rbelanec commited on
Commit
70a2313
·
verified ·
1 Parent(s): 8ddfcf6

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
+ "down_proj",
14
+ "v_proj",
15
+ "k_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:d4fdc22cb6ec12a7e70704e0a5365e486d3754916a03c14e21da2de204679b64
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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 5, "total_steps": 40000, "loss": 3.6253, "lr": 4.999999876629946e-05, "epoch": 0.08849557522123894, "percentage": 0.01, "elapsed_time": "0:00:03", "remaining_time": "8:31:01", "throughput": 797.24, "total_tokens": 3056}
2
+ {"current_steps": 10, "total_steps": 40000, "loss": 3.4451, "lr": 4.999999375439123e-05, "epoch": 0.17699115044247787, "percentage": 0.03, "elapsed_time": "0:00:05", "remaining_time": "6:19:26", "throughput": 1101.69, "total_tokens": 6272}
3
+ {"current_steps": 15, "total_steps": 40000, "loss": 2.416, "lr": 4.9999984887169785e-05, "epoch": 0.26548672566371684, "percentage": 0.04, "elapsed_time": "0:00:07", "remaining_time": "5:19:57", "throughput": 1288.59, "total_tokens": 9280}
4
+ {"current_steps": 20, "total_steps": 40000, "loss": 3.2018, "lr": 4.9999972164636506e-05, "epoch": 0.35398230088495575, "percentage": 0.05, "elapsed_time": "0:00:08", "remaining_time": "4:54:11", "throughput": 1462.29, "total_tokens": 12912}
5
+ {"current_steps": 25, "total_steps": 40000, "loss": 3.8599, "lr": 4.999995558679334e-05, "epoch": 0.4424778761061947, "percentage": 0.06, "elapsed_time": "0:00:10", "remaining_time": "4:34:39", "throughput": 1563.35, "total_tokens": 16112}
6
+ {"current_steps": 30, "total_steps": 40000, "loss": 3.2129, "lr": 4.999993515364287e-05, "epoch": 0.5309734513274337, "percentage": 0.07, "elapsed_time": "0:00:11", "remaining_time": "4:21:37", "throughput": 1579.32, "total_tokens": 18608}
7
+ {"current_steps": 35, "total_steps": 40000, "loss": 3.6123, "lr": 4.999991086518822e-05, "epoch": 0.6194690265486725, "percentage": 0.09, "elapsed_time": "0:00:13", "remaining_time": "4:13:47", "throughput": 1654.52, "total_tokens": 22064}
8
+ {"current_steps": 40, "total_steps": 40000, "loss": 3.2592, "lr": 4.999988272143315e-05, "epoch": 0.7079646017699115, "percentage": 0.1, "elapsed_time": "0:00:14", "remaining_time": "4:07:40", "throughput": 1681.2, "total_tokens": 25008}
9
+ {"current_steps": 45, "total_steps": 40000, "loss": 3.5102, "lr": 4.999985072238199e-05, "epoch": 0.7964601769911505, "percentage": 0.11, "elapsed_time": "0:00:16", "remaining_time": "4:02:20", "throughput": 1685.35, "total_tokens": 27600}
10
+ {"current_steps": 50, "total_steps": 40000, "loss": 3.2641, "lr": 4.999981486803969e-05, "epoch": 0.8849557522123894, "percentage": 0.12, "elapsed_time": "0:00:17", "remaining_time": "3:57:40", "throughput": 1693.36, "total_tokens": 30224}
11
+ {"current_steps": 55, "total_steps": 40000, "loss": 2.6876, "lr": 4.999977515841176e-05, "epoch": 0.9734513274336283, "percentage": 0.14, "elapsed_time": "0:00:19", "remaining_time": "3:54:00", "throughput": 1683.35, "total_tokens": 32544}
12
+ {"current_steps": 60, "total_steps": 40000, "loss": 1.3488, "lr": 4.9999731593504344e-05, "epoch": 1.0530973451327434, "percentage": 0.15, "elapsed_time": "0:00:21", "remaining_time": "3:53:22", "throughput": 1673.41, "total_tokens": 35200}
13
+ {"current_steps": 65, "total_steps": 40000, "loss": 1.6611, "lr": 4.999968417332415e-05, "epoch": 1.1415929203539823, "percentage": 0.16, "elapsed_time": "0:00:22", "remaining_time": "3:50:56", "throughput": 1694.12, "total_tokens": 38208}
14
+ {"current_steps": 70, "total_steps": 40000, "loss": 1.6599, "lr": 4.999963289787848e-05, "epoch": 1.2300884955752212, "percentage": 0.18, "elapsed_time": "0:00:24", "remaining_time": "3:48:42", "throughput": 1700.7, "total_tokens": 40912}
15
+ {"current_steps": 75, "total_steps": 40000, "loss": 1.155, "lr": 4.999957776717526e-05, "epoch": 1.3185840707964602, "percentage": 0.19, "elapsed_time": "0:00:25", "remaining_time": "3:47:12", "throughput": 1725.61, "total_tokens": 44192}
16
+ {"current_steps": 80, "total_steps": 40000, "loss": 1.0851, "lr": 4.9999518781222984e-05, "epoch": 1.407079646017699, "percentage": 0.2, "elapsed_time": "0:00:27", "remaining_time": "3:45:23", "throughput": 1735.17, "total_tokens": 47024}
17
+ {"current_steps": 85, "total_steps": 40000, "loss": 0.8315, "lr": 4.9999455940030746e-05, "epoch": 1.495575221238938, "percentage": 0.21, "elapsed_time": "0:00:28", "remaining_time": "3:44:27", "throughput": 1751.81, "total_tokens": 50240}
18
+ {"current_steps": 90, "total_steps": 40000, "loss": 0.978, "lr": 4.999938924360824e-05, "epoch": 1.584070796460177, "percentage": 0.22, "elapsed_time": "0:00:30", "remaining_time": "3:42:59", "throughput": 1747.38, "total_tokens": 52720}
19
+ {"current_steps": 95, "total_steps": 40000, "loss": 0.9195, "lr": 4.999931869196575e-05, "epoch": 1.672566371681416, "percentage": 0.24, "elapsed_time": "0:00:31", "remaining_time": "3:42:07", "throughput": 1761.49, "total_tokens": 55888}
20
+ {"current_steps": 100, "total_steps": 40000, "loss": 0.7086, "lr": 4.999924428511416e-05, "epoch": 1.7610619469026547, "percentage": 0.25, "elapsed_time": "0:00:33", "remaining_time": "3:41:07", "throughput": 1765.48, "total_tokens": 58704}
21
+ {"current_steps": 105, "total_steps": 40000, "loss": 0.9335, "lr": 4.999916602306494e-05, "epoch": 1.8495575221238938, "percentage": 0.26, "elapsed_time": "0:00:34", "remaining_time": "3:40:18", "throughput": 1769.22, "total_tokens": 61552}
22
+ {"current_steps": 110, "total_steps": 40000, "loss": 0.887, "lr": 4.999908390583016e-05, "epoch": 1.9380530973451329, "percentage": 0.27, "elapsed_time": "0:00:36", "remaining_time": "3:39:10", "throughput": 1775.43, "total_tokens": 64384}
23
+ {"current_steps": 115, "total_steps": 40000, "loss": 0.3881, "lr": 4.999899793342247e-05, "epoch": 2.017699115044248, "percentage": 0.29, "elapsed_time": "0:00:37", "remaining_time": "3:39:19", "throughput": 1754.45, "total_tokens": 66568}
24
+ {"current_steps": 120, "total_steps": 40000, "loss": 0.4905, "lr": 4.999890810585516e-05, "epoch": 2.106194690265487, "percentage": 0.3, "elapsed_time": "0:00:39", "remaining_time": "3:38:48", "throughput": 1761.58, "total_tokens": 69592}
25
+ {"current_steps": 125, "total_steps": 40000, "loss": 0.4135, "lr": 4.999881442314206e-05, "epoch": 2.1946902654867255, "percentage": 0.31, "elapsed_time": "0:00:41", "remaining_time": "3:38:03", "throughput": 1762.36, "total_tokens": 72280}
26
+ {"current_steps": 130, "total_steps": 40000, "loss": 0.2818, "lr": 4.9998716885297617e-05, "epoch": 2.2831858407079646, "percentage": 0.33, "elapsed_time": "0:00:42", "remaining_time": "3:37:24", "throughput": 1771.97, "total_tokens": 75368}
27
+ {"current_steps": 135, "total_steps": 40000, "loss": 0.4329, "lr": 4.999861549233688e-05, "epoch": 2.3716814159292037, "percentage": 0.34, "elapsed_time": "0:00:44", "remaining_time": "3:36:36", "throughput": 1771.03, "total_tokens": 77944}
28
+ {"current_steps": 140, "total_steps": 40000, "loss": 0.3536, "lr": 4.999851024427548e-05, "epoch": 2.4601769911504423, "percentage": 0.35, "elapsed_time": "0:00:45", "remaining_time": "3:36:02", "throughput": 1777.38, "total_tokens": 80920}
29
+ {"current_steps": 145, "total_steps": 40000, "loss": 1.1544, "lr": 4.999840114112965e-05, "epoch": 2.5486725663716814, "percentage": 0.36, "elapsed_time": "0:00:47", "remaining_time": "3:35:26", "throughput": 1785.27, "total_tokens": 83960}
30
+ {"current_steps": 150, "total_steps": 40000, "loss": 0.6234, "lr": 4.999828818291621e-05, "epoch": 2.6371681415929205, "percentage": 0.38, "elapsed_time": "0:00:48", "remaining_time": "3:35:01", "throughput": 1787.18, "total_tokens": 86792}
31
+ {"current_steps": 155, "total_steps": 40000, "loss": 0.5628, "lr": 4.999817136965259e-05, "epoch": 2.725663716814159, "percentage": 0.39, "elapsed_time": "0:00:50", "remaining_time": "3:34:52", "throughput": 1803.33, "total_tokens": 90440}
32
+ {"current_steps": 160, "total_steps": 40000, "loss": 0.2403, "lr": 4.9998050701356794e-05, "epoch": 2.814159292035398, "percentage": 0.4, "elapsed_time": "0:00:51", "remaining_time": "3:34:27", "throughput": 1809.81, "total_tokens": 93528}
33
+ {"current_steps": 165, "total_steps": 40000, "loss": 0.3111, "lr": 4.999792617804744e-05, "epoch": 2.9026548672566372, "percentage": 0.41, "elapsed_time": "0:00:53", "remaining_time": "3:33:52", "throughput": 1806.83, "total_tokens": 96040}
34
+ {"current_steps": 170, "total_steps": 40000, "loss": 0.3729, "lr": 4.9997797799743724e-05, "epoch": 2.991150442477876, "percentage": 0.43, "elapsed_time": "0:00:54", "remaining_time": "3:33:30", "throughput": 1810.62, "total_tokens": 99000}
35
+ {"current_steps": 175, "total_steps": 40000, "loss": 0.4527, "lr": 4.999766556646545e-05, "epoch": 3.0707964601769913, "percentage": 0.44, "elapsed_time": "0:00:56", "remaining_time": "3:33:51", "throughput": 1800.1, "total_tokens": 101496}
36
+ {"current_steps": 180, "total_steps": 40000, "loss": 0.2204, "lr": 4.9997529478232996e-05, "epoch": 3.15929203539823, "percentage": 0.45, "elapsed_time": "0:00:57", "remaining_time": "3:33:25", "throughput": 1803.39, "total_tokens": 104392}
37
+ {"current_steps": 185, "total_steps": 40000, "loss": 0.2422, "lr": 4.9997389535067365e-05, "epoch": 3.247787610619469, "percentage": 0.46, "elapsed_time": "0:00:59", "remaining_time": "3:33:01", "throughput": 1804.9, "total_tokens": 107192}
38
+ {"current_steps": 190, "total_steps": 40000, "loss": 0.3352, "lr": 4.999724573699012e-05, "epoch": 3.336283185840708, "percentage": 0.47, "elapsed_time": "0:01:00", "remaining_time": "3:32:46", "throughput": 1810.79, "total_tokens": 110328}
39
+ {"current_steps": 195, "total_steps": 40000, "loss": 0.2355, "lr": 4.9997098084023457e-05, "epoch": 3.4247787610619467, "percentage": 0.49, "elapsed_time": "0:01:02", "remaining_time": "3:32:19", "throughput": 1815.82, "total_tokens": 113320}
40
+ {"current_steps": 200, "total_steps": 40000, "loss": 0.4422, "lr": 4.999694657619013e-05, "epoch": 3.5132743362831858, "percentage": 0.5, "elapsed_time": "0:01:03", "remaining_time": "3:32:00", "throughput": 1818.54, "total_tokens": 116248}
41
+ {"current_steps": 200, "total_steps": 40000, "eval_loss": 0.48029711842536926, "epoch": 3.5132743362831858, "percentage": 0.5, "elapsed_time": "0:01:04", "remaining_time": "3:34:52", "throughput": 1794.31, "total_tokens": 116248}
42
+ {"current_steps": 205, "total_steps": 40000, "loss": 0.2245, "lr": 4.999679121351352e-05, "epoch": 3.601769911504425, "percentage": 0.51, "elapsed_time": "0:01:07", "remaining_time": "3:37:59", "throughput": 1773.03, "total_tokens": 119464}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cf6d4de1965c671c97b48c4990d4814170c1d7ae06b992a13573cc45cef3a71
3
+ size 5752