furmaniak commited on
Commit
1150914
·
verified ·
1 Parent(s): 3d53b59

Model save

Browse files
Files changed (3) hide show
  1. README.md +1 -1
  2. trainer_log.jsonl +1 -158
  3. training_args.bin +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # qwen2.5-32b-openalex
18
 
19
- This model is a fine-tuned version of [Qwen/Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) on the openalex dataset.
20
 
21
  ## Model description
22
 
 
16
 
17
  # qwen2.5-32b-openalex
18
 
19
+ This model is a fine-tuned version of [Qwen/Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) on an unknown dataset.
20
 
21
  ## Model description
22
 
trainer_log.jsonl CHANGED
@@ -1,158 +1 @@
1
- {"current_steps": 401, "total_steps": 557, "loss": 1.5168, "lr": 2e-05, "epoch": 0.7192825112107624, "percentage": 71.99, "elapsed_time": "0:06:53", "remaining_time": "0:02:41"}
2
- {"current_steps": 402, "total_steps": 557, "loss": 1.5175, "lr": 2e-05, "epoch": 0.7210762331838565, "percentage": 72.17, "elapsed_time": "0:13:41", "remaining_time": "0:05:16"}
3
- {"current_steps": 403, "total_steps": 557, "loss": 1.5211, "lr": 2e-05, "epoch": 0.7228699551569506, "percentage": 72.35, "elapsed_time": "0:20:23", "remaining_time": "0:07:47"}
4
- {"current_steps": 404, "total_steps": 557, "loss": 1.5228, "lr": 2e-05, "epoch": 0.7246636771300449, "percentage": 72.53, "elapsed_time": "0:27:04", "remaining_time": "0:10:15"}
5
- {"current_steps": 405, "total_steps": 557, "loss": 1.522, "lr": 2e-05, "epoch": 0.726457399103139, "percentage": 72.71, "elapsed_time": "0:33:46", "remaining_time": "0:12:40"}
6
- {"current_steps": 406, "total_steps": 557, "loss": 1.525, "lr": 2e-05, "epoch": 0.7282511210762331, "percentage": 72.89, "elapsed_time": "0:40:27", "remaining_time": "0:15:02"}
7
- {"current_steps": 407, "total_steps": 557, "loss": 1.5172, "lr": 2e-05, "epoch": 0.7300448430493274, "percentage": 73.07, "elapsed_time": "0:47:12", "remaining_time": "0:17:23"}
8
- {"current_steps": 408, "total_steps": 557, "loss": 1.5246, "lr": 2e-05, "epoch": 0.7318385650224215, "percentage": 73.25, "elapsed_time": "0:53:49", "remaining_time": "0:19:39"}
9
- {"current_steps": 409, "total_steps": 557, "loss": 1.5132, "lr": 2e-05, "epoch": 0.7336322869955157, "percentage": 73.43, "elapsed_time": "1:00:26", "remaining_time": "0:21:52"}
10
- {"current_steps": 410, "total_steps": 557, "loss": 1.5248, "lr": 2e-05, "epoch": 0.7354260089686099, "percentage": 73.61, "elapsed_time": "1:07:01", "remaining_time": "0:24:01"}
11
- {"current_steps": 411, "total_steps": 557, "loss": 1.5196, "lr": 2e-05, "epoch": 0.737219730941704, "percentage": 73.79, "elapsed_time": "1:13:40", "remaining_time": "0:26:10"}
12
- {"current_steps": 412, "total_steps": 557, "loss": 1.5096, "lr": 2e-05, "epoch": 0.7390134529147983, "percentage": 73.97, "elapsed_time": "1:20:15", "remaining_time": "0:28:14"}
13
- {"current_steps": 413, "total_steps": 557, "loss": 1.5162, "lr": 2e-05, "epoch": 0.7408071748878924, "percentage": 74.15, "elapsed_time": "1:26:59", "remaining_time": "0:30:19"}
14
- {"current_steps": 414, "total_steps": 557, "loss": 1.5189, "lr": 2e-05, "epoch": 0.7426008968609865, "percentage": 74.33, "elapsed_time": "1:33:36", "remaining_time": "0:32:19"}
15
- {"current_steps": 415, "total_steps": 557, "loss": 1.5194, "lr": 2e-05, "epoch": 0.7443946188340808, "percentage": 74.51, "elapsed_time": "1:40:13", "remaining_time": "0:34:17"}
16
- {"current_steps": 416, "total_steps": 557, "loss": 1.5191, "lr": 2e-05, "epoch": 0.7461883408071749, "percentage": 74.69, "elapsed_time": "1:46:52", "remaining_time": "0:36:13"}
17
- {"current_steps": 417, "total_steps": 557, "loss": 1.5177, "lr": 2e-05, "epoch": 0.747982062780269, "percentage": 74.87, "elapsed_time": "1:53:30", "remaining_time": "0:38:06"}
18
- {"current_steps": 418, "total_steps": 557, "loss": 1.514, "lr": 2e-05, "epoch": 0.7497757847533633, "percentage": 75.04, "elapsed_time": "2:00:08", "remaining_time": "0:39:56"}
19
- {"current_steps": 419, "total_steps": 557, "loss": 1.5154, "lr": 2e-05, "epoch": 0.7515695067264574, "percentage": 75.22, "elapsed_time": "2:06:46", "remaining_time": "0:41:45"}
20
- {"current_steps": 420, "total_steps": 557, "loss": 1.5223, "lr": 2e-05, "epoch": 0.7533632286995515, "percentage": 75.4, "elapsed_time": "2:13:24", "remaining_time": "0:43:30"}
21
- {"current_steps": 421, "total_steps": 557, "loss": 1.5152, "lr": 2e-05, "epoch": 0.7551569506726458, "percentage": 75.58, "elapsed_time": "2:20:00", "remaining_time": "0:45:13"}
22
- {"current_steps": 422, "total_steps": 557, "loss": 1.5185, "lr": 2e-05, "epoch": 0.7569506726457399, "percentage": 75.76, "elapsed_time": "2:26:37", "remaining_time": "0:46:54"}
23
- {"current_steps": 423, "total_steps": 557, "loss": 1.4986, "lr": 2e-05, "epoch": 0.758744394618834, "percentage": 75.94, "elapsed_time": "2:33:15", "remaining_time": "0:48:33"}
24
- {"current_steps": 424, "total_steps": 557, "loss": 1.5071, "lr": 2e-05, "epoch": 0.7605381165919283, "percentage": 76.12, "elapsed_time": "2:39:53", "remaining_time": "0:50:09"}
25
- {"current_steps": 425, "total_steps": 557, "loss": 1.5006, "lr": 2e-05, "epoch": 0.7623318385650224, "percentage": 76.3, "elapsed_time": "2:46:32", "remaining_time": "0:51:43"}
26
- {"current_steps": 426, "total_steps": 557, "loss": 1.5201, "lr": 2e-05, "epoch": 0.7641255605381166, "percentage": 76.48, "elapsed_time": "2:53:09", "remaining_time": "0:53:14"}
27
- {"current_steps": 427, "total_steps": 557, "loss": 1.5213, "lr": 2e-05, "epoch": 0.7659192825112108, "percentage": 76.66, "elapsed_time": "2:59:46", "remaining_time": "0:54:44"}
28
- {"current_steps": 428, "total_steps": 557, "loss": 1.5178, "lr": 2e-05, "epoch": 0.7677130044843049, "percentage": 76.84, "elapsed_time": "3:06:23", "remaining_time": "0:56:10"}
29
- {"current_steps": 429, "total_steps": 557, "loss": 1.5085, "lr": 2e-05, "epoch": 0.7695067264573991, "percentage": 77.02, "elapsed_time": "3:13:02", "remaining_time": "0:57:35"}
30
- {"current_steps": 430, "total_steps": 557, "loss": 1.5124, "lr": 2e-05, "epoch": 0.7713004484304933, "percentage": 77.2, "elapsed_time": "3:19:39", "remaining_time": "0:58:58"}
31
- {"current_steps": 431, "total_steps": 557, "loss": 1.5299, "lr": 2e-05, "epoch": 0.7730941704035874, "percentage": 77.38, "elapsed_time": "3:26:23", "remaining_time": "1:00:20"}
32
- {"current_steps": 432, "total_steps": 557, "loss": 1.5095, "lr": 2e-05, "epoch": 0.7748878923766817, "percentage": 77.56, "elapsed_time": "3:33:03", "remaining_time": "1:01:39"}
33
- {"current_steps": 433, "total_steps": 557, "loss": 1.5193, "lr": 2e-05, "epoch": 0.7766816143497758, "percentage": 77.74, "elapsed_time": "3:39:45", "remaining_time": "1:02:56"}
34
- {"current_steps": 434, "total_steps": 557, "loss": 1.5214, "lr": 2e-05, "epoch": 0.7784753363228699, "percentage": 77.92, "elapsed_time": "3:46:26", "remaining_time": "1:04:10"}
35
- {"current_steps": 435, "total_steps": 557, "loss": 1.5208, "lr": 2e-05, "epoch": 0.7802690582959642, "percentage": 78.1, "elapsed_time": "3:53:05", "remaining_time": "1:05:22"}
36
- {"current_steps": 436, "total_steps": 557, "loss": 1.5227, "lr": 2e-05, "epoch": 0.7820627802690583, "percentage": 78.28, "elapsed_time": "3:59:43", "remaining_time": "1:06:31"}
37
- {"current_steps": 437, "total_steps": 557, "loss": 1.5248, "lr": 2e-05, "epoch": 0.7838565022421524, "percentage": 78.46, "elapsed_time": "4:06:20", "remaining_time": "1:07:38"}
38
- {"current_steps": 438, "total_steps": 557, "loss": 1.5222, "lr": 2e-05, "epoch": 0.7856502242152467, "percentage": 78.64, "elapsed_time": "4:13:00", "remaining_time": "1:08:44"}
39
- {"current_steps": 439, "total_steps": 557, "loss": 1.5205, "lr": 2e-05, "epoch": 0.7874439461883408, "percentage": 78.82, "elapsed_time": "4:19:37", "remaining_time": "1:09:47"}
40
- {"current_steps": 440, "total_steps": 557, "loss": 1.5189, "lr": 2e-05, "epoch": 0.7892376681614349, "percentage": 78.99, "elapsed_time": "4:26:15", "remaining_time": "1:10:48"}
41
- {"current_steps": 441, "total_steps": 557, "loss": 1.5156, "lr": 2e-05, "epoch": 0.7910313901345292, "percentage": 79.17, "elapsed_time": "4:32:52", "remaining_time": "1:11:46"}
42
- {"current_steps": 442, "total_steps": 557, "loss": 1.5116, "lr": 2e-05, "epoch": 0.7928251121076233, "percentage": 79.35, "elapsed_time": "4:39:32", "remaining_time": "1:12:43"}
43
- {"current_steps": 443, "total_steps": 557, "loss": 1.5153, "lr": 2e-05, "epoch": 0.7946188340807175, "percentage": 79.53, "elapsed_time": "4:46:09", "remaining_time": "1:13:38"}
44
- {"current_steps": 444, "total_steps": 557, "loss": 1.5246, "lr": 2e-05, "epoch": 0.7964125560538117, "percentage": 79.71, "elapsed_time": "4:52:46", "remaining_time": "1:14:30"}
45
- {"current_steps": 445, "total_steps": 557, "loss": 1.5282, "lr": 2e-05, "epoch": 0.7982062780269058, "percentage": 79.89, "elapsed_time": "4:59:22", "remaining_time": "1:15:20"}
46
- {"current_steps": 446, "total_steps": 557, "loss": 1.5108, "lr": 2e-05, "epoch": 0.8, "percentage": 80.07, "elapsed_time": "5:06:00", "remaining_time": "1:16:09"}
47
- {"current_steps": 447, "total_steps": 557, "loss": 1.51, "lr": 2e-05, "epoch": 0.8017937219730942, "percentage": 80.25, "elapsed_time": "5:12:37", "remaining_time": "1:16:55"}
48
- {"current_steps": 448, "total_steps": 557, "loss": 1.5139, "lr": 2e-05, "epoch": 0.8035874439461883, "percentage": 80.43, "elapsed_time": "5:19:17", "remaining_time": "1:17:40"}
49
- {"current_steps": 449, "total_steps": 557, "loss": 1.5091, "lr": 2e-05, "epoch": 0.8053811659192825, "percentage": 80.61, "elapsed_time": "5:25:54", "remaining_time": "1:18:23"}
50
- {"current_steps": 450, "total_steps": 557, "loss": 1.5122, "lr": 2e-05, "epoch": 0.8071748878923767, "percentage": 80.79, "elapsed_time": "5:32:30", "remaining_time": "1:19:03"}
51
- {"current_steps": 451, "total_steps": 557, "loss": 1.52, "lr": 2e-05, "epoch": 0.8089686098654708, "percentage": 80.97, "elapsed_time": "5:39:15", "remaining_time": "1:19:44"}
52
- {"current_steps": 452, "total_steps": 557, "loss": 1.5197, "lr": 2e-05, "epoch": 0.810762331838565, "percentage": 81.15, "elapsed_time": "5:45:57", "remaining_time": "1:20:22"}
53
- {"current_steps": 453, "total_steps": 557, "loss": 1.5117, "lr": 2e-05, "epoch": 0.8125560538116592, "percentage": 81.33, "elapsed_time": "5:52:37", "remaining_time": "1:20:57"}
54
- {"current_steps": 454, "total_steps": 557, "loss": 1.5033, "lr": 2e-05, "epoch": 0.8143497757847533, "percentage": 81.51, "elapsed_time": "5:59:14", "remaining_time": "1:21:30"}
55
- {"current_steps": 455, "total_steps": 557, "loss": 1.5166, "lr": 2e-05, "epoch": 0.8161434977578476, "percentage": 81.69, "elapsed_time": "6:05:59", "remaining_time": "1:22:02"}
56
- {"current_steps": 456, "total_steps": 557, "loss": 1.5149, "lr": 2e-05, "epoch": 0.8179372197309417, "percentage": 81.87, "elapsed_time": "6:12:37", "remaining_time": "1:22:32"}
57
- {"current_steps": 457, "total_steps": 557, "loss": 1.5093, "lr": 2e-05, "epoch": 0.8197309417040358, "percentage": 82.05, "elapsed_time": "6:19:15", "remaining_time": "1:22:59"}
58
- {"current_steps": 458, "total_steps": 557, "loss": 1.5141, "lr": 2e-05, "epoch": 0.8215246636771301, "percentage": 82.23, "elapsed_time": "6:26:00", "remaining_time": "1:23:26"}
59
- {"current_steps": 459, "total_steps": 557, "loss": 1.5241, "lr": 2e-05, "epoch": 0.8233183856502242, "percentage": 82.41, "elapsed_time": "6:32:38", "remaining_time": "1:23:49"}
60
- {"current_steps": 460, "total_steps": 557, "loss": 1.5068, "lr": 2e-05, "epoch": 0.8251121076233184, "percentage": 82.59, "elapsed_time": "6:39:15", "remaining_time": "1:24:11"}
61
- {"current_steps": 461, "total_steps": 557, "loss": 1.5052, "lr": 2e-05, "epoch": 0.8269058295964126, "percentage": 82.76, "elapsed_time": "6:45:53", "remaining_time": "1:24:31"}
62
- {"current_steps": 462, "total_steps": 557, "loss": 1.5071, "lr": 2e-05, "epoch": 0.8286995515695067, "percentage": 82.94, "elapsed_time": "6:52:31", "remaining_time": "1:24:49"}
63
- {"current_steps": 463, "total_steps": 557, "loss": 1.5189, "lr": 2e-05, "epoch": 0.8304932735426009, "percentage": 83.12, "elapsed_time": "6:59:08", "remaining_time": "1:25:05"}
64
- {"current_steps": 464, "total_steps": 557, "loss": 1.5183, "lr": 2e-05, "epoch": 0.8322869955156951, "percentage": 83.3, "elapsed_time": "7:05:47", "remaining_time": "1:25:20"}
65
- {"current_steps": 465, "total_steps": 557, "loss": 1.5213, "lr": 2e-05, "epoch": 0.8340807174887892, "percentage": 83.48, "elapsed_time": "7:12:25", "remaining_time": "1:25:33"}
66
- {"current_steps": 466, "total_steps": 557, "loss": 1.5182, "lr": 2e-05, "epoch": 0.8358744394618834, "percentage": 83.66, "elapsed_time": "7:19:05", "remaining_time": "1:25:44"}
67
- {"current_steps": 467, "total_steps": 557, "loss": 1.5092, "lr": 2e-05, "epoch": 0.8376681614349776, "percentage": 83.84, "elapsed_time": "7:25:43", "remaining_time": "1:25:54"}
68
- {"current_steps": 468, "total_steps": 557, "loss": 1.5186, "lr": 2e-05, "epoch": 0.8394618834080717, "percentage": 84.02, "elapsed_time": "7:32:20", "remaining_time": "1:26:01"}
69
- {"current_steps": 469, "total_steps": 557, "loss": 1.5097, "lr": 2e-05, "epoch": 0.841255605381166, "percentage": 84.2, "elapsed_time": "7:38:58", "remaining_time": "1:26:07"}
70
- {"current_steps": 470, "total_steps": 557, "loss": 1.5173, "lr": 2e-05, "epoch": 0.8430493273542601, "percentage": 84.38, "elapsed_time": "7:45:36", "remaining_time": "1:26:11"}
71
- {"current_steps": 471, "total_steps": 557, "loss": 1.5108, "lr": 2e-05, "epoch": 0.8448430493273542, "percentage": 84.56, "elapsed_time": "7:52:13", "remaining_time": "1:26:13"}
72
- {"current_steps": 472, "total_steps": 557, "loss": 1.5272, "lr": 2e-05, "epoch": 0.8466367713004485, "percentage": 84.74, "elapsed_time": "7:58:52", "remaining_time": "1:26:14"}
73
- {"current_steps": 473, "total_steps": 557, "loss": 1.5193, "lr": 2e-05, "epoch": 0.8484304932735426, "percentage": 84.92, "elapsed_time": "8:05:31", "remaining_time": "1:26:13"}
74
- {"current_steps": 474, "total_steps": 557, "loss": 1.5165, "lr": 2e-05, "epoch": 0.8502242152466367, "percentage": 85.1, "elapsed_time": "8:12:09", "remaining_time": "1:26:10"}
75
- {"current_steps": 475, "total_steps": 557, "loss": 1.5228, "lr": 2e-05, "epoch": 0.852017937219731, "percentage": 85.28, "elapsed_time": "8:18:47", "remaining_time": "1:26:06"}
76
- {"current_steps": 476, "total_steps": 557, "loss": 1.5188, "lr": 2e-05, "epoch": 0.8538116591928251, "percentage": 85.46, "elapsed_time": "8:25:27", "remaining_time": "1:26:00"}
77
- {"current_steps": 477, "total_steps": 557, "loss": 1.5199, "lr": 2e-05, "epoch": 0.8556053811659193, "percentage": 85.64, "elapsed_time": "8:32:03", "remaining_time": "1:25:52"}
78
- {"current_steps": 478, "total_steps": 557, "loss": 1.516, "lr": 2e-05, "epoch": 0.8573991031390135, "percentage": 85.82, "elapsed_time": "8:38:42", "remaining_time": "1:25:43"}
79
- {"current_steps": 479, "total_steps": 557, "loss": 1.5218, "lr": 2e-05, "epoch": 0.8591928251121076, "percentage": 86.0, "elapsed_time": "8:45:19", "remaining_time": "1:25:32"}
80
- {"current_steps": 480, "total_steps": 557, "loss": 1.5155, "lr": 2e-05, "epoch": 0.8609865470852018, "percentage": 86.18, "elapsed_time": "8:51:58", "remaining_time": "1:25:20"}
81
- {"current_steps": 481, "total_steps": 557, "loss": 1.5205, "lr": 2e-05, "epoch": 0.862780269058296, "percentage": 86.36, "elapsed_time": "8:58:36", "remaining_time": "1:25:06"}
82
- {"current_steps": 482, "total_steps": 557, "loss": 1.5019, "lr": 2e-05, "epoch": 0.8645739910313901, "percentage": 86.54, "elapsed_time": "9:05:13", "remaining_time": "1:24:50"}
83
- {"current_steps": 483, "total_steps": 557, "loss": 1.5217, "lr": 2e-05, "epoch": 0.8663677130044843, "percentage": 86.71, "elapsed_time": "9:11:50", "remaining_time": "1:24:32"}
84
- {"current_steps": 484, "total_steps": 557, "loss": 1.5073, "lr": 2e-05, "epoch": 0.8681614349775785, "percentage": 86.89, "elapsed_time": "9:18:28", "remaining_time": "1:24:13"}
85
- {"current_steps": 485, "total_steps": 557, "loss": 1.5101, "lr": 2e-05, "epoch": 0.8699551569506726, "percentage": 87.07, "elapsed_time": "9:25:05", "remaining_time": "1:23:53"}
86
- {"current_steps": 486, "total_steps": 557, "loss": 1.5209, "lr": 2e-05, "epoch": 0.8717488789237668, "percentage": 87.25, "elapsed_time": "9:31:41", "remaining_time": "1:23:31"}
87
- {"current_steps": 487, "total_steps": 557, "loss": 1.5275, "lr": 2e-05, "epoch": 0.873542600896861, "percentage": 87.43, "elapsed_time": "9:38:18", "remaining_time": "1:23:07"}
88
- {"current_steps": 488, "total_steps": 557, "loss": 1.521, "lr": 2e-05, "epoch": 0.8753363228699551, "percentage": 87.61, "elapsed_time": "9:44:55", "remaining_time": "1:22:42"}
89
- {"current_steps": 489, "total_steps": 557, "loss": 1.5253, "lr": 2e-05, "epoch": 0.8771300448430494, "percentage": 87.79, "elapsed_time": "9:51:35", "remaining_time": "1:22:16"}
90
- {"current_steps": 490, "total_steps": 557, "loss": 1.5128, "lr": 2e-05, "epoch": 0.8789237668161435, "percentage": 87.97, "elapsed_time": "9:58:15", "remaining_time": "1:21:48"}
91
- {"current_steps": 491, "total_steps": 557, "loss": 1.5216, "lr": 2e-05, "epoch": 0.8807174887892377, "percentage": 88.15, "elapsed_time": "10:04:56", "remaining_time": "1:21:18"}
92
- {"current_steps": 492, "total_steps": 557, "loss": 1.5102, "lr": 2e-05, "epoch": 0.8825112107623319, "percentage": 88.33, "elapsed_time": "10:11:37", "remaining_time": "1:20:48"}
93
- {"current_steps": 493, "total_steps": 557, "loss": 1.5152, "lr": 2e-05, "epoch": 0.884304932735426, "percentage": 88.51, "elapsed_time": "10:18:20", "remaining_time": "1:20:16"}
94
- {"current_steps": 494, "total_steps": 557, "loss": 1.5134, "lr": 2e-05, "epoch": 0.8860986547085202, "percentage": 88.69, "elapsed_time": "10:25:04", "remaining_time": "1:19:43"}
95
- {"current_steps": 495, "total_steps": 557, "loss": 1.5213, "lr": 2e-05, "epoch": 0.8878923766816144, "percentage": 88.87, "elapsed_time": "10:31:46", "remaining_time": "1:19:07"}
96
- {"current_steps": 496, "total_steps": 557, "loss": 1.5254, "lr": 2e-05, "epoch": 0.8896860986547085, "percentage": 89.05, "elapsed_time": "10:38:28", "remaining_time": "1:18:31"}
97
- {"current_steps": 497, "total_steps": 557, "loss": 1.5042, "lr": 2e-05, "epoch": 0.8914798206278027, "percentage": 89.23, "elapsed_time": "10:45:10", "remaining_time": "1:17:53"}
98
- {"current_steps": 498, "total_steps": 557, "loss": 1.5141, "lr": 2e-05, "epoch": 0.8932735426008969, "percentage": 89.41, "elapsed_time": "10:51:50", "remaining_time": "1:17:13"}
99
- {"current_steps": 499, "total_steps": 557, "loss": 1.5189, "lr": 2e-05, "epoch": 0.895067264573991, "percentage": 89.59, "elapsed_time": "10:58:32", "remaining_time": "1:16:32"}
100
- {"current_steps": 500, "total_steps": 557, "loss": 1.5128, "lr": 2e-05, "epoch": 0.8968609865470852, "percentage": 89.77, "elapsed_time": "11:05:12", "remaining_time": "1:15:50"}
101
- {"current_steps": 501, "total_steps": 557, "loss": 1.5331, "lr": 2e-05, "epoch": 0.8986547085201794, "percentage": 89.95, "elapsed_time": "11:19:44", "remaining_time": "1:15:58"}
102
- {"current_steps": 502, "total_steps": 557, "loss": 1.5143, "lr": 2e-05, "epoch": 0.9004484304932735, "percentage": 90.13, "elapsed_time": "11:26:25", "remaining_time": "1:15:12"}
103
- {"current_steps": 503, "total_steps": 557, "loss": 1.5237, "lr": 2e-05, "epoch": 0.9022421524663677, "percentage": 90.31, "elapsed_time": "11:33:11", "remaining_time": "1:14:25"}
104
- {"current_steps": 504, "total_steps": 557, "loss": 1.5236, "lr": 2e-05, "epoch": 0.9040358744394619, "percentage": 90.48, "elapsed_time": "11:39:53", "remaining_time": "1:13:36"}
105
- {"current_steps": 505, "total_steps": 557, "loss": 1.5189, "lr": 2e-05, "epoch": 0.905829596412556, "percentage": 90.66, "elapsed_time": "11:46:34", "remaining_time": "1:12:45"}
106
- {"current_steps": 506, "total_steps": 557, "loss": 1.519, "lr": 2e-05, "epoch": 0.9076233183856502, "percentage": 90.84, "elapsed_time": "11:53:15", "remaining_time": "1:11:53"}
107
- {"current_steps": 507, "total_steps": 557, "loss": 1.5176, "lr": 2e-05, "epoch": 0.9094170403587444, "percentage": 91.02, "elapsed_time": "11:59:55", "remaining_time": "1:10:59"}
108
- {"current_steps": 508, "total_steps": 557, "loss": 1.5055, "lr": 2e-05, "epoch": 0.9112107623318386, "percentage": 91.2, "elapsed_time": "12:06:38", "remaining_time": "1:10:05"}
109
- {"current_steps": 509, "total_steps": 557, "loss": 1.5224, "lr": 2e-05, "epoch": 0.9130044843049328, "percentage": 91.38, "elapsed_time": "12:13:19", "remaining_time": "1:09:09"}
110
- {"current_steps": 510, "total_steps": 557, "loss": 1.5129, "lr": 2e-05, "epoch": 0.9147982062780269, "percentage": 91.56, "elapsed_time": "12:19:59", "remaining_time": "1:08:11"}
111
- {"current_steps": 511, "total_steps": 557, "loss": 1.52, "lr": 2e-05, "epoch": 0.9165919282511211, "percentage": 91.74, "elapsed_time": "12:26:47", "remaining_time": "1:07:13"}
112
- {"current_steps": 512, "total_steps": 557, "loss": 1.5194, "lr": 2e-05, "epoch": 0.9183856502242153, "percentage": 91.92, "elapsed_time": "12:33:29", "remaining_time": "1:06:13"}
113
- {"current_steps": 513, "total_steps": 557, "loss": 1.5187, "lr": 2e-05, "epoch": 0.9201793721973094, "percentage": 92.1, "elapsed_time": "12:40:10", "remaining_time": "1:05:12"}
114
- {"current_steps": 514, "total_steps": 557, "loss": 1.5059, "lr": 2e-05, "epoch": 0.9219730941704036, "percentage": 92.28, "elapsed_time": "12:46:52", "remaining_time": "1:04:09"}
115
- {"current_steps": 515, "total_steps": 557, "loss": 1.5102, "lr": 2e-05, "epoch": 0.9237668161434978, "percentage": 92.46, "elapsed_time": "12:53:35", "remaining_time": "1:03:05"}
116
- {"current_steps": 516, "total_steps": 557, "loss": 1.5217, "lr": 2e-05, "epoch": 0.9255605381165919, "percentage": 92.64, "elapsed_time": "13:00:17", "remaining_time": "1:01:59"}
117
- {"current_steps": 517, "total_steps": 557, "loss": 1.5243, "lr": 2e-05, "epoch": 0.9273542600896861, "percentage": 92.82, "elapsed_time": "13:06:59", "remaining_time": "1:00:53"}
118
- {"current_steps": 518, "total_steps": 557, "loss": 1.5054, "lr": 2e-05, "epoch": 0.9291479820627803, "percentage": 93.0, "elapsed_time": "13:13:43", "remaining_time": "0:59:45"}
119
- {"current_steps": 519, "total_steps": 557, "loss": 1.5053, "lr": 2e-05, "epoch": 0.9309417040358744, "percentage": 93.18, "elapsed_time": "13:20:25", "remaining_time": "0:58:36"}
120
- {"current_steps": 520, "total_steps": 557, "loss": 1.5151, "lr": 2e-05, "epoch": 0.9327354260089686, "percentage": 93.36, "elapsed_time": "13:27:08", "remaining_time": "0:57:25"}
121
- {"current_steps": 521, "total_steps": 557, "loss": 1.5099, "lr": 2e-05, "epoch": 0.9345291479820628, "percentage": 93.54, "elapsed_time": "13:33:50", "remaining_time": "0:56:14"}
122
- {"current_steps": 522, "total_steps": 557, "loss": 1.5256, "lr": 2e-05, "epoch": 0.9363228699551569, "percentage": 93.72, "elapsed_time": "13:40:32", "remaining_time": "0:55:01"}
123
- {"current_steps": 523, "total_steps": 557, "loss": 1.5056, "lr": 2e-05, "epoch": 0.9381165919282511, "percentage": 93.9, "elapsed_time": "13:47:15", "remaining_time": "0:53:46"}
124
- {"current_steps": 524, "total_steps": 557, "loss": 1.5285, "lr": 2e-05, "epoch": 0.9399103139013453, "percentage": 94.08, "elapsed_time": "13:53:59", "remaining_time": "0:52:31"}
125
- {"current_steps": 525, "total_steps": 557, "loss": 1.5136, "lr": 2e-05, "epoch": 0.9417040358744395, "percentage": 94.25, "elapsed_time": "14:00:39", "remaining_time": "0:51:14"}
126
- {"current_steps": 526, "total_steps": 557, "loss": 1.5119, "lr": 2e-05, "epoch": 0.9434977578475336, "percentage": 94.43, "elapsed_time": "14:07:20", "remaining_time": "0:49:56"}
127
- {"current_steps": 527, "total_steps": 557, "loss": 1.5228, "lr": 2e-05, "epoch": 0.9452914798206278, "percentage": 94.61, "elapsed_time": "14:14:03", "remaining_time": "0:48:37"}
128
- {"current_steps": 528, "total_steps": 557, "loss": 1.5258, "lr": 2e-05, "epoch": 0.947085201793722, "percentage": 94.79, "elapsed_time": "14:20:44", "remaining_time": "0:47:16"}
129
- {"current_steps": 529, "total_steps": 557, "loss": 1.5156, "lr": 2e-05, "epoch": 0.9488789237668162, "percentage": 94.97, "elapsed_time": "14:27:22", "remaining_time": "0:45:54"}
130
- {"current_steps": 530, "total_steps": 557, "loss": 1.5171, "lr": 2e-05, "epoch": 0.9506726457399103, "percentage": 95.15, "elapsed_time": "14:33:59", "remaining_time": "0:44:31"}
131
- {"current_steps": 531, "total_steps": 557, "loss": 1.5125, "lr": 2e-05, "epoch": 0.9524663677130045, "percentage": 95.33, "elapsed_time": "14:40:37", "remaining_time": "0:43:07"}
132
- {"current_steps": 532, "total_steps": 557, "loss": 1.5182, "lr": 2e-05, "epoch": 0.9542600896860987, "percentage": 95.51, "elapsed_time": "14:47:14", "remaining_time": "0:41:41"}
133
- {"current_steps": 533, "total_steps": 557, "loss": 1.5139, "lr": 2e-05, "epoch": 0.9560538116591928, "percentage": 95.69, "elapsed_time": "14:53:53", "remaining_time": "0:40:15"}
134
- {"current_steps": 534, "total_steps": 557, "loss": 1.5239, "lr": 2e-05, "epoch": 0.957847533632287, "percentage": 95.87, "elapsed_time": "15:00:29", "remaining_time": "0:38:47"}
135
- {"current_steps": 535, "total_steps": 557, "loss": 1.5159, "lr": 2e-05, "epoch": 0.9596412556053812, "percentage": 96.05, "elapsed_time": "15:07:06", "remaining_time": "0:37:18"}
136
- {"current_steps": 536, "total_steps": 557, "loss": 1.5174, "lr": 2e-05, "epoch": 0.9614349775784753, "percentage": 96.23, "elapsed_time": "15:13:44", "remaining_time": "0:35:47"}
137
- {"current_steps": 537, "total_steps": 557, "loss": 1.5171, "lr": 2e-05, "epoch": 0.9632286995515695, "percentage": 96.41, "elapsed_time": "15:20:22", "remaining_time": "0:34:16"}
138
- {"current_steps": 538, "total_steps": 557, "loss": 1.5223, "lr": 2e-05, "epoch": 0.9650224215246637, "percentage": 96.59, "elapsed_time": "15:26:59", "remaining_time": "0:32:44"}
139
- {"current_steps": 539, "total_steps": 557, "loss": 1.5282, "lr": 2e-05, "epoch": 0.9668161434977578, "percentage": 96.77, "elapsed_time": "15:33:42", "remaining_time": "0:31:10"}
140
- {"current_steps": 540, "total_steps": 557, "loss": 1.5092, "lr": 2e-05, "epoch": 0.968609865470852, "percentage": 96.95, "elapsed_time": "15:40:20", "remaining_time": "0:29:36"}
141
- {"current_steps": 541, "total_steps": 557, "loss": 1.5068, "lr": 2e-05, "epoch": 0.9704035874439462, "percentage": 97.13, "elapsed_time": "15:46:59", "remaining_time": "0:28:00"}
142
- {"current_steps": 542, "total_steps": 557, "loss": 1.5089, "lr": 2e-05, "epoch": 0.9721973094170404, "percentage": 97.31, "elapsed_time": "15:53:38", "remaining_time": "0:26:23"}
143
- {"current_steps": 543, "total_steps": 557, "loss": 1.5217, "lr": 2e-05, "epoch": 0.9739910313901345, "percentage": 97.49, "elapsed_time": "16:00:21", "remaining_time": "0:24:45"}
144
- {"current_steps": 544, "total_steps": 557, "loss": 1.5143, "lr": 2e-05, "epoch": 0.9757847533632287, "percentage": 97.67, "elapsed_time": "16:07:02", "remaining_time": "0:23:06"}
145
- {"current_steps": 545, "total_steps": 557, "loss": 1.5276, "lr": 2e-05, "epoch": 0.9775784753363229, "percentage": 97.85, "elapsed_time": "16:13:39", "remaining_time": "0:21:26"}
146
- {"current_steps": 546, "total_steps": 557, "loss": 1.5222, "lr": 2e-05, "epoch": 0.979372197309417, "percentage": 98.03, "elapsed_time": "16:20:17", "remaining_time": "0:19:44"}
147
- {"current_steps": 547, "total_steps": 557, "loss": 1.5276, "lr": 2e-05, "epoch": 0.9811659192825112, "percentage": 98.2, "elapsed_time": "16:26:55", "remaining_time": "0:18:02"}
148
- {"current_steps": 548, "total_steps": 557, "loss": 1.5217, "lr": 2e-05, "epoch": 0.9829596412556054, "percentage": 98.38, "elapsed_time": "16:33:35", "remaining_time": "0:16:19"}
149
- {"current_steps": 549, "total_steps": 557, "loss": 1.5194, "lr": 2e-05, "epoch": 0.9847533632286996, "percentage": 98.56, "elapsed_time": "16:40:14", "remaining_time": "0:14:34"}
150
- {"current_steps": 550, "total_steps": 557, "loss": 1.5138, "lr": 2e-05, "epoch": 0.9865470852017937, "percentage": 98.74, "elapsed_time": "16:46:52", "remaining_time": "0:12:48"}
151
- {"current_steps": 551, "total_steps": 557, "loss": 1.5044, "lr": 2e-05, "epoch": 0.9883408071748879, "percentage": 98.92, "elapsed_time": "16:53:29", "remaining_time": "0:11:02"}
152
- {"current_steps": 552, "total_steps": 557, "loss": 1.5165, "lr": 2e-05, "epoch": 0.9901345291479821, "percentage": 99.1, "elapsed_time": "17:00:11", "remaining_time": "0:09:14"}
153
- {"current_steps": 553, "total_steps": 557, "loss": 1.5291, "lr": 2e-05, "epoch": 0.9919282511210762, "percentage": 99.28, "elapsed_time": "17:06:50", "remaining_time": "0:07:25"}
154
- {"current_steps": 554, "total_steps": 557, "loss": 1.5109, "lr": 2e-05, "epoch": 0.9937219730941704, "percentage": 99.46, "elapsed_time": "17:13:28", "remaining_time": "0:05:35"}
155
- {"current_steps": 555, "total_steps": 557, "loss": 1.5212, "lr": 2e-05, "epoch": 0.9955156950672646, "percentage": 99.64, "elapsed_time": "17:20:06", "remaining_time": "0:03:44"}
156
- {"current_steps": 556, "total_steps": 557, "loss": 1.5106, "lr": 2e-05, "epoch": 0.9973094170403587, "percentage": 99.82, "elapsed_time": "17:26:45", "remaining_time": "0:01:52"}
157
- {"current_steps": 557, "total_steps": 557, "loss": 1.5099, "lr": 2e-05, "epoch": 0.9991031390134529, "percentage": 100.0, "elapsed_time": "17:33:24", "remaining_time": "0:00:00"}
158
- {"current_steps": 557, "total_steps": 557, "epoch": 0.9991031390134529, "percentage": 100.0, "elapsed_time": "17:42:07", "remaining_time": "0:00:00"}
 
1
+ {"current_steps": 557, "total_steps": 557, "epoch": 0.9991031390134529, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ad09cbd3278e201ac3fa5ce175ad9e8e7ad1e91b6d045ffa313186b1a9162b8
3
  size 7736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edbce3021fec5142ee6350f88b996f2edba74841c2f294b086a307e2da2d598d
3
  size 7736