "modules_to_save": null,
10
+ "peft_type": "IA3",
11
+ "revision": null,
12
+ "target_modules": [
13
+ "k_proj",
14
+ "v_proj",
15
+ "down_proj"
16
+ ],
17
+ "task_type": "CAUSAL_LM"
18
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:408ce7e15e0c64ce132d55e16a2d8cbd964a9446fa948347d830d7918e8c7b39
3
+ size 798032
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": 2.3548, "lr": 4.999999876629946e-05, "epoch": 0.0023573785950023575, "percentage": 0.01, "elapsed_time": "0:00:04", "remaining_time": "9:25:47", "throughput": 1078.24, "total_tokens": 4576}
2
+ {"current_steps": 10, "total_steps": 40000, "loss": 1.7132, "lr": 4.999999375439123e-05, "epoch": 0.004714757190004715, "percentage": 0.03, "elapsed_time": "0:00:06", "remaining_time": "7:34:12", "throughput": 1321.84, "total_tokens": 9008}
3
+ {"current_steps": 15, "total_steps": 40000, "loss": 1.1918, "lr": 4.9999984887169785e-05, "epoch": 0.007072135785007072, "percentage": 0.04, "elapsed_time": "0:00:09", "remaining_time": "6:54:57", "throughput": 1456.11, "total_tokens": 13600}
4
+ {"current_steps": 20, "total_steps": 40000, "loss": 0.8352, "lr": 4.9999972164636506e-05, "epoch": 0.00942951438000943, "percentage": 0.05, "elapsed_time": "0:00:11", "remaining_time": "6:37:31", "throughput": 1560.89, "total_tokens": 18624}
5
+ {"current_steps": 25, "total_steps": 40000, "loss": 2.7531, "lr": 4.999995558679334e-05, "epoch": 0.011786892975011787, "percentage": 0.06, "elapsed_time": "0:00:14", "remaining_time": "6:26:10", "throughput": 1613.19, "total_tokens": 23376}
6
+ {"current_steps": 30, "total_steps": 40000, "loss": 1.0359, "lr": 4.999993515364287e-05, "epoch": 0.014144271570014143, "percentage": 0.07, "elapsed_time": "0:00:17", "remaining_time": "6:19:04", "throughput": 1629.89, "total_tokens": 27824}
7
+ {"current_steps": 35, "total_steps": 40000, "loss": 1.7229, "lr": 4.999991086518822e-05, "epoch": 0.0165016501650165, "percentage": 0.09, "elapsed_time": "0:00:19", "remaining_time": "6:13:06", "throughput": 1614.22, "total_tokens": 31648}
8
+ {"current_steps": 40, "total_steps": 40000, "loss": 2.6721, "lr": 4.999988272143315e-05, "epoch": 0.01885902876001886, "percentage": 0.1, "elapsed_time": "0:00:22", "remaining_time": "6:08:17", "throughput": 1623.88, "total_tokens": 35920}
9
+ {"current_steps": 45, "total_steps": 40000, "loss": 2.3733, "lr": 4.999985072238199e-05, "epoch": 0.021216407355021217, "percentage": 0.11, "elapsed_time": "0:00:24", "remaining_time": "6:04:57", "throughput": 1631.61, "total_tokens": 40240}
10
+ {"current_steps": 50, "total_steps": 40000, "loss": 1.2121, "lr": 4.999981486803969e-05, "epoch": 0.023573785950023574, "percentage": 0.12, "elapsed_time": "0:00:27", "remaining_time": "6:02:17", "throughput": 1642.62, "total_tokens": 44688}
11
+ {"current_steps": 55, "total_steps": 40000, "loss": 2.1081, "lr": 4.999977515841176e-05, "epoch": 0.02593116454502593, "percentage": 0.14, "elapsed_time": "0:00:29", "remaining_time": "6:00:25", "throughput": 1663.58, "total_tokens": 49536}
12
+ {"current_steps": 60, "total_steps": 40000, "loss": 1.0722, "lr": 4.9999731593504344e-05, "epoch": 0.028288543140028287, "percentage": 0.15, "elapsed_time": "0:00:32", "remaining_time": "5:59:07", "throughput": 1687.48, "total_tokens": 54624}
13
+ {"current_steps": 65, "total_steps": 40000, "loss": 2.3518, "lr": 4.999968417332415e-05, "epoch": 0.030645921735030647, "percentage": 0.16, "elapsed_time": "0:00:34", "remaining_time": "5:57:39", "throughput": 1702.2, "total_tokens": 59456}
14
+ {"current_steps": 70, "total_steps": 40000, "loss": 1.36, "lr": 4.999963289787848e-05, "epoch": 0.033003300330033, "percentage": 0.18, "elapsed_time": "0:00:37", "remaining_time": "5:57:11", "throughput": 1723.84, "total_tokens": 64768}
15
+ {"current_steps": 75, "total_steps": 40000, "loss": 1.5187, "lr": 4.999957776717526e-05, "epoch": 0.03536067892503536, "percentage": 0.19, "elapsed_time": "0:00:40", "remaining_time": "5:55:31", "throughput": 1717.28, "total_tokens": 68816}
16
+ {"current_steps": 80, "total_steps": 40000, "loss": 1.0985, "lr": 4.9999518781222984e-05, "epoch": 0.03771805752003772, "percentage": 0.2, "elapsed_time": "0:00:42", "remaining_time": "5:54:52", "throughput": 1724.88, "total_tokens": 73600}
17
+ {"current_steps": 85, "total_steps": 40000, "loss": 0.7415, "lr": 4.9999455940030746e-05, "epoch": 0.040075436115040074, "percentage": 0.21, "elapsed_time": "0:00:45", "remaining_time": "5:54:00", "throughput": 1719.51, "total_tokens": 77776}
18
+ {"current_steps": 90, "total_steps": 40000, "loss": 1.1496, "lr": 4.999938924360824e-05, "epoch": 0.042432814710042434, "percentage": 0.22, "elapsed_time": "0:00:47", "remaining_time": "5:52:57", "throughput": 1713.66, "total_tokens": 81840}
19
+ {"current_steps": 95, "total_steps": 40000, "loss": 1.2144, "lr": 4.999931869196575e-05, "epoch": 0.04479019330504479, "percentage": 0.24, "elapsed_time": "0:00:50", "remaining_time": "5:52:07", "throughput": 1709.54, "total_tokens": 85984}
20
+ {"current_steps": 100, "total_steps": 40000, "loss": 0.7548, "lr": 4.999924428511416e-05, "epoch": 0.04714757190004715, "percentage": 0.25, "elapsed_time": "0:00:52", "remaining_time": "5:51:13", "throughput": 1718.55, "total_tokens": 90768}
21
+ {"current_steps": 105, "total_steps": 40000, "loss": 1.1614, "lr": 4.999916602306494e-05, "epoch": 0.04950495049504951, "percentage": 0.26, "elapsed_time": "0:00:55", "remaining_time": "5:50:22", "throughput": 1718.31, "total_tokens": 95072}
22
+ {"current_steps": 110, "total_steps": 40000, "loss": 0.3894, "lr": 4.999908390583016e-05, "epoch": 0.05186232909005186, "percentage": 0.27, "elapsed_time": "0:00:57", "remaining_time": "5:50:21", "throughput": 1722.33, "total_tokens": 99840}
23
+ {"current_steps": 115, "total_steps": 40000, "loss": 1.0233, "lr": 4.999899793342247e-05, "epoch": 0.05421970768505422, "percentage": 0.29, "elapsed_time": "0:01:00", "remaining_time": "5:50:18", "throughput": 1734.62, "total_tokens": 105120}
24
+ {"current_steps": 120, "total_steps": 40000, "loss": 1.0272, "lr": 4.999890810585516e-05, "epoch": 0.056577086280056574, "percentage": 0.3, "elapsed_time": "0:01:03", "remaining_time": "5:50:30", "throughput": 1743.11, "total_tokens": 110304}
25
+ {"current_steps": 125, "total_steps": 40000, "loss": 1.2749, "lr": 4.999881442314206e-05, "epoch": 0.058934464875058934, "percentage": 0.31, "elapsed_time": "0:01:06", "remaining_time": "5:51:22", "throughput": 1757.41, "total_tokens": 116144}
26
+ {"current_steps": 130, "total_steps": 40000, "loss": 0.6719, "lr": 4.9998716885297617e-05, "epoch": 0.061291843470061294, "percentage": 0.33, "elapsed_time": "0:01:08", "remaining_time": "5:51:07", "throughput": 1766.98, "total_tokens": 121376}
27
+ {"current_steps": 135, "total_steps": 40000, "loss": 0.5433, "lr": 4.999861549233688e-05, "epoch": 0.06364922206506365, "percentage": 0.34, "elapsed_time": "0:01:11", "remaining_time": "5:50:29", "throughput": 1775.34, "total_tokens": 126432}
28
+ {"current_steps": 140, "total_steps": 40000, "loss": 1.3956, "lr": 4.999851024427548e-05, "epoch": 0.066006600660066, "percentage": 0.35, "elapsed_time": "0:01:13", "remaining_time": "5:49:56", "throughput": 1777.12, "total_tokens": 131056}
29
+ {"current_steps": 145, "total_steps": 40000, "loss": 0.3613, "lr": 4.999840114112965e-05, "epoch": 0.06836397925506836, "percentage": 0.36, "elapsed_time": "0:01:16", "remaining_time": "5:49:19", "throughput": 1778.02, "total_tokens": 135584}
30
+ {"current_steps": 150, "total_steps": 40000, "loss": 0.7073, "lr": 4.999828818291621e-05, "epoch": 0.07072135785007072, "percentage": 0.38, "elapsed_time": "0:01:18", "remaining_time": "5:48:31", "throughput": 1779.38, "total_tokens": 140064}
31
+ {"current_steps": 155, "total_steps": 40000, "loss": 0.5126, "lr": 4.999817136965259e-05, "epoch": 0.07307873644507308, "percentage": 0.39, "elapsed_time": "0:01:21", "remaining_time": "5:48:01", "throughput": 1785.77, "total_tokens": 145056}
32
+ {"current_steps": 160, "total_steps": 40000, "loss": 0.3773, "lr": 4.9998050701356794e-05, "epoch": 0.07543611504007544, "percentage": 0.4, "elapsed_time": "0:01:23", "remaining_time": "5:47:19", "throughput": 1785.93, "total_tokens": 149472}
33
+ {"current_steps": 165, "total_steps": 40000, "loss": 0.4055, "lr": 4.999792617804744e-05, "epoch": 0.07779349363507779, "percentage": 0.41, "elapsed_time": "0:01:26", "remaining_time": "5:46:31", "throughput": 1796.58, "total_tokens": 154720}
34
+ {"current_steps": 170, "total_steps": 40000, "loss": 0.5772, "lr": 4.9997797799743724e-05, "epoch": 0.08015087223008015, "percentage": 0.43, "elapsed_time": "0:01:28", "remaining_time": "5:45:55", "throughput": 1802.72, "total_tokens": 159696}
35
+ {"current_steps": 175, "total_steps": 40000, "loss": 0.7229, "lr": 4.999766556646545e-05, "epoch": 0.08250825082508251, "percentage": 0.44, "elapsed_time": "0:01:31", "remaining_time": "5:45:27", "throughput": 1809.22, "total_tokens": 164784}
36
+ {"current_steps": 180, "total_steps": 40000, "loss": 0.6353, "lr": 4.9997529478232996e-05, "epoch": 0.08486562942008487, "percentage": 0.45, "elapsed_time": "0:01:33", "remaining_time": "5:44:52", "throughput": 1804.33, "total_tokens": 168768}
37
+ {"current_steps": 185, "total_steps": 40000, "loss": 1.0214, "lr": 4.9997389535067365e-05, "epoch": 0.08722300801508723, "percentage": 0.46, "elapsed_time": "0:01:35", "remaining_time": "5:44:09", "throughput": 1810.85, "total_tokens": 173744}
38
+ {"current_steps": 190, "total_steps": 40000, "loss": 0.4407, "lr": 4.999724573699012e-05, "epoch": 0.08958038661008957, "percentage": 0.47, "elapsed_time": "0:01:38", "remaining_time": "5:43:35", "throughput": 1806.39, "total_tokens": 177728}
39
+ {"current_steps": 195, "total_steps": 40000, "loss": 0.7167, "lr": 4.9997098084023457e-05, "epoch": 0.09193776520509193, "percentage": 0.49, "elapsed_time": "0:01:40", "remaining_time": "5:42:24", "throughput": 1809.64, "total_tokens": 182128}
40
+ {"current_steps": 200, "total_steps": 40000, "loss": 0.3747, "lr": 4.999694657619013e-05, "epoch": 0.0942951438000943, "percentage": 0.5, "elapsed_time": "0:01:43", "remaining_time": "5:42:15", "throughput": 1809.89, "total_tokens": 186768}
41
+ {"current_steps": 200, "total_steps": 40000, "eval_loss": 0.6101182103157043, "epoch": 0.0942951438000943, "percentage": 0.5, "elapsed_time": "0:02:14", "remaining_time": "7:25:19", "throughput": 1391.0, "total_tokens": 186768}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d66df8c0de01cfc3c214520fc74d8c1ec7e94312b5aef69384635771e4723ae5
3
+ size 5752