chchen commited on
Commit
e65350d
·
verified ·
1 Parent(s): 3c773dd

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
- "o_proj",
24
  "down_proj",
 
 
25
  "up_proj",
26
  "gate_proj",
27
  "k_proj",
28
- "q_proj",
29
- "v_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "down_proj",
24
+ "v_proj",
25
+ "q_proj",
26
  "up_proj",
27
  "gate_proj",
28
  "k_proj",
29
+ "o_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 sha256:47984187a90c6e2962d15a21b794f55128288d7c0a8bf27a5595c3c6baf19188
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9d40bedd56a75872f6c23af38ace24cb77698eabe263d1eb154f6e1fb1a3fa3
3
  size 83945296
llama3_lora_sft.yaml CHANGED
@@ -12,7 +12,7 @@ lora_target: all
12
  dataset: course-doc-train-fold6
13
  dataset_dir: data_private
14
  template: llama3
15
- cutoff_len: 2048
16
  # max_samples: 1000
17
  overwrite_cache: true
18
  preprocessing_num_workers: 16
 
12
  dataset: course-doc-train-fold6
13
  dataset_dir: data_private
14
  template: llama3
15
+ cutoff_len: 8192
16
  # max_samples: 1000
17
  overwrite_cache: true
18
  preprocessing_num_workers: 16
trainer_log.jsonl CHANGED
@@ -1,138 +1,13 @@
1
- {"current_steps": 1, "total_steps": 125, "loss": 0.1625, "lr": 7.692307692307694e-06, "epoch": 0.03950617283950617, "percentage": 0.8, "elapsed_time": "0:00:23", "remaining_time": "0:49:00"}
2
- {"current_steps": 2, "total_steps": 125, "loss": 0.2251, "lr": 1.5384615384615387e-05, "epoch": 0.07901234567901234, "percentage": 1.6, "elapsed_time": "0:00:48", "remaining_time": "0:49:14"}
3
- {"current_steps": 3, "total_steps": 125, "loss": 0.1538, "lr": 2.307692307692308e-05, "epoch": 0.11851851851851852, "percentage": 2.4, "elapsed_time": "0:01:11", "remaining_time": "0:48:42"}
4
- {"current_steps": 4, "total_steps": 125, "loss": 0.1968, "lr": 3.0769230769230774e-05, "epoch": 0.1580246913580247, "percentage": 3.2, "elapsed_time": "0:01:38", "remaining_time": "0:49:46"}
5
- {"current_steps": 5, "total_steps": 125, "loss": 0.2309, "lr": 3.846153846153846e-05, "epoch": 0.19753086419753085, "percentage": 4.0, "elapsed_time": "0:02:06", "remaining_time": "0:50:41"}
6
- {"current_steps": 6, "total_steps": 125, "loss": 0.2071, "lr": 4.615384615384616e-05, "epoch": 0.23703703703703705, "percentage": 4.8, "elapsed_time": "0:02:34", "remaining_time": "0:50:57"}
7
- {"current_steps": 7, "total_steps": 125, "loss": 0.2325, "lr": 5.384615384615385e-05, "epoch": 0.2765432098765432, "percentage": 5.6, "elapsed_time": "0:03:01", "remaining_time": "0:50:57"}
8
- {"current_steps": 8, "total_steps": 125, "loss": 0.2162, "lr": 6.153846153846155e-05, "epoch": 0.3160493827160494, "percentage": 6.4, "elapsed_time": "0:03:30", "remaining_time": "0:51:15"}
9
- {"current_steps": 9, "total_steps": 125, "loss": 0.2196, "lr": 6.923076923076924e-05, "epoch": 0.35555555555555557, "percentage": 7.2, "elapsed_time": "0:03:57", "remaining_time": "0:50:57"}
10
- {"current_steps": 10, "total_steps": 125, "loss": 0.1439, "lr": 7.692307692307693e-05, "epoch": 0.3950617283950617, "percentage": 8.0, "elapsed_time": "0:04:24", "remaining_time": "0:50:40"}
11
- {"current_steps": 10, "total_steps": 125, "eval_loss": 0.13264411687850952, "epoch": 0.3950617283950617, "percentage": 8.0, "elapsed_time": "0:04:45", "remaining_time": "0:54:48"}
12
- {"current_steps": 11, "total_steps": 125, "loss": 0.1487, "lr": 8.461538461538461e-05, "epoch": 0.4345679012345679, "percentage": 8.8, "elapsed_time": "0:05:16", "remaining_time": "0:54:41"}
13
- {"current_steps": 12, "total_steps": 125, "loss": 0.1322, "lr": 9.230769230769232e-05, "epoch": 0.4740740740740741, "percentage": 9.6, "elapsed_time": "0:05:43", "remaining_time": "0:53:57"}
14
- {"current_steps": 13, "total_steps": 125, "loss": 0.1338, "lr": 0.0001, "epoch": 0.5135802469135803, "percentage": 10.4, "elapsed_time": "0:06:11", "remaining_time": "0:53:19"}
15
- {"current_steps": 14, "total_steps": 125, "loss": 0.1373, "lr": 9.998033131915266e-05, "epoch": 0.5530864197530864, "percentage": 11.2, "elapsed_time": "0:06:34", "remaining_time": "0:52:11"}
16
- {"current_steps": 15, "total_steps": 125, "loss": 0.1856, "lr": 9.992134075089084e-05, "epoch": 0.5925925925925926, "percentage": 12.0, "elapsed_time": "0:07:02", "remaining_time": "0:51:34"}
17
- {"current_steps": 16, "total_steps": 125, "loss": 0.1996, "lr": 9.982307470588098e-05, "epoch": 0.6320987654320988, "percentage": 12.8, "elapsed_time": "0:07:28", "remaining_time": "0:50:57"}
18
- {"current_steps": 17, "total_steps": 125, "loss": 0.1396, "lr": 9.968561049466214e-05, "epoch": 0.671604938271605, "percentage": 13.6, "elapsed_time": "0:07:58", "remaining_time": "0:50:39"}
19
- {"current_steps": 18, "total_steps": 125, "loss": 0.1335, "lr": 9.950905626682228e-05, "epoch": 0.7111111111111111, "percentage": 14.4, "elapsed_time": "0:08:23", "remaining_time": "0:49:54"}
20
- {"current_steps": 19, "total_steps": 125, "loss": 0.0606, "lr": 9.92935509259118e-05, "epoch": 0.7506172839506173, "percentage": 15.2, "elapsed_time": "0:08:52", "remaining_time": "0:49:29"}
21
- {"current_steps": 20, "total_steps": 125, "loss": 0.0809, "lr": 9.903926402016153e-05, "epoch": 0.7901234567901234, "percentage": 16.0, "elapsed_time": "0:09:19", "remaining_time": "0:48:56"}
22
- {"current_steps": 20, "total_steps": 125, "eval_loss": 0.0766303762793541, "epoch": 0.7901234567901234, "percentage": 16.0, "elapsed_time": "0:09:40", "remaining_time": "0:50:49"}
23
- {"current_steps": 21, "total_steps": 125, "loss": 0.0812, "lr": 9.874639560909117e-05, "epoch": 0.8296296296296296, "percentage": 16.8, "elapsed_time": "0:10:11", "remaining_time": "0:50:30"}
24
- {"current_steps": 22, "total_steps": 125, "loss": 0.1503, "lr": 9.841517610611309e-05, "epoch": 0.8691358024691358, "percentage": 17.6, "elapsed_time": "0:10:39", "remaining_time": "0:49:53"}
25
- {"current_steps": 23, "total_steps": 125, "loss": 0.171, "lr": 9.804586609725499e-05, "epoch": 0.908641975308642, "percentage": 18.4, "elapsed_time": "0:11:05", "remaining_time": "0:49:09"}
26
- {"current_steps": 24, "total_steps": 125, "loss": 0.0547, "lr": 9.763875613614482e-05, "epoch": 0.9481481481481482, "percentage": 19.2, "elapsed_time": "0:11:30", "remaining_time": "0:48:23"}
27
- {"current_steps": 25, "total_steps": 125, "loss": 0.223, "lr": 9.719416651541839e-05, "epoch": 0.9876543209876543, "percentage": 20.0, "elapsed_time": "0:11:57", "remaining_time": "0:47:48"}
28
- {"current_steps": 26, "total_steps": 125, "loss": 0.2313, "lr": 9.671244701472999e-05, "epoch": 1.0271604938271606, "percentage": 20.8, "elapsed_time": "0:12:25", "remaining_time": "0:47:17"}
29
- {"current_steps": 27, "total_steps": 125, "loss": 0.0629, "lr": 9.619397662556435e-05, "epoch": 1.0666666666666667, "percentage": 21.6, "elapsed_time": "0:12:50", "remaining_time": "0:46:38"}
30
- {"current_steps": 28, "total_steps": 125, "loss": 0.1191, "lr": 9.563916325306594e-05, "epoch": 1.106172839506173, "percentage": 22.4, "elapsed_time": "0:13:19", "remaining_time": "0:46:08"}
31
- {"current_steps": 29, "total_steps": 125, "loss": 0.0748, "lr": 9.504844339512095e-05, "epoch": 1.145679012345679, "percentage": 23.2, "elapsed_time": "0:13:45", "remaining_time": "0:45:33"}
32
- {"current_steps": 30, "total_steps": 125, "loss": 0.0712, "lr": 9.442228179894362e-05, "epoch": 1.1851851851851851, "percentage": 24.0, "elapsed_time": "0:14:12", "remaining_time": "0:44:58"}
33
- {"current_steps": 30, "total_steps": 125, "eval_loss": 0.0628211572766304, "epoch": 1.1851851851851851, "percentage": 24.0, "elapsed_time": "0:14:33", "remaining_time": "0:46:06"}
34
- {"current_steps": 31, "total_steps": 125, "loss": 0.1239, "lr": 9.376117109543769e-05, "epoch": 1.2246913580246914, "percentage": 24.8, "elapsed_time": "0:15:06", "remaining_time": "0:45:48"}
35
- {"current_steps": 32, "total_steps": 125, "loss": 0.1279, "lr": 9.306563141162046e-05, "epoch": 1.2641975308641975, "percentage": 25.6, "elapsed_time": "0:15:31", "remaining_time": "0:45:07"}
36
- {"current_steps": 33, "total_steps": 125, "loss": 0.121, "lr": 9.233620996141421e-05, "epoch": 1.3037037037037038, "percentage": 26.4, "elapsed_time": "0:15:59", "remaining_time": "0:44:33"}
37
- {"current_steps": 34, "total_steps": 125, "loss": 0.1291, "lr": 9.157348061512727e-05, "epoch": 1.34320987654321, "percentage": 27.2, "elapsed_time": "0:16:26", "remaining_time": "0:44:01"}
38
- {"current_steps": 35, "total_steps": 125, "loss": 0.1045, "lr": 9.077804344796302e-05, "epoch": 1.382716049382716, "percentage": 28.0, "elapsed_time": "0:16:53", "remaining_time": "0:43:25"}
39
- {"current_steps": 36, "total_steps": 125, "loss": 0.0558, "lr": 8.995052426791247e-05, "epoch": 1.4222222222222223, "percentage": 28.8, "elapsed_time": "0:17:16", "remaining_time": "0:42:43"}
40
- {"current_steps": 37, "total_steps": 125, "loss": 0.0944, "lr": 8.90915741234015e-05, "epoch": 1.4617283950617284, "percentage": 29.6, "elapsed_time": "0:17:46", "remaining_time": "0:42:15"}
41
- {"current_steps": 38, "total_steps": 125, "loss": 0.1417, "lr": 8.820186879108038e-05, "epoch": 1.5012345679012347, "percentage": 30.4, "elapsed_time": "0:18:12", "remaining_time": "0:41:42"}
42
- {"current_steps": 39, "total_steps": 125, "loss": 0.068, "lr": 8.728210824415827e-05, "epoch": 1.5407407407407407, "percentage": 31.2, "elapsed_time": "0:18:38", "remaining_time": "0:41:07"}
43
- {"current_steps": 40, "total_steps": 125, "loss": 0.0819, "lr": 8.633301610170135e-05, "epoch": 1.5802469135802468, "percentage": 32.0, "elapsed_time": "0:19:05", "remaining_time": "0:40:34"}
44
- {"current_steps": 40, "total_steps": 125, "eval_loss": 0.056919973343610764, "epoch": 1.5802469135802468, "percentage": 32.0, "elapsed_time": "0:19:27", "remaining_time": "0:41:20"}
45
- {"current_steps": 41, "total_steps": 125, "loss": 0.0991, "lr": 8.535533905932738e-05, "epoch": 1.6197530864197531, "percentage": 32.8, "elapsed_time": "0:19:57", "remaining_time": "0:40:53"}
46
- {"current_steps": 42, "total_steps": 125, "loss": 0.1049, "lr": 8.434984630174509e-05, "epoch": 1.6592592592592592, "percentage": 33.6, "elapsed_time": "0:20:23", "remaining_time": "0:40:17"}
47
- {"current_steps": 43, "total_steps": 125, "loss": 0.0925, "lr": 8.33173288976002e-05, "epoch": 1.6987654320987655, "percentage": 34.4, "elapsed_time": "0:20:50", "remaining_time": "0:39:44"}
48
- {"current_steps": 44, "total_steps": 125, "loss": 0.0848, "lr": 8.225859917710439e-05, "epoch": 1.7382716049382716, "percentage": 35.2, "elapsed_time": "0:21:17", "remaining_time": "0:39:12"}
49
- {"current_steps": 45, "total_steps": 125, "loss": 0.0974, "lr": 8.117449009293668e-05, "epoch": 1.7777777777777777, "percentage": 36.0, "elapsed_time": "0:21:44", "remaining_time": "0:38:38"}
50
- {"current_steps": 46, "total_steps": 125, "loss": 0.0807, "lr": 8.006585456492029e-05, "epoch": 1.817283950617284, "percentage": 36.8, "elapsed_time": "0:22:07", "remaining_time": "0:37:59"}
51
- {"current_steps": 47, "total_steps": 125, "loss": 0.0914, "lr": 7.89335648089903e-05, "epoch": 1.8567901234567903, "percentage": 37.6, "elapsed_time": "0:22:35", "remaining_time": "0:37:29"}
52
- {"current_steps": 48, "total_steps": 125, "loss": 0.09, "lr": 7.777851165098012e-05, "epoch": 1.8962962962962964, "percentage": 38.4, "elapsed_time": "0:23:01", "remaining_time": "0:36:55"}
53
- {"current_steps": 49, "total_steps": 125, "loss": 0.0619, "lr": 7.660160382576683e-05, "epoch": 1.9358024691358025, "percentage": 39.2, "elapsed_time": "0:23:28", "remaining_time": "0:36:24"}
54
- {"current_steps": 50, "total_steps": 125, "loss": 0.0566, "lr": 7.540376726232648e-05, "epoch": 1.9753086419753085, "percentage": 40.0, "elapsed_time": "0:23:55", "remaining_time": "0:35:53"}
55
- {"current_steps": 50, "total_steps": 125, "eval_loss": 0.05362074822187424, "epoch": 1.9753086419753085, "percentage": 40.0, "elapsed_time": "0:24:17", "remaining_time": "0:36:26"}
56
- {"current_steps": 51, "total_steps": 125, "loss": 0.2196, "lr": 7.4185944355262e-05, "epoch": 2.0148148148148146, "percentage": 40.8, "elapsed_time": "0:24:49", "remaining_time": "0:36:01"}
57
- {"current_steps": 52, "total_steps": 125, "loss": 0.0867, "lr": 7.294909322337689e-05, "epoch": 2.054320987654321, "percentage": 41.6, "elapsed_time": "0:25:16", "remaining_time": "0:35:28"}
58
- {"current_steps": 53, "total_steps": 125, "loss": 0.1006, "lr": 7.169418695587791e-05, "epoch": 2.093827160493827, "percentage": 42.4, "elapsed_time": "0:25:43", "remaining_time": "0:34:56"}
59
- {"current_steps": 54, "total_steps": 125, "loss": 0.1168, "lr": 7.042221284679982e-05, "epoch": 2.1333333333333333, "percentage": 43.2, "elapsed_time": "0:26:09", "remaining_time": "0:34:23"}
60
- {"current_steps": 55, "total_steps": 125, "loss": 0.1033, "lr": 6.91341716182545e-05, "epoch": 2.1728395061728394, "percentage": 44.0, "elapsed_time": "0:26:33", "remaining_time": "0:33:48"}
61
- {"current_steps": 56, "total_steps": 125, "loss": 0.0952, "lr": 6.783107663311565e-05, "epoch": 2.212345679012346, "percentage": 44.8, "elapsed_time": "0:27:00", "remaining_time": "0:33:16"}
62
- {"current_steps": 57, "total_steps": 125, "loss": 0.101, "lr": 6.651395309775837e-05, "epoch": 2.251851851851852, "percentage": 45.6, "elapsed_time": "0:27:28", "remaining_time": "0:32:46"}
63
- {"current_steps": 58, "total_steps": 125, "loss": 0.1318, "lr": 6.518383725548074e-05, "epoch": 2.291358024691358, "percentage": 46.4, "elapsed_time": "0:27:53", "remaining_time": "0:32:13"}
64
- {"current_steps": 59, "total_steps": 125, "loss": 0.0725, "lr": 6.384177557124247e-05, "epoch": 2.330864197530864, "percentage": 47.2, "elapsed_time": "0:28:19", "remaining_time": "0:31:40"}
65
- {"current_steps": 60, "total_steps": 125, "loss": 0.0224, "lr": 6.248882390836135e-05, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:28:45", "remaining_time": "0:31:08"}
66
- {"current_steps": 60, "total_steps": 125, "eval_loss": 0.05220804363489151, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:29:06", "remaining_time": "0:31:32"}
67
- {"current_steps": 61, "total_steps": 125, "loss": 0.0616, "lr": 6.112604669781572e-05, "epoch": 2.4098765432098768, "percentage": 48.8, "elapsed_time": "0:29:38", "remaining_time": "0:31:06"}
68
- {"current_steps": 62, "total_steps": 125, "loss": 0.0636, "lr": 5.9754516100806423e-05, "epoch": 2.449382716049383, "percentage": 49.6, "elapsed_time": "0:30:05", "remaining_time": "0:30:34"}
69
- {"current_steps": 63, "total_steps": 125, "loss": 0.1148, "lr": 5.837531116523682e-05, "epoch": 2.488888888888889, "percentage": 50.4, "elapsed_time": "0:30:31", "remaining_time": "0:30:02"}
70
- {"current_steps": 64, "total_steps": 125, "loss": 0.0568, "lr": 5.698951697677498e-05, "epoch": 2.528395061728395, "percentage": 51.2, "elapsed_time": "0:30:59", "remaining_time": "0:29:31"}
71
- {"current_steps": 65, "total_steps": 125, "loss": 0.1027, "lr": 5.559822380516539e-05, "epoch": 2.567901234567901, "percentage": 52.0, "elapsed_time": "0:31:25", "remaining_time": "0:29:00"}
72
- {"current_steps": 66, "total_steps": 125, "loss": 0.1131, "lr": 5.420252624646238e-05, "epoch": 2.6074074074074076, "percentage": 52.8, "elapsed_time": "0:31:52", "remaining_time": "0:28:29"}
73
- {"current_steps": 67, "total_steps": 125, "loss": 0.0755, "lr": 5.2803522361859594e-05, "epoch": 2.6469135802469137, "percentage": 53.6, "elapsed_time": "0:32:19", "remaining_time": "0:27:59"}
74
- {"current_steps": 68, "total_steps": 125, "loss": 0.067, "lr": 5.140231281379345e-05, "epoch": 2.68641975308642, "percentage": 54.4, "elapsed_time": "0:32:48", "remaining_time": "0:27:30"}
75
- {"current_steps": 69, "total_steps": 125, "loss": 0.0524, "lr": 5e-05, "epoch": 2.725925925925926, "percentage": 55.2, "elapsed_time": "0:33:14", "remaining_time": "0:26:59"}
76
- {"current_steps": 70, "total_steps": 125, "loss": 0.0542, "lr": 4.859768718620656e-05, "epoch": 2.765432098765432, "percentage": 56.0, "elapsed_time": "0:33:43", "remaining_time": "0:26:29"}
77
- {"current_steps": 70, "total_steps": 125, "eval_loss": 0.05078903213143349, "epoch": 2.765432098765432, "percentage": 56.0, "elapsed_time": "0:34:04", "remaining_time": "0:26:46"}
78
- {"current_steps": 71, "total_steps": 125, "loss": 0.0836, "lr": 4.7196477638140404e-05, "epoch": 2.8049382716049385, "percentage": 56.8, "elapsed_time": "0:34:37", "remaining_time": "0:26:19"}
79
- {"current_steps": 72, "total_steps": 125, "loss": 0.043, "lr": 4.579747375353763e-05, "epoch": 2.8444444444444446, "percentage": 57.6, "elapsed_time": "0:35:02", "remaining_time": "0:25:47"}
80
- {"current_steps": 73, "total_steps": 125, "loss": 0.1009, "lr": 4.4401776194834613e-05, "epoch": 2.8839506172839506, "percentage": 58.4, "elapsed_time": "0:35:28", "remaining_time": "0:25:16"}
81
- {"current_steps": 74, "total_steps": 125, "loss": 0.0785, "lr": 4.3010483023225045e-05, "epoch": 2.9234567901234567, "percentage": 59.2, "elapsed_time": "0:35:53", "remaining_time": "0:24:44"}
82
- {"current_steps": 75, "total_steps": 125, "loss": 0.0766, "lr": 4.162468883476319e-05, "epoch": 2.962962962962963, "percentage": 60.0, "elapsed_time": "0:36:20", "remaining_time": "0:24:13"}
83
- {"current_steps": 76, "total_steps": 125, "loss": 0.1528, "lr": 4.0245483899193595e-05, "epoch": 3.0024691358024693, "percentage": 60.8, "elapsed_time": "0:36:46", "remaining_time": "0:23:42"}
84
- {"current_steps": 77, "total_steps": 125, "loss": 0.0984, "lr": 3.887395330218429e-05, "epoch": 3.0419753086419754, "percentage": 61.6, "elapsed_time": "0:37:11", "remaining_time": "0:23:11"}
85
- {"current_steps": 78, "total_steps": 125, "loss": 0.0575, "lr": 3.7511176091638653e-05, "epoch": 3.0814814814814815, "percentage": 62.4, "elapsed_time": "0:37:37", "remaining_time": "0:22:40"}
86
- {"current_steps": 79, "total_steps": 125, "loss": 0.1051, "lr": 3.6158224428757535e-05, "epoch": 3.1209876543209876, "percentage": 63.2, "elapsed_time": "0:38:03", "remaining_time": "0:22:09"}
87
- {"current_steps": 80, "total_steps": 125, "loss": 0.0704, "lr": 3.4816162744519263e-05, "epoch": 3.1604938271604937, "percentage": 64.0, "elapsed_time": "0:38:27", "remaining_time": "0:21:38"}
88
- {"current_steps": 80, "total_steps": 125, "eval_loss": 0.05049747973680496, "epoch": 3.1604938271604937, "percentage": 64.0, "elapsed_time": "0:38:49", "remaining_time": "0:21:50"}
89
- {"current_steps": 81, "total_steps": 125, "loss": 0.0672, "lr": 3.3486046902241664e-05, "epoch": 3.2, "percentage": 64.8, "elapsed_time": "0:39:19", "remaining_time": "0:21:21"}
90
- {"current_steps": 82, "total_steps": 125, "loss": 0.0672, "lr": 3.216892336688435e-05, "epoch": 3.2395061728395063, "percentage": 65.6, "elapsed_time": "0:39:47", "remaining_time": "0:20:51"}
91
- {"current_steps": 83, "total_steps": 125, "loss": 0.087, "lr": 3.086582838174551e-05, "epoch": 3.2790123456790123, "percentage": 66.4, "elapsed_time": "0:40:11", "remaining_time": "0:20:20"}
92
- {"current_steps": 84, "total_steps": 125, "loss": 0.111, "lr": 2.9577787153200197e-05, "epoch": 3.3185185185185184, "percentage": 67.2, "elapsed_time": "0:40:37", "remaining_time": "0:19:49"}
93
- {"current_steps": 85, "total_steps": 125, "loss": 0.0597, "lr": 2.8305813044122097e-05, "epoch": 3.3580246913580245, "percentage": 68.0, "elapsed_time": "0:41:04", "remaining_time": "0:19:19"}
94
- {"current_steps": 86, "total_steps": 125, "loss": 0.0588, "lr": 2.705090677662311e-05, "epoch": 3.397530864197531, "percentage": 68.8, "elapsed_time": "0:41:30", "remaining_time": "0:18:49"}
95
- {"current_steps": 87, "total_steps": 125, "loss": 0.022, "lr": 2.581405564473801e-05, "epoch": 3.437037037037037, "percentage": 69.6, "elapsed_time": "0:41:59", "remaining_time": "0:18:20"}
96
- {"current_steps": 88, "total_steps": 125, "loss": 0.0512, "lr": 2.459623273767354e-05, "epoch": 3.476543209876543, "percentage": 70.4, "elapsed_time": "0:42:26", "remaining_time": "0:17:50"}
97
- {"current_steps": 89, "total_steps": 125, "loss": 0.0779, "lr": 2.3398396174233178e-05, "epoch": 3.5160493827160493, "percentage": 71.2, "elapsed_time": "0:42:54", "remaining_time": "0:17:21"}
98
- {"current_steps": 90, "total_steps": 125, "loss": 0.1065, "lr": 2.2221488349019903e-05, "epoch": 3.5555555555555554, "percentage": 72.0, "elapsed_time": "0:43:20", "remaining_time": "0:16:51"}
99
- {"current_steps": 90, "total_steps": 125, "eval_loss": 0.0507526732981205, "epoch": 3.5555555555555554, "percentage": 72.0, "elapsed_time": "0:43:41", "remaining_time": "0:16:59"}
100
- {"current_steps": 91, "total_steps": 125, "loss": 0.0986, "lr": 2.1066435191009715e-05, "epoch": 3.595061728395062, "percentage": 72.8, "elapsed_time": "0:44:14", "remaining_time": "0:16:31"}
101
- {"current_steps": 92, "total_steps": 125, "loss": 0.059, "lr": 1.9934145435079702e-05, "epoch": 3.634567901234568, "percentage": 73.6, "elapsed_time": "0:44:41", "remaining_time": "0:16:01"}
102
- {"current_steps": 93, "total_steps": 125, "loss": 0.0638, "lr": 1.8825509907063327e-05, "epoch": 3.674074074074074, "percentage": 74.4, "elapsed_time": "0:45:12", "remaining_time": "0:15:33"}
103
- {"current_steps": 94, "total_steps": 125, "loss": 0.0602, "lr": 1.774140082289563e-05, "epoch": 3.71358024691358, "percentage": 75.2, "elapsed_time": "0:45:36", "remaining_time": "0:15:02"}
104
- {"current_steps": 95, "total_steps": 125, "loss": 0.0802, "lr": 1.6682671102399805e-05, "epoch": 3.753086419753086, "percentage": 76.0, "elapsed_time": "0:46:04", "remaining_time": "0:14:33"}
105
- {"current_steps": 96, "total_steps": 125, "loss": 0.0545, "lr": 1.5650153698254916e-05, "epoch": 3.7925925925925927, "percentage": 76.8, "elapsed_time": "0:46:29", "remaining_time": "0:14:02"}
106
- {"current_steps": 97, "total_steps": 125, "loss": 0.082, "lr": 1.4644660940672627e-05, "epoch": 3.832098765432099, "percentage": 77.6, "elapsed_time": "0:46:54", "remaining_time": "0:13:32"}
107
- {"current_steps": 98, "total_steps": 125, "loss": 0.1217, "lr": 1.3666983898298657e-05, "epoch": 3.871604938271605, "percentage": 78.4, "elapsed_time": "0:47:20", "remaining_time": "0:13:02"}
108
- {"current_steps": 99, "total_steps": 125, "loss": 0.1271, "lr": 1.2717891755841722e-05, "epoch": 3.911111111111111, "percentage": 79.2, "elapsed_time": "0:47:50", "remaining_time": "0:12:33"}
109
- {"current_steps": 100, "total_steps": 125, "loss": 0.0613, "lr": 1.1798131208919627e-05, "epoch": 3.950617283950617, "percentage": 80.0, "elapsed_time": "0:48:14", "remaining_time": "0:12:03"}
110
- {"current_steps": 100, "total_steps": 125, "eval_loss": 0.05035708099603653, "epoch": 3.950617283950617, "percentage": 80.0, "elapsed_time": "0:48:36", "remaining_time": "0:12:09"}
111
- {"current_steps": 101, "total_steps": 125, "loss": 0.0817, "lr": 1.090842587659851e-05, "epoch": 3.9901234567901236, "percentage": 80.8, "elapsed_time": "0:49:10", "remaining_time": "0:11:41"}
112
- {"current_steps": 102, "total_steps": 125, "loss": 0.1086, "lr": 1.004947573208756e-05, "epoch": 4.029629629629629, "percentage": 81.6, "elapsed_time": "0:49:36", "remaining_time": "0:11:11"}
113
- {"current_steps": 103, "total_steps": 125, "loss": 0.1082, "lr": 9.221956552036992e-06, "epoch": 4.069135802469136, "percentage": 82.4, "elapsed_time": "0:50:03", "remaining_time": "0:10:41"}
114
- {"current_steps": 104, "total_steps": 125, "loss": 0.0117, "lr": 8.426519384872733e-06, "epoch": 4.108641975308642, "percentage": 83.2, "elapsed_time": "0:50:32", "remaining_time": "0:10:12"}
115
- {"current_steps": 105, "total_steps": 125, "loss": 0.0907, "lr": 7.663790038585793e-06, "epoch": 4.148148148148148, "percentage": 84.0, "elapsed_time": "0:50:58", "remaining_time": "0:09:42"}
116
- {"current_steps": 106, "total_steps": 125, "loss": 0.0606, "lr": 6.934368588379553e-06, "epoch": 4.187654320987654, "percentage": 84.8, "elapsed_time": "0:51:26", "remaining_time": "0:09:13"}
117
- {"current_steps": 107, "total_steps": 125, "loss": 0.1158, "lr": 6.238828904562316e-06, "epoch": 4.22716049382716, "percentage": 85.6, "elapsed_time": "0:51:55", "remaining_time": "0:08:44"}
118
- {"current_steps": 108, "total_steps": 125, "loss": 0.0746, "lr": 5.577718201056392e-06, "epoch": 4.266666666666667, "percentage": 86.4, "elapsed_time": "0:52:20", "remaining_time": "0:08:14"}
119
- {"current_steps": 109, "total_steps": 125, "loss": 0.0622, "lr": 4.951556604879048e-06, "epoch": 4.306172839506173, "percentage": 87.2, "elapsed_time": "0:52:47", "remaining_time": "0:07:45"}
120
- {"current_steps": 110, "total_steps": 125, "loss": 0.0526, "lr": 4.360836746934055e-06, "epoch": 4.345679012345679, "percentage": 88.0, "elapsed_time": "0:53:15", "remaining_time": "0:07:15"}
121
- {"current_steps": 110, "total_steps": 125, "eval_loss": 0.050025228410959244, "epoch": 4.345679012345679, "percentage": 88.0, "elapsed_time": "0:53:36", "remaining_time": "0:07:18"}
122
- {"current_steps": 111, "total_steps": 125, "loss": 0.0814, "lr": 3.8060233744356633e-06, "epoch": 4.385185185185185, "percentage": 88.8, "elapsed_time": "0:54:09", "remaining_time": "0:06:49"}
123
- {"current_steps": 112, "total_steps": 125, "loss": 0.0414, "lr": 3.2875529852700147e-06, "epoch": 4.424691358024692, "percentage": 89.6, "elapsed_time": "0:54:38", "remaining_time": "0:06:20"}
124
- {"current_steps": 113, "total_steps": 125, "loss": 0.0657, "lr": 2.8058334845816213e-06, "epoch": 4.4641975308641975, "percentage": 90.4, "elapsed_time": "0:55:02", "remaining_time": "0:05:50"}
125
- {"current_steps": 114, "total_steps": 125, "loss": 0.0963, "lr": 2.361243863855184e-06, "epoch": 4.503703703703704, "percentage": 91.2, "elapsed_time": "0:55:29", "remaining_time": "0:05:21"}
126
- {"current_steps": 115, "total_steps": 125, "loss": 0.1072, "lr": 1.9541339027450256e-06, "epoch": 4.54320987654321, "percentage": 92.0, "elapsed_time": "0:55:56", "remaining_time": "0:04:51"}
127
- {"current_steps": 116, "total_steps": 125, "loss": 0.0651, "lr": 1.584823893886933e-06, "epoch": 4.582716049382716, "percentage": 92.8, "elapsed_time": "0:56:22", "remaining_time": "0:04:22"}
128
- {"current_steps": 117, "total_steps": 125, "loss": 0.0652, "lr": 1.2536043909088191e-06, "epoch": 4.622222222222222, "percentage": 93.6, "elapsed_time": "0:56:49", "remaining_time": "0:03:53"}
129
- {"current_steps": 118, "total_steps": 125, "loss": 0.064, "lr": 9.607359798384785e-07, "epoch": 4.661728395061728, "percentage": 94.4, "elapsed_time": "0:57:13", "remaining_time": "0:03:23"}
130
- {"current_steps": 119, "total_steps": 125, "loss": 0.0533, "lr": 7.064490740882057e-07, "epoch": 4.701234567901235, "percentage": 95.2, "elapsed_time": "0:57:40", "remaining_time": "0:02:54"}
131
- {"current_steps": 120, "total_steps": 125, "loss": 0.057, "lr": 4.909437331777179e-07, "epoch": 4.7407407407407405, "percentage": 96.0, "elapsed_time": "0:58:08", "remaining_time": "0:02:25"}
132
- {"current_steps": 120, "total_steps": 125, "eval_loss": 0.05005127191543579, "epoch": 4.7407407407407405, "percentage": 96.0, "elapsed_time": "0:58:29", "remaining_time": "0:02:26"}
133
- {"current_steps": 121, "total_steps": 125, "loss": 0.0811, "lr": 3.143895053378698e-07, "epoch": 4.780246913580247, "percentage": 96.8, "elapsed_time": "0:59:03", "remaining_time": "0:01:57"}
134
- {"current_steps": 122, "total_steps": 125, "loss": 0.0958, "lr": 1.7692529411904578e-07, "epoch": 4.8197530864197535, "percentage": 97.6, "elapsed_time": "0:59:29", "remaining_time": "0:01:27"}
135
- {"current_steps": 123, "total_steps": 125, "loss": 0.1079, "lr": 7.865924910916977e-08, "epoch": 4.859259259259259, "percentage": 98.4, "elapsed_time": "0:59:54", "remaining_time": "0:00:58"}
136
- {"current_steps": 124, "total_steps": 125, "loss": 0.0238, "lr": 1.9668680847356735e-08, "epoch": 4.898765432098766, "percentage": 99.2, "elapsed_time": "1:00:21", "remaining_time": "0:00:29"}
137
- {"current_steps": 125, "total_steps": 125, "loss": 0.0797, "lr": 0.0, "epoch": 4.938271604938271, "percentage": 100.0, "elapsed_time": "1:00:46", "remaining_time": "0:00:00"}
138
- {"current_steps": 125, "total_steps": 125, "epoch": 4.938271604938271, "percentage": 100.0, "elapsed_time": "1:00:51", "remaining_time": "0:00:00"}
 
1
+ {"current_steps": 1, "total_steps": 125, "loss": 0.1412, "lr": 7.692307692307694e-06, "epoch": 0.03950617283950617, "percentage": 0.8, "elapsed_time": "0:00:28", "remaining_time": "0:58:12"}
2
+ {"current_steps": 2, "total_steps": 125, "loss": 0.1086, "lr": 1.5384615384615387e-05, "epoch": 0.07901234567901234, "percentage": 1.6, "elapsed_time": "0:01:08", "remaining_time": "1:10:20"}
3
+ {"current_steps": 3, "total_steps": 125, "loss": 0.1358, "lr": 2.307692307692308e-05, "epoch": 0.11851851851851852, "percentage": 2.4, "elapsed_time": "0:01:35", "remaining_time": "1:04:45"}
4
+ {"current_steps": 4, "total_steps": 125, "loss": 0.1104, "lr": 3.0769230769230774e-05, "epoch": 0.1580246913580247, "percentage": 3.2, "elapsed_time": "0:02:19", "remaining_time": "1:10:34"}
5
+ {"current_steps": 5, "total_steps": 125, "loss": 0.0977, "lr": 3.846153846153846e-05, "epoch": 0.19753086419753085, "percentage": 4.0, "elapsed_time": "0:03:10", "remaining_time": "1:16:14"}
6
+ {"current_steps": 6, "total_steps": 125, "loss": 0.1038, "lr": 4.615384615384616e-05, "epoch": 0.23703703703703705, "percentage": 4.8, "elapsed_time": "0:03:59", "remaining_time": "1:19:11"}
7
+ {"current_steps": 7, "total_steps": 125, "loss": 0.1097, "lr": 5.384615384615385e-05, "epoch": 0.2765432098765432, "percentage": 5.6, "elapsed_time": "0:04:41", "remaining_time": "1:19:08"}
8
+ {"current_steps": 8, "total_steps": 125, "loss": 0.0907, "lr": 6.153846153846155e-05, "epoch": 0.3160493827160494, "percentage": 6.4, "elapsed_time": "0:05:33", "remaining_time": "1:21:11"}
9
+ {"current_steps": 9, "total_steps": 125, "loss": 0.0835, "lr": 6.923076923076924e-05, "epoch": 0.35555555555555557, "percentage": 7.2, "elapsed_time": "0:06:25", "remaining_time": "1:22:52"}
10
+ {"current_steps": 10, "total_steps": 125, "loss": 0.0816, "lr": 7.692307692307693e-05, "epoch": 0.3950617283950617, "percentage": 8.0, "elapsed_time": "0:07:01", "remaining_time": "1:20:50"}
11
+ {"current_steps": 10, "total_steps": 125, "eval_loss": 0.08752671629190445, "epoch": 0.3950617283950617, "percentage": 8.0, "elapsed_time": "0:07:28", "remaining_time": "1:26:03"}
12
+ {"current_steps": 11, "total_steps": 125, "loss": 0.0813, "lr": 8.461538461538461e-05, "epoch": 0.4345679012345679, "percentage": 8.8, "elapsed_time": "0:08:18", "remaining_time": "1:26:07"}
13
+ {"current_steps": 12, "total_steps": 125, "loss": 0.0706, "lr": 9.230769230769232e-05, "epoch": 0.4740740740740741, "percentage": 9.6, "elapsed_time": "0:08:59", "remaining_time": "1:24:36"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e573ff6dc99963c407e557d7bf52943b257d4e2e9f088f8dd75e52281c45009c
3
  size 5624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eea5152542bfcb2345a3467ef41018b38b8f98a2306ada3b5e81a2cea817dbf
3
  size 5624