sedrickkeh commited on
Commit
81fdcf8
·
verified ·
1 Parent(s): b49e622

Training in progress, epoch 1

Browse files
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19e520627a0049b14f9cf39e629e56767c50af62af262cb2dcecac01ae1c8560
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53f77e04cccfdc4ee0f5449b45476554ef03384f3bac5b8d8f4041eeea4864ab
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f162cf1b534b29d1db2bc074588983ff7f7e10d46b3dbf6d68431cdeb18dbcb4
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ae0612ac8bd62286c0a690b298e0a109afa88531fc5241fce25c6aa079bd503
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7eb6f6ed39c5fc2d608da8ac5273c0a68f4611ae1d3f23aa7cb88e6e450604cf
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fa4872c63f01e71480864d11636a0af5772276f7e7ac66bb8f6ad12987139e8
3
  size 4540516344
trainer_log.jsonl CHANGED
@@ -48,3 +48,52 @@
48
  {"current_steps": 480, "total_steps": 986, "loss": 0.5506, "lr": 5e-06, "epoch": 0.9721518987341772, "percentage": 48.68, "elapsed_time": "7:26:43", "remaining_time": "7:50:55"}
49
  {"current_steps": 490, "total_steps": 986, "loss": 0.5472, "lr": 5e-06, "epoch": 0.9924050632911392, "percentage": 49.7, "elapsed_time": "7:36:01", "remaining_time": "7:41:36"}
50
  {"current_steps": 493, "total_steps": 986, "eval_loss": 0.06877367943525314, "epoch": 0.9984810126582279, "percentage": 50.0, "elapsed_time": "7:48:00", "remaining_time": "7:48:00"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  {"current_steps": 480, "total_steps": 986, "loss": 0.5506, "lr": 5e-06, "epoch": 0.9721518987341772, "percentage": 48.68, "elapsed_time": "7:26:43", "remaining_time": "7:50:55"}
49
  {"current_steps": 490, "total_steps": 986, "loss": 0.5472, "lr": 5e-06, "epoch": 0.9924050632911392, "percentage": 49.7, "elapsed_time": "7:36:01", "remaining_time": "7:41:36"}
50
  {"current_steps": 493, "total_steps": 986, "eval_loss": 0.06877367943525314, "epoch": 0.9984810126582279, "percentage": 50.0, "elapsed_time": "7:48:00", "remaining_time": "7:48:00"}
51
+ {"current_steps": 500, "total_steps": 986, "loss": 0.5062, "lr": 5e-06, "epoch": 1.0126582278481013, "percentage": 50.71, "elapsed_time": "7:54:55", "remaining_time": "7:41:38"}
52
+ {"current_steps": 510, "total_steps": 986, "loss": 0.4713, "lr": 5e-06, "epoch": 1.0329113924050632, "percentage": 51.72, "elapsed_time": "8:04:13", "remaining_time": "7:31:56"}
53
+ {"current_steps": 520, "total_steps": 986, "loss": 0.4665, "lr": 5e-06, "epoch": 1.0531645569620254, "percentage": 52.74, "elapsed_time": "8:13:31", "remaining_time": "7:22:16"}
54
+ {"current_steps": 530, "total_steps": 986, "loss": 0.4683, "lr": 5e-06, "epoch": 1.0734177215189873, "percentage": 53.75, "elapsed_time": "8:22:50", "remaining_time": "7:12:38"}
55
+ {"current_steps": 540, "total_steps": 986, "loss": 0.4641, "lr": 5e-06, "epoch": 1.0936708860759494, "percentage": 54.77, "elapsed_time": "8:32:10", "remaining_time": "7:03:01"}
56
+ {"current_steps": 550, "total_steps": 986, "loss": 0.4664, "lr": 5e-06, "epoch": 1.1139240506329113, "percentage": 55.78, "elapsed_time": "8:41:29", "remaining_time": "6:53:23"}
57
+ {"current_steps": 560, "total_steps": 986, "loss": 0.4633, "lr": 5e-06, "epoch": 1.1341772151898735, "percentage": 56.8, "elapsed_time": "8:50:48", "remaining_time": "6:43:47"}
58
+ {"current_steps": 570, "total_steps": 986, "loss": 0.4693, "lr": 5e-06, "epoch": 1.1544303797468354, "percentage": 57.81, "elapsed_time": "9:00:07", "remaining_time": "6:34:11"}
59
+ {"current_steps": 580, "total_steps": 986, "loss": 0.4677, "lr": 5e-06, "epoch": 1.1746835443037975, "percentage": 58.82, "elapsed_time": "9:09:26", "remaining_time": "6:24:36"}
60
+ {"current_steps": 590, "total_steps": 986, "loss": 0.4611, "lr": 5e-06, "epoch": 1.1949367088607594, "percentage": 59.84, "elapsed_time": "9:18:45", "remaining_time": "6:15:01"}
61
+ {"current_steps": 600, "total_steps": 986, "loss": 0.4683, "lr": 5e-06, "epoch": 1.2151898734177216, "percentage": 60.85, "elapsed_time": "9:28:04", "remaining_time": "6:05:27"}
62
+ {"current_steps": 610, "total_steps": 986, "loss": 0.4648, "lr": 5e-06, "epoch": 1.2354430379746835, "percentage": 61.87, "elapsed_time": "9:37:24", "remaining_time": "5:55:54"}
63
+ {"current_steps": 620, "total_steps": 986, "loss": 0.4691, "lr": 5e-06, "epoch": 1.2556962025316456, "percentage": 62.88, "elapsed_time": "9:46:43", "remaining_time": "5:46:21"}
64
+ {"current_steps": 630, "total_steps": 986, "loss": 0.4699, "lr": 5e-06, "epoch": 1.2759493670886077, "percentage": 63.89, "elapsed_time": "9:56:04", "remaining_time": "5:36:49"}
65
+ {"current_steps": 640, "total_steps": 986, "loss": 0.47, "lr": 5e-06, "epoch": 1.2962025316455696, "percentage": 64.91, "elapsed_time": "10:05:24", "remaining_time": "5:27:17"}
66
+ {"current_steps": 650, "total_steps": 986, "loss": 0.4747, "lr": 5e-06, "epoch": 1.3164556962025316, "percentage": 65.92, "elapsed_time": "10:14:44", "remaining_time": "5:17:46"}
67
+ {"current_steps": 660, "total_steps": 986, "loss": 0.4637, "lr": 5e-06, "epoch": 1.3367088607594937, "percentage": 66.94, "elapsed_time": "10:24:02", "remaining_time": "5:08:14"}
68
+ {"current_steps": 670, "total_steps": 986, "loss": 0.4768, "lr": 5e-06, "epoch": 1.3569620253164558, "percentage": 67.95, "elapsed_time": "10:33:20", "remaining_time": "4:58:42"}
69
+ {"current_steps": 680, "total_steps": 986, "loss": 0.4733, "lr": 5e-06, "epoch": 1.3772151898734177, "percentage": 68.97, "elapsed_time": "10:42:39", "remaining_time": "4:49:11"}
70
+ {"current_steps": 690, "total_steps": 986, "loss": 0.473, "lr": 5e-06, "epoch": 1.3974683544303796, "percentage": 69.98, "elapsed_time": "10:51:59", "remaining_time": "4:39:41"}
71
+ {"current_steps": 700, "total_steps": 986, "loss": 0.4712, "lr": 5e-06, "epoch": 1.4177215189873418, "percentage": 70.99, "elapsed_time": "11:01:17", "remaining_time": "4:30:10"}
72
+ {"current_steps": 710, "total_steps": 986, "loss": 0.477, "lr": 5e-06, "epoch": 1.437974683544304, "percentage": 72.01, "elapsed_time": "11:10:35", "remaining_time": "4:20:40"}
73
+ {"current_steps": 720, "total_steps": 986, "loss": 0.4772, "lr": 5e-06, "epoch": 1.4582278481012658, "percentage": 73.02, "elapsed_time": "11:19:54", "remaining_time": "4:11:11"}
74
+ {"current_steps": 730, "total_steps": 986, "loss": 0.4799, "lr": 5e-06, "epoch": 1.4784810126582277, "percentage": 74.04, "elapsed_time": "11:29:12", "remaining_time": "4:01:41"}
75
+ {"current_steps": 740, "total_steps": 986, "loss": 0.4728, "lr": 5e-06, "epoch": 1.4987341772151899, "percentage": 75.05, "elapsed_time": "11:38:31", "remaining_time": "3:52:12"}
76
+ {"current_steps": 750, "total_steps": 986, "loss": 0.4757, "lr": 5e-06, "epoch": 1.518987341772152, "percentage": 76.06, "elapsed_time": "11:47:50", "remaining_time": "3:42:44"}
77
+ {"current_steps": 760, "total_steps": 986, "loss": 0.4768, "lr": 5e-06, "epoch": 1.539240506329114, "percentage": 77.08, "elapsed_time": "11:57:09", "remaining_time": "3:33:15"}
78
+ {"current_steps": 770, "total_steps": 986, "loss": 0.4759, "lr": 5e-06, "epoch": 1.5594936708860758, "percentage": 78.09, "elapsed_time": "12:06:27", "remaining_time": "3:23:47"}
79
+ {"current_steps": 780, "total_steps": 986, "loss": 0.4766, "lr": 5e-06, "epoch": 1.579746835443038, "percentage": 79.11, "elapsed_time": "12:15:45", "remaining_time": "3:14:19"}
80
+ {"current_steps": 790, "total_steps": 986, "loss": 0.4789, "lr": 5e-06, "epoch": 1.6, "percentage": 80.12, "elapsed_time": "12:25:05", "remaining_time": "3:04:51"}
81
+ {"current_steps": 800, "total_steps": 986, "loss": 0.4736, "lr": 5e-06, "epoch": 1.620253164556962, "percentage": 81.14, "elapsed_time": "12:34:24", "remaining_time": "2:55:24"}
82
+ {"current_steps": 810, "total_steps": 986, "loss": 0.466, "lr": 5e-06, "epoch": 1.640506329113924, "percentage": 82.15, "elapsed_time": "12:43:43", "remaining_time": "2:45:56"}
83
+ {"current_steps": 820, "total_steps": 986, "loss": 0.4743, "lr": 5e-06, "epoch": 1.660759493670886, "percentage": 83.16, "elapsed_time": "12:53:02", "remaining_time": "2:36:29"}
84
+ {"current_steps": 830, "total_steps": 986, "loss": 0.4703, "lr": 5e-06, "epoch": 1.6810126582278482, "percentage": 84.18, "elapsed_time": "13:02:22", "remaining_time": "2:27:02"}
85
+ {"current_steps": 840, "total_steps": 986, "loss": 0.4711, "lr": 5e-06, "epoch": 1.70126582278481, "percentage": 85.19, "elapsed_time": "13:11:40", "remaining_time": "2:17:35"}
86
+ {"current_steps": 850, "total_steps": 986, "loss": 0.4734, "lr": 5e-06, "epoch": 1.721518987341772, "percentage": 86.21, "elapsed_time": "13:20:58", "remaining_time": "2:08:09"}
87
+ {"current_steps": 860, "total_steps": 986, "loss": 0.4733, "lr": 5e-06, "epoch": 1.7417721518987341, "percentage": 87.22, "elapsed_time": "13:30:18", "remaining_time": "1:58:43"}
88
+ {"current_steps": 870, "total_steps": 986, "loss": 0.4764, "lr": 5e-06, "epoch": 1.7620253164556963, "percentage": 88.24, "elapsed_time": "13:39:37", "remaining_time": "1:49:17"}
89
+ {"current_steps": 880, "total_steps": 986, "loss": 0.477, "lr": 5e-06, "epoch": 1.7822784810126582, "percentage": 89.25, "elapsed_time": "13:48:56", "remaining_time": "1:39:51"}
90
+ {"current_steps": 890, "total_steps": 986, "loss": 0.4741, "lr": 5e-06, "epoch": 1.80253164556962, "percentage": 90.26, "elapsed_time": "13:58:16", "remaining_time": "1:30:25"}
91
+ {"current_steps": 900, "total_steps": 986, "loss": 0.4744, "lr": 5e-06, "epoch": 1.8227848101265822, "percentage": 91.28, "elapsed_time": "14:07:35", "remaining_time": "1:20:59"}
92
+ {"current_steps": 910, "total_steps": 986, "loss": 0.477, "lr": 5e-06, "epoch": 1.8430379746835444, "percentage": 92.29, "elapsed_time": "14:16:54", "remaining_time": "1:11:33"}
93
+ {"current_steps": 920, "total_steps": 986, "loss": 0.4764, "lr": 5e-06, "epoch": 1.8632911392405065, "percentage": 93.31, "elapsed_time": "14:26:13", "remaining_time": "1:02:08"}
94
+ {"current_steps": 930, "total_steps": 986, "loss": 0.4734, "lr": 5e-06, "epoch": 1.8835443037974684, "percentage": 94.32, "elapsed_time": "14:35:32", "remaining_time": "0:52:43"}
95
+ {"current_steps": 940, "total_steps": 986, "loss": 0.4775, "lr": 5e-06, "epoch": 1.9037974683544303, "percentage": 95.33, "elapsed_time": "14:44:50", "remaining_time": "0:43:18"}
96
+ {"current_steps": 950, "total_steps": 986, "loss": 0.4785, "lr": 5e-06, "epoch": 1.9240506329113924, "percentage": 96.35, "elapsed_time": "14:54:10", "remaining_time": "0:33:53"}
97
+ {"current_steps": 960, "total_steps": 986, "loss": 0.4827, "lr": 5e-06, "epoch": 1.9443037974683546, "percentage": 97.36, "elapsed_time": "15:03:29", "remaining_time": "0:24:28"}
98
+ {"current_steps": 970, "total_steps": 986, "loss": 0.4807, "lr": 5e-06, "epoch": 1.9645569620253165, "percentage": 98.38, "elapsed_time": "15:12:48", "remaining_time": "0:15:03"}
99
+ {"current_steps": 980, "total_steps": 986, "loss": 0.4813, "lr": 5e-06, "epoch": 1.9848101265822784, "percentage": 99.39, "elapsed_time": "15:22:07", "remaining_time": "0:05:38"}