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:
|
| 3 |
size 4877660776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53ed1d85aff68259e0cf43e045174cc7632aae41693045a52df003118448c281
|
| 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:
|
| 3 |
size 4932751008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40d585d40fcc02c8a1a028b88adcafea804abfa9e04c2cfab7d277b0b07ff3d6
|
| 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:
|
| 3 |
size 4330865200
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09b78c7fe64d9c0b84dad1ebfbebf71895e89f3f66f17f1cb8e5b13f4d3d7466
|
| 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:
|
| 3 |
size 1089994880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:010825508c674dad6d757b502c46d6690da0f52745a5e69f5ce430c0ce002fab
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -75,3 +75,77 @@
|
|
| 75 |
{"current_steps": 75, "total_steps": 222, "loss": 0.6942, "lr": 8.40774613995817e-06, "epoch": 1.0135135135135136, "percentage": 33.78, "elapsed_time": "0:38:42", "remaining_time": "1:15:52"}
|
| 76 |
{"current_steps": 76, "total_steps": 222, "loss": 0.7572, "lr": 8.349561828589276e-06, "epoch": 1.027027027027027, "percentage": 34.23, "elapsed_time": "0:39:14", "remaining_time": "1:15:22"}
|
| 77 |
{"current_steps": 77, "total_steps": 222, "loss": 0.7606, "lr": 8.29054273619019e-06, "epoch": 1.0405405405405406, "percentage": 34.68, "elapsed_time": "0:39:49", "remaining_time": "1:14:59"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 75 |
{"current_steps": 75, "total_steps": 222, "loss": 0.6942, "lr": 8.40774613995817e-06, "epoch": 1.0135135135135136, "percentage": 33.78, "elapsed_time": "0:38:42", "remaining_time": "1:15:52"}
|
| 76 |
{"current_steps": 76, "total_steps": 222, "loss": 0.7572, "lr": 8.349561828589276e-06, "epoch": 1.027027027027027, "percentage": 34.23, "elapsed_time": "0:39:14", "remaining_time": "1:15:22"}
|
| 77 |
{"current_steps": 77, "total_steps": 222, "loss": 0.7606, "lr": 8.29054273619019e-06, "epoch": 1.0405405405405406, "percentage": 34.68, "elapsed_time": "0:39:49", "remaining_time": "1:14:59"}
|
| 78 |
+
{"current_steps": 78, "total_steps": 222, "loss": 0.7307, "lr": 8.23070357155605e-06, "epoch": 1.054054054054054, "percentage": 35.14, "elapsed_time": "0:40:11", "remaining_time": "1:14:12"}
|
| 79 |
+
{"current_steps": 79, "total_steps": 222, "loss": 0.7647, "lr": 8.170059247861194e-06, "epoch": 1.0675675675675675, "percentage": 35.59, "elapsed_time": "0:40:44", "remaining_time": "1:13:43"}
|
| 80 |
+
{"current_steps": 80, "total_steps": 222, "loss": 0.7751, "lr": 8.108624878942477e-06, "epoch": 1.0810810810810811, "percentage": 36.04, "elapsed_time": "0:41:15", "remaining_time": "1:13:13"}
|
| 81 |
+
{"current_steps": 81, "total_steps": 222, "loss": 0.7494, "lr": 8.046415775532585e-06, "epoch": 1.0945945945945945, "percentage": 36.49, "elapsed_time": "0:41:45", "remaining_time": "1:12:41"}
|
| 82 |
+
{"current_steps": 82, "total_steps": 222, "loss": 0.7426, "lr": 7.98344744144428e-06, "epoch": 1.1081081081081081, "percentage": 36.94, "elapsed_time": "0:42:14", "remaining_time": "1:12:06"}
|
| 83 |
+
{"current_steps": 83, "total_steps": 222, "loss": 0.7647, "lr": 7.919735569706533e-06, "epoch": 1.1216216216216217, "percentage": 37.39, "elapsed_time": "0:42:42", "remaining_time": "1:11:31"}
|
| 84 |
+
{"current_steps": 84, "total_steps": 222, "loss": 0.7245, "lr": 7.855296038653474e-06, "epoch": 1.135135135135135, "percentage": 37.84, "elapsed_time": "0:43:16", "remaining_time": "1:11:05"}
|
| 85 |
+
{"current_steps": 85, "total_steps": 222, "loss": 0.7239, "lr": 7.7901449079672e-06, "epoch": 1.1486486486486487, "percentage": 38.29, "elapsed_time": "0:43:46", "remaining_time": "1:10:33"}
|
| 86 |
+
{"current_steps": 86, "total_steps": 222, "loss": 0.7654, "lr": 7.724298414675353e-06, "epoch": 1.1621621621621623, "percentage": 38.74, "elapsed_time": "0:44:17", "remaining_time": "1:10:02"}
|
| 87 |
+
{"current_steps": 87, "total_steps": 222, "loss": 0.7537, "lr": 7.657772969104508e-06, "epoch": 1.1756756756756757, "percentage": 39.19, "elapsed_time": "0:44:54", "remaining_time": "1:09:41"}
|
| 88 |
+
{"current_steps": 88, "total_steps": 222, "loss": 0.7221, "lr": 7.590585150790388e-06, "epoch": 1.1891891891891893, "percentage": 39.64, "elapsed_time": "0:45:26", "remaining_time": "1:09:11"}
|
| 89 |
+
{"current_steps": 89, "total_steps": 222, "loss": 0.7081, "lr": 7.522751704345888e-06, "epoch": 1.2027027027027026, "percentage": 40.09, "elapsed_time": "0:45:53", "remaining_time": "1:08:35"}
|
| 90 |
+
{"current_steps": 90, "total_steps": 222, "loss": 0.7524, "lr": 7.454289535287968e-06, "epoch": 1.2162162162162162, "percentage": 40.54, "elapsed_time": "0:46:22", "remaining_time": "1:08:00"}
|
| 91 |
+
{"current_steps": 91, "total_steps": 222, "loss": 0.6637, "lr": 7.385215705824449e-06, "epoch": 1.2297297297297298, "percentage": 40.99, "elapsed_time": "0:46:51", "remaining_time": "1:07:27"}
|
| 92 |
+
{"current_steps": 92, "total_steps": 222, "loss": 0.7065, "lr": 7.315547430601739e-06, "epoch": 1.2432432432432432, "percentage": 41.44, "elapsed_time": "0:47:22", "remaining_time": "1:06:57"}
|
| 93 |
+
{"current_steps": 93, "total_steps": 222, "loss": 0.723, "lr": 7.245302072414602e-06, "epoch": 1.2567567567567568, "percentage": 41.89, "elapsed_time": "0:47:49", "remaining_time": "1:06:20"}
|
| 94 |
+
{"current_steps": 94, "total_steps": 222, "loss": 0.7719, "lr": 7.174497137878967e-06, "epoch": 1.2702702702702702, "percentage": 42.34, "elapsed_time": "0:48:21", "remaining_time": "1:05:50"}
|
| 95 |
+
{"current_steps": 95, "total_steps": 222, "loss": 0.7035, "lr": 7.103150273068922e-06, "epoch": 1.2837837837837838, "percentage": 42.79, "elapsed_time": "0:48:49", "remaining_time": "1:05:16"}
|
| 96 |
+
{"current_steps": 96, "total_steps": 222, "loss": 0.7166, "lr": 7.0312792591189465e-06, "epoch": 1.2972972972972974, "percentage": 43.24, "elapsed_time": "0:49:23", "remaining_time": "1:04:49"}
|
| 97 |
+
{"current_steps": 97, "total_steps": 222, "loss": 0.6376, "lr": 6.958902007792466e-06, "epoch": 1.3108108108108107, "percentage": 43.69, "elapsed_time": "0:49:58", "remaining_time": "1:04:24"}
|
| 98 |
+
{"current_steps": 98, "total_steps": 222, "loss": 0.7584, "lr": 6.886036557017881e-06, "epoch": 1.3243243243243243, "percentage": 44.14, "elapsed_time": "0:50:27", "remaining_time": "1:03:50"}
|
| 99 |
+
{"current_steps": 99, "total_steps": 222, "loss": 0.7153, "lr": 6.8127010663931235e-06, "epoch": 1.3378378378378377, "percentage": 44.59, "elapsed_time": "0:50:53", "remaining_time": "1:03:13"}
|
| 100 |
+
{"current_steps": 100, "total_steps": 222, "loss": 0.7733, "lr": 6.738913812659913e-06, "epoch": 1.3513513513513513, "percentage": 45.05, "elapsed_time": "0:51:26", "remaining_time": "1:02:46"}
|
| 101 |
+
{"current_steps": 101, "total_steps": 222, "loss": 0.7214, "lr": 6.664693185148808e-06, "epoch": 1.364864864864865, "percentage": 45.5, "elapsed_time": "0:52:03", "remaining_time": "1:02:22"}
|
| 102 |
+
{"current_steps": 102, "total_steps": 222, "loss": 0.7847, "lr": 6.590057681196191e-06, "epoch": 1.3783783783783785, "percentage": 45.95, "elapsed_time": "0:52:30", "remaining_time": "1:01:45"}
|
| 103 |
+
{"current_steps": 103, "total_steps": 222, "loss": 0.6675, "lr": 6.515025901534364e-06, "epoch": 1.3918918918918919, "percentage": 46.4, "elapsed_time": "0:53:00", "remaining_time": "1:01:14"}
|
| 104 |
+
{"current_steps": 104, "total_steps": 222, "loss": 0.7974, "lr": 6.439616545655833e-06, "epoch": 1.4054054054054055, "percentage": 46.85, "elapsed_time": "0:53:29", "remaining_time": "1:00:41"}
|
| 105 |
+
{"current_steps": 105, "total_steps": 222, "loss": 0.7488, "lr": 6.363848407153017e-06, "epoch": 1.4189189189189189, "percentage": 47.3, "elapsed_time": "0:54:00", "remaining_time": "1:00:10"}
|
| 106 |
+
{"current_steps": 106, "total_steps": 222, "loss": 0.7153, "lr": 6.2877403690344854e-06, "epoch": 1.4324324324324325, "percentage": 47.75, "elapsed_time": "0:54:38", "remaining_time": "0:59:47"}
|
| 107 |
+
{"current_steps": 107, "total_steps": 222, "loss": 0.7326, "lr": 6.2113113990189165e-06, "epoch": 1.445945945945946, "percentage": 48.2, "elapsed_time": "0:55:09", "remaining_time": "0:59:16"}
|
| 108 |
+
{"current_steps": 108, "total_steps": 222, "loss": 0.7548, "lr": 6.134580544807951e-06, "epoch": 1.4594594594594594, "percentage": 48.65, "elapsed_time": "0:55:41", "remaining_time": "0:58:47"}
|
| 109 |
+
{"current_steps": 109, "total_steps": 222, "loss": 0.6864, "lr": 6.057566929339096e-06, "epoch": 1.472972972972973, "percentage": 49.1, "elapsed_time": "0:56:12", "remaining_time": "0:58:15"}
|
| 110 |
+
{"current_steps": 110, "total_steps": 222, "loss": 0.7329, "lr": 5.980289746019892e-06, "epoch": 1.4864864864864864, "percentage": 49.55, "elapsed_time": "0:56:44", "remaining_time": "0:57:46"}
|
| 111 |
+
{"current_steps": 111, "total_steps": 222, "loss": 0.656, "lr": 5.902768253944511e-06, "epoch": 1.5, "percentage": 50.0, "elapsed_time": "0:57:19", "remaining_time": "0:57:19"}
|
| 112 |
+
{"current_steps": 112, "total_steps": 222, "loss": 0.7652, "lr": 5.825021773093997e-06, "epoch": 1.5135135135135136, "percentage": 50.45, "elapsed_time": "0:57:49", "remaining_time": "0:56:47"}
|
| 113 |
+
{"current_steps": 113, "total_steps": 222, "loss": 0.7708, "lr": 5.747069679521306e-06, "epoch": 1.527027027027027, "percentage": 50.9, "elapsed_time": "0:58:19", "remaining_time": "0:56:15"}
|
| 114 |
+
{"current_steps": 114, "total_steps": 222, "loss": 0.7192, "lr": 5.668931400522396e-06, "epoch": 1.5405405405405406, "percentage": 51.35, "elapsed_time": "0:58:49", "remaining_time": "0:55:43"}
|
| 115 |
+
{"current_steps": 115, "total_steps": 222, "loss": 0.6781, "lr": 5.5906264097945405e-06, "epoch": 1.554054054054054, "percentage": 51.8, "elapsed_time": "0:59:18", "remaining_time": "0:55:11"}
|
| 116 |
+
{"current_steps": 116, "total_steps": 222, "loss": 0.7641, "lr": 5.512174222583066e-06, "epoch": 1.5675675675675675, "percentage": 52.25, "elapsed_time": "0:59:48", "remaining_time": "0:54:39"}
|
| 117 |
+
{"current_steps": 117, "total_steps": 222, "loss": 0.7091, "lr": 5.433594390817755e-06, "epoch": 1.5810810810810811, "percentage": 52.7, "elapsed_time": "1:00:25", "remaining_time": "0:54:13"}
|
| 118 |
+
{"current_steps": 118, "total_steps": 222, "loss": 0.7345, "lr": 5.35490649824008e-06, "epoch": 1.5945945945945947, "percentage": 53.15, "elapsed_time": "1:00:57", "remaining_time": "0:53:43"}
|
| 119 |
+
{"current_steps": 119, "total_steps": 222, "loss": 0.7331, "lr": 5.276130155522541e-06, "epoch": 1.6081081081081081, "percentage": 53.6, "elapsed_time": "1:01:28", "remaining_time": "0:53:12"}
|
| 120 |
+
{"current_steps": 120, "total_steps": 222, "loss": 0.7725, "lr": 5.197284995381264e-06, "epoch": 1.6216216216216215, "percentage": 54.05, "elapsed_time": "1:02:00", "remaining_time": "0:52:42"}
|
| 121 |
+
{"current_steps": 121, "total_steps": 222, "loss": 0.7716, "lr": 5.1183906676831195e-06, "epoch": 1.635135135135135, "percentage": 54.5, "elapsed_time": "1:02:33", "remaining_time": "0:52:13"}
|
| 122 |
+
{"current_steps": 122, "total_steps": 222, "loss": 0.6676, "lr": 5.039466834548568e-06, "epoch": 1.6486486486486487, "percentage": 54.95, "elapsed_time": "1:02:58", "remaining_time": "0:51:36"}
|
| 123 |
+
{"current_steps": 123, "total_steps": 222, "loss": 0.7117, "lr": 4.960533165451435e-06, "epoch": 1.6621621621621623, "percentage": 55.41, "elapsed_time": "1:03:24", "remaining_time": "0:51:02"}
|
| 124 |
+
{"current_steps": 124, "total_steps": 222, "loss": 0.7336, "lr": 4.881609332316881e-06, "epoch": 1.6756756756756757, "percentage": 55.86, "elapsed_time": "1:04:00", "remaining_time": "0:50:35"}
|
| 125 |
+
{"current_steps": 125, "total_steps": 222, "loss": 0.7896, "lr": 4.802715004618737e-06, "epoch": 1.689189189189189, "percentage": 56.31, "elapsed_time": "1:04:27", "remaining_time": "0:50:01"}
|
| 126 |
+
{"current_steps": 126, "total_steps": 222, "loss": 0.7379, "lr": 4.72386984447746e-06, "epoch": 1.7027027027027026, "percentage": 56.76, "elapsed_time": "1:04:51", "remaining_time": "0:49:24"}
|
| 127 |
+
{"current_steps": 127, "total_steps": 222, "loss": 0.6873, "lr": 4.6450935017599205e-06, "epoch": 1.7162162162162162, "percentage": 57.21, "elapsed_time": "1:05:20", "remaining_time": "0:48:52"}
|
| 128 |
+
{"current_steps": 128, "total_steps": 222, "loss": 0.7693, "lr": 4.566405609182247e-06, "epoch": 1.7297297297297298, "percentage": 57.66, "elapsed_time": "1:05:53", "remaining_time": "0:48:23"}
|
| 129 |
+
{"current_steps": 129, "total_steps": 222, "loss": 0.7212, "lr": 4.4878257774169345e-06, "epoch": 1.7432432432432432, "percentage": 58.11, "elapsed_time": "1:06:21", "remaining_time": "0:47:50"}
|
| 130 |
+
{"current_steps": 130, "total_steps": 222, "loss": 0.7144, "lr": 4.40937359020546e-06, "epoch": 1.7567567567567568, "percentage": 58.56, "elapsed_time": "1:06:52", "remaining_time": "0:47:19"}
|
| 131 |
+
{"current_steps": 131, "total_steps": 222, "loss": 0.6818, "lr": 4.3310685994776055e-06, "epoch": 1.7702702702702702, "percentage": 59.01, "elapsed_time": "1:07:14", "remaining_time": "0:46:42"}
|
| 132 |
+
{"current_steps": 132, "total_steps": 222, "loss": 0.6852, "lr": 4.252930320478695e-06, "epoch": 1.7837837837837838, "percentage": 59.46, "elapsed_time": "1:07:40", "remaining_time": "0:46:08"}
|
| 133 |
+
{"current_steps": 133, "total_steps": 222, "loss": 0.7232, "lr": 4.1749782269060045e-06, "epoch": 1.7972972972972974, "percentage": 59.91, "elapsed_time": "1:08:12", "remaining_time": "0:45:38"}
|
| 134 |
+
{"current_steps": 134, "total_steps": 222, "loss": 0.6698, "lr": 4.097231746055491e-06, "epoch": 1.810810810810811, "percentage": 60.36, "elapsed_time": "1:08:44", "remaining_time": "0:45:08"}
|
| 135 |
+
{"current_steps": 135, "total_steps": 222, "loss": 0.7136, "lr": 4.01971025398011e-06, "epoch": 1.8243243243243243, "percentage": 60.81, "elapsed_time": "1:09:10", "remaining_time": "0:44:34"}
|
| 136 |
+
{"current_steps": 136, "total_steps": 222, "loss": 0.7264, "lr": 3.9424330706609055e-06, "epoch": 1.8378378378378377, "percentage": 61.26, "elapsed_time": "1:09:36", "remaining_time": "0:44:01"}
|
| 137 |
+
{"current_steps": 137, "total_steps": 222, "loss": 0.7292, "lr": 3.865419455192049e-06, "epoch": 1.8513513513513513, "percentage": 61.71, "elapsed_time": "1:09:59", "remaining_time": "0:43:25"}
|
| 138 |
+
{"current_steps": 138, "total_steps": 222, "loss": 0.7389, "lr": 3.788688600981085e-06, "epoch": 1.864864864864865, "percentage": 62.16, "elapsed_time": "1:10:34", "remaining_time": "0:42:57"}
|
| 139 |
+
{"current_steps": 139, "total_steps": 222, "loss": 0.759, "lr": 3.712259630965518e-06, "epoch": 1.8783783783783785, "percentage": 62.61, "elapsed_time": "1:11:06", "remaining_time": "0:42:27"}
|
| 140 |
+
{"current_steps": 140, "total_steps": 222, "loss": 0.6806, "lr": 3.636151592846985e-06, "epoch": 1.8918918918918919, "percentage": 63.06, "elapsed_time": "1:11:34", "remaining_time": "0:41:55"}
|
| 141 |
+
{"current_steps": 141, "total_steps": 222, "loss": 0.7607, "lr": 3.5603834543441683e-06, "epoch": 1.9054054054054053, "percentage": 63.51, "elapsed_time": "1:12:00", "remaining_time": "0:41:22"}
|
| 142 |
+
{"current_steps": 142, "total_steps": 222, "loss": 0.7334, "lr": 3.484974098465636e-06, "epoch": 1.9189189189189189, "percentage": 63.96, "elapsed_time": "1:12:29", "remaining_time": "0:40:50"}
|
| 143 |
+
{"current_steps": 143, "total_steps": 222, "loss": 0.7651, "lr": 3.4099423188038094e-06, "epoch": 1.9324324324324325, "percentage": 64.41, "elapsed_time": "1:12:57", "remaining_time": "0:40:18"}
|
| 144 |
+
{"current_steps": 144, "total_steps": 222, "loss": 0.7539, "lr": 3.3353068148511957e-06, "epoch": 1.945945945945946, "percentage": 64.86, "elapsed_time": "1:13:23", "remaining_time": "0:39:45"}
|
| 145 |
+
{"current_steps": 145, "total_steps": 222, "loss": 0.7079, "lr": 3.2610861873400884e-06, "epoch": 1.9594594594594594, "percentage": 65.32, "elapsed_time": "1:13:58", "remaining_time": "0:39:16"}
|
| 146 |
+
{"current_steps": 146, "total_steps": 222, "loss": 0.7173, "lr": 3.187298933606878e-06, "epoch": 1.972972972972973, "percentage": 65.77, "elapsed_time": "1:14:24", "remaining_time": "0:38:43"}
|
| 147 |
+
{"current_steps": 147, "total_steps": 222, "loss": 0.7489, "lr": 3.1139634429821198e-06, "epoch": 1.9864864864864864, "percentage": 66.22, "elapsed_time": "1:14:52", "remaining_time": "0:38:12"}
|
| 148 |
+
{"current_steps": 148, "total_steps": 222, "loss": 0.7437, "lr": 3.0410979922075344e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:15:17", "remaining_time": "0:37:38"}
|
| 149 |
+
{"current_steps": 149, "total_steps": 222, "loss": 0.7376, "lr": 2.968720740881056e-06, "epoch": 2.0135135135135136, "percentage": 67.12, "elapsed_time": "1:16:45", "remaining_time": "0:37:36"}
|
| 150 |
+
{"current_steps": 150, "total_steps": 222, "loss": 0.6356, "lr": 2.8968497269310803e-06, "epoch": 2.027027027027027, "percentage": 67.57, "elapsed_time": "1:17:16", "remaining_time": "0:37:05"}
|
| 151 |
+
{"current_steps": 151, "total_steps": 222, "loss": 0.6941, "lr": 2.825502862121036e-06, "epoch": 2.0405405405405403, "percentage": 68.02, "elapsed_time": "1:17:42", "remaining_time": "0:36:32"}
|