sedrickkeh commited on
Commit
e334966
·
verified ·
1 Parent(s): efb4055

Training in progress, epoch 1

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c48b449df4966486ef2b71be13c2ed7f57724298cf32f86e77c4c2227ddece4
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:439550c86a644ef33c99174a091647664a5ef335a2b98e390f6ea6a601357306
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43f01905ec270a34db96ebec8abd733b016ccf2d4d437e52319b9172daa6ede0
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed49a857241163a3ead15d3bd87a644ddafd7718e9eea3a53370d79e22d3af46
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ceb92a2e9a10b7b878c5642c7569f6a86194ee8014c4d869287dd5774754a0c
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f09af0aba76b8ac10049d7ec00601970c857124beca76e816d26f5d802267f66
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49604ea3f4cd149e54e1e02733b1ae00f4fbf432d0d21434f0c0bb8291c4c36c
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daee6effc19c228eb79da39e7dfbe89b9d1aff6135ec8759f612cc1e521d357f
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -48,3 +48,52 @@
48
  {"current_steps": 48, "total_steps": 147, "loss": 0.6143, "lr": 6.828427124746191e-05, "epoch": 0.9624060150375939, "percentage": 32.65, "elapsed_time": "2:02:33", "remaining_time": "4:12:46"}
49
  {"current_steps": 49, "total_steps": 147, "loss": 0.5971, "lr": 6.760316045928449e-05, "epoch": 0.9824561403508771, "percentage": 33.33, "elapsed_time": "2:05:04", "remaining_time": "4:10:08"}
50
  {"current_steps": 50, "total_steps": 147, "loss": 1.0623, "lr": 6.690641494805011e-05, "epoch": 1.0150375939849625, "percentage": 34.01, "elapsed_time": "2:09:08", "remaining_time": "4:10:32"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  {"current_steps": 48, "total_steps": 147, "loss": 0.6143, "lr": 6.828427124746191e-05, "epoch": 0.9624060150375939, "percentage": 32.65, "elapsed_time": "2:02:33", "remaining_time": "4:12:46"}
49
  {"current_steps": 49, "total_steps": 147, "loss": 0.5971, "lr": 6.760316045928449e-05, "epoch": 0.9824561403508771, "percentage": 33.33, "elapsed_time": "2:05:04", "remaining_time": "4:10:08"}
50
  {"current_steps": 50, "total_steps": 147, "loss": 1.0623, "lr": 6.690641494805011e-05, "epoch": 1.0150375939849625, "percentage": 34.01, "elapsed_time": "2:09:08", "remaining_time": "4:10:32"}
51
+ {"current_steps": 51, "total_steps": 147, "loss": 0.5949, "lr": 6.619442935781141e-05, "epoch": 1.0350877192982457, "percentage": 34.69, "elapsed_time": "2:11:40", "remaining_time": "4:07:51"}
52
+ {"current_steps": 52, "total_steps": 147, "loss": 0.5965, "lr": 6.546760696476354e-05, "epoch": 1.055137844611529, "percentage": 35.37, "elapsed_time": "2:14:12", "remaining_time": "4:05:11"}
53
+ {"current_steps": 53, "total_steps": 147, "loss": 0.5817, "lr": 6.472635944882421e-05, "epoch": 1.0751879699248121, "percentage": 36.05, "elapsed_time": "2:16:45", "remaining_time": "4:02:32"}
54
+ {"current_steps": 54, "total_steps": 147, "loss": 0.5936, "lr": 6.397110666045388e-05, "epoch": 1.0952380952380953, "percentage": 36.73, "elapsed_time": "2:19:16", "remaining_time": "3:59:51"}
55
+ {"current_steps": 55, "total_steps": 147, "loss": 0.597, "lr": 6.320227638284793e-05, "epoch": 1.1152882205513786, "percentage": 37.41, "elapsed_time": "2:21:47", "remaining_time": "3:57:11"}
56
+ {"current_steps": 56, "total_steps": 147, "loss": 0.5895, "lr": 6.242030408963576e-05, "epoch": 1.1353383458646618, "percentage": 38.1, "elapsed_time": "2:24:19", "remaining_time": "3:54:31"}
57
+ {"current_steps": 57, "total_steps": 147, "loss": 0.5796, "lr": 6.162563269822391e-05, "epoch": 1.155388471177945, "percentage": 38.78, "elapsed_time": "2:26:50", "remaining_time": "3:51:51"}
58
+ {"current_steps": 58, "total_steps": 147, "loss": 0.5756, "lr": 6.0818712318922894e-05, "epoch": 1.1754385964912282, "percentage": 39.46, "elapsed_time": "2:29:22", "remaining_time": "3:49:12"}
59
+ {"current_steps": 59, "total_steps": 147, "loss": 0.5899, "lr": 6.000000000000001e-05, "epoch": 1.1954887218045114, "percentage": 40.14, "elapsed_time": "2:31:53", "remaining_time": "3:46:33"}
60
+ {"current_steps": 60, "total_steps": 147, "loss": 0.5756, "lr": 5.916995946880228e-05, "epoch": 1.2155388471177946, "percentage": 40.82, "elapsed_time": "2:34:25", "remaining_time": "3:43:54"}
61
+ {"current_steps": 61, "total_steps": 147, "loss": 0.5717, "lr": 5.832906086909642e-05, "epoch": 1.2355889724310778, "percentage": 41.5, "elapsed_time": "2:36:56", "remaining_time": "3:41:16"}
62
+ {"current_steps": 62, "total_steps": 147, "loss": 0.5719, "lr": 5.747778049477438e-05, "epoch": 1.255639097744361, "percentage": 42.18, "elapsed_time": "2:39:29", "remaining_time": "3:38:39"}
63
+ {"current_steps": 63, "total_steps": 147, "loss": 0.5767, "lr": 5.661660052007547e-05, "epoch": 1.2756892230576442, "percentage": 42.86, "elapsed_time": "2:42:02", "remaining_time": "3:36:03"}
64
+ {"current_steps": 64, "total_steps": 147, "loss": 0.5754, "lr": 5.574600872647766e-05, "epoch": 1.2957393483709274, "percentage": 43.54, "elapsed_time": "2:44:34", "remaining_time": "3:33:25"}
65
+ {"current_steps": 65, "total_steps": 147, "loss": 0.5806, "lr": 5.48664982264131e-05, "epoch": 1.3157894736842106, "percentage": 44.22, "elapsed_time": "2:47:05", "remaining_time": "3:30:47"}
66
+ {"current_steps": 66, "total_steps": 147, "loss": 0.5622, "lr": 5.397856718396394e-05, "epoch": 1.3358395989974938, "percentage": 44.9, "elapsed_time": "2:49:36", "remaining_time": "3:28:09"}
67
+ {"current_steps": 67, "total_steps": 147, "loss": 0.5635, "lr": 5.3082718532696874e-05, "epoch": 1.355889724310777, "percentage": 45.58, "elapsed_time": "2:52:09", "remaining_time": "3:25:33"}
68
+ {"current_steps": 68, "total_steps": 147, "loss": 0.5728, "lr": 5.217945969079629e-05, "epoch": 1.3759398496240602, "percentage": 46.26, "elapsed_time": "2:54:41", "remaining_time": "3:22:56"}
69
+ {"current_steps": 69, "total_steps": 147, "loss": 0.5829, "lr": 5.1269302273657195e-05, "epoch": 1.3959899749373434, "percentage": 46.94, "elapsed_time": "2:57:13", "remaining_time": "3:20:20"}
70
+ {"current_steps": 70, "total_steps": 147, "loss": 0.5797, "lr": 5.0352761804100835e-05, "epoch": 1.4160401002506267, "percentage": 47.62, "elapsed_time": "2:59:45", "remaining_time": "3:17:43"}
71
+ {"current_steps": 71, "total_steps": 147, "loss": 0.5678, "lr": 4.94303574203771e-05, "epoch": 1.4360902255639099, "percentage": 48.3, "elapsed_time": "3:02:16", "remaining_time": "3:15:06"}
72
+ {"current_steps": 72, "total_steps": 147, "loss": 0.5644, "lr": 4.8502611582119065e-05, "epoch": 1.456140350877193, "percentage": 48.98, "elapsed_time": "3:04:47", "remaining_time": "3:12:29"}
73
+ {"current_steps": 73, "total_steps": 147, "loss": 0.5696, "lr": 4.7570049774416414e-05, "epoch": 1.4761904761904763, "percentage": 49.66, "elapsed_time": "3:07:18", "remaining_time": "3:09:52"}
74
+ {"current_steps": 74, "total_steps": 147, "loss": 0.5574, "lr": 4.663320021017497e-05, "epoch": 1.4962406015037595, "percentage": 50.34, "elapsed_time": "3:09:49", "remaining_time": "3:07:15"}
75
+ {"current_steps": 75, "total_steps": 147, "loss": 0.5683, "lr": 4.5692593530931416e-05, "epoch": 1.5162907268170427, "percentage": 51.02, "elapsed_time": "3:12:20", "remaining_time": "3:04:39"}
76
+ {"current_steps": 76, "total_steps": 147, "loss": 0.565, "lr": 4.474876250629221e-05, "epoch": 1.536340852130326, "percentage": 51.7, "elapsed_time": "3:14:53", "remaining_time": "3:02:03"}
77
+ {"current_steps": 77, "total_steps": 147, "loss": 0.5641, "lr": 4.38022417321673e-05, "epoch": 1.556390977443609, "percentage": 52.38, "elapsed_time": "3:17:24", "remaining_time": "2:59:27"}
78
+ {"current_steps": 78, "total_steps": 147, "loss": 0.557, "lr": 4.2853567327969296e-05, "epoch": 1.5764411027568923, "percentage": 53.06, "elapsed_time": "3:19:55", "remaining_time": "2:56:51"}
79
+ {"current_steps": 79, "total_steps": 147, "loss": 0.5578, "lr": 4.19032766329497e-05, "epoch": 1.5964912280701755, "percentage": 53.74, "elapsed_time": "3:22:26", "remaining_time": "2:54:14"}
80
+ {"current_steps": 80, "total_steps": 147, "loss": 0.5622, "lr": 4.0951907901844296e-05, "epoch": 1.6165413533834587, "percentage": 54.42, "elapsed_time": "3:24:57", "remaining_time": "2:51:38"}
81
+ {"current_steps": 81, "total_steps": 147, "loss": 0.5657, "lr": 4e-05, "epoch": 1.636591478696742, "percentage": 55.1, "elapsed_time": "3:27:30", "remaining_time": "2:49:04"}
82
+ {"current_steps": 82, "total_steps": 147, "loss": 0.5603, "lr": 3.904809209815571e-05, "epoch": 1.6566416040100251, "percentage": 55.78, "elapsed_time": "3:30:02", "remaining_time": "2:46:29"}
83
+ {"current_steps": 83, "total_steps": 147, "loss": 0.5572, "lr": 3.809672336705031e-05, "epoch": 1.6766917293233083, "percentage": 56.46, "elapsed_time": "3:32:34", "remaining_time": "2:43:54"}
84
+ {"current_steps": 84, "total_steps": 147, "loss": 0.5544, "lr": 3.714643267203071e-05, "epoch": 1.6967418546365916, "percentage": 57.14, "elapsed_time": "3:35:07", "remaining_time": "2:41:20"}
85
+ {"current_steps": 85, "total_steps": 147, "loss": 0.5584, "lr": 3.6197758267832705e-05, "epoch": 1.7167919799498748, "percentage": 57.82, "elapsed_time": "3:37:39", "remaining_time": "2:38:45"}
86
+ {"current_steps": 86, "total_steps": 147, "loss": 0.5677, "lr": 3.5251237493707804e-05, "epoch": 1.736842105263158, "percentage": 58.5, "elapsed_time": "3:40:11", "remaining_time": "2:36:11"}
87
+ {"current_steps": 87, "total_steps": 147, "loss": 0.5632, "lr": 3.4307406469068604e-05, "epoch": 1.7568922305764412, "percentage": 59.18, "elapsed_time": "3:42:43", "remaining_time": "2:33:36"}
88
+ {"current_steps": 88, "total_steps": 147, "loss": 0.5512, "lr": 3.3366799789825044e-05, "epoch": 1.7769423558897244, "percentage": 59.86, "elapsed_time": "3:45:14", "remaining_time": "2:31:01"}
89
+ {"current_steps": 89, "total_steps": 147, "loss": 0.5493, "lr": 3.2429950225583606e-05, "epoch": 1.7969924812030076, "percentage": 60.54, "elapsed_time": "3:47:46", "remaining_time": "2:28:26"}
90
+ {"current_steps": 90, "total_steps": 147, "loss": 0.5522, "lr": 3.1497388417880935e-05, "epoch": 1.8170426065162908, "percentage": 61.22, "elapsed_time": "3:50:17", "remaining_time": "2:25:51"}
91
+ {"current_steps": 91, "total_steps": 147, "loss": 0.5533, "lr": 3.0569642579622905e-05, "epoch": 1.837092731829574, "percentage": 61.9, "elapsed_time": "3:52:50", "remaining_time": "2:23:17"}
92
+ {"current_steps": 92, "total_steps": 147, "loss": 0.538, "lr": 2.9647238195899168e-05, "epoch": 1.8571428571428572, "percentage": 62.59, "elapsed_time": "3:55:21", "remaining_time": "2:20:42"}
93
+ {"current_steps": 93, "total_steps": 147, "loss": 0.5613, "lr": 2.873069772634281e-05, "epoch": 1.8771929824561404, "percentage": 63.27, "elapsed_time": "3:57:53", "remaining_time": "2:18:07"}
94
+ {"current_steps": 94, "total_steps": 147, "loss": 0.5561, "lr": 2.7820540309203728e-05, "epoch": 1.8972431077694236, "percentage": 63.95, "elapsed_time": "4:00:24", "remaining_time": "2:15:33"}
95
+ {"current_steps": 95, "total_steps": 147, "loss": 0.5619, "lr": 2.691728146730314e-05, "epoch": 1.9172932330827068, "percentage": 64.63, "elapsed_time": "4:02:56", "remaining_time": "2:12:58"}
96
+ {"current_steps": 96, "total_steps": 147, "loss": 0.557, "lr": 2.6021432816036073e-05, "epoch": 1.93734335839599, "percentage": 65.31, "elapsed_time": "4:05:28", "remaining_time": "2:10:24"}
97
+ {"current_steps": 97, "total_steps": 147, "loss": 0.55, "lr": 2.5133501773586905e-05, "epoch": 1.9573934837092732, "percentage": 65.99, "elapsed_time": "4:08:02", "remaining_time": "2:07:51"}
98
+ {"current_steps": 98, "total_steps": 147, "loss": 0.5615, "lr": 2.425399127352235e-05, "epoch": 1.9774436090225564, "percentage": 66.67, "elapsed_time": "4:10:34", "remaining_time": "2:05:17"}
99
+ {"current_steps": 99, "total_steps": 147, "loss": 0.984, "lr": 2.338339947992455e-05, "epoch": 2.0100250626566414, "percentage": 67.35, "elapsed_time": "4:14:41", "remaining_time": "2:03:29"}