rbelanec commited on
Commit
b0a49fe
·
verified ·
1 Parent(s): c1f161d

Training in progress, step 200

Browse files
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
+ "input_layernorm",
11
+ "norm",
12
+ "post_attention_layernorm"
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 sha256:165e5eaf3296dfc5e4d6df6eeed3cbb96540db72002b64e8c1d02d2d71e9618a
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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 5, "total_steps": 40000, "loss": 0.784, "lr": 4.999999876629946e-05, "epoch": 0.05555555555555555, "percentage": 0.01, "elapsed_time": "0:00:03", "remaining_time": "8:07:30", "throughput": 380.66, "total_tokens": 1392}
2
+ {"current_steps": 10, "total_steps": 40000, "loss": 0.7496, "lr": 4.999999375439123e-05, "epoch": 0.1111111111111111, "percentage": 0.03, "elapsed_time": "0:00:05", "remaining_time": "5:56:01", "throughput": 524.18, "total_tokens": 2800}
3
+ {"current_steps": 15, "total_steps": 40000, "loss": 0.4286, "lr": 4.9999984887169785e-05, "epoch": 0.16666666666666666, "percentage": 0.04, "elapsed_time": "0:00:06", "remaining_time": "4:55:09", "throughput": 635.79, "total_tokens": 4224}
4
+ {"current_steps": 20, "total_steps": 40000, "loss": 0.6328, "lr": 4.9999972164636506e-05, "epoch": 0.2222222222222222, "percentage": 0.05, "elapsed_time": "0:00:07", "remaining_time": "4:24:34", "throughput": 711.24, "total_tokens": 5648}
5
+ {"current_steps": 25, "total_steps": 40000, "loss": 0.5817, "lr": 4.999995558679334e-05, "epoch": 0.2777777777777778, "percentage": 0.06, "elapsed_time": "0:00:09", "remaining_time": "4:06:17", "throughput": 761.75, "total_tokens": 7040}
6
+ {"current_steps": 30, "total_steps": 40000, "loss": 0.737, "lr": 4.999993515364287e-05, "epoch": 0.3333333333333333, "percentage": 0.07, "elapsed_time": "0:00:10", "remaining_time": "3:54:13", "throughput": 799.4, "total_tokens": 8432}
7
+ {"current_steps": 35, "total_steps": 40000, "loss": 0.5493, "lr": 4.999991086518822e-05, "epoch": 0.3888888888888889, "percentage": 0.09, "elapsed_time": "0:00:11", "remaining_time": "3:45:22", "throughput": 830.91, "total_tokens": 9840}
8
+ {"current_steps": 40, "total_steps": 40000, "loss": 0.5154, "lr": 4.999988272143315e-05, "epoch": 0.4444444444444444, "percentage": 0.1, "elapsed_time": "0:00:13", "remaining_time": "3:38:44", "throughput": 852.52, "total_tokens": 11200}
9
+ {"current_steps": 45, "total_steps": 40000, "loss": 0.5871, "lr": 4.999985072238199e-05, "epoch": 0.5, "percentage": 0.11, "elapsed_time": "0:00:14", "remaining_time": "3:33:40", "throughput": 875.41, "total_tokens": 12640}
10
+ {"current_steps": 50, "total_steps": 40000, "loss": 0.8127, "lr": 4.999981486803969e-05, "epoch": 0.5555555555555556, "percentage": 0.12, "elapsed_time": "0:00:15", "remaining_time": "3:29:43", "throughput": 892.99, "total_tokens": 14064}
11
+ {"current_steps": 55, "total_steps": 40000, "loss": 0.6461, "lr": 4.999977515841176e-05, "epoch": 0.6111111111111112, "percentage": 0.14, "elapsed_time": "0:00:17", "remaining_time": "3:26:19", "throughput": 908.61, "total_tokens": 15488}
12
+ {"current_steps": 60, "total_steps": 40000, "loss": 0.4239, "lr": 4.9999731593504344e-05, "epoch": 0.6666666666666666, "percentage": 0.15, "elapsed_time": "0:00:18", "remaining_time": "3:23:29", "throughput": 921.18, "total_tokens": 16896}
13
+ {"current_steps": 65, "total_steps": 40000, "loss": 0.8264, "lr": 4.999968417332415e-05, "epoch": 0.7222222222222222, "percentage": 0.16, "elapsed_time": "0:00:19", "remaining_time": "3:21:04", "throughput": 933.73, "total_tokens": 18336}
14
+ {"current_steps": 70, "total_steps": 40000, "loss": 0.8734, "lr": 4.999963289787848e-05, "epoch": 0.7777777777777778, "percentage": 0.18, "elapsed_time": "0:00:20", "remaining_time": "3:19:02", "throughput": 943.83, "total_tokens": 19760}
15
+ {"current_steps": 75, "total_steps": 40000, "loss": 0.6753, "lr": 4.999957776717526e-05, "epoch": 0.8333333333333334, "percentage": 0.19, "elapsed_time": "0:00:22", "remaining_time": "3:17:15", "throughput": 950.68, "total_tokens": 21136}
16
+ {"current_steps": 80, "total_steps": 40000, "loss": 0.6989, "lr": 4.9999518781222984e-05, "epoch": 0.8888888888888888, "percentage": 0.2, "elapsed_time": "0:00:23", "remaining_time": "3:15:38", "throughput": 959.02, "total_tokens": 22560}
17
+ {"current_steps": 85, "total_steps": 40000, "loss": 0.7929, "lr": 4.9999455940030746e-05, "epoch": 0.9444444444444444, "percentage": 0.21, "elapsed_time": "0:00:24", "remaining_time": "3:14:19", "throughput": 964.04, "total_tokens": 23936}
18
+ {"current_steps": 90, "total_steps": 40000, "loss": 0.8061, "lr": 4.999938924360824e-05, "epoch": 1.0, "percentage": 0.22, "elapsed_time": "0:00:26", "remaining_time": "3:13:59", "throughput": 963.7, "total_tokens": 25296}
19
+ {"current_steps": 95, "total_steps": 40000, "loss": 0.5393, "lr": 4.999931869196575e-05, "epoch": 1.0555555555555556, "percentage": 0.24, "elapsed_time": "0:00:27", "remaining_time": "3:14:50", "throughput": 959.5, "total_tokens": 26704}
20
+ {"current_steps": 100, "total_steps": 40000, "loss": 0.9247, "lr": 4.999924428511416e-05, "epoch": 1.1111111111111112, "percentage": 0.25, "elapsed_time": "0:00:29", "remaining_time": "3:13:43", "throughput": 963.92, "total_tokens": 28080}
21
+ {"current_steps": 105, "total_steps": 40000, "loss": 0.5715, "lr": 4.999916602306494e-05, "epoch": 1.1666666666666667, "percentage": 0.26, "elapsed_time": "0:00:30", "remaining_time": "3:12:47", "throughput": 968.09, "total_tokens": 29472}
22
+ {"current_steps": 110, "total_steps": 40000, "loss": 0.4882, "lr": 4.999908390583016e-05, "epoch": 1.2222222222222223, "percentage": 0.27, "elapsed_time": "0:00:31", "remaining_time": "3:11:51", "throughput": 972.8, "total_tokens": 30880}
23
+ {"current_steps": 115, "total_steps": 40000, "loss": 0.688, "lr": 4.999899793342247e-05, "epoch": 1.2777777777777777, "percentage": 0.29, "elapsed_time": "0:00:33", "remaining_time": "3:10:59", "throughput": 976.73, "total_tokens": 32272}
24
+ {"current_steps": 120, "total_steps": 40000, "loss": 0.544, "lr": 4.999890810585516e-05, "epoch": 1.3333333333333333, "percentage": 0.3, "elapsed_time": "0:00:34", "remaining_time": "3:10:11", "throughput": 979.45, "total_tokens": 33632}
25
+ {"current_steps": 125, "total_steps": 40000, "loss": 0.4482, "lr": 4.999881442314206e-05, "epoch": 1.3888888888888888, "percentage": 0.31, "elapsed_time": "0:00:35", "remaining_time": "3:09:26", "throughput": 984.25, "total_tokens": 35072}
26
+ {"current_steps": 130, "total_steps": 40000, "loss": 0.6174, "lr": 4.9998716885297617e-05, "epoch": 1.4444444444444444, "percentage": 0.33, "elapsed_time": "0:00:36", "remaining_time": "3:08:44", "throughput": 989.27, "total_tokens": 36528}
27
+ {"current_steps": 135, "total_steps": 40000, "loss": 0.7418, "lr": 4.999861549233688e-05, "epoch": 1.5, "percentage": 0.34, "elapsed_time": "0:00:38", "remaining_time": "3:08:07", "throughput": 992.49, "total_tokens": 37936}
28
+ {"current_steps": 140, "total_steps": 40000, "loss": 0.7942, "lr": 4.999851024427548e-05, "epoch": 1.5555555555555556, "percentage": 0.35, "elapsed_time": "0:00:39", "remaining_time": "3:07:30", "throughput": 995.25, "total_tokens": 39328}
29
+ {"current_steps": 145, "total_steps": 40000, "loss": 0.7202, "lr": 4.999840114112965e-05, "epoch": 1.6111111111111112, "percentage": 0.36, "elapsed_time": "0:00:40", "remaining_time": "3:06:56", "throughput": 998.64, "total_tokens": 40752}
30
+ {"current_steps": 150, "total_steps": 40000, "loss": 1.1254, "lr": 4.999828818291621e-05, "epoch": 1.6666666666666665, "percentage": 0.38, "elapsed_time": "0:00:42", "remaining_time": "3:06:26", "throughput": 1000.14, "total_tokens": 42112}
31
+ {"current_steps": 155, "total_steps": 40000, "loss": 0.5516, "lr": 4.999817136965259e-05, "epoch": 1.7222222222222223, "percentage": 0.39, "elapsed_time": "0:00:43", "remaining_time": "3:05:58", "throughput": 1002.22, "total_tokens": 43504}
32
+ {"current_steps": 160, "total_steps": 40000, "loss": 0.4954, "lr": 4.9998050701356794e-05, "epoch": 1.7777777777777777, "percentage": 0.4, "elapsed_time": "0:00:44", "remaining_time": "3:05:33", "throughput": 1003.42, "total_tokens": 44864}
33
+ {"current_steps": 165, "total_steps": 40000, "loss": 0.6199, "lr": 4.999792617804744e-05, "epoch": 1.8333333333333335, "percentage": 0.41, "elapsed_time": "0:00:46", "remaining_time": "3:05:07", "throughput": 1004.66, "total_tokens": 46224}
34
+ {"current_steps": 170, "total_steps": 40000, "loss": 0.5659, "lr": 4.9997797799743724e-05, "epoch": 1.8888888888888888, "percentage": 0.43, "elapsed_time": "0:00:47", "remaining_time": "3:04:43", "throughput": 1005.9, "total_tokens": 47584}
35
+ {"current_steps": 175, "total_steps": 40000, "loss": 0.5763, "lr": 4.999766556646545e-05, "epoch": 1.9444444444444444, "percentage": 0.44, "elapsed_time": "0:00:48", "remaining_time": "3:04:19", "throughput": 1008.48, "total_tokens": 49008}
36
+ {"current_steps": 180, "total_steps": 40000, "loss": 0.6208, "lr": 4.9997529478232996e-05, "epoch": 2.0, "percentage": 0.45, "elapsed_time": "0:00:50", "remaining_time": "3:04:31", "throughput": 1007.4, "total_tokens": 50416}
37
+ {"current_steps": 185, "total_steps": 40000, "loss": 0.5378, "lr": 4.9997389535067365e-05, "epoch": 2.0555555555555554, "percentage": 0.46, "elapsed_time": "0:00:51", "remaining_time": "3:05:11", "throughput": 1004.08, "total_tokens": 51840}
38
+ {"current_steps": 190, "total_steps": 40000, "loss": 0.6913, "lr": 4.999724573699012e-05, "epoch": 2.111111111111111, "percentage": 0.47, "elapsed_time": "0:00:52", "remaining_time": "3:04:49", "throughput": 1005.44, "total_tokens": 53216}
39
+ {"current_steps": 195, "total_steps": 40000, "loss": 0.3655, "lr": 4.9997098084023457e-05, "epoch": 2.1666666666666665, "percentage": 0.49, "elapsed_time": "0:00:54", "remaining_time": "3:04:29", "throughput": 1007.29, "total_tokens": 54624}
40
+ {"current_steps": 200, "total_steps": 40000, "loss": 0.5247, "lr": 4.999694657619013e-05, "epoch": 2.2222222222222223, "percentage": 0.5, "elapsed_time": "0:00:55", "remaining_time": "3:04:08", "throughput": 1009.79, "total_tokens": 56064}
41
+ {"current_steps": 200, "total_steps": 40000, "eval_loss": 0.645279049873352, "epoch": 2.2222222222222223, "percentage": 0.5, "elapsed_time": "0:00:56", "remaining_time": "3:07:38", "throughput": 990.93, "total_tokens": 56064}
42
+ {"current_steps": 205, "total_steps": 40000, "loss": 0.7277, "lr": 4.999679121351352e-05, "epoch": 2.2777777777777777, "percentage": 0.51, "elapsed_time": "0:00:58", "remaining_time": "3:09:23", "throughput": 981.83, "total_tokens": 57472}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d62bb1c312548d083c0e64c470bc3dbd03b565f5cdf3526a91a7b9fdbf7873dd
3
+ size 5752