Training in progress, step 1500
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +51 -0
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 65309632
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94d4307985ce2a057348edf87e2c21821a976e2146130075abc3f5f0e790c154
|
3 |
size 65309632
|
trainer_log.jsonl
CHANGED
@@ -100,3 +100,54 @@
|
|
100 |
{"current_steps": 990, "total_steps": 1686, "loss": 1.4872, "accuracy": 0.44999998807907104, "learning_rate": 1.8239381598343576e-06, "epoch": 1.76039119804401, "percentage": 58.72, "elapsed_time": "3:02:59", "remaining_time": "2:08:39"}
|
101 |
{"current_steps": 1000, "total_steps": 1686, "loss": 1.5401, "accuracy": 0.4749999940395355, "learning_rate": 1.779207600392312e-06, "epoch": 1.7781729273171816, "percentage": 59.31, "elapsed_time": "3:06:18", "remaining_time": "2:07:48"}
|
102 |
{"current_steps": 1000, "total_steps": 1686, "eval_loss": 1.5269325971603394, "epoch": 1.7781729273171816, "percentage": 59.31, "elapsed_time": "3:13:06", "remaining_time": "2:12:28"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
100 |
{"current_steps": 990, "total_steps": 1686, "loss": 1.4872, "accuracy": 0.44999998807907104, "learning_rate": 1.8239381598343576e-06, "epoch": 1.76039119804401, "percentage": 58.72, "elapsed_time": "3:02:59", "remaining_time": "2:08:39"}
|
101 |
{"current_steps": 1000, "total_steps": 1686, "loss": 1.5401, "accuracy": 0.4749999940395355, "learning_rate": 1.779207600392312e-06, "epoch": 1.7781729273171816, "percentage": 59.31, "elapsed_time": "3:06:18", "remaining_time": "2:07:48"}
|
102 |
{"current_steps": 1000, "total_steps": 1686, "eval_loss": 1.5269325971603394, "epoch": 1.7781729273171816, "percentage": 59.31, "elapsed_time": "3:13:06", "remaining_time": "2:12:28"}
|
103 |
+
{"current_steps": 1010, "total_steps": 1686, "loss": 1.5549, "accuracy": 0.45625001192092896, "learning_rate": 1.7347273253353552e-06, "epoch": 1.7959546565903532, "percentage": 59.91, "elapsed_time": "3:16:16", "remaining_time": "2:11:21"}
|
104 |
+
{"current_steps": 1020, "total_steps": 1686, "loss": 1.5345, "accuracy": 0.46875, "learning_rate": 1.690512779774029e-06, "epoch": 1.8137363858635251, "percentage": 60.5, "elapsed_time": "3:19:31", "remaining_time": "2:10:16"}
|
105 |
+
{"current_steps": 1030, "total_steps": 1686, "loss": 1.4553, "accuracy": 0.518750011920929, "learning_rate": 1.6465793165482838e-06, "epoch": 1.831518115136697, "percentage": 61.09, "elapsed_time": "3:22:46", "remaining_time": "2:09:08"}
|
106 |
+
{"current_steps": 1040, "total_steps": 1686, "loss": 1.5112, "accuracy": 0.5687500238418579, "learning_rate": 1.6029421908964305e-06, "epoch": 1.849299844409869, "percentage": 61.68, "elapsed_time": "3:25:43", "remaining_time": "2:07:47"}
|
107 |
+
{"current_steps": 1050, "total_steps": 1686, "loss": 1.529, "accuracy": 0.4937500059604645, "learning_rate": 1.559616555157985e-06, "epoch": 1.8670815736830408, "percentage": 62.28, "elapsed_time": "3:28:58", "remaining_time": "2:06:34"}
|
108 |
+
{"current_steps": 1060, "total_steps": 1686, "loss": 1.5985, "accuracy": 0.46875, "learning_rate": 1.516617453512252e-06, "epoch": 1.8848633029562125, "percentage": 62.87, "elapsed_time": "3:32:10", "remaining_time": "2:05:18"}
|
109 |
+
{"current_steps": 1070, "total_steps": 1686, "loss": 1.4506, "accuracy": 0.5062500238418579, "learning_rate": 1.473959816754449e-06, "epoch": 1.9026450322293842, "percentage": 63.46, "elapsed_time": "3:35:14", "remaining_time": "2:03:54"}
|
110 |
+
{"current_steps": 1080, "total_steps": 1686, "loss": 1.5255, "accuracy": 0.44999998807907104, "learning_rate": 1.4316584571112213e-06, "epoch": 1.920426761502556, "percentage": 64.06, "elapsed_time": "3:38:25", "remaining_time": "2:02:33"}
|
111 |
+
{"current_steps": 1090, "total_steps": 1686, "loss": 1.5134, "accuracy": 0.48750001192092896, "learning_rate": 1.389728063097306e-06, "epoch": 1.938208490775728, "percentage": 64.65, "elapsed_time": "3:41:41", "remaining_time": "2:01:13"}
|
112 |
+
{"current_steps": 1100, "total_steps": 1686, "loss": 1.4884, "accuracy": 0.5249999761581421, "learning_rate": 1.348183194415179e-06, "epoch": 1.9559902200488999, "percentage": 65.24, "elapsed_time": "3:44:38", "remaining_time": "1:59:40"}
|
113 |
+
{"current_steps": 1110, "total_steps": 1686, "loss": 1.5057, "accuracy": 0.512499988079071, "learning_rate": 1.3070382768994015e-06, "epoch": 1.9737719493220716, "percentage": 65.84, "elapsed_time": "3:47:54", "remaining_time": "1:58:15"}
|
114 |
+
{"current_steps": 1120, "total_steps": 1686, "loss": 1.5613, "accuracy": 0.4937500059604645, "learning_rate": 1.2663075975074746e-06, "epoch": 1.9915536785952432, "percentage": 66.43, "elapsed_time": "3:51:11", "remaining_time": "1:56:50"}
|
115 |
+
{"current_steps": 1130, "total_steps": 1686, "loss": 1.615, "accuracy": 0.4625000059604645, "learning_rate": 1.2260052993589034e-06, "epoch": 2.009335407868415, "percentage": 67.02, "elapsed_time": "3:54:24", "remaining_time": "1:55:20"}
|
116 |
+
{"current_steps": 1140, "total_steps": 1686, "loss": 1.5179, "accuracy": 0.5375000238418579, "learning_rate": 1.1861453768242099e-06, "epoch": 2.027117137141587, "percentage": 67.62, "elapsed_time": "3:57:33", "remaining_time": "1:53:46"}
|
117 |
+
{"current_steps": 1150, "total_steps": 1686, "loss": 1.6125, "accuracy": 0.4937500059604645, "learning_rate": 1.1467416706655982e-06, "epoch": 2.044898866414759, "percentage": 68.21, "elapsed_time": "4:00:54", "remaining_time": "1:52:17"}
|
118 |
+
{"current_steps": 1160, "total_steps": 1686, "loss": 1.5053, "accuracy": 0.550000011920929, "learning_rate": 1.1078078632309559e-06, "epoch": 2.062680595687931, "percentage": 68.8, "elapsed_time": "4:04:00", "remaining_time": "1:50:38"}
|
119 |
+
{"current_steps": 1170, "total_steps": 1686, "loss": 1.5773, "accuracy": 0.48124998807907104, "learning_rate": 1.0693574737028627e-06, "epoch": 2.0804623249611023, "percentage": 69.4, "elapsed_time": "4:07:14", "remaining_time": "1:49:02"}
|
120 |
+
{"current_steps": 1180, "total_steps": 1686, "loss": 1.4589, "accuracy": 0.4749999940395355, "learning_rate": 1.0314038534042586e-06, "epoch": 2.098244054234274, "percentage": 69.99, "elapsed_time": "4:10:30", "remaining_time": "1:47:25"}
|
121 |
+
{"current_steps": 1190, "total_steps": 1686, "loss": 1.4943, "accuracy": 0.4937500059604645, "learning_rate": 9.939601811623946e-07, "epoch": 2.116025783507446, "percentage": 70.58, "elapsed_time": "4:13:33", "remaining_time": "1:45:41"}
|
122 |
+
{"current_steps": 1200, "total_steps": 1686, "loss": 1.4962, "accuracy": 0.543749988079071, "learning_rate": 9.570394587326825e-07, "epoch": 2.133807512780618, "percentage": 71.17, "elapsed_time": "4:16:43", "remaining_time": "1:43:58"}
|
123 |
+
{"current_steps": 1210, "total_steps": 1686, "loss": 1.5204, "accuracy": 0.5625, "learning_rate": 9.206545062840302e-07, "epoch": 2.15158924205379, "percentage": 71.77, "elapsed_time": "4:19:51", "remaining_time": "1:42:13"}
|
124 |
+
{"current_steps": 1220, "total_steps": 1686, "loss": 1.4132, "accuracy": 0.48750001192092896, "learning_rate": 8.848179579472285e-07, "epoch": 2.1693709713269618, "percentage": 72.36, "elapsed_time": "4:23:04", "remaining_time": "1:40:29"}
|
125 |
+
{"current_steps": 1230, "total_steps": 1686, "loss": 1.4426, "accuracy": 0.581250011920929, "learning_rate": 8.495422574279403e-07, "epoch": 2.1871527006001332, "percentage": 72.95, "elapsed_time": "4:26:06", "remaining_time": "1:38:39"}
|
126 |
+
{"current_steps": 1240, "total_steps": 1686, "loss": 1.578, "accuracy": 0.5375000238418579, "learning_rate": 8.148396536858063e-07, "epoch": 2.204934429873305, "percentage": 73.55, "elapsed_time": "4:29:18", "remaining_time": "1:36:52"}
|
127 |
+
{"current_steps": 1250, "total_steps": 1686, "loss": 1.4695, "accuracy": 0.48124998807907104, "learning_rate": 7.807221966811815e-07, "epoch": 2.222716159146477, "percentage": 74.14, "elapsed_time": "4:32:36", "remaining_time": "1:35:04"}
|
128 |
+
{"current_steps": 1260, "total_steps": 1686, "loss": 1.5047, "accuracy": 0.48124998807907104, "learning_rate": 7.47201733190962e-07, "epoch": 2.240497888419649, "percentage": 74.73, "elapsed_time": "4:35:51", "remaining_time": "1:33:16"}
|
129 |
+
{"current_steps": 1270, "total_steps": 1686, "loss": 1.4755, "accuracy": 0.53125, "learning_rate": 7.142899026949721e-07, "epoch": 2.258279617692821, "percentage": 75.33, "elapsed_time": "4:39:05", "remaining_time": "1:31:24"}
|
130 |
+
{"current_steps": 1280, "total_steps": 1686, "loss": 1.4613, "accuracy": 0.5249999761581421, "learning_rate": 6.819981333343273e-07, "epoch": 2.2760613469659923, "percentage": 75.92, "elapsed_time": "4:42:08", "remaining_time": "1:29:29"}
|
131 |
+
{"current_steps": 1290, "total_steps": 1686, "loss": 1.6191, "accuracy": 0.41874998807907104, "learning_rate": 6.503376379431839e-07, "epoch": 2.293843076239164, "percentage": 76.51, "elapsed_time": "4:45:22", "remaining_time": "1:27:36"}
|
132 |
+
{"current_steps": 1300, "total_steps": 1686, "loss": 1.5413, "accuracy": 0.5062500238418579, "learning_rate": 6.193194101552502e-07, "epoch": 2.311624805512336, "percentage": 77.11, "elapsed_time": "4:48:40", "remaining_time": "1:25:42"}
|
133 |
+
{"current_steps": 1310, "total_steps": 1686, "loss": 1.5893, "accuracy": 0.48750001192092896, "learning_rate": 5.889542205864083e-07, "epoch": 2.329406534785508, "percentage": 77.7, "elapsed_time": "4:51:39", "remaining_time": "1:23:42"}
|
134 |
+
{"current_steps": 1320, "total_steps": 1686, "loss": 1.5284, "accuracy": 0.4000000059604645, "learning_rate": 5.592526130947862e-07, "epoch": 2.34718826405868, "percentage": 78.29, "elapsed_time": "4:54:56", "remaining_time": "1:21:46"}
|
135 |
+
{"current_steps": 1330, "total_steps": 1686, "loss": 1.4519, "accuracy": 0.48750001192092896, "learning_rate": 5.302249011195507e-07, "epoch": 2.3649699933318518, "percentage": 78.88, "elapsed_time": "4:57:50", "remaining_time": "1:19:43"}
|
136 |
+
{"current_steps": 1340, "total_steps": 1686, "loss": 1.5372, "accuracy": 0.59375, "learning_rate": 5.018811640997307e-07, "epoch": 2.382751722605023, "percentage": 79.48, "elapsed_time": "5:01:11", "remaining_time": "1:17:46"}
|
137 |
+
{"current_steps": 1350, "total_steps": 1686, "loss": 1.5422, "accuracy": 0.48750001192092896, "learning_rate": 4.7423124397427105e-07, "epoch": 2.400533451878195, "percentage": 80.07, "elapsed_time": "5:04:03", "remaining_time": "1:15:40"}
|
138 |
+
{"current_steps": 1360, "total_steps": 1686, "loss": 1.4623, "accuracy": 0.53125, "learning_rate": 4.472847417645787e-07, "epoch": 2.418315181151367, "percentage": 80.66, "elapsed_time": "5:07:07", "remaining_time": "1:13:37"}
|
139 |
+
{"current_steps": 1370, "total_steps": 1686, "loss": 1.5411, "accuracy": 0.4749999940395355, "learning_rate": 4.210510142406993e-07, "epoch": 2.436096910424539, "percentage": 81.26, "elapsed_time": "5:10:10", "remaining_time": "1:11:32"}
|
140 |
+
{"current_steps": 1380, "total_steps": 1686, "loss": 1.5265, "accuracy": 0.46875, "learning_rate": 3.9553917067232966e-07, "epoch": 2.4538786396977104, "percentage": 81.85, "elapsed_time": "5:13:19", "remaining_time": "1:09:28"}
|
141 |
+
{"current_steps": 1390, "total_steps": 1686, "loss": 1.5, "accuracy": 0.4625000059604645, "learning_rate": 3.707580696657509e-07, "epoch": 2.4716603689708823, "percentage": 82.44, "elapsed_time": "5:16:21", "remaining_time": "1:07:22"}
|
142 |
+
{"current_steps": 1400, "total_steps": 1686, "loss": 1.5593, "accuracy": 0.42500001192092896, "learning_rate": 3.4671631608781815e-07, "epoch": 2.489442098244054, "percentage": 83.04, "elapsed_time": "5:19:19", "remaining_time": "1:05:14"}
|
143 |
+
{"current_steps": 1410, "total_steps": 1686, "loss": 1.4962, "accuracy": 0.4312500059604645, "learning_rate": 3.234222580780405e-07, "epoch": 2.507223827517226, "percentage": 83.63, "elapsed_time": "5:22:17", "remaining_time": "1:03:05"}
|
144 |
+
{"current_steps": 1420, "total_steps": 1686, "loss": 1.6331, "accuracy": 0.5, "learning_rate": 3.0088398414982375e-07, "epoch": 2.525005556790398, "percentage": 84.22, "elapsed_time": "5:25:22", "remaining_time": "1:00:57"}
|
145 |
+
{"current_steps": 1430, "total_steps": 1686, "loss": 1.4895, "accuracy": 0.550000011920929, "learning_rate": 2.7910932038184487e-07, "epoch": 2.54278728606357, "percentage": 84.82, "elapsed_time": "5:28:23", "remaining_time": "0:58:47"}
|
146 |
+
{"current_steps": 1440, "total_steps": 1686, "loss": 1.4769, "accuracy": 0.5, "learning_rate": 2.5810582770057325e-07, "epoch": 2.5605690153367417, "percentage": 85.41, "elapsed_time": "5:31:39", "remaining_time": "0:56:39"}
|
147 |
+
{"current_steps": 1450, "total_steps": 1686, "loss": 1.5116, "accuracy": 0.45625001192092896, "learning_rate": 2.3788079925484402e-07, "epoch": 2.578350744609913, "percentage": 86.0, "elapsed_time": "5:34:57", "remaining_time": "0:54:31"}
|
148 |
+
{"current_steps": 1460, "total_steps": 1686, "loss": 1.5064, "accuracy": 0.5249999761581421, "learning_rate": 2.1844125788342661e-07, "epoch": 2.596132473883085, "percentage": 86.6, "elapsed_time": "5:37:59", "remaining_time": "0:52:19"}
|
149 |
+
{"current_steps": 1470, "total_steps": 1686, "loss": 1.4586, "accuracy": 0.512499988079071, "learning_rate": 1.9979395367644428e-07, "epoch": 2.613914203156257, "percentage": 87.19, "elapsed_time": "5:40:56", "remaining_time": "0:50:05"}
|
150 |
+
{"current_steps": 1480, "total_steps": 1686, "loss": 1.5353, "accuracy": 0.518750011920929, "learning_rate": 1.81945361631512e-07, "epoch": 2.631695932429429, "percentage": 87.78, "elapsed_time": "5:44:07", "remaining_time": "0:47:53"}
|
151 |
+
{"current_steps": 1490, "total_steps": 1686, "loss": 1.5003, "accuracy": 0.5062500238418579, "learning_rate": 1.6490167940538343e-07, "epoch": 2.6494776617026004, "percentage": 88.37, "elapsed_time": "5:47:26", "remaining_time": "0:45:42"}
|
152 |
+
{"current_steps": 1500, "total_steps": 1686, "loss": 1.4914, "accuracy": 0.48124998807907104, "learning_rate": 1.4866882516191339e-07, "epoch": 2.6672593909757722, "percentage": 88.97, "elapsed_time": "5:50:45", "remaining_time": "0:43:29"}
|
153 |
+
{"current_steps": 1500, "total_steps": 1686, "eval_loss": 1.5154520273208618, "epoch": 2.6672593909757722, "percentage": 88.97, "elapsed_time": "5:57:37", "remaining_time": "0:44:20"}
|