sedrickkeh commited on
Commit
91e4399
·
verified ·
1 Parent(s): a47dea8

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 sha256:7af3f27ac50e8a834e1871d4992aaf6a37fd97ab4b3f0722cc66ea6217904310
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e4f3330623d1adbb2b57e2181649954762cf0d45d7cede8808e02f2c0db11d7
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a526a2d6d56ccdeccf9d52d3b651b113d959bc68a00d47735904c767d955d3e
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eca4038b971dd3f072b6130f4660ce9d4e5fd6ffc8c61ecc4a8b44d24a5a0488
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81709d2d076d289055e8825a0b2855d798b64ae9ab3c32dc29f101330a4c02a8
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07d1acc1a75db2c9427dc8114305e1cce36d51a1aa9b7cf314dba0f81c3b2f00
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5245634b8076e3218b831aca1a9d8dc06cb6a4d99c5743a07222169a326d70e4
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e8b845f93401151a1619821a4ccb9e61276abef1760c72c3c77a1c308a43a61
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -89,3 +89,47 @@
89
  {"current_steps": 880, "total_steps": 1332, "loss": 0.765, "lr": 5e-06, "epoch": 1.9783647091879741, "percentage": 66.07, "elapsed_time": "14:18:33", "remaining_time": "7:20:59"}
90
  {"current_steps": 889, "total_steps": 1332, "eval_loss": 0.8013474345207214, "epoch": 1.998595110986232, "percentage": 66.74, "elapsed_time": "14:35:35", "remaining_time": "7:16:18"}
91
  {"current_steps": 890, "total_steps": 1332, "loss": 0.7904, "lr": 5e-06, "epoch": 2.0011239112110144, "percentage": 66.82, "elapsed_time": "14:37:19", "remaining_time": "7:15:42"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
89
  {"current_steps": 880, "total_steps": 1332, "loss": 0.765, "lr": 5e-06, "epoch": 1.9783647091879741, "percentage": 66.07, "elapsed_time": "14:18:33", "remaining_time": "7:20:59"}
90
  {"current_steps": 889, "total_steps": 1332, "eval_loss": 0.8013474345207214, "epoch": 1.998595110986232, "percentage": 66.74, "elapsed_time": "14:35:35", "remaining_time": "7:16:18"}
91
  {"current_steps": 890, "total_steps": 1332, "loss": 0.7904, "lr": 5e-06, "epoch": 2.0011239112110144, "percentage": 66.82, "elapsed_time": "14:37:19", "remaining_time": "7:15:42"}
92
+ {"current_steps": 900, "total_steps": 1332, "loss": 0.7189, "lr": 5e-06, "epoch": 2.0236021354313007, "percentage": 67.57, "elapsed_time": "14:46:58", "remaining_time": "7:05:44"}
93
+ {"current_steps": 910, "total_steps": 1332, "loss": 0.7202, "lr": 5e-06, "epoch": 2.0460803596515875, "percentage": 68.32, "elapsed_time": "14:56:39", "remaining_time": "6:55:48"}
94
+ {"current_steps": 920, "total_steps": 1332, "loss": 0.7223, "lr": 5e-06, "epoch": 2.0685585838718743, "percentage": 69.07, "elapsed_time": "15:06:19", "remaining_time": "6:45:52"}
95
+ {"current_steps": 930, "total_steps": 1332, "loss": 0.7187, "lr": 5e-06, "epoch": 2.0910368080921606, "percentage": 69.82, "elapsed_time": "15:16:00", "remaining_time": "6:35:57"}
96
+ {"current_steps": 940, "total_steps": 1332, "loss": 0.7224, "lr": 5e-06, "epoch": 2.1135150323124474, "percentage": 70.57, "elapsed_time": "15:25:40", "remaining_time": "6:26:01"}
97
+ {"current_steps": 950, "total_steps": 1332, "loss": 0.7213, "lr": 5e-06, "epoch": 2.1359932565327338, "percentage": 71.32, "elapsed_time": "15:35:21", "remaining_time": "6:16:06"}
98
+ {"current_steps": 960, "total_steps": 1332, "loss": 0.7233, "lr": 5e-06, "epoch": 2.1584714807530205, "percentage": 72.07, "elapsed_time": "15:45:02", "remaining_time": "6:06:12"}
99
+ {"current_steps": 970, "total_steps": 1332, "loss": 0.7234, "lr": 5e-06, "epoch": 2.1809497049733073, "percentage": 72.82, "elapsed_time": "15:54:42", "remaining_time": "5:56:17"}
100
+ {"current_steps": 980, "total_steps": 1332, "loss": 0.7238, "lr": 5e-06, "epoch": 2.2034279291935936, "percentage": 73.57, "elapsed_time": "16:04:22", "remaining_time": "5:46:23"}
101
+ {"current_steps": 990, "total_steps": 1332, "loss": 0.7197, "lr": 5e-06, "epoch": 2.2259061534138804, "percentage": 74.32, "elapsed_time": "16:14:02", "remaining_time": "5:36:29"}
102
+ {"current_steps": 1000, "total_steps": 1332, "loss": 0.7239, "lr": 5e-06, "epoch": 2.2483843776341668, "percentage": 75.08, "elapsed_time": "16:23:42", "remaining_time": "5:26:35"}
103
+ {"current_steps": 1010, "total_steps": 1332, "loss": 0.7237, "lr": 5e-06, "epoch": 2.2708626018544535, "percentage": 75.83, "elapsed_time": "16:33:22", "remaining_time": "5:16:41"}
104
+ {"current_steps": 1020, "total_steps": 1332, "loss": 0.7246, "lr": 5e-06, "epoch": 2.29334082607474, "percentage": 76.58, "elapsed_time": "16:43:03", "remaining_time": "5:06:48"}
105
+ {"current_steps": 1030, "total_steps": 1332, "loss": 0.7253, "lr": 5e-06, "epoch": 2.3158190502950267, "percentage": 77.33, "elapsed_time": "16:52:42", "remaining_time": "4:56:55"}
106
+ {"current_steps": 1040, "total_steps": 1332, "loss": 0.7257, "lr": 5e-06, "epoch": 2.3382972745153134, "percentage": 78.08, "elapsed_time": "17:02:23", "remaining_time": "4:47:03"}
107
+ {"current_steps": 1050, "total_steps": 1332, "loss": 0.7275, "lr": 5e-06, "epoch": 2.3607754987355998, "percentage": 78.83, "elapsed_time": "17:12:03", "remaining_time": "4:37:10"}
108
+ {"current_steps": 1060, "total_steps": 1332, "loss": 0.7257, "lr": 5e-06, "epoch": 2.3832537229558866, "percentage": 79.58, "elapsed_time": "17:21:44", "remaining_time": "4:27:18"}
109
+ {"current_steps": 1070, "total_steps": 1332, "loss": 0.7272, "lr": 5e-06, "epoch": 2.405731947176173, "percentage": 80.33, "elapsed_time": "17:31:24", "remaining_time": "4:17:26"}
110
+ {"current_steps": 1080, "total_steps": 1332, "loss": 0.7264, "lr": 5e-06, "epoch": 2.4282101713964597, "percentage": 81.08, "elapsed_time": "17:41:04", "remaining_time": "4:07:35"}
111
+ {"current_steps": 1090, "total_steps": 1332, "loss": 0.7255, "lr": 5e-06, "epoch": 2.4506883956167465, "percentage": 81.83, "elapsed_time": "17:50:45", "remaining_time": "3:57:43"}
112
+ {"current_steps": 1100, "total_steps": 1332, "loss": 0.7241, "lr": 5e-06, "epoch": 2.473166619837033, "percentage": 82.58, "elapsed_time": "18:00:26", "remaining_time": "3:47:52"}
113
+ {"current_steps": 1110, "total_steps": 1332, "loss": 0.7243, "lr": 5e-06, "epoch": 2.4956448440573196, "percentage": 83.33, "elapsed_time": "18:10:07", "remaining_time": "3:38:01"}
114
+ {"current_steps": 1120, "total_steps": 1332, "loss": 0.7247, "lr": 5e-06, "epoch": 2.518123068277606, "percentage": 84.08, "elapsed_time": "18:19:48", "remaining_time": "3:28:10"}
115
+ {"current_steps": 1130, "total_steps": 1332, "loss": 0.7214, "lr": 5e-06, "epoch": 2.5406012924978927, "percentage": 84.83, "elapsed_time": "18:29:28", "remaining_time": "3:18:19"}
116
+ {"current_steps": 1140, "total_steps": 1332, "loss": 0.7261, "lr": 5e-06, "epoch": 2.5630795167181795, "percentage": 85.59, "elapsed_time": "18:39:09", "remaining_time": "3:08:29"}
117
+ {"current_steps": 1150, "total_steps": 1332, "loss": 0.7251, "lr": 5e-06, "epoch": 2.585557740938466, "percentage": 86.34, "elapsed_time": "18:48:49", "remaining_time": "2:58:38"}
118
+ {"current_steps": 1160, "total_steps": 1332, "loss": 0.7257, "lr": 5e-06, "epoch": 2.6080359651587526, "percentage": 87.09, "elapsed_time": "18:58:30", "remaining_time": "2:48:48"}
119
+ {"current_steps": 1170, "total_steps": 1332, "loss": 0.7243, "lr": 5e-06, "epoch": 2.630514189379039, "percentage": 87.84, "elapsed_time": "19:08:10", "remaining_time": "2:38:58"}
120
+ {"current_steps": 1180, "total_steps": 1332, "loss": 0.7285, "lr": 5e-06, "epoch": 2.6529924135993257, "percentage": 88.59, "elapsed_time": "19:17:50", "remaining_time": "2:29:08"}
121
+ {"current_steps": 1190, "total_steps": 1332, "loss": 0.7279, "lr": 5e-06, "epoch": 2.675470637819612, "percentage": 89.34, "elapsed_time": "19:27:30", "remaining_time": "2:19:19"}
122
+ {"current_steps": 1200, "total_steps": 1332, "loss": 0.7219, "lr": 5e-06, "epoch": 2.697948862039899, "percentage": 90.09, "elapsed_time": "19:37:11", "remaining_time": "2:09:29"}
123
+ {"current_steps": 1210, "total_steps": 1332, "loss": 0.7241, "lr": 5e-06, "epoch": 2.7204270862601856, "percentage": 90.84, "elapsed_time": "19:46:52", "remaining_time": "1:59:40"}
124
+ {"current_steps": 1220, "total_steps": 1332, "loss": 0.7282, "lr": 5e-06, "epoch": 2.742905310480472, "percentage": 91.59, "elapsed_time": "19:56:33", "remaining_time": "1:49:50"}
125
+ {"current_steps": 1230, "total_steps": 1332, "loss": 0.7242, "lr": 5e-06, "epoch": 2.7653835347007587, "percentage": 92.34, "elapsed_time": "20:06:13", "remaining_time": "1:40:01"}
126
+ {"current_steps": 1240, "total_steps": 1332, "loss": 0.7222, "lr": 5e-06, "epoch": 2.7878617589210455, "percentage": 93.09, "elapsed_time": "20:15:55", "remaining_time": "1:30:12"}
127
+ {"current_steps": 1250, "total_steps": 1332, "loss": 0.7217, "lr": 5e-06, "epoch": 2.810339983141332, "percentage": 93.84, "elapsed_time": "20:25:36", "remaining_time": "1:20:23"}
128
+ {"current_steps": 1260, "total_steps": 1332, "loss": 0.7215, "lr": 5e-06, "epoch": 2.832818207361618, "percentage": 94.59, "elapsed_time": "20:35:17", "remaining_time": "1:10:35"}
129
+ {"current_steps": 1270, "total_steps": 1332, "loss": 0.7309, "lr": 5e-06, "epoch": 2.855296431581905, "percentage": 95.35, "elapsed_time": "20:44:58", "remaining_time": "1:00:46"}
130
+ {"current_steps": 1280, "total_steps": 1332, "loss": 0.7266, "lr": 5e-06, "epoch": 2.8777746558021917, "percentage": 96.1, "elapsed_time": "20:54:38", "remaining_time": "0:50:58"}
131
+ {"current_steps": 1290, "total_steps": 1332, "loss": 0.7282, "lr": 5e-06, "epoch": 2.900252880022478, "percentage": 96.85, "elapsed_time": "21:04:17", "remaining_time": "0:41:09"}
132
+ {"current_steps": 1300, "total_steps": 1332, "loss": 0.7279, "lr": 5e-06, "epoch": 2.922731104242765, "percentage": 97.6, "elapsed_time": "21:13:57", "remaining_time": "0:31:21"}
133
+ {"current_steps": 1310, "total_steps": 1332, "loss": 0.7227, "lr": 5e-06, "epoch": 2.9452093284630516, "percentage": 98.35, "elapsed_time": "21:23:37", "remaining_time": "0:21:33"}
134
+ {"current_steps": 1320, "total_steps": 1332, "loss": 0.7311, "lr": 5e-06, "epoch": 2.967687552683338, "percentage": 99.1, "elapsed_time": "21:33:19", "remaining_time": "0:11:45"}
135
+ {"current_steps": 1330, "total_steps": 1332, "loss": 0.723, "lr": 5e-06, "epoch": 2.9901657769036247, "percentage": 99.85, "elapsed_time": "21:42:59", "remaining_time": "0:01:57"}