chchen commited on
Commit
323ac9d
·
verified ·
1 Parent(s): 98e12d9

Training in progress, step 10

Browse files
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "q_proj",
24
- "up_proj",
25
- "down_proj",
26
- "o_proj",
27
  "gate_proj",
 
 
 
 
28
  "v_proj",
29
- "k_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
 
 
23
  "gate_proj",
24
+ "o_proj",
25
+ "down_proj",
26
+ "q_proj",
27
+ "k_proj",
28
  "v_proj",
29
+ "up_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70e8891c2e1d44d551c93a8bc39d16cfbab17c2079ac964821aad9457a9af36d
3
  size 87360584
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8304a25b6a733352a4df622bb239069fe251edc07bf3b19e6b7c4a823f853d06
3
  size 87360584
llama3_lora_sft.yaml CHANGED
@@ -12,7 +12,7 @@ lora_target: all
12
  dataset: course-doc-train-fold1
13
  dataset_dir: data_private
14
  template: mistral
15
- cutoff_len: 2048
16
  # max_samples: 1000
17
  overwrite_cache: true
18
  preprocessing_num_workers: 16
 
12
  dataset: course-doc-train-fold1
13
  dataset_dir: data_private
14
  template: mistral
15
+ cutoff_len: 8192
16
  # max_samples: 1000
17
  overwrite_cache: true
18
  preprocessing_num_workers: 16
trainer_log.jsonl CHANGED
@@ -1,138 +1,11 @@
1
- {"current_steps": 1, "total_steps": 125, "loss": 0.2092, "lr": 7.692307692307694e-06, "epoch": 0.03950617283950617, "percentage": 0.8, "elapsed_time": "0:00:30", "remaining_time": "1:02:37"}
2
- {"current_steps": 2, "total_steps": 125, "loss": 0.221, "lr": 1.5384615384615387e-05, "epoch": 0.07901234567901234, "percentage": 1.6, "elapsed_time": "0:00:58", "remaining_time": "0:59:51"}
3
- {"current_steps": 3, "total_steps": 125, "loss": 0.211, "lr": 2.307692307692308e-05, "epoch": 0.11851851851851852, "percentage": 2.4, "elapsed_time": "0:01:26", "remaining_time": "0:58:29"}
4
- {"current_steps": 4, "total_steps": 125, "loss": 0.2472, "lr": 3.0769230769230774e-05, "epoch": 0.1580246913580247, "percentage": 3.2, "elapsed_time": "0:01:55", "remaining_time": "0:58:18"}
5
- {"current_steps": 5, "total_steps": 125, "loss": 0.2688, "lr": 3.846153846153846e-05, "epoch": 0.19753086419753085, "percentage": 4.0, "elapsed_time": "0:02:26", "remaining_time": "0:58:39"}
6
- {"current_steps": 6, "total_steps": 125, "loss": 0.1779, "lr": 4.615384615384616e-05, "epoch": 0.23703703703703705, "percentage": 4.8, "elapsed_time": "0:02:58", "remaining_time": "0:58:52"}
7
- {"current_steps": 7, "total_steps": 125, "loss": 0.2425, "lr": 5.384615384615385e-05, "epoch": 0.2765432098765432, "percentage": 5.6, "elapsed_time": "0:03:29", "remaining_time": "0:58:59"}
8
- {"current_steps": 8, "total_steps": 125, "loss": 0.201, "lr": 6.153846153846155e-05, "epoch": 0.3160493827160494, "percentage": 6.4, "elapsed_time": "0:04:01", "remaining_time": "0:58:56"}
9
- {"current_steps": 9, "total_steps": 125, "loss": 0.1341, "lr": 6.923076923076924e-05, "epoch": 0.35555555555555557, "percentage": 7.2, "elapsed_time": "0:04:34", "remaining_time": "0:59:00"}
10
- {"current_steps": 10, "total_steps": 125, "loss": 0.1495, "lr": 7.692307692307693e-05, "epoch": 0.3950617283950617, "percentage": 8.0, "elapsed_time": "0:05:04", "remaining_time": "0:58:24"}
11
- {"current_steps": 10, "total_steps": 125, "eval_loss": 0.13552844524383545, "epoch": 0.3950617283950617, "percentage": 8.0, "elapsed_time": "0:05:31", "remaining_time": "1:03:33"}
12
- {"current_steps": 11, "total_steps": 125, "loss": 0.1, "lr": 8.461538461538461e-05, "epoch": 0.4345679012345679, "percentage": 8.8, "elapsed_time": "0:06:07", "remaining_time": "1:03:23"}
13
- {"current_steps": 12, "total_steps": 125, "loss": 0.1806, "lr": 9.230769230769232e-05, "epoch": 0.4740740740740741, "percentage": 9.6, "elapsed_time": "0:06:39", "remaining_time": "1:02:37"}
14
- {"current_steps": 13, "total_steps": 125, "loss": 0.0953, "lr": 0.0001, "epoch": 0.5135802469135803, "percentage": 10.4, "elapsed_time": "0:07:09", "remaining_time": "1:01:40"}
15
- {"current_steps": 14, "total_steps": 125, "loss": 0.0955, "lr": 9.998033131915266e-05, "epoch": 0.5530864197530864, "percentage": 11.2, "elapsed_time": "0:07:40", "remaining_time": "1:00:53"}
16
- {"current_steps": 15, "total_steps": 125, "loss": 0.0593, "lr": 9.992134075089084e-05, "epoch": 0.5925925925925926, "percentage": 12.0, "elapsed_time": "0:08:12", "remaining_time": "1:00:13"}
17
- {"current_steps": 16, "total_steps": 125, "loss": 0.1111, "lr": 9.982307470588098e-05, "epoch": 0.6320987654320988, "percentage": 12.8, "elapsed_time": "0:08:46", "remaining_time": "0:59:44"}
18
- {"current_steps": 17, "total_steps": 125, "loss": 0.1019, "lr": 9.968561049466214e-05, "epoch": 0.671604938271605, "percentage": 13.6, "elapsed_time": "0:09:20", "remaining_time": "0:59:21"}
19
- {"current_steps": 18, "total_steps": 125, "loss": 0.0538, "lr": 9.950905626682228e-05, "epoch": 0.7111111111111111, "percentage": 14.4, "elapsed_time": "0:09:51", "remaining_time": "0:58:35"}
20
- {"current_steps": 19, "total_steps": 125, "loss": 0.1104, "lr": 9.92935509259118e-05, "epoch": 0.7506172839506173, "percentage": 15.2, "elapsed_time": "0:10:24", "remaining_time": "0:58:03"}
21
- {"current_steps": 20, "total_steps": 125, "loss": 0.0292, "lr": 9.903926402016153e-05, "epoch": 0.7901234567901234, "percentage": 16.0, "elapsed_time": "0:10:54", "remaining_time": "0:57:17"}
22
- {"current_steps": 20, "total_steps": 125, "eval_loss": 0.09099149703979492, "epoch": 0.7901234567901234, "percentage": 16.0, "elapsed_time": "0:11:22", "remaining_time": "0:59:41"}
23
- {"current_steps": 21, "total_steps": 125, "loss": 0.1058, "lr": 9.874639560909117e-05, "epoch": 0.8296296296296296, "percentage": 16.8, "elapsed_time": "0:12:00", "remaining_time": "0:59:27"}
24
- {"current_steps": 22, "total_steps": 125, "loss": 0.073, "lr": 9.841517610611309e-05, "epoch": 0.8691358024691358, "percentage": 17.6, "elapsed_time": "0:12:30", "remaining_time": "0:58:33"}
25
- {"current_steps": 23, "total_steps": 125, "loss": 0.0987, "lr": 9.804586609725499e-05, "epoch": 0.908641975308642, "percentage": 18.4, "elapsed_time": "0:13:04", "remaining_time": "0:57:57"}
26
- {"current_steps": 24, "total_steps": 125, "loss": 0.0759, "lr": 9.763875613614482e-05, "epoch": 0.9481481481481482, "percentage": 19.2, "elapsed_time": "0:13:37", "remaining_time": "0:57:19"}
27
- {"current_steps": 25, "total_steps": 125, "loss": 0.0906, "lr": 9.719416651541839e-05, "epoch": 0.9876543209876543, "percentage": 20.0, "elapsed_time": "0:14:08", "remaining_time": "0:56:34"}
28
- {"current_steps": 26, "total_steps": 125, "loss": 0.0834, "lr": 9.671244701472999e-05, "epoch": 1.0271604938271606, "percentage": 20.8, "elapsed_time": "0:14:37", "remaining_time": "0:55:42"}
29
- {"current_steps": 27, "total_steps": 125, "loss": 0.0708, "lr": 9.619397662556435e-05, "epoch": 1.0666666666666667, "percentage": 21.6, "elapsed_time": "0:15:10", "remaining_time": "0:55:03"}
30
- {"current_steps": 28, "total_steps": 125, "loss": 0.0484, "lr": 9.563916325306594e-05, "epoch": 1.106172839506173, "percentage": 22.4, "elapsed_time": "0:15:43", "remaining_time": "0:54:27"}
31
- {"current_steps": 29, "total_steps": 125, "loss": 0.1173, "lr": 9.504844339512095e-05, "epoch": 1.145679012345679, "percentage": 23.2, "elapsed_time": "0:16:16", "remaining_time": "0:53:52"}
32
- {"current_steps": 30, "total_steps": 125, "loss": 0.0626, "lr": 9.442228179894362e-05, "epoch": 1.1851851851851851, "percentage": 24.0, "elapsed_time": "0:16:49", "remaining_time": "0:53:15"}
33
- {"current_steps": 30, "total_steps": 125, "eval_loss": 0.0796937569975853, "epoch": 1.1851851851851851, "percentage": 24.0, "elapsed_time": "0:17:16", "remaining_time": "0:54:42"}
34
- {"current_steps": 31, "total_steps": 125, "loss": 0.0648, "lr": 9.376117109543769e-05, "epoch": 1.2246913580246914, "percentage": 24.8, "elapsed_time": "0:17:52", "remaining_time": "0:54:10"}
35
- {"current_steps": 32, "total_steps": 125, "loss": 0.1198, "lr": 9.306563141162046e-05, "epoch": 1.2641975308641975, "percentage": 25.6, "elapsed_time": "0:18:20", "remaining_time": "0:53:19"}
36
- {"current_steps": 33, "total_steps": 125, "loss": 0.0634, "lr": 9.233620996141421e-05, "epoch": 1.3037037037037038, "percentage": 26.4, "elapsed_time": "0:18:54", "remaining_time": "0:52:43"}
37
- {"current_steps": 34, "total_steps": 125, "loss": 0.0646, "lr": 9.157348061512727e-05, "epoch": 1.34320987654321, "percentage": 27.2, "elapsed_time": "0:19:24", "remaining_time": "0:51:55"}
38
- {"current_steps": 35, "total_steps": 125, "loss": 0.0508, "lr": 9.077804344796302e-05, "epoch": 1.382716049382716, "percentage": 28.0, "elapsed_time": "0:19:58", "remaining_time": "0:51:21"}
39
- {"current_steps": 36, "total_steps": 125, "loss": 0.0632, "lr": 8.995052426791247e-05, "epoch": 1.4222222222222223, "percentage": 28.8, "elapsed_time": "0:20:30", "remaining_time": "0:50:41"}
40
- {"current_steps": 37, "total_steps": 125, "loss": 0.0322, "lr": 8.90915741234015e-05, "epoch": 1.4617283950617284, "percentage": 29.6, "elapsed_time": "0:21:03", "remaining_time": "0:50:04"}
41
- {"current_steps": 38, "total_steps": 125, "loss": 0.102, "lr": 8.820186879108038e-05, "epoch": 1.5012345679012347, "percentage": 30.4, "elapsed_time": "0:21:33", "remaining_time": "0:49:22"}
42
- {"current_steps": 39, "total_steps": 125, "loss": 0.0599, "lr": 8.728210824415827e-05, "epoch": 1.5407407407407407, "percentage": 31.2, "elapsed_time": "0:22:03", "remaining_time": "0:48:38"}
43
- {"current_steps": 40, "total_steps": 125, "loss": 0.0771, "lr": 8.633301610170135e-05, "epoch": 1.5802469135802468, "percentage": 32.0, "elapsed_time": "0:22:35", "remaining_time": "0:48:01"}
44
- {"current_steps": 40, "total_steps": 125, "eval_loss": 0.07648379355669022, "epoch": 1.5802469135802468, "percentage": 32.0, "elapsed_time": "0:23:03", "remaining_time": "0:48:59"}
45
- {"current_steps": 41, "total_steps": 125, "loss": 0.0774, "lr": 8.535533905932738e-05, "epoch": 1.6197530864197531, "percentage": 32.8, "elapsed_time": "0:23:40", "remaining_time": "0:48:29"}
46
- {"current_steps": 42, "total_steps": 125, "loss": 0.1063, "lr": 8.434984630174509e-05, "epoch": 1.6592592592592592, "percentage": 33.6, "elapsed_time": "0:24:10", "remaining_time": "0:47:47"}
47
- {"current_steps": 43, "total_steps": 125, "loss": 0.0696, "lr": 8.33173288976002e-05, "epoch": 1.6987654320987655, "percentage": 34.4, "elapsed_time": "0:24:43", "remaining_time": "0:47:09"}
48
- {"current_steps": 44, "total_steps": 125, "loss": 0.0831, "lr": 8.225859917710439e-05, "epoch": 1.7382716049382716, "percentage": 35.2, "elapsed_time": "0:25:16", "remaining_time": "0:46:32"}
49
- {"current_steps": 45, "total_steps": 125, "loss": 0.0672, "lr": 8.117449009293668e-05, "epoch": 1.7777777777777777, "percentage": 36.0, "elapsed_time": "0:25:48", "remaining_time": "0:45:53"}
50
- {"current_steps": 46, "total_steps": 125, "loss": 0.0554, "lr": 8.006585456492029e-05, "epoch": 1.817283950617284, "percentage": 36.8, "elapsed_time": "0:26:23", "remaining_time": "0:45:19"}
51
- {"current_steps": 47, "total_steps": 125, "loss": 0.0709, "lr": 7.89335648089903e-05, "epoch": 1.8567901234567903, "percentage": 37.6, "elapsed_time": "0:26:56", "remaining_time": "0:44:42"}
52
- {"current_steps": 48, "total_steps": 125, "loss": 0.0288, "lr": 7.777851165098012e-05, "epoch": 1.8962962962962964, "percentage": 38.4, "elapsed_time": "0:27:30", "remaining_time": "0:44:07"}
53
- {"current_steps": 49, "total_steps": 125, "loss": 0.0914, "lr": 7.660160382576683e-05, "epoch": 1.9358024691358025, "percentage": 39.2, "elapsed_time": "0:28:05", "remaining_time": "0:43:34"}
54
- {"current_steps": 50, "total_steps": 125, "loss": 0.1056, "lr": 7.540376726232648e-05, "epoch": 1.9753086419753085, "percentage": 40.0, "elapsed_time": "0:28:40", "remaining_time": "0:43:00"}
55
- {"current_steps": 50, "total_steps": 125, "eval_loss": 0.07425841689109802, "epoch": 1.9753086419753085, "percentage": 40.0, "elapsed_time": "0:29:07", "remaining_time": "0:43:41"}
56
- {"current_steps": 51, "total_steps": 125, "loss": 0.0605, "lr": 7.4185944355262e-05, "epoch": 2.0148148148148146, "percentage": 40.8, "elapsed_time": "0:29:46", "remaining_time": "0:43:12"}
57
- {"current_steps": 52, "total_steps": 125, "loss": 0.1024, "lr": 7.294909322337689e-05, "epoch": 2.054320987654321, "percentage": 41.6, "elapsed_time": "0:30:17", "remaining_time": "0:42:30"}
58
- {"current_steps": 53, "total_steps": 125, "loss": 0.0575, "lr": 7.169418695587791e-05, "epoch": 2.093827160493827, "percentage": 42.4, "elapsed_time": "0:30:49", "remaining_time": "0:41:52"}
59
- {"current_steps": 54, "total_steps": 125, "loss": 0.0522, "lr": 7.042221284679982e-05, "epoch": 2.1333333333333333, "percentage": 43.2, "elapsed_time": "0:31:21", "remaining_time": "0:41:14"}
60
- {"current_steps": 55, "total_steps": 125, "loss": 0.0401, "lr": 6.91341716182545e-05, "epoch": 2.1728395061728394, "percentage": 44.0, "elapsed_time": "0:31:54", "remaining_time": "0:40:37"}
61
- {"current_steps": 56, "total_steps": 125, "loss": 0.0464, "lr": 6.783107663311565e-05, "epoch": 2.212345679012346, "percentage": 44.8, "elapsed_time": "0:32:28", "remaining_time": "0:40:00"}
62
- {"current_steps": 57, "total_steps": 125, "loss": 0.0846, "lr": 6.651395309775837e-05, "epoch": 2.251851851851852, "percentage": 45.6, "elapsed_time": "0:33:03", "remaining_time": "0:39:26"}
63
- {"current_steps": 58, "total_steps": 125, "loss": 0.0517, "lr": 6.518383725548074e-05, "epoch": 2.291358024691358, "percentage": 46.4, "elapsed_time": "0:33:35", "remaining_time": "0:38:47"}
64
- {"current_steps": 59, "total_steps": 125, "loss": 0.0636, "lr": 6.384177557124247e-05, "epoch": 2.330864197530864, "percentage": 47.2, "elapsed_time": "0:34:04", "remaining_time": "0:38:07"}
65
- {"current_steps": 60, "total_steps": 125, "loss": 0.0558, "lr": 6.248882390836135e-05, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:34:38", "remaining_time": "0:37:31"}
66
- {"current_steps": 60, "total_steps": 125, "eval_loss": 0.07404763251543045, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:35:05", "remaining_time": "0:38:01"}
67
- {"current_steps": 61, "total_steps": 125, "loss": 0.0448, "lr": 6.112604669781572e-05, "epoch": 2.4098765432098768, "percentage": 48.8, "elapsed_time": "0:35:44", "remaining_time": "0:37:30"}
68
- {"current_steps": 62, "total_steps": 125, "loss": 0.09, "lr": 5.9754516100806423e-05, "epoch": 2.449382716049383, "percentage": 49.6, "elapsed_time": "0:36:17", "remaining_time": "0:36:52"}
69
- {"current_steps": 63, "total_steps": 125, "loss": 0.0662, "lr": 5.837531116523682e-05, "epoch": 2.488888888888889, "percentage": 50.4, "elapsed_time": "0:36:48", "remaining_time": "0:36:13"}
70
- {"current_steps": 64, "total_steps": 125, "loss": 0.0232, "lr": 5.698951697677498e-05, "epoch": 2.528395061728395, "percentage": 51.2, "elapsed_time": "0:37:21", "remaining_time": "0:35:36"}
71
- {"current_steps": 65, "total_steps": 125, "loss": 0.0993, "lr": 5.559822380516539e-05, "epoch": 2.567901234567901, "percentage": 52.0, "elapsed_time": "0:37:52", "remaining_time": "0:34:58"}
72
- {"current_steps": 66, "total_steps": 125, "loss": 0.0291, "lr": 5.420252624646238e-05, "epoch": 2.6074074074074076, "percentage": 52.8, "elapsed_time": "0:38:24", "remaining_time": "0:34:19"}
73
- {"current_steps": 67, "total_steps": 125, "loss": 0.0668, "lr": 5.2803522361859594e-05, "epoch": 2.6469135802469137, "percentage": 53.6, "elapsed_time": "0:38:56", "remaining_time": "0:33:42"}
74
- {"current_steps": 68, "total_steps": 125, "loss": 0.0499, "lr": 5.140231281379345e-05, "epoch": 2.68641975308642, "percentage": 54.4, "elapsed_time": "0:39:28", "remaining_time": "0:33:05"}
75
- {"current_steps": 69, "total_steps": 125, "loss": 0.0246, "lr": 5e-05, "epoch": 2.725925925925926, "percentage": 55.2, "elapsed_time": "0:39:57", "remaining_time": "0:32:26"}
76
- {"current_steps": 70, "total_steps": 125, "loss": 0.0488, "lr": 4.859768718620656e-05, "epoch": 2.765432098765432, "percentage": 56.0, "elapsed_time": "0:40:28", "remaining_time": "0:31:48"}
77
- {"current_steps": 70, "total_steps": 125, "eval_loss": 0.07281763106584549, "epoch": 2.765432098765432, "percentage": 56.0, "elapsed_time": "0:40:55", "remaining_time": "0:32:09"}
78
- {"current_steps": 71, "total_steps": 125, "loss": 0.0297, "lr": 4.7196477638140404e-05, "epoch": 2.8049382716049385, "percentage": 56.8, "elapsed_time": "0:41:31", "remaining_time": "0:31:34"}
79
- {"current_steps": 72, "total_steps": 125, "loss": 0.1215, "lr": 4.579747375353763e-05, "epoch": 2.8444444444444446, "percentage": 57.6, "elapsed_time": "0:42:05", "remaining_time": "0:30:59"}
80
- {"current_steps": 73, "total_steps": 125, "loss": 0.0685, "lr": 4.4401776194834613e-05, "epoch": 2.8839506172839506, "percentage": 58.4, "elapsed_time": "0:42:37", "remaining_time": "0:30:21"}
81
- {"current_steps": 74, "total_steps": 125, "loss": 0.0445, "lr": 4.3010483023225045e-05, "epoch": 2.9234567901234567, "percentage": 59.2, "elapsed_time": "0:43:11", "remaining_time": "0:29:45"}
82
- {"current_steps": 75, "total_steps": 125, "loss": 0.0871, "lr": 4.162468883476319e-05, "epoch": 2.962962962962963, "percentage": 60.0, "elapsed_time": "0:43:42", "remaining_time": "0:29:08"}
83
- {"current_steps": 76, "total_steps": 125, "loss": 0.1052, "lr": 4.0245483899193595e-05, "epoch": 3.0024691358024693, "percentage": 60.8, "elapsed_time": "0:44:15", "remaining_time": "0:28:32"}
84
- {"current_steps": 77, "total_steps": 125, "loss": 0.0561, "lr": 3.887395330218429e-05, "epoch": 3.0419753086419754, "percentage": 61.6, "elapsed_time": "0:44:50", "remaining_time": "0:27:57"}
85
- {"current_steps": 78, "total_steps": 125, "loss": 0.0765, "lr": 3.7511176091638653e-05, "epoch": 3.0814814814814815, "percentage": 62.4, "elapsed_time": "0:45:23", "remaining_time": "0:27:21"}
86
- {"current_steps": 79, "total_steps": 125, "loss": 0.0297, "lr": 3.6158224428757535e-05, "epoch": 3.1209876543209876, "percentage": 63.2, "elapsed_time": "0:45:56", "remaining_time": "0:26:44"}
87
- {"current_steps": 80, "total_steps": 125, "loss": 0.0649, "lr": 3.4816162744519263e-05, "epoch": 3.1604938271604937, "percentage": 64.0, "elapsed_time": "0:46:29", "remaining_time": "0:26:08"}
88
- {"current_steps": 80, "total_steps": 125, "eval_loss": 0.07212765514850616, "epoch": 3.1604938271604937, "percentage": 64.0, "elapsed_time": "0:46:56", "remaining_time": "0:26:24"}
89
- {"current_steps": 81, "total_steps": 125, "loss": 0.0629, "lr": 3.3486046902241664e-05, "epoch": 3.2, "percentage": 64.8, "elapsed_time": "0:47:32", "remaining_time": "0:25:49"}
90
- {"current_steps": 82, "total_steps": 125, "loss": 0.0604, "lr": 3.216892336688435e-05, "epoch": 3.2395061728395063, "percentage": 65.6, "elapsed_time": "0:48:06", "remaining_time": "0:25:13"}
91
- {"current_steps": 83, "total_steps": 125, "loss": 0.0625, "lr": 3.086582838174551e-05, "epoch": 3.2790123456790123, "percentage": 66.4, "elapsed_time": "0:48:38", "remaining_time": "0:24:36"}
92
- {"current_steps": 84, "total_steps": 125, "loss": 0.0459, "lr": 2.9577787153200197e-05, "epoch": 3.3185185185185184, "percentage": 67.2, "elapsed_time": "0:49:10", "remaining_time": "0:24:00"}
93
- {"current_steps": 85, "total_steps": 125, "loss": 0.0455, "lr": 2.8305813044122097e-05, "epoch": 3.3580246913580245, "percentage": 68.0, "elapsed_time": "0:49:45", "remaining_time": "0:23:24"}
94
- {"current_steps": 86, "total_steps": 125, "loss": 0.0586, "lr": 2.705090677662311e-05, "epoch": 3.397530864197531, "percentage": 68.8, "elapsed_time": "0:50:18", "remaining_time": "0:22:48"}
95
- {"current_steps": 87, "total_steps": 125, "loss": 0.0397, "lr": 2.581405564473801e-05, "epoch": 3.437037037037037, "percentage": 69.6, "elapsed_time": "0:50:50", "remaining_time": "0:22:12"}
96
- {"current_steps": 88, "total_steps": 125, "loss": 0.0692, "lr": 2.459623273767354e-05, "epoch": 3.476543209876543, "percentage": 70.4, "elapsed_time": "0:51:22", "remaining_time": "0:21:36"}
97
- {"current_steps": 89, "total_steps": 125, "loss": 0.0569, "lr": 2.3398396174233178e-05, "epoch": 3.5160493827160493, "percentage": 71.2, "elapsed_time": "0:51:56", "remaining_time": "0:21:00"}
98
- {"current_steps": 90, "total_steps": 125, "loss": 0.0235, "lr": 2.2221488349019903e-05, "epoch": 3.5555555555555554, "percentage": 72.0, "elapsed_time": "0:52:27", "remaining_time": "0:20:23"}
99
- {"current_steps": 90, "total_steps": 125, "eval_loss": 0.07221826165914536, "epoch": 3.5555555555555554, "percentage": 72.0, "elapsed_time": "0:52:54", "remaining_time": "0:20:34"}
100
- {"current_steps": 91, "total_steps": 125, "loss": 0.0741, "lr": 2.1066435191009715e-05, "epoch": 3.595061728395062, "percentage": 72.8, "elapsed_time": "0:53:31", "remaining_time": "0:19:59"}
101
- {"current_steps": 92, "total_steps": 125, "loss": 0.0564, "lr": 1.9934145435079702e-05, "epoch": 3.634567901234568, "percentage": 73.6, "elapsed_time": "0:54:02", "remaining_time": "0:19:23"}
102
- {"current_steps": 93, "total_steps": 125, "loss": 0.0475, "lr": 1.8825509907063327e-05, "epoch": 3.674074074074074, "percentage": 74.4, "elapsed_time": "0:54:36", "remaining_time": "0:18:47"}
103
- {"current_steps": 94, "total_steps": 125, "loss": 0.0784, "lr": 1.774140082289563e-05, "epoch": 3.71358024691358, "percentage": 75.2, "elapsed_time": "0:55:07", "remaining_time": "0:18:10"}
104
- {"current_steps": 95, "total_steps": 125, "loss": 0.0717, "lr": 1.6682671102399805e-05, "epoch": 3.753086419753086, "percentage": 76.0, "elapsed_time": "0:55:35", "remaining_time": "0:17:33"}
105
- {"current_steps": 96, "total_steps": 125, "loss": 0.069, "lr": 1.5650153698254916e-05, "epoch": 3.7925925925925927, "percentage": 76.8, "elapsed_time": "0:56:05", "remaining_time": "0:16:56"}
106
- {"current_steps": 97, "total_steps": 125, "loss": 0.0418, "lr": 1.4644660940672627e-05, "epoch": 3.832098765432099, "percentage": 77.6, "elapsed_time": "0:56:38", "remaining_time": "0:16:20"}
107
- {"current_steps": 98, "total_steps": 125, "loss": 0.0234, "lr": 1.3666983898298657e-05, "epoch": 3.871604938271605, "percentage": 78.4, "elapsed_time": "0:57:09", "remaining_time": "0:15:44"}
108
- {"current_steps": 99, "total_steps": 125, "loss": 0.0318, "lr": 1.2717891755841722e-05, "epoch": 3.911111111111111, "percentage": 79.2, "elapsed_time": "0:57:42", "remaining_time": "0:15:09"}
109
- {"current_steps": 100, "total_steps": 125, "loss": 0.0508, "lr": 1.1798131208919627e-05, "epoch": 3.950617283950617, "percentage": 80.0, "elapsed_time": "0:58:12", "remaining_time": "0:14:33"}
110
- {"current_steps": 100, "total_steps": 125, "eval_loss": 0.07205358892679214, "epoch": 3.950617283950617, "percentage": 80.0, "elapsed_time": "0:58:39", "remaining_time": "0:14:39"}
111
- {"current_steps": 101, "total_steps": 125, "loss": 0.0662, "lr": 1.090842587659851e-05, "epoch": 3.9901234567901236, "percentage": 80.8, "elapsed_time": "0:59:14", "remaining_time": "0:14:04"}
112
- {"current_steps": 102, "total_steps": 125, "loss": 0.0723, "lr": 1.004947573208756e-05, "epoch": 4.029629629629629, "percentage": 81.6, "elapsed_time": "0:59:48", "remaining_time": "0:13:29"}
113
- {"current_steps": 103, "total_steps": 125, "loss": 0.0347, "lr": 9.221956552036992e-06, "epoch": 4.069135802469136, "percentage": 82.4, "elapsed_time": "1:00:21", "remaining_time": "0:12:53"}
114
- {"current_steps": 104, "total_steps": 125, "loss": 0.052, "lr": 8.426519384872733e-06, "epoch": 4.108641975308642, "percentage": 83.2, "elapsed_time": "1:00:55", "remaining_time": "0:12:18"}
115
- {"current_steps": 105, "total_steps": 125, "loss": 0.0788, "lr": 7.663790038585793e-06, "epoch": 4.148148148148148, "percentage": 84.0, "elapsed_time": "1:01:29", "remaining_time": "0:11:42"}
116
- {"current_steps": 106, "total_steps": 125, "loss": 0.0573, "lr": 6.934368588379553e-06, "epoch": 4.187654320987654, "percentage": 84.8, "elapsed_time": "1:01:58", "remaining_time": "0:11:06"}
117
- {"current_steps": 107, "total_steps": 125, "loss": 0.0591, "lr": 6.238828904562316e-06, "epoch": 4.22716049382716, "percentage": 85.6, "elapsed_time": "1:02:30", "remaining_time": "0:10:30"}
118
- {"current_steps": 108, "total_steps": 125, "loss": 0.0401, "lr": 5.577718201056392e-06, "epoch": 4.266666666666667, "percentage": 86.4, "elapsed_time": "1:03:00", "remaining_time": "0:09:55"}
119
- {"current_steps": 109, "total_steps": 125, "loss": 0.0729, "lr": 4.951556604879048e-06, "epoch": 4.306172839506173, "percentage": 87.2, "elapsed_time": "1:03:35", "remaining_time": "0:09:20"}
120
- {"current_steps": 110, "total_steps": 125, "loss": 0.0334, "lr": 4.360836746934055e-06, "epoch": 4.345679012345679, "percentage": 88.0, "elapsed_time": "1:04:08", "remaining_time": "0:08:44"}
121
- {"current_steps": 110, "total_steps": 125, "eval_loss": 0.07236602902412415, "epoch": 4.345679012345679, "percentage": 88.0, "elapsed_time": "1:04:35", "remaining_time": "0:08:48"}
122
- {"current_steps": 111, "total_steps": 125, "loss": 0.0384, "lr": 3.8060233744356633e-06, "epoch": 4.385185185185185, "percentage": 88.8, "elapsed_time": "1:05:11", "remaining_time": "0:08:13"}
123
- {"current_steps": 112, "total_steps": 125, "loss": 0.0651, "lr": 3.2875529852700147e-06, "epoch": 4.424691358024692, "percentage": 89.6, "elapsed_time": "1:05:41", "remaining_time": "0:07:37"}
124
- {"current_steps": 113, "total_steps": 125, "loss": 0.0191, "lr": 2.8058334845816213e-06, "epoch": 4.4641975308641975, "percentage": 90.4, "elapsed_time": "1:06:09", "remaining_time": "0:07:01"}
125
- {"current_steps": 114, "total_steps": 125, "loss": 0.0309, "lr": 2.361243863855184e-06, "epoch": 4.503703703703704, "percentage": 91.2, "elapsed_time": "1:06:38", "remaining_time": "0:06:25"}
126
- {"current_steps": 115, "total_steps": 125, "loss": 0.0692, "lr": 1.9541339027450256e-06, "epoch": 4.54320987654321, "percentage": 92.0, "elapsed_time": "1:07:10", "remaining_time": "0:05:50"}
127
- {"current_steps": 116, "total_steps": 125, "loss": 0.0566, "lr": 1.584823893886933e-06, "epoch": 4.582716049382716, "percentage": 92.8, "elapsed_time": "1:07:36", "remaining_time": "0:05:14"}
128
- {"current_steps": 117, "total_steps": 125, "loss": 0.0455, "lr": 1.2536043909088191e-06, "epoch": 4.622222222222222, "percentage": 93.6, "elapsed_time": "1:08:08", "remaining_time": "0:04:39"}
129
- {"current_steps": 118, "total_steps": 125, "loss": 0.0226, "lr": 9.607359798384785e-07, "epoch": 4.661728395061728, "percentage": 94.4, "elapsed_time": "1:08:39", "remaining_time": "0:04:04"}
130
- {"current_steps": 119, "total_steps": 125, "loss": 0.0561, "lr": 7.064490740882057e-07, "epoch": 4.701234567901235, "percentage": 95.2, "elapsed_time": "1:09:11", "remaining_time": "0:03:29"}
131
- {"current_steps": 120, "total_steps": 125, "loss": 0.0604, "lr": 4.909437331777179e-07, "epoch": 4.7407407407407405, "percentage": 96.0, "elapsed_time": "1:09:45", "remaining_time": "0:02:54"}
132
- {"current_steps": 120, "total_steps": 125, "eval_loss": 0.07253248989582062, "epoch": 4.7407407407407405, "percentage": 96.0, "elapsed_time": "1:10:13", "remaining_time": "0:02:55"}
133
- {"current_steps": 121, "total_steps": 125, "loss": 0.0269, "lr": 3.143895053378698e-07, "epoch": 4.780246913580247, "percentage": 96.8, "elapsed_time": "1:10:46", "remaining_time": "0:02:20"}
134
- {"current_steps": 122, "total_steps": 125, "loss": 0.058, "lr": 1.7692529411904578e-07, "epoch": 4.8197530864197535, "percentage": 97.6, "elapsed_time": "1:11:20", "remaining_time": "0:01:45"}
135
- {"current_steps": 123, "total_steps": 125, "loss": 0.0415, "lr": 7.865924910916977e-08, "epoch": 4.859259259259259, "percentage": 98.4, "elapsed_time": "1:11:54", "remaining_time": "0:01:10"}
136
- {"current_steps": 124, "total_steps": 125, "loss": 0.0583, "lr": 1.9668680847356735e-08, "epoch": 4.898765432098766, "percentage": 99.2, "elapsed_time": "1:12:25", "remaining_time": "0:00:35"}
137
- {"current_steps": 125, "total_steps": 125, "loss": 0.0166, "lr": 0.0, "epoch": 4.938271604938271, "percentage": 100.0, "elapsed_time": "1:12:56", "remaining_time": "0:00:00"}
138
- {"current_steps": 125, "total_steps": 125, "epoch": 4.938271604938271, "percentage": 100.0, "elapsed_time": "1:12:59", "remaining_time": "0:00:00"}
 
1
+ {"current_steps": 1, "total_steps": 125, "loss": 0.1275, "lr": 7.692307692307694e-06, "epoch": 0.03950617283950617, "percentage": 0.8, "elapsed_time": "0:00:49", "remaining_time": "1:41:59"}
2
+ {"current_steps": 2, "total_steps": 125, "loss": 0.1494, "lr": 1.5384615384615387e-05, "epoch": 0.07901234567901234, "percentage": 1.6, "elapsed_time": "0:01:38", "remaining_time": "1:41:18"}
3
+ {"current_steps": 3, "total_steps": 125, "loss": 0.1651, "lr": 2.307692307692308e-05, "epoch": 0.11851851851851852, "percentage": 2.4, "elapsed_time": "0:02:19", "remaining_time": "1:34:25"}
4
+ {"current_steps": 4, "total_steps": 125, "loss": 0.1353, "lr": 3.0769230769230774e-05, "epoch": 0.1580246913580247, "percentage": 3.2, "elapsed_time": "0:03:12", "remaining_time": "1:36:53"}
5
+ {"current_steps": 5, "total_steps": 125, "loss": 0.1333, "lr": 3.846153846153846e-05, "epoch": 0.19753086419753085, "percentage": 4.0, "elapsed_time": "0:04:01", "remaining_time": "1:36:24"}
6
+ {"current_steps": 6, "total_steps": 125, "loss": 0.127, "lr": 4.615384615384616e-05, "epoch": 0.23703703703703705, "percentage": 4.8, "elapsed_time": "0:04:48", "remaining_time": "1:35:24"}
7
+ {"current_steps": 7, "total_steps": 125, "loss": 0.1032, "lr": 5.384615384615385e-05, "epoch": 0.2765432098765432, "percentage": 5.6, "elapsed_time": "0:05:43", "remaining_time": "1:36:25"}
8
+ {"current_steps": 8, "total_steps": 125, "loss": 0.1066, "lr": 6.153846153846155e-05, "epoch": 0.3160493827160494, "percentage": 6.4, "elapsed_time": "0:06:31", "remaining_time": "1:35:29"}
9
+ {"current_steps": 9, "total_steps": 125, "loss": 0.0923, "lr": 6.923076923076924e-05, "epoch": 0.35555555555555557, "percentage": 7.2, "elapsed_time": "0:07:12", "remaining_time": "1:32:55"}
10
+ {"current_steps": 10, "total_steps": 125, "loss": 0.0823, "lr": 7.692307692307693e-05, "epoch": 0.3950617283950617, "percentage": 8.0, "elapsed_time": "0:07:54", "remaining_time": "1:30:52"}
11
+ {"current_steps": 10, "total_steps": 125, "eval_loss": 0.07050123810768127, "epoch": 0.3950617283950617, "percentage": 8.0, "elapsed_time": "0:08:25", "remaining_time": "1:36:55"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27880cdeacab7fd8fd866868e3c3559e88caf51526f3f011f6f9fdf9202d3c71
3
  size 5624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:309414a65af4743d4a112910b8a17f204b9ab26e912eea9a8ecdb862cd641bb7
3
  size 5624