sedrickkeh commited on
Commit
2237d76
·
verified ·
1 Parent(s): 326b61c

Training in progress, step 165

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2845b2c2fbb325b07117280312ec89fa391559ff8a49386419fd0c7c249b5d56
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:947129636623f087b4fd99bb35fa83f97ab11ece59357e909364dd2bc8a4b0c1
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:b2fb7ef9aecc47c86fb8747764a69785bf9d2e49bd26a86cfba51a86011c32fd
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:590296a24fa82e16aad574322ef0e1169aa6933e7158edd33e2582bd48bdbd43
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ad711b9b85d29072812cca1ea28597ebca80212c277b971608eca668396eae8
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a992a8804a3cdc5f41518211016b6d79061debfde20c9e6e2cd975f0842a7ebc
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28fda9f1102bb033980b7e4343e01abac9ff22c87b3c69a9bdcbc6d1d30570c8
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c8bc47f7a353278425039aecdedb57877f2780e007a079d7cb3a9807ce55813
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -98,3 +98,69 @@
98
  {"current_steps": 98, "total_steps": 165, "loss": 0.5204, "lr": 4.259786641731344e-06, "epoch": 1.7737556561085972, "percentage": 59.39, "elapsed_time": "7:18:56", "remaining_time": "5:00:05"}
99
  {"current_steps": 99, "total_steps": 165, "loss": 0.5207, "lr": 4.154995898390756e-06, "epoch": 1.7918552036199094, "percentage": 60.0, "elapsed_time": "7:23:26", "remaining_time": "4:55:37"}
100
  {"current_steps": 100, "total_steps": 165, "loss": 0.5401, "lr": 4.050585886562858e-06, "epoch": 1.8099547511312217, "percentage": 60.61, "elapsed_time": "7:27:55", "remaining_time": "4:51:08"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
98
  {"current_steps": 98, "total_steps": 165, "loss": 0.5204, "lr": 4.259786641731344e-06, "epoch": 1.7737556561085972, "percentage": 59.39, "elapsed_time": "7:18:56", "remaining_time": "5:00:05"}
99
  {"current_steps": 99, "total_steps": 165, "loss": 0.5207, "lr": 4.154995898390756e-06, "epoch": 1.7918552036199094, "percentage": 60.0, "elapsed_time": "7:23:26", "remaining_time": "4:55:37"}
100
  {"current_steps": 100, "total_steps": 165, "loss": 0.5401, "lr": 4.050585886562858e-06, "epoch": 1.8099547511312217, "percentage": 60.61, "elapsed_time": "7:27:55", "remaining_time": "4:51:08"}
101
+ {"current_steps": 101, "total_steps": 165, "loss": 0.525, "lr": 3.94660365002137e-06, "epoch": 1.8280542986425339, "percentage": 61.21, "elapsed_time": "7:33:28", "remaining_time": "4:47:21"}
102
+ {"current_steps": 102, "total_steps": 165, "loss": 0.5267, "lr": 3.843096039798293e-06, "epoch": 1.8461538461538463, "percentage": 61.82, "elapsed_time": "7:37:57", "remaining_time": "4:42:51"}
103
+ {"current_steps": 103, "total_steps": 165, "loss": 0.5225, "lr": 3.7401096930743753e-06, "epoch": 1.8642533936651584, "percentage": 62.42, "elapsed_time": "7:42:25", "remaining_time": "4:38:21"}
104
+ {"current_steps": 104, "total_steps": 165, "loss": 0.5183, "lr": 3.6376910121658867e-06, "epoch": 1.8823529411764706, "percentage": 63.03, "elapsed_time": "7:46:54", "remaining_time": "4:33:51"}
105
+ {"current_steps": 105, "total_steps": 165, "loss": 0.5338, "lr": 3.5358861436172487e-06, "epoch": 1.9004524886877827, "percentage": 63.64, "elapsed_time": "7:51:23", "remaining_time": "4:29:22"}
106
+ {"current_steps": 106, "total_steps": 165, "loss": 0.5248, "lr": 3.4347409574088896e-06, "epoch": 1.9185520361990949, "percentage": 64.24, "elapsed_time": "7:55:51", "remaining_time": "4:24:51"}
107
+ {"current_steps": 107, "total_steps": 165, "loss": 0.5172, "lr": 3.3343010262897125e-06, "epoch": 1.9366515837104072, "percentage": 64.85, "elapsed_time": "8:00:19", "remaining_time": "4:20:22"}
108
+ {"current_steps": 108, "total_steps": 165, "loss": 0.5416, "lr": 3.234611605243496e-06, "epoch": 1.9547511312217196, "percentage": 65.45, "elapsed_time": "8:04:49", "remaining_time": "4:15:52"}
109
+ {"current_steps": 109, "total_steps": 165, "loss": 0.5169, "lr": 3.1357176110984578e-06, "epoch": 1.9728506787330318, "percentage": 66.06, "elapsed_time": "8:09:19", "remaining_time": "4:11:23"}
110
+ {"current_steps": 110, "total_steps": 165, "loss": 0.5031, "lr": 3.0376636022891813e-06, "epoch": 1.990950226244344, "percentage": 66.67, "elapsed_time": "8:13:49", "remaining_time": "4:06:54"}
111
+ {"current_steps": 111, "total_steps": 165, "loss": 0.8733, "lr": 2.9404937587800374e-06, "epoch": 2.009049773755656, "percentage": 67.27, "elapsed_time": "8:18:47", "remaining_time": "4:02:39"}
112
+ {"current_steps": 112, "total_steps": 165, "loss": 0.5102, "lr": 2.8442518621591085e-06, "epoch": 2.0271493212669682, "percentage": 67.88, "elapsed_time": "8:23:16", "remaining_time": "3:58:09"}
113
+ {"current_steps": 113, "total_steps": 165, "loss": 0.4991, "lr": 2.748981275911633e-06, "epoch": 2.0452488687782804, "percentage": 68.48, "elapsed_time": "8:27:45", "remaining_time": "3:53:39"}
114
+ {"current_steps": 114, "total_steps": 165, "loss": 0.4811, "lr": 2.6547249258818162e-06, "epoch": 2.0633484162895925, "percentage": 69.09, "elapsed_time": "8:32:15", "remaining_time": "3:49:10"}
115
+ {"current_steps": 115, "total_steps": 165, "loss": 0.5246, "lr": 2.5615252809318287e-06, "epoch": 2.081447963800905, "percentage": 69.7, "elapsed_time": "8:36:46", "remaining_time": "3:44:40"}
116
+ {"current_steps": 116, "total_steps": 165, "loss": 0.5181, "lr": 2.469424333806718e-06, "epoch": 2.0995475113122173, "percentage": 70.3, "elapsed_time": "8:41:18", "remaining_time": "3:40:12"}
117
+ {"current_steps": 117, "total_steps": 165, "loss": 0.5112, "lr": 2.3784635822138424e-06, "epoch": 2.1176470588235294, "percentage": 70.91, "elapsed_time": "8:45:45", "remaining_time": "3:35:41"}
118
+ {"current_steps": 118, "total_steps": 165, "loss": 0.5114, "lr": 2.288684010125325e-06, "epoch": 2.1357466063348416, "percentage": 71.52, "elapsed_time": "8:50:15", "remaining_time": "3:31:12"}
119
+ {"current_steps": 119, "total_steps": 165, "loss": 0.4967, "lr": 2.2001260693120236e-06, "epoch": 2.1538461538461537, "percentage": 72.12, "elapsed_time": "8:54:45", "remaining_time": "3:26:42"}
120
+ {"current_steps": 120, "total_steps": 165, "loss": 0.4959, "lr": 2.1128296611172593e-06, "epoch": 2.171945701357466, "percentage": 72.73, "elapsed_time": "8:59:13", "remaining_time": "3:22:12"}
121
+ {"current_steps": 121, "total_steps": 165, "loss": 0.5088, "lr": 2.0268341184785674e-06, "epoch": 2.1900452488687785, "percentage": 73.33, "elapsed_time": "9:03:40", "remaining_time": "3:17:41"}
122
+ {"current_steps": 122, "total_steps": 165, "loss": 0.4917, "lr": 1.9421781882055447e-06, "epoch": 2.2081447963800906, "percentage": 73.94, "elapsed_time": "9:08:08", "remaining_time": "3:13:11"}
123
+ {"current_steps": 123, "total_steps": 165, "loss": 0.5023, "lr": 1.8589000135217882e-06, "epoch": 2.226244343891403, "percentage": 74.55, "elapsed_time": "9:12:38", "remaining_time": "3:08:42"}
124
+ {"current_steps": 124, "total_steps": 165, "loss": 0.4863, "lr": 1.7770371168788042e-06, "epoch": 2.244343891402715, "percentage": 75.15, "elapsed_time": "9:17:06", "remaining_time": "3:04:12"}
125
+ {"current_steps": 125, "total_steps": 165, "loss": 0.4873, "lr": 1.6966263830495939e-06, "epoch": 2.262443438914027, "percentage": 75.76, "elapsed_time": "9:21:36", "remaining_time": "2:59:42"}
126
+ {"current_steps": 126, "total_steps": 165, "loss": 0.4977, "lr": 1.6177040425095664e-06, "epoch": 2.2805429864253393, "percentage": 76.36, "elapsed_time": "9:26:07", "remaining_time": "2:55:13"}
127
+ {"current_steps": 127, "total_steps": 165, "loss": 0.4998, "lr": 1.5403056551122697e-06, "epoch": 2.2986425339366514, "percentage": 76.97, "elapsed_time": "9:30:37", "remaining_time": "2:50:44"}
128
+ {"current_steps": 128, "total_steps": 165, "loss": 0.5061, "lr": 1.4644660940672628e-06, "epoch": 2.3167420814479636, "percentage": 77.58, "elapsed_time": "9:35:08", "remaining_time": "2:46:15"}
129
+ {"current_steps": 129, "total_steps": 165, "loss": 0.5169, "lr": 1.390219530227378e-06, "epoch": 2.334841628959276, "percentage": 78.18, "elapsed_time": "9:39:39", "remaining_time": "2:41:45"}
130
+ {"current_steps": 130, "total_steps": 165, "loss": 0.5023, "lr": 1.3175994166924394e-06, "epoch": 2.3529411764705883, "percentage": 78.79, "elapsed_time": "9:44:08", "remaining_time": "2:37:16"}
131
+ {"current_steps": 131, "total_steps": 165, "loss": 0.4753, "lr": 1.246638473736378e-06, "epoch": 2.3710407239819005, "percentage": 79.39, "elapsed_time": "9:48:36", "remaining_time": "2:32:46"}
132
+ {"current_steps": 132, "total_steps": 165, "loss": 0.5136, "lr": 1.1773686740645384e-06, "epoch": 2.3891402714932126, "percentage": 80.0, "elapsed_time": "9:53:05", "remaining_time": "2:28:16"}
133
+ {"current_steps": 133, "total_steps": 165, "loss": 0.5009, "lr": 1.1098212284078037e-06, "epoch": 2.4072398190045248, "percentage": 80.61, "elapsed_time": "9:57:34", "remaining_time": "2:23:46"}
134
+ {"current_steps": 134, "total_steps": 165, "loss": 0.5246, "lr": 1.0440265714600573e-06, "epoch": 2.425339366515837, "percentage": 81.21, "elapsed_time": "10:02:02", "remaining_time": "2:19:16"}
135
+ {"current_steps": 135, "total_steps": 165, "loss": 0.5026, "lr": 9.80014348165298e-07, "epoch": 2.4434389140271495, "percentage": 81.82, "elapsed_time": "10:06:30", "remaining_time": "2:14:46"}
136
+ {"current_steps": 136, "total_steps": 165, "loss": 0.492, "lr": 9.178134003605721e-07, "epoch": 2.4615384615384617, "percentage": 82.42, "elapsed_time": "10:10:59", "remaining_time": "2:10:17"}
137
+ {"current_steps": 137, "total_steps": 165, "loss": 0.5105, "lr": 8.574517537807897e-07, "epoch": 2.479638009049774, "percentage": 83.03, "elapsed_time": "10:15:28", "remaining_time": "2:05:47"}
138
+ {"current_steps": 138, "total_steps": 165, "loss": 0.5143, "lr": 7.989566054312286e-07, "epoch": 2.497737556561086, "percentage": 83.64, "elapsed_time": "10:19:56", "remaining_time": "2:01:17"}
139
+ {"current_steps": 139, "total_steps": 165, "loss": 0.4849, "lr": 7.423543113334436e-07, "epoch": 2.515837104072398, "percentage": 84.24, "elapsed_time": "10:24:25", "remaining_time": "1:56:48"}
140
+ {"current_steps": 140, "total_steps": 165, "loss": 0.4903, "lr": 6.876703746500984e-07, "epoch": 2.5339366515837103, "percentage": 84.85, "elapsed_time": "10:28:53", "remaining_time": "1:52:18"}
141
+ {"current_steps": 141, "total_steps": 165, "loss": 0.4772, "lr": 6.349294341940593e-07, "epoch": 2.5520361990950224, "percentage": 85.45, "elapsed_time": "10:33:20", "remaining_time": "1:47:48"}
142
+ {"current_steps": 142, "total_steps": 165, "loss": 0.5162, "lr": 5.841552533269534e-07, "epoch": 2.5701357466063346, "percentage": 86.06, "elapsed_time": "10:37:48", "remaining_time": "1:43:18"}
143
+ {"current_steps": 143, "total_steps": 165, "loss": 0.4976, "lr": 5.353707092521581e-07, "epoch": 2.588235294117647, "percentage": 86.67, "elapsed_time": "10:42:17", "remaining_time": "1:38:48"}
144
+ {"current_steps": 144, "total_steps": 165, "loss": 0.5116, "lr": 4.885977827070748e-07, "epoch": 2.6063348416289593, "percentage": 87.27, "elapsed_time": "10:46:45", "remaining_time": "1:34:19"}
145
+ {"current_steps": 145, "total_steps": 165, "loss": 0.5115, "lr": 4.43857548059321e-07, "epoch": 2.6244343891402715, "percentage": 87.88, "elapsed_time": "10:51:13", "remaining_time": "1:29:49"}
146
+ {"current_steps": 146, "total_steps": 165, "loss": 0.4798, "lr": 4.0117016381130636e-07, "epoch": 2.6425339366515836, "percentage": 88.48, "elapsed_time": "10:55:41", "remaining_time": "1:25:19"}
147
+ {"current_steps": 147, "total_steps": 165, "loss": 0.4998, "lr": 3.6055486351745327e-07, "epoch": 2.660633484162896, "percentage": 89.09, "elapsed_time": "11:00:08", "remaining_time": "1:20:49"}
148
+ {"current_steps": 148, "total_steps": 165, "loss": 0.5039, "lr": 3.220299471181898e-07, "epoch": 2.6787330316742084, "percentage": 89.7, "elapsed_time": "11:04:37", "remaining_time": "1:16:20"}
149
+ {"current_steps": 149, "total_steps": 165, "loss": 0.4928, "lr": 2.85612772694579e-07, "epoch": 2.6968325791855206, "percentage": 90.3, "elapsed_time": "11:09:05", "remaining_time": "1:11:50"}
150
+ {"current_steps": 150, "total_steps": 165, "loss": 0.5131, "lr": 2.5131974864734063e-07, "epoch": 2.7149321266968327, "percentage": 90.91, "elapsed_time": "11:13:34", "remaining_time": "1:07:21"}
151
+ {"current_steps": 151, "total_steps": 165, "loss": 0.5145, "lr": 2.1916632630374579e-07, "epoch": 2.733031674208145, "percentage": 91.52, "elapsed_time": "11:18:03", "remaining_time": "1:02:51"}
152
+ {"current_steps": 152, "total_steps": 165, "loss": 0.4964, "lr": 1.8916699295575324e-07, "epoch": 2.751131221719457, "percentage": 92.12, "elapsed_time": "11:22:30", "remaining_time": "0:58:22"}
153
+ {"current_steps": 153, "total_steps": 165, "loss": 0.4855, "lr": 1.6133526533250566e-07, "epoch": 2.769230769230769, "percentage": 92.73, "elapsed_time": "11:26:58", "remaining_time": "0:53:52"}
154
+ {"current_steps": 154, "total_steps": 165, "loss": 0.4966, "lr": 1.3568368351012718e-07, "epoch": 2.7873303167420813, "percentage": 93.33, "elapsed_time": "11:31:25", "remaining_time": "0:49:23"}
155
+ {"current_steps": 155, "total_steps": 165, "loss": 0.4974, "lr": 1.1222380526156929e-07, "epoch": 2.8054298642533935, "percentage": 93.94, "elapsed_time": "11:35:55", "remaining_time": "0:44:53"}
156
+ {"current_steps": 156, "total_steps": 165, "loss": 0.5191, "lr": 9.096620084905472e-08, "epoch": 2.8235294117647056, "percentage": 94.55, "elapsed_time": "11:40:23", "remaining_time": "0:40:24"}
157
+ {"current_steps": 157, "total_steps": 165, "loss": 0.5268, "lr": 7.192044826145772e-08, "epoch": 2.841628959276018, "percentage": 95.15, "elapsed_time": "11:44:50", "remaining_time": "0:35:54"}
158
+ {"current_steps": 158, "total_steps": 165, "loss": 0.5088, "lr": 5.509512889877333e-08, "epoch": 2.8597285067873304, "percentage": 95.76, "elapsed_time": "11:49:17", "remaining_time": "0:31:25"}
159
+ {"current_steps": 159, "total_steps": 165, "loss": 0.4942, "lr": 4.0497823705615836e-08, "epoch": 2.8778280542986425, "percentage": 96.36, "elapsed_time": "11:53:46", "remaining_time": "0:26:56"}
160
+ {"current_steps": 160, "total_steps": 165, "loss": 0.5331, "lr": 2.8135109755487723e-08, "epoch": 2.8959276018099547, "percentage": 96.97, "elapsed_time": "11:58:15", "remaining_time": "0:22:26"}
161
+ {"current_steps": 161, "total_steps": 165, "loss": 0.4901, "lr": 1.8012557287367394e-08, "epoch": 2.914027149321267, "percentage": 97.58, "elapsed_time": "12:02:44", "remaining_time": "0:17:57"}
162
+ {"current_steps": 162, "total_steps": 165, "loss": 0.5096, "lr": 1.0134727195937332e-08, "epoch": 2.9321266968325794, "percentage": 98.18, "elapsed_time": "12:07:14", "remaining_time": "0:13:28"}
163
+ {"current_steps": 163, "total_steps": 165, "loss": 0.5248, "lr": 4.505168976592922e-09, "epoch": 2.9502262443438916, "percentage": 98.79, "elapsed_time": "12:11:42", "remaining_time": "0:08:58"}
164
+ {"current_steps": 164, "total_steps": 165, "loss": 0.5081, "lr": 1.1264191261528557e-09, "epoch": 2.9683257918552037, "percentage": 99.39, "elapsed_time": "12:16:10", "remaining_time": "0:04:29"}
165
+ {"current_steps": 165, "total_steps": 165, "loss": 0.5126, "lr": 0.0, "epoch": 2.986425339366516, "percentage": 100.0, "elapsed_time": "12:20:38", "remaining_time": "0:00:00"}
166
+ {"current_steps": 165, "total_steps": 165, "epoch": 2.986425339366516, "percentage": 100.0, "elapsed_time": "12:21:48", "remaining_time": "0:00:00"}