Hugging Face's logo

rbelanec
/
test

Text Generation
PEFT
Safetensors
Transformers
llama-factory
conversational
Model card Files
xet
Community
rbelanec commited on
Commit
9d80d3d
·
verified ·
1 Parent(s): 431df2c

Training in progress, step 7

Browse files
Files changed (4) hide show
  1. adapter_config.json +3 -3
  2. adapter_model.safetensors +2 -2
  3. trainer_log.jsonl +12 -43
  4. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -6,11 +6,11 @@
6
  "revision": null,
7
  "target_modules": [
8
  "o_proj",
9
- "v_proj",
10
- "up_proj",
11
  "down_proj",
 
12
  "q_proj",
13
- "k_proj"
 
14
  ],
15
  "task_type": "CAUSAL_LM"
16
  }
 
6
  "revision": null,
7
  "target_modules": [
8
  "o_proj",
 
 
9
  "down_proj",
10
+ "k_proj",
11
  "q_proj",
12
+ "up_proj",
13
+ "v_proj"
14
  ],
15
  "task_type": "CAUSAL_LM"
16
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:434d92bdf22308ada82c55657344041a47d5ad9cd87553d78a484f8fe58ce4ff
3
- size 2818586248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4389bc853785f6f0b7a549fab1b3063262a707c18b546f54d132629472ce6fa5
3
+ size 2819582528
trainer_log.jsonl CHANGED
@@ -1,43 +1,12 @@
1
- {"current_steps": 5, "total_steps": 125, "loss": 1.0409, "lr": 1.5384615384615387e-05, "epoch": 0.04, "percentage": 4.0, "elapsed_time": "0:00:04", "remaining_time": "0:01:57", "throughput": 436.96, "total_tokens": 2144}
2
- {"current_steps": 7, "total_steps": 125, "eval_loss": 0.3513108789920807, "epoch": 0.056, "percentage": 5.6, "elapsed_time": "0:00:05", "remaining_time": "0:01:39", "throughput": 487.23, "total_tokens": 2880}
3
- {"current_steps": 10, "total_steps": 125, "loss": 0.4086, "lr": 3.461538461538462e-05, "epoch": 0.08, "percentage": 8.0, "elapsed_time": "0:00:44", "remaining_time": "0:08:27", "throughput": 93.46, "total_tokens": 4128}
4
- {"current_steps": 14, "total_steps": 125, "eval_loss": 1.1120651960372925, "epoch": 0.112, "percentage": 11.2, "elapsed_time": "0:00:45", "remaining_time": "0:06:01", "throughput": 129.93, "total_tokens": 5920}
5
- {"current_steps": 15, "total_steps": 125, "loss": 0.8807, "lr": 4.999016565957633e-05, "epoch": 0.12, "percentage": 12.0, "elapsed_time": "0:01:12", "remaining_time": "0:08:53", "throughput": 85.84, "total_tokens": 6240}
6
- {"current_steps": 20, "total_steps": 125, "loss": 0.9267, "lr": 4.96467754629559e-05, "epoch": 0.16, "percentage": 16.0, "elapsed_time": "0:01:13", "remaining_time": "0:06:26", "throughput": 109.92, "total_tokens": 8096}
7
- {"current_steps": 21, "total_steps": 125, "eval_loss": 0.35109928250312805, "epoch": 0.168, "percentage": 16.8, "elapsed_time": "0:01:14", "remaining_time": "0:06:09", "throughput": 112.93, "total_tokens": 8416}
8
- {"current_steps": 25, "total_steps": 125, "loss": 0.7142, "lr": 4.881937806807241e-05, "epoch": 0.2, "percentage": 20.0, "elapsed_time": "0:01:35", "remaining_time": "0:06:22", "throughput": 105.64, "total_tokens": 10112}
9
- {"current_steps": 28, "total_steps": 125, "eval_loss": 0.38589543104171753, "epoch": 0.224, "percentage": 22.4, "elapsed_time": "0:01:36", "remaining_time": "0:05:35", "throughput": 116.17, "total_tokens": 11264}
10
- {"current_steps": 30, "total_steps": 125, "loss": 0.385, "lr": 4.752422169756048e-05, "epoch": 0.24, "percentage": 24.0, "elapsed_time": "0:02:05", "remaining_time": "0:06:38", "throughput": 95.58, "total_tokens": 12032}
11
- {"current_steps": 35, "total_steps": 125, "loss": 0.5983, "lr": 4.5786740307563636e-05, "epoch": 0.28, "percentage": 28.0, "elapsed_time": "0:02:06", "remaining_time": "0:05:26", "throughput": 108.97, "total_tokens": 13824}
12
- {"current_steps": 35, "total_steps": 125, "eval_loss": 0.658510684967041, "epoch": 0.28, "percentage": 28.0, "elapsed_time": "0:02:07", "remaining_time": "0:05:27", "throughput": 108.4, "total_tokens": 13824}
13
- {"current_steps": 40, "total_steps": 125, "loss": 0.394, "lr": 4.364105412207914e-05, "epoch": 0.32, "percentage": 32.0, "elapsed_time": "0:02:25", "remaining_time": "0:05:08", "throughput": 109.17, "total_tokens": 15840}
14
- {"current_steps": 42, "total_steps": 125, "eval_loss": 0.41257768869400024, "epoch": 0.336, "percentage": 33.6, "elapsed_time": "0:02:26", "remaining_time": "0:04:48", "throughput": 114.07, "total_tokens": 16672}
15
- {"current_steps": 45, "total_steps": 125, "loss": 0.4533, "lr": 4.1129299588552193e-05, "epoch": 0.36, "percentage": 36.0, "elapsed_time": "0:02:51", "remaining_time": "0:05:04", "throughput": 104.78, "total_tokens": 17920}
16
- {"current_steps": 49, "total_steps": 125, "eval_loss": 1.1762187480926514, "epoch": 0.392, "percentage": 39.2, "elapsed_time": "0:02:52", "remaining_time": "0:04:27", "throughput": 111.92, "total_tokens": 19296}
17
- {"current_steps": 50, "total_steps": 125, "loss": 0.1866, "lr": 3.830080191288342e-05, "epoch": 0.4, "percentage": 40.0, "elapsed_time": "0:03:21", "remaining_time": "0:05:01", "throughput": 98.04, "total_tokens": 19712}
18
- {"current_steps": 55, "total_steps": 125, "loss": 1.3512, "lr": 3.521110642339991e-05, "epoch": 0.44, "percentage": 44.0, "elapsed_time": "0:03:22", "remaining_time": "0:04:17", "throughput": 108.65, "total_tokens": 21952}
19
- {"current_steps": 56, "total_steps": 125, "eval_loss": 0.806473433971405, "epoch": 0.448, "percentage": 44.8, "elapsed_time": "0:03:22", "remaining_time": "0:04:09", "throughput": 110.56, "total_tokens": 22432}
20
- {"current_steps": 60, "total_steps": 125, "loss": 0.7948, "lr": 3.1920887785621235e-05, "epoch": 0.48, "percentage": 48.0, "elapsed_time": "0:03:41", "remaining_time": "0:03:59", "throughput": 109.23, "total_tokens": 24160}
21
- {"current_steps": 63, "total_steps": 125, "eval_loss": 1.0268325805664062, "epoch": 0.504, "percentage": 50.4, "elapsed_time": "0:03:42", "remaining_time": "0:03:38", "throughput": 114.67, "total_tokens": 25504}
22
- {"current_steps": 65, "total_steps": 125, "loss": 0.6941, "lr": 2.849475848838749e-05, "epoch": 0.52, "percentage": 52.0, "elapsed_time": "0:04:04", "remaining_time": "0:03:45", "throughput": 106.72, "total_tokens": 26112}
23
- {"current_steps": 70, "total_steps": 125, "loss": 0.3463, "lr": 2.5e-05, "epoch": 0.56, "percentage": 56.0, "elapsed_time": "0:04:05", "remaining_time": "0:03:13", "throughput": 114.24, "total_tokens": 28064}
24
- {"current_steps": 70, "total_steps": 125, "eval_loss": 0.35280704498291016, "epoch": 0.56, "percentage": 56.0, "elapsed_time": "0:04:06", "remaining_time": "0:03:13", "throughput": 113.93, "total_tokens": 28064}
25
- {"current_steps": 75, "total_steps": 125, "loss": 0.3652, "lr": 2.1505241511612522e-05, "epoch": 0.6, "percentage": 60.0, "elapsed_time": "0:04:37", "remaining_time": "0:03:04", "throughput": 107.65, "total_tokens": 29824}
26
- {"current_steps": 77, "total_steps": 125, "eval_loss": 0.3505268096923828, "epoch": 0.616, "percentage": 61.6, "elapsed_time": "0:04:38", "remaining_time": "0:02:53", "throughput": 110.46, "total_tokens": 30720}
27
- {"current_steps": 80, "total_steps": 125, "loss": 0.3476, "lr": 1.8079112214378768e-05, "epoch": 0.64, "percentage": 64.0, "elapsed_time": "0:04:55", "remaining_time": "0:02:46", "throughput": 107.81, "total_tokens": 31904}
28
- {"current_steps": 84, "total_steps": 125, "eval_loss": 0.34708982706069946, "epoch": 0.672, "percentage": 67.2, "elapsed_time": "0:04:57", "remaining_time": "0:02:25", "throughput": 112.69, "total_tokens": 33504}
29
- {"current_steps": 85, "total_steps": 125, "loss": 0.3491, "lr": 1.4788893576600099e-05, "epoch": 0.68, "percentage": 68.0, "elapsed_time": "0:05:18", "remaining_time": "0:02:29", "throughput": 106.64, "total_tokens": 33984}
30
- {"current_steps": 90, "total_steps": 125, "loss": 0.3395, "lr": 1.1699198087116589e-05, "epoch": 0.72, "percentage": 72.0, "elapsed_time": "0:05:19", "remaining_time": "0:02:04", "throughput": 111.91, "total_tokens": 35776}
31
- {"current_steps": 91, "total_steps": 125, "eval_loss": 0.3647787868976593, "epoch": 0.728, "percentage": 72.8, "elapsed_time": "0:05:20", "remaining_time": "0:01:59", "throughput": 112.7, "total_tokens": 36128}
32
- {"current_steps": 95, "total_steps": 125, "loss": 0.4569, "lr": 8.870700411447816e-06, "epoch": 0.76, "percentage": 76.0, "elapsed_time": "0:05:50", "remaining_time": "0:01:50", "throughput": 106.92, "total_tokens": 37472}
33
- {"current_steps": 98, "total_steps": 125, "eval_loss": 0.3610990643501282, "epoch": 0.784, "percentage": 78.4, "elapsed_time": "0:05:51", "remaining_time": "0:01:36", "throughput": 109.73, "total_tokens": 38592}
34
- {"current_steps": 100, "total_steps": 125, "loss": 0.3916, "lr": 6.358945877920861e-06, "epoch": 0.8, "percentage": 80.0, "elapsed_time": "0:06:10", "remaining_time": "0:01:32", "throughput": 106.05, "total_tokens": 39328}
35
- {"current_steps": 105, "total_steps": 125, "loss": 0.3191, "lr": 4.213259692436367e-06, "epoch": 0.84, "percentage": 84.0, "elapsed_time": "0:06:11", "remaining_time": "0:01:10", "throughput": 111.02, "total_tokens": 41280}
36
- {"current_steps": 105, "total_steps": 125, "eval_loss": 0.43045976758003235, "epoch": 0.84, "percentage": 84.0, "elapsed_time": "0:06:12", "remaining_time": "0:01:10", "throughput": 110.81, "total_tokens": 41280}
37
- {"current_steps": 110, "total_steps": 125, "loss": 0.3951, "lr": 2.475778302439524e-06, "epoch": 0.88, "percentage": 88.0, "elapsed_time": "0:06:32", "remaining_time": "0:00:53", "throughput": 110.83, "total_tokens": 43552}
38
- {"current_steps": 112, "total_steps": 125, "eval_loss": 0.4486384391784668, "epoch": 0.896, "percentage": 89.6, "elapsed_time": "0:06:33", "remaining_time": "0:00:45", "throughput": 112.08, "total_tokens": 44160}
39
- {"current_steps": 115, "total_steps": 125, "loss": 0.3107, "lr": 1.180621931927592e-06, "epoch": 0.92, "percentage": 92.0, "elapsed_time": "0:06:58", "remaining_time": "0:00:36", "throughput": 107.98, "total_tokens": 45216}
40
- {"current_steps": 119, "total_steps": 125, "eval_loss": 0.44127246737480164, "epoch": 0.952, "percentage": 95.2, "elapsed_time": "0:07:00", "remaining_time": "0:00:21", "throughput": 111.72, "total_tokens": 46944}
41
- {"current_steps": 120, "total_steps": 125, "loss": 0.2809, "lr": 3.5322453704410286e-07, "epoch": 0.96, "percentage": 96.0, "elapsed_time": "0:07:26", "remaining_time": "0:00:18", "throughput": 106.0, "total_tokens": 47360}
42
- {"current_steps": 125, "total_steps": 125, "loss": 0.4785, "lr": 9.834340423678368e-09, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:07:28", "remaining_time": "0:00:00", "throughput": 110.18, "total_tokens": 49376}
43
- {"current_steps": 125, "total_steps": 125, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:07:50", "remaining_time": "0:00:00", "throughput": 105.0, "total_tokens": 49376}
 
1
+ {"current_steps": 5, "total_steps": 125, "loss": 10.9709, "lr": 1.5384615384615387e-05, "epoch": 0.04, "percentage": 4.0, "elapsed_time": "0:00:01", "remaining_time": "0:00:45", "throughput": 1126.49, "total_tokens": 2144}
2
+ {"current_steps": 7, "total_steps": 125, "eval_loss": 6.5227251052856445, "epoch": 0.056, "percentage": 5.6, "elapsed_time": "0:00:02", "remaining_time": "0:00:49", "throughput": 985.42, "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": "0:00:23", "remaining_time": "0:04:25", "throughput": 178.62, "total_tokens": 4128}
4
+ {"current_steps": 14, "total_steps": 125, "eval_loss": 1.382468581199646, "epoch": 0.112, "percentage": 11.2, "elapsed_time": "0:00:24", "remaining_time": "0:03:13", "throughput": 242.05, "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": "0:00:35", "remaining_time": "0:04:21", "throughput": 174.88, "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": "0:00:36", "remaining_time": "0:03:11", "throughput": 222.01, "total_tokens": 8096}
7
+ {"current_steps": 21, "total_steps": 125, "eval_loss": 0.4987373352050781, "epoch": 0.168, "percentage": 16.8, "elapsed_time": "0:00:37", "remaining_time": "0:03:04", "throughput": 225.31, "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": "0:00:49", "remaining_time": "0:03:17", "throughput": 205.26, "total_tokens": 10112}
9
+ {"current_steps": 28, "total_steps": 125, "eval_loss": 0.4531269073486328, "epoch": 0.224, "percentage": 22.4, "elapsed_time": "0:00:50", "remaining_time": "0:02:55", "throughput": 222.87, "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": "0:01:02", "remaining_time": "0:03:16", "throughput": 193.76, "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": "0:01:02", "remaining_time": "0:02:41", "throughput": 219.77, "total_tokens": 13824}
12
+ {"current_steps": 35, "total_steps": 125, "eval_loss": 0.36931881308555603, "epoch": 0.28, "percentage": 28.0, "elapsed_time": "0:01:03", "remaining_time": "0:02:44", "throughput": 216.75, "total_tokens": 13824}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c15b67a3611dd4d5558e3b4704da8db313ee1413361e088cac2394f243a8d3e4
3
  size 6097
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2748056f7e661a88a39d01dcfeb31641675efffc05f00f667e18bb847f69af83
3
  size 6097