rbelanec commited on
Commit
0496307
·
verified ·
1 Parent(s): 150f73c

Training in progress, step 13

Browse files
adapter_config.json CHANGED
@@ -5,11 +5,7 @@
5
  "peft_type": "BITFIT",
6
  "revision": null,
7
  "target_modules": [
8
- "up_proj",
9
  "v_proj",
10
- "down_proj",
11
- "o_proj",
12
- "k_proj",
13
  "q_proj"
14
  ],
15
  "task_type": "CAUSAL_LM"
 
5
  "peft_type": "BITFIT",
6
  "revision": null,
7
  "target_modules": [
 
8
  "v_proj",
 
 
 
9
  "q_proj"
10
  ],
11
  "task_type": "CAUSAL_LM"
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bfbad3b3bbe0780e94ac83258a352ada4e15b8231133708e191bf48a16ed199f
3
- size 2819582528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16afb188e887538ca3cdcdd45ce22fc17234562dc5f31e5a76ee9273276ea8fa
3
+ size 335717200
trainer_log.jsonl CHANGED
@@ -1,43 +1,14 @@
1
- {"current_steps": 5, "total_steps": 125, "loss": 10.9709, "lr": 1.5384615384615387e-05, "epoch": 0.04, "percentage": 4.0, "elapsed_time": "0:00:02", "remaining_time": "0:01:09", "throughput": 735.72, "total_tokens": 2144}
2
- {"current_steps": 7, "total_steps": 125, "eval_loss": 6.5227251052856445, "epoch": 0.056, "percentage": 5.6, "elapsed_time": "0:00:03", "remaining_time": "0:01:06", "throughput": 732.42, "total_tokens": 2880}
3
- {"current_steps": 10, "total_steps": 125, "loss": 6.4075, "lr": 3.461538461538462e-05, "epoch": 0.08, "percentage": 8.0, "elapsed_time": "0:00:20", "remaining_time": "0:03:52", "throughput": 203.87, "total_tokens": 4128}
4
- {"current_steps": 14, "total_steps": 125, "eval_loss": 1.382468581199646, "epoch": 0.112, "percentage": 11.2, "elapsed_time": "0:00:21", "remaining_time": "0:02:51", "throughput": 273.75, "total_tokens": 5920}
5
- {"current_steps": 15, "total_steps": 125, "loss": 2.5338, "lr": 4.999016565957633e-05, "epoch": 0.12, "percentage": 12.0, "elapsed_time": "0:00:30", "remaining_time": "0:03:43", "throughput": 204.83, "total_tokens": 6240}
6
- {"current_steps": 20, "total_steps": 125, "loss": 0.5326, "lr": 4.96467754629559e-05, "epoch": 0.16, "percentage": 16.0, "elapsed_time": "0:00:31", "remaining_time": "0:02:44", "throughput": 259.14, "total_tokens": 8096}
7
- {"current_steps": 21, "total_steps": 125, "eval_loss": 0.4987373352050781, "epoch": 0.168, "percentage": 16.8, "elapsed_time": "0:00:31", "remaining_time": "0:02:38", "throughput": 263.74, "total_tokens": 8416}
8
- {"current_steps": 25, "total_steps": 125, "loss": 0.4144, "lr": 4.881937806807241e-05, "epoch": 0.2, "percentage": 20.0, "elapsed_time": "0:00:39", "remaining_time": "0:02:37", "throughput": 256.96, "total_tokens": 10112}
9
- {"current_steps": 28, "total_steps": 125, "eval_loss": 0.4531269073486328, "epoch": 0.224, "percentage": 22.4, "elapsed_time": "0:00:40", "remaining_time": "0:02:19", "throughput": 279.63, "total_tokens": 11264}
10
- {"current_steps": 30, "total_steps": 125, "loss": 0.4563, "lr": 4.752422169756048e-05, "epoch": 0.24, "percentage": 24.0, "elapsed_time": "0:00:47", "remaining_time": "0:02:30", "throughput": 253.43, "total_tokens": 12032}
11
- {"current_steps": 35, "total_steps": 125, "loss": 0.4802, "lr": 4.5786740307563636e-05, "epoch": 0.28, "percentage": 28.0, "elapsed_time": "0:00:48", "remaining_time": "0:02:04", "throughput": 286.57, "total_tokens": 13824}
12
- {"current_steps": 35, "total_steps": 125, "eval_loss": 0.36931881308555603, "epoch": 0.28, "percentage": 28.0, "elapsed_time": "0:00:48", "remaining_time": "0:02:05", "throughput": 282.37, "total_tokens": 13824}
13
- {"current_steps": 40, "total_steps": 125, "loss": 0.3809, "lr": 4.364105412207914e-05, "epoch": 0.32, "percentage": 32.0, "elapsed_time": "0:00:58", "remaining_time": "0:02:05", "throughput": 268.48, "total_tokens": 15840}
14
- {"current_steps": 42, "total_steps": 125, "eval_loss": 0.3872639238834381, "epoch": 0.336, "percentage": 33.6, "elapsed_time": "0:01:00", "remaining_time": "0:01:58", "throughput": 277.51, "total_tokens": 16672}
15
- {"current_steps": 45, "total_steps": 125, "loss": 0.3844, "lr": 4.1129299588552193e-05, "epoch": 0.36, "percentage": 36.0, "elapsed_time": "0:01:09", "remaining_time": "0:02:03", "throughput": 257.82, "total_tokens": 17920}
16
- {"current_steps": 49, "total_steps": 125, "eval_loss": 0.3777945637702942, "epoch": 0.392, "percentage": 39.2, "elapsed_time": "0:01:10", "remaining_time": "0:01:50", "throughput": 272.03, "total_tokens": 19296}
17
- {"current_steps": 50, "total_steps": 125, "loss": 0.2817, "lr": 3.830080191288342e-05, "epoch": 0.4, "percentage": 40.0, "elapsed_time": "0:01:26", "remaining_time": "0:02:09", "throughput": 227.54, "total_tokens": 19712}
18
- {"current_steps": 55, "total_steps": 125, "loss": 0.3831, "lr": 3.521110642339991e-05, "epoch": 0.44, "percentage": 44.0, "elapsed_time": "0:01:27", "remaining_time": "0:01:51", "throughput": 250.88, "total_tokens": 21952}
19
- {"current_steps": 56, "total_steps": 125, "eval_loss": 0.4436803460121155, "epoch": 0.448, "percentage": 44.8, "elapsed_time": "0:01:28", "remaining_time": "0:01:48", "throughput": 253.75, "total_tokens": 22432}
20
- {"current_steps": 60, "total_steps": 125, "loss": 0.5576, "lr": 3.1920887785621235e-05, "epoch": 0.48, "percentage": 48.0, "elapsed_time": "0:01:37", "remaining_time": "0:01:46", "throughput": 246.65, "total_tokens": 24160}
21
- {"current_steps": 63, "total_steps": 125, "eval_loss": 0.35032057762145996, "epoch": 0.504, "percentage": 50.4, "elapsed_time": "0:01:39", "remaining_time": "0:01:37", "throughput": 257.13, "total_tokens": 25504}
22
- {"current_steps": 65, "total_steps": 125, "loss": 0.4013, "lr": 2.849475848838749e-05, "epoch": 0.52, "percentage": 52.0, "elapsed_time": "0:01:48", "remaining_time": "0:01:40", "throughput": 240.47, "total_tokens": 26112}
23
- {"current_steps": 70, "total_steps": 125, "loss": 0.3242, "lr": 2.5e-05, "epoch": 0.56, "percentage": 56.0, "elapsed_time": "0:01:49", "remaining_time": "0:01:25", "throughput": 256.58, "total_tokens": 28064}
24
- {"current_steps": 70, "total_steps": 125, "eval_loss": 0.37164703011512756, "epoch": 0.56, "percentage": 56.0, "elapsed_time": "0:01:50", "remaining_time": "0:01:26", "throughput": 254.81, "total_tokens": 28064}
25
- {"current_steps": 75, "total_steps": 125, "loss": 0.3963, "lr": 2.1505241511612522e-05, "epoch": 0.6, "percentage": 60.0, "elapsed_time": "0:02:00", "remaining_time": "0:01:20", "throughput": 248.35, "total_tokens": 29824}
26
- {"current_steps": 77, "total_steps": 125, "eval_loss": 0.3748786747455597, "epoch": 0.616, "percentage": 61.6, "elapsed_time": "0:02:01", "remaining_time": "0:01:15", "throughput": 253.82, "total_tokens": 30720}
27
- {"current_steps": 80, "total_steps": 125, "loss": 0.3946, "lr": 1.8079112214378768e-05, "epoch": 0.64, "percentage": 64.0, "elapsed_time": "0:02:17", "remaining_time": "0:01:17", "throughput": 232.48, "total_tokens": 31904}
28
- {"current_steps": 84, "total_steps": 125, "eval_loss": 0.3603578209877014, "epoch": 0.672, "percentage": 67.2, "elapsed_time": "0:02:18", "remaining_time": "0:01:07", "throughput": 241.67, "total_tokens": 33504}
29
- {"current_steps": 85, "total_steps": 125, "loss": 0.3496, "lr": 1.4788893576600099e-05, "epoch": 0.68, "percentage": 68.0, "elapsed_time": "0:02:27", "remaining_time": "0:01:09", "throughput": 230.5, "total_tokens": 33984}
30
- {"current_steps": 90, "total_steps": 125, "loss": 0.337, "lr": 1.1699198087116589e-05, "epoch": 0.72, "percentage": 72.0, "elapsed_time": "0:02:28", "remaining_time": "0:00:57", "throughput": 241.34, "total_tokens": 35776}
31
- {"current_steps": 91, "total_steps": 125, "eval_loss": 0.35710158944129944, "epoch": 0.728, "percentage": 72.8, "elapsed_time": "0:02:28", "remaining_time": "0:00:55", "throughput": 242.48, "total_tokens": 36128}
32
- {"current_steps": 95, "total_steps": 125, "loss": 0.4315, "lr": 8.870700411447816e-06, "epoch": 0.76, "percentage": 76.0, "elapsed_time": "0:02:36", "remaining_time": "0:00:49", "throughput": 239.38, "total_tokens": 37472}
33
- {"current_steps": 98, "total_steps": 125, "eval_loss": 0.3520326614379883, "epoch": 0.784, "percentage": 78.4, "elapsed_time": "0:02:37", "remaining_time": "0:00:43", "throughput": 244.54, "total_tokens": 38592}
34
- {"current_steps": 100, "total_steps": 125, "loss": 0.38, "lr": 6.358945877920861e-06, "epoch": 0.8, "percentage": 80.0, "elapsed_time": "0:02:46", "remaining_time": "0:00:41", "throughput": 235.57, "total_tokens": 39328}
35
- {"current_steps": 105, "total_steps": 125, "loss": 0.371, "lr": 4.213259692436367e-06, "epoch": 0.84, "percentage": 84.0, "elapsed_time": "0:02:47", "remaining_time": "0:00:31", "throughput": 246.21, "total_tokens": 41280}
36
- {"current_steps": 105, "total_steps": 125, "eval_loss": 0.34758228063583374, "epoch": 0.84, "percentage": 84.0, "elapsed_time": "0:02:48", "remaining_time": "0:00:32", "throughput": 245.11, "total_tokens": 41280}
37
- {"current_steps": 110, "total_steps": 125, "loss": 0.364, "lr": 2.475778302439524e-06, "epoch": 0.88, "percentage": 88.0, "elapsed_time": "0:02:57", "remaining_time": "0:00:24", "throughput": 244.9, "total_tokens": 43552}
38
- {"current_steps": 112, "total_steps": 125, "eval_loss": 0.34589245915412903, "epoch": 0.896, "percentage": 89.6, "elapsed_time": "0:02:58", "remaining_time": "0:00:20", "throughput": 246.85, "total_tokens": 44160}
39
- {"current_steps": 115, "total_steps": 125, "loss": 0.3554, "lr": 1.180621931927592e-06, "epoch": 0.92, "percentage": 92.0, "elapsed_time": "0:03:15", "remaining_time": "0:00:17", "throughput": 231.09, "total_tokens": 45216}
40
- {"current_steps": 119, "total_steps": 125, "eval_loss": 0.3492301404476166, "epoch": 0.952, "percentage": 95.2, "elapsed_time": "0:03:17", "remaining_time": "0:00:09", "throughput": 238.18, "total_tokens": 46944}
41
- {"current_steps": 120, "total_steps": 125, "loss": 0.3494, "lr": 3.5322453704410286e-07, "epoch": 0.96, "percentage": 96.0, "elapsed_time": "0:03:25", "remaining_time": "0:00:08", "throughput": 230.1, "total_tokens": 47360}
42
- {"current_steps": 125, "total_steps": 125, "loss": 0.3588, "lr": 9.834340423678368e-09, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:03:26", "remaining_time": "0:00:00", "throughput": 238.53, "total_tokens": 49376}
43
- {"current_steps": 125, "total_steps": 125, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:03:37", "remaining_time": "0:00:00", "throughput": 226.8, "total_tokens": 49376}
 
1
+ {"current_steps": 5, "total_steps": 249, "loss": 0.8323, "lr": 8.000000000000001e-06, "epoch": 0.020080321285140562, "percentage": 2.01, "elapsed_time": "0:00:05", "remaining_time": "0:04:22", "throughput": 154.92, "total_tokens": 832}
2
+ {"current_steps": 10, "total_steps": 249, "loss": 0.7462, "lr": 1.8e-05, "epoch": 0.040160642570281124, "percentage": 4.02, "elapsed_time": "0:00:05", "remaining_time": "0:02:16", "throughput": 309.05, "total_tokens": 1760}
3
+ {"current_steps": 13, "total_steps": 249, "eval_loss": 0.6849029660224915, "epoch": 0.05220883534136546, "percentage": 5.22, "elapsed_time": "0:00:06", "remaining_time": "0:01:57", "throughput": 354.64, "total_tokens": 2288}
4
+ {"current_steps": 15, "total_steps": 249, "loss": 0.71, "lr": 2.8000000000000003e-05, "epoch": 0.060240963855421686, "percentage": 6.02, "elapsed_time": "0:00:09", "remaining_time": "0:02:28", "throughput": 273.83, "total_tokens": 2608}
5
+ {"current_steps": 20, "total_steps": 249, "loss": 0.5466, "lr": 3.8e-05, "epoch": 0.08032128514056225, "percentage": 8.03, "elapsed_time": "0:00:09", "remaining_time": "0:01:52", "throughput": 358.99, "total_tokens": 3536}
6
+ {"current_steps": 25, "total_steps": 249, "loss": 0.6639, "lr": 4.8e-05, "epoch": 0.10040160642570281, "percentage": 10.04, "elapsed_time": "0:00:10", "remaining_time": "0:01:31", "throughput": 441.8, "total_tokens": 4496}
7
+ {"current_steps": 26, "total_steps": 249, "eval_loss": 0.45566946268081665, "epoch": 0.10441767068273092, "percentage": 10.44, "elapsed_time": "0:00:10", "remaining_time": "0:01:32", "throughput": 431.04, "total_tokens": 4656}
8
+ {"current_steps": 30, "total_steps": 249, "loss": 0.5107, "lr": 4.996067037544542e-05, "epoch": 0.12048192771084337, "percentage": 12.05, "elapsed_time": "0:00:12", "remaining_time": "0:01:33", "throughput": 422.01, "total_tokens": 5424}
9
+ {"current_steps": 35, "total_steps": 249, "loss": 0.3742, "lr": 4.980110583549062e-05, "epoch": 0.14056224899598393, "percentage": 14.06, "elapsed_time": "0:00:13", "remaining_time": "0:01:20", "throughput": 478.42, "total_tokens": 6304}
10
+ {"current_steps": 39, "total_steps": 249, "eval_loss": 0.3848888874053955, "epoch": 0.1566265060240964, "percentage": 15.66, "elapsed_time": "0:00:14", "remaining_time": "0:01:15", "throughput": 495.43, "total_tokens": 6944}
11
+ {"current_steps": 40, "total_steps": 249, "loss": 0.3994, "lr": 4.951963201008076e-05, "epoch": 0.1606425702811245, "percentage": 16.06, "elapsed_time": "0:00:15", "remaining_time": "0:01:20", "throughput": 458.29, "total_tokens": 7072}
12
+ {"current_steps": 45, "total_steps": 249, "loss": 0.3929, "lr": 4.91176324775594e-05, "epoch": 0.18072289156626506, "percentage": 18.07, "elapsed_time": "0:00:15", "remaining_time": "0:01:11", "throughput": 498.33, "total_tokens": 7856}
13
+ {"current_steps": 50, "total_steps": 249, "loss": 0.3565, "lr": 4.8597083257709194e-05, "epoch": 0.20080321285140562, "percentage": 20.08, "elapsed_time": "0:00:16", "remaining_time": "0:01:04", "throughput": 551.64, "total_tokens": 8880}
14
+ {"current_steps": 52, "total_steps": 249, "eval_loss": 0.3768366277217865, "epoch": 0.20883534136546184, "percentage": 20.88, "elapsed_time": "0:00:16", "remaining_time": "0:01:03", "throughput": 548.86, "total_tokens": 9232}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:acc568c9cbb33de9a3eafbda48735873409500bc6aefe53fe5eab764d8b19ad5
3
  size 6097
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d3bdf3a163b7ee13e312a224f1f3c698026232fb95184906217a8d73515393f
3
  size 6097