sedrickkeh commited on
Commit
b3fac13
·
verified ·
1 Parent(s): ee8be6a

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 sha256:831283a61ea9121eaf2245846ad1ebeb5cd48b6794a06821a6cdcbeab8f3b3c8
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a603d797ba8373d1f9fa4a869e627c7aacf58924c3840e03db4fb738be1316f
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e3e203b445c65a7f46309e90ce83c0869af438bbef474d2d6f1fe03b6fae99f
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55ec7ad9121d4b9e8854ae826ef66da228fb1f77de5b7aabe9058ce6bb78b37d
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:da98d25bc4704f5a9c2ad0ea31c2093b7c5d9335e46309620cc8cf0008fa3680
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a874097d61a8ce6bf2d12f0b776fa0b402caac79ea32545cbcf685a9524a55d4
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:dc1b13158387d40ebc079991f6d357a4b5cd89cc53f9a83c83628f5f5136f0df
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:731a9b91e6ae404866feb399a07bf7615a6b4118475c561d926e4ee06bbb98b2
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -85,3 +85,44 @@
85
  {"current_steps": 840, "total_steps": 1266, "loss": 0.5968, "lr": 5e-06, "epoch": 1.9869899467770549, "percentage": 66.35, "elapsed_time": "6:52:35", "remaining_time": "3:29:14"}
86
  {"current_steps": 845, "total_steps": 1266, "eval_loss": 0.6400034427642822, "epoch": 1.9988172678888232, "percentage": 66.75, "elapsed_time": "6:58:57", "remaining_time": "3:28:44"}
87
  {"current_steps": 850, "total_steps": 1266, "loss": 0.5995, "lr": 5e-06, "epoch": 2.0106445890005915, "percentage": 67.14, "elapsed_time": "7:02:09", "remaining_time": "3:26:36"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
85
  {"current_steps": 840, "total_steps": 1266, "loss": 0.5968, "lr": 5e-06, "epoch": 1.9869899467770549, "percentage": 66.35, "elapsed_time": "6:52:35", "remaining_time": "3:29:14"}
86
  {"current_steps": 845, "total_steps": 1266, "eval_loss": 0.6400034427642822, "epoch": 1.9988172678888232, "percentage": 66.75, "elapsed_time": "6:58:57", "remaining_time": "3:28:44"}
87
  {"current_steps": 850, "total_steps": 1266, "loss": 0.5995, "lr": 5e-06, "epoch": 2.0106445890005915, "percentage": 67.14, "elapsed_time": "7:02:09", "remaining_time": "3:26:36"}
88
+ {"current_steps": 860, "total_steps": 1266, "loss": 0.5669, "lr": 5e-06, "epoch": 2.0342992312241277, "percentage": 67.93, "elapsed_time": "7:07:00", "remaining_time": "3:21:35"}
89
+ {"current_steps": 870, "total_steps": 1266, "loss": 0.5668, "lr": 5e-06, "epoch": 2.057953873447664, "percentage": 68.72, "elapsed_time": "7:11:51", "remaining_time": "3:16:34"}
90
+ {"current_steps": 880, "total_steps": 1266, "loss": 0.559, "lr": 5e-06, "epoch": 2.0816085156712005, "percentage": 69.51, "elapsed_time": "7:16:43", "remaining_time": "3:11:33"}
91
+ {"current_steps": 890, "total_steps": 1266, "loss": 0.5615, "lr": 5e-06, "epoch": 2.1052631578947367, "percentage": 70.3, "elapsed_time": "7:21:34", "remaining_time": "3:06:33"}
92
+ {"current_steps": 900, "total_steps": 1266, "loss": 0.567, "lr": 5e-06, "epoch": 2.1289178001182734, "percentage": 71.09, "elapsed_time": "7:26:25", "remaining_time": "3:01:32"}
93
+ {"current_steps": 910, "total_steps": 1266, "loss": 0.5616, "lr": 5e-06, "epoch": 2.1525724423418096, "percentage": 71.88, "elapsed_time": "7:31:16", "remaining_time": "2:56:32"}
94
+ {"current_steps": 920, "total_steps": 1266, "loss": 0.5634, "lr": 5e-06, "epoch": 2.1762270845653457, "percentage": 72.67, "elapsed_time": "7:36:07", "remaining_time": "2:51:32"}
95
+ {"current_steps": 930, "total_steps": 1266, "loss": 0.5627, "lr": 5e-06, "epoch": 2.1998817267888824, "percentage": 73.46, "elapsed_time": "7:40:59", "remaining_time": "2:46:32"}
96
+ {"current_steps": 940, "total_steps": 1266, "loss": 0.5643, "lr": 5e-06, "epoch": 2.2235363690124186, "percentage": 74.25, "elapsed_time": "7:45:50", "remaining_time": "2:41:33"}
97
+ {"current_steps": 950, "total_steps": 1266, "loss": 0.5702, "lr": 5e-06, "epoch": 2.247191011235955, "percentage": 75.04, "elapsed_time": "7:50:41", "remaining_time": "2:36:34"}
98
+ {"current_steps": 960, "total_steps": 1266, "loss": 0.564, "lr": 5e-06, "epoch": 2.2708456534594914, "percentage": 75.83, "elapsed_time": "7:55:33", "remaining_time": "2:31:35"}
99
+ {"current_steps": 970, "total_steps": 1266, "loss": 0.5657, "lr": 5e-06, "epoch": 2.2945002956830276, "percentage": 76.62, "elapsed_time": "8:00:24", "remaining_time": "2:26:36"}
100
+ {"current_steps": 980, "total_steps": 1266, "loss": 0.5696, "lr": 5e-06, "epoch": 2.3181549379065642, "percentage": 77.41, "elapsed_time": "8:05:16", "remaining_time": "2:21:37"}
101
+ {"current_steps": 990, "total_steps": 1266, "loss": 0.5673, "lr": 5e-06, "epoch": 2.3418095801301004, "percentage": 78.2, "elapsed_time": "8:10:07", "remaining_time": "2:16:38"}
102
+ {"current_steps": 1000, "total_steps": 1266, "loss": 0.5674, "lr": 5e-06, "epoch": 2.365464222353637, "percentage": 78.99, "elapsed_time": "8:14:59", "remaining_time": "2:11:40"}
103
+ {"current_steps": 1010, "total_steps": 1266, "loss": 0.5656, "lr": 5e-06, "epoch": 2.3891188645771733, "percentage": 79.78, "elapsed_time": "8:19:51", "remaining_time": "2:06:41"}
104
+ {"current_steps": 1020, "total_steps": 1266, "loss": 0.5632, "lr": 5e-06, "epoch": 2.4127735068007095, "percentage": 80.57, "elapsed_time": "8:24:43", "remaining_time": "2:01:43"}
105
+ {"current_steps": 1030, "total_steps": 1266, "loss": 0.5662, "lr": 5e-06, "epoch": 2.436428149024246, "percentage": 81.36, "elapsed_time": "8:29:34", "remaining_time": "1:56:45"}
106
+ {"current_steps": 1040, "total_steps": 1266, "loss": 0.5669, "lr": 5e-06, "epoch": 2.4600827912477823, "percentage": 82.15, "elapsed_time": "8:34:26", "remaining_time": "1:51:47"}
107
+ {"current_steps": 1050, "total_steps": 1266, "loss": 0.5694, "lr": 5e-06, "epoch": 2.483737433471319, "percentage": 82.94, "elapsed_time": "8:39:17", "remaining_time": "1:46:49"}
108
+ {"current_steps": 1060, "total_steps": 1266, "loss": 0.5686, "lr": 5e-06, "epoch": 2.507392075694855, "percentage": 83.73, "elapsed_time": "8:44:08", "remaining_time": "1:41:51"}
109
+ {"current_steps": 1070, "total_steps": 1266, "loss": 0.5709, "lr": 5e-06, "epoch": 2.5310467179183913, "percentage": 84.52, "elapsed_time": "8:49:00", "remaining_time": "1:36:54"}
110
+ {"current_steps": 1080, "total_steps": 1266, "loss": 0.5718, "lr": 5e-06, "epoch": 2.554701360141928, "percentage": 85.31, "elapsed_time": "8:53:52", "remaining_time": "1:31:56"}
111
+ {"current_steps": 1090, "total_steps": 1266, "loss": 0.5661, "lr": 5e-06, "epoch": 2.578356002365464, "percentage": 86.1, "elapsed_time": "8:58:43", "remaining_time": "1:26:59"}
112
+ {"current_steps": 1100, "total_steps": 1266, "loss": 0.5681, "lr": 5e-06, "epoch": 2.6020106445890008, "percentage": 86.89, "elapsed_time": "9:03:35", "remaining_time": "1:22:01"}
113
+ {"current_steps": 1110, "total_steps": 1266, "loss": 0.566, "lr": 5e-06, "epoch": 2.625665286812537, "percentage": 87.68, "elapsed_time": "9:08:26", "remaining_time": "1:17:04"}
114
+ {"current_steps": 1120, "total_steps": 1266, "loss": 0.5773, "lr": 5e-06, "epoch": 2.649319929036073, "percentage": 88.47, "elapsed_time": "9:13:17", "remaining_time": "1:12:07"}
115
+ {"current_steps": 1130, "total_steps": 1266, "loss": 0.5646, "lr": 5e-06, "epoch": 2.67297457125961, "percentage": 89.26, "elapsed_time": "9:18:09", "remaining_time": "1:07:10"}
116
+ {"current_steps": 1140, "total_steps": 1266, "loss": 0.5653, "lr": 5e-06, "epoch": 2.696629213483146, "percentage": 90.05, "elapsed_time": "9:23:00", "remaining_time": "1:02:13"}
117
+ {"current_steps": 1150, "total_steps": 1266, "loss": 0.5689, "lr": 5e-06, "epoch": 2.7202838557066826, "percentage": 90.84, "elapsed_time": "9:27:52", "remaining_time": "0:57:16"}
118
+ {"current_steps": 1160, "total_steps": 1266, "loss": 0.5751, "lr": 5e-06, "epoch": 2.743938497930219, "percentage": 91.63, "elapsed_time": "9:32:43", "remaining_time": "0:52:20"}
119
+ {"current_steps": 1170, "total_steps": 1266, "loss": 0.5659, "lr": 5e-06, "epoch": 2.767593140153755, "percentage": 92.42, "elapsed_time": "9:37:35", "remaining_time": "0:47:23"}
120
+ {"current_steps": 1180, "total_steps": 1266, "loss": 0.5696, "lr": 5e-06, "epoch": 2.7912477823772917, "percentage": 93.21, "elapsed_time": "9:42:27", "remaining_time": "0:42:26"}
121
+ {"current_steps": 1190, "total_steps": 1266, "loss": 0.5692, "lr": 5e-06, "epoch": 2.814902424600828, "percentage": 94.0, "elapsed_time": "9:47:18", "remaining_time": "0:37:30"}
122
+ {"current_steps": 1200, "total_steps": 1266, "loss": 0.5676, "lr": 5e-06, "epoch": 2.8385570668243645, "percentage": 94.79, "elapsed_time": "9:52:10", "remaining_time": "0:32:34"}
123
+ {"current_steps": 1210, "total_steps": 1266, "loss": 0.569, "lr": 5e-06, "epoch": 2.8622117090479007, "percentage": 95.58, "elapsed_time": "9:57:01", "remaining_time": "0:27:37"}
124
+ {"current_steps": 1220, "total_steps": 1266, "loss": 0.563, "lr": 5e-06, "epoch": 2.885866351271437, "percentage": 96.37, "elapsed_time": "10:01:53", "remaining_time": "0:22:41"}
125
+ {"current_steps": 1230, "total_steps": 1266, "loss": 0.5695, "lr": 5e-06, "epoch": 2.9095209934949735, "percentage": 97.16, "elapsed_time": "10:06:45", "remaining_time": "0:17:45"}
126
+ {"current_steps": 1240, "total_steps": 1266, "loss": 0.5706, "lr": 5e-06, "epoch": 2.9331756357185097, "percentage": 97.95, "elapsed_time": "10:11:36", "remaining_time": "0:12:49"}
127
+ {"current_steps": 1250, "total_steps": 1266, "loss": 0.5786, "lr": 5e-06, "epoch": 2.9568302779420463, "percentage": 98.74, "elapsed_time": "10:16:28", "remaining_time": "0:07:53"}
128
+ {"current_steps": 1260, "total_steps": 1266, "loss": 0.572, "lr": 5e-06, "epoch": 2.9804849201655825, "percentage": 99.53, "elapsed_time": "10:21:19", "remaining_time": "0:02:57"}