sedrickkeh commited on
Commit
486d008
·
verified ·
1 Parent(s): 45ff578

Training in progress, epoch 2

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6598257a87e55fb345f4be66e577064ba528bbb703ee9db826edfb2a62d30cd
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc3754483bb33283e61eca11248ddc2b389035b92373b2e505d21ee390ce94ff
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7632afd41d46c187acb4c32d0126ecbbf692e9b14d2bdb62b339ea6c574c6a7
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a11e3406056a471ebd671f506a3f46ee81a758af3314f98412fafa96f25b066d
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40797bfe5d063225afa14fb3a4e5113878f876f50ada2d09b04c17bab94d601b
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37a51f96f9af2f30cad0545ed5df176dc29351bbbd69543bfce1aa01084fe531
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:04d37efc339577349e9325348116f0d5a3be2fa42fbdcf40e30e9c882fc68598
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aff262713588c2e3cedc778495cc9560c592244f59c929a1ca1757c181690f19
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -57,3 +57,32 @@
57
  {"current_steps": 560, "total_steps": 861, "loss": 0.6885, "lr": 5e-06, "epoch": 1.9465682015638577, "percentage": 65.04, "elapsed_time": "9:03:13", "remaining_time": "4:51:58"}
58
  {"current_steps": 570, "total_steps": 861, "loss": 0.693, "lr": 5e-06, "epoch": 1.9813205907906168, "percentage": 66.2, "elapsed_time": "9:12:49", "remaining_time": "4:42:13"}
59
  {"current_steps": 575, "total_steps": 861, "eval_loss": 0.7325075268745422, "epoch": 1.9986967854039965, "percentage": 66.78, "elapsed_time": "9:22:53", "remaining_time": "4:39:58"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57
  {"current_steps": 560, "total_steps": 861, "loss": 0.6885, "lr": 5e-06, "epoch": 1.9465682015638577, "percentage": 65.04, "elapsed_time": "9:03:13", "remaining_time": "4:51:58"}
58
  {"current_steps": 570, "total_steps": 861, "loss": 0.693, "lr": 5e-06, "epoch": 1.9813205907906168, "percentage": 66.2, "elapsed_time": "9:12:49", "remaining_time": "4:42:13"}
59
  {"current_steps": 575, "total_steps": 861, "eval_loss": 0.7325075268745422, "epoch": 1.9986967854039965, "percentage": 66.78, "elapsed_time": "9:22:53", "remaining_time": "4:39:58"}
60
+ {"current_steps": 580, "total_steps": 861, "loss": 0.694, "lr": 5e-06, "epoch": 2.016507384882711, "percentage": 67.36, "elapsed_time": "9:28:40", "remaining_time": "4:35:30"}
61
+ {"current_steps": 590, "total_steps": 861, "loss": 0.6416, "lr": 5e-06, "epoch": 2.05125977410947, "percentage": 68.52, "elapsed_time": "9:38:16", "remaining_time": "4:25:37"}
62
+ {"current_steps": 600, "total_steps": 861, "loss": 0.6347, "lr": 5e-06, "epoch": 2.086012163336229, "percentage": 69.69, "elapsed_time": "9:47:52", "remaining_time": "4:15:43"}
63
+ {"current_steps": 610, "total_steps": 861, "loss": 0.6382, "lr": 5e-06, "epoch": 2.1207645525629886, "percentage": 70.85, "elapsed_time": "9:57:28", "remaining_time": "4:05:50"}
64
+ {"current_steps": 620, "total_steps": 861, "loss": 0.6316, "lr": 5e-06, "epoch": 2.155516941789748, "percentage": 72.01, "elapsed_time": "10:07:04", "remaining_time": "3:55:58"}
65
+ {"current_steps": 630, "total_steps": 861, "loss": 0.64, "lr": 5e-06, "epoch": 2.1902693310165073, "percentage": 73.17, "elapsed_time": "10:16:38", "remaining_time": "3:46:06"}
66
+ {"current_steps": 640, "total_steps": 861, "loss": 0.6352, "lr": 5e-06, "epoch": 2.2250217202432667, "percentage": 74.33, "elapsed_time": "10:26:14", "remaining_time": "3:36:15"}
67
+ {"current_steps": 650, "total_steps": 861, "loss": 0.6415, "lr": 5e-06, "epoch": 2.259774109470026, "percentage": 75.49, "elapsed_time": "10:35:50", "remaining_time": "3:26:24"}
68
+ {"current_steps": 660, "total_steps": 861, "loss": 0.6409, "lr": 5e-06, "epoch": 2.2945264986967855, "percentage": 76.66, "elapsed_time": "10:45:26", "remaining_time": "3:16:34"}
69
+ {"current_steps": 670, "total_steps": 861, "loss": 0.641, "lr": 5e-06, "epoch": 2.329278887923545, "percentage": 77.82, "elapsed_time": "10:55:02", "remaining_time": "3:06:44"}
70
+ {"current_steps": 680, "total_steps": 861, "loss": 0.6343, "lr": 5e-06, "epoch": 2.3640312771503043, "percentage": 78.98, "elapsed_time": "11:04:38", "remaining_time": "2:56:54"}
71
+ {"current_steps": 690, "total_steps": 861, "loss": 0.6424, "lr": 5e-06, "epoch": 2.3987836663770636, "percentage": 80.14, "elapsed_time": "11:14:14", "remaining_time": "2:47:05"}
72
+ {"current_steps": 700, "total_steps": 861, "loss": 0.6402, "lr": 5e-06, "epoch": 2.4335360556038226, "percentage": 81.3, "elapsed_time": "11:23:50", "remaining_time": "2:37:17"}
73
+ {"current_steps": 710, "total_steps": 861, "loss": 0.6405, "lr": 5e-06, "epoch": 2.468288444830582, "percentage": 82.46, "elapsed_time": "11:33:27", "remaining_time": "2:27:28"}
74
+ {"current_steps": 720, "total_steps": 861, "loss": 0.639, "lr": 5e-06, "epoch": 2.5030408340573413, "percentage": 83.62, "elapsed_time": "11:43:03", "remaining_time": "2:17:40"}
75
+ {"current_steps": 730, "total_steps": 861, "loss": 0.6451, "lr": 5e-06, "epoch": 2.5377932232841007, "percentage": 84.79, "elapsed_time": "11:52:40", "remaining_time": "2:07:53"}
76
+ {"current_steps": 740, "total_steps": 861, "loss": 0.6451, "lr": 5e-06, "epoch": 2.57254561251086, "percentage": 85.95, "elapsed_time": "12:02:16", "remaining_time": "1:58:06"}
77
+ {"current_steps": 750, "total_steps": 861, "loss": 0.6452, "lr": 5e-06, "epoch": 2.6072980017376195, "percentage": 87.11, "elapsed_time": "12:11:51", "remaining_time": "1:48:18"}
78
+ {"current_steps": 760, "total_steps": 861, "loss": 0.6435, "lr": 5e-06, "epoch": 2.642050390964379, "percentage": 88.27, "elapsed_time": "12:21:27", "remaining_time": "1:38:32"}
79
+ {"current_steps": 770, "total_steps": 861, "loss": 0.6393, "lr": 5e-06, "epoch": 2.6768027801911383, "percentage": 89.43, "elapsed_time": "12:31:03", "remaining_time": "1:28:45"}
80
+ {"current_steps": 780, "total_steps": 861, "loss": 0.6416, "lr": 5e-06, "epoch": 2.711555169417897, "percentage": 90.59, "elapsed_time": "12:40:39", "remaining_time": "1:18:59"}
81
+ {"current_steps": 790, "total_steps": 861, "loss": 0.6413, "lr": 5e-06, "epoch": 2.7463075586446566, "percentage": 91.75, "elapsed_time": "12:50:15", "remaining_time": "1:09:13"}
82
+ {"current_steps": 800, "total_steps": 861, "loss": 0.6441, "lr": 5e-06, "epoch": 2.781059947871416, "percentage": 92.92, "elapsed_time": "12:59:51", "remaining_time": "0:59:27"}
83
+ {"current_steps": 810, "total_steps": 861, "loss": 0.6432, "lr": 5e-06, "epoch": 2.8158123370981754, "percentage": 94.08, "elapsed_time": "13:09:28", "remaining_time": "0:49:42"}
84
+ {"current_steps": 820, "total_steps": 861, "loss": 0.644, "lr": 5e-06, "epoch": 2.8505647263249347, "percentage": 95.24, "elapsed_time": "13:19:04", "remaining_time": "0:39:57"}
85
+ {"current_steps": 830, "total_steps": 861, "loss": 0.6399, "lr": 5e-06, "epoch": 2.885317115551694, "percentage": 96.4, "elapsed_time": "13:28:41", "remaining_time": "0:30:12"}
86
+ {"current_steps": 840, "total_steps": 861, "loss": 0.6454, "lr": 5e-06, "epoch": 2.9200695047784535, "percentage": 97.56, "elapsed_time": "13:38:16", "remaining_time": "0:20:27"}
87
+ {"current_steps": 850, "total_steps": 861, "loss": 0.6416, "lr": 5e-06, "epoch": 2.954821894005213, "percentage": 98.72, "elapsed_time": "13:47:52", "remaining_time": "0:10:42"}
88
+ {"current_steps": 860, "total_steps": 861, "loss": 0.644, "lr": 5e-06, "epoch": 2.9895742832319723, "percentage": 99.88, "elapsed_time": "13:57:29", "remaining_time": "0:00:58"}