gsmyrnis commited on
Commit
4b28e9a
·
verified ·
1 Parent(s): ffc736b

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 sha256:75aa6866f01526ac57a064edffcde505d028554ddb80b6e2f7a995b470af14f2
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5a18b4cd23249d5f1371851cf6641cc0ea68befa57401db700c6a1a7abaca1a
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53f0d3a99fe6d3a96fc34e485ebca7cd9ce3a36ef836ee618b647501cde95ac8
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16d81277902f6f54fba1db78a5a241facf3fd458ec7996e42b8aec781031c9dd
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:c4b1e1eedb208fa99f97a87da23fba6de9c2d2b05f91ba19465356fd8ca15d83
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7e489a73ad30e2db985afbfbfb37285d92dac6061749f8c8fd4576d5eb85ac5
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:521f6fcef90cb2784c8519cfa56128cbaf2281b1c1b9ef8d6a1e84ee825da1f8
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f503bc03deb1c6776f8a28b3cf6f77f855b0760fc61b4ac468b9c05699225f3c
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -77,3 +77,47 @@
77
  {"current_steps": 760, "total_steps": 1281, "loss": 0.4864, "lr": 5e-06, "epoch": 1.7798594847775175, "percentage": 59.33, "elapsed_time": "1:17:25", "remaining_time": "0:53:04"}
78
  {"current_steps": 770, "total_steps": 1281, "loss": 0.4877, "lr": 5e-06, "epoch": 1.8032786885245902, "percentage": 60.11, "elapsed_time": "1:18:24", "remaining_time": "0:52:01"}
79
  {"current_steps": 780, "total_steps": 1281, "loss": 0.491, "lr": 5e-06, "epoch": 1.8266978922716628, "percentage": 60.89, "elapsed_time": "1:19:23", "remaining_time": "0:50:59"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
77
  {"current_steps": 760, "total_steps": 1281, "loss": 0.4864, "lr": 5e-06, "epoch": 1.7798594847775175, "percentage": 59.33, "elapsed_time": "1:17:25", "remaining_time": "0:53:04"}
78
  {"current_steps": 770, "total_steps": 1281, "loss": 0.4877, "lr": 5e-06, "epoch": 1.8032786885245902, "percentage": 60.11, "elapsed_time": "1:18:24", "remaining_time": "0:52:01"}
79
  {"current_steps": 780, "total_steps": 1281, "loss": 0.491, "lr": 5e-06, "epoch": 1.8266978922716628, "percentage": 60.89, "elapsed_time": "1:19:23", "remaining_time": "0:50:59"}
80
+ {"current_steps": 790, "total_steps": 1281, "loss": 0.4919, "lr": 5e-06, "epoch": 1.8501170960187352, "percentage": 61.67, "elapsed_time": "1:20:23", "remaining_time": "0:49:57"}
81
+ {"current_steps": 800, "total_steps": 1281, "loss": 0.4875, "lr": 5e-06, "epoch": 1.8735362997658078, "percentage": 62.45, "elapsed_time": "1:21:22", "remaining_time": "0:48:55"}
82
+ {"current_steps": 810, "total_steps": 1281, "loss": 0.4936, "lr": 5e-06, "epoch": 1.8969555035128804, "percentage": 63.23, "elapsed_time": "1:22:21", "remaining_time": "0:47:53"}
83
+ {"current_steps": 820, "total_steps": 1281, "loss": 0.4888, "lr": 5e-06, "epoch": 1.920374707259953, "percentage": 64.01, "elapsed_time": "1:23:21", "remaining_time": "0:46:51"}
84
+ {"current_steps": 830, "total_steps": 1281, "loss": 0.4893, "lr": 5e-06, "epoch": 1.9437939110070257, "percentage": 64.79, "elapsed_time": "1:24:20", "remaining_time": "0:45:49"}
85
+ {"current_steps": 840, "total_steps": 1281, "loss": 0.4915, "lr": 5e-06, "epoch": 1.9672131147540983, "percentage": 65.57, "elapsed_time": "1:25:19", "remaining_time": "0:44:47"}
86
+ {"current_steps": 850, "total_steps": 1281, "loss": 0.4902, "lr": 5e-06, "epoch": 1.990632318501171, "percentage": 66.35, "elapsed_time": "1:26:19", "remaining_time": "0:43:46"}
87
+ {"current_steps": 854, "total_steps": 1281, "eval_loss": 0.5077147483825684, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:27:24", "remaining_time": "0:43:42"}
88
+ {"current_steps": 860, "total_steps": 1281, "loss": 0.4752, "lr": 5e-06, "epoch": 2.0140515222482436, "percentage": 67.14, "elapsed_time": "1:29:27", "remaining_time": "0:43:47"}
89
+ {"current_steps": 870, "total_steps": 1281, "loss": 0.4669, "lr": 5e-06, "epoch": 2.037470725995316, "percentage": 67.92, "elapsed_time": "1:30:27", "remaining_time": "0:42:44"}
90
+ {"current_steps": 880, "total_steps": 1281, "loss": 0.4614, "lr": 5e-06, "epoch": 2.060889929742389, "percentage": 68.7, "elapsed_time": "1:31:27", "remaining_time": "0:41:40"}
91
+ {"current_steps": 890, "total_steps": 1281, "loss": 0.4659, "lr": 5e-06, "epoch": 2.0843091334894615, "percentage": 69.48, "elapsed_time": "1:32:26", "remaining_time": "0:40:36"}
92
+ {"current_steps": 900, "total_steps": 1281, "loss": 0.4593, "lr": 5e-06, "epoch": 2.107728337236534, "percentage": 70.26, "elapsed_time": "1:33:25", "remaining_time": "0:39:33"}
93
+ {"current_steps": 910, "total_steps": 1281, "loss": 0.4677, "lr": 5e-06, "epoch": 2.1311475409836067, "percentage": 71.04, "elapsed_time": "1:34:25", "remaining_time": "0:38:29"}
94
+ {"current_steps": 920, "total_steps": 1281, "loss": 0.4652, "lr": 5e-06, "epoch": 2.1545667447306793, "percentage": 71.82, "elapsed_time": "1:35:24", "remaining_time": "0:37:26"}
95
+ {"current_steps": 930, "total_steps": 1281, "loss": 0.4681, "lr": 5e-06, "epoch": 2.177985948477752, "percentage": 72.6, "elapsed_time": "1:36:23", "remaining_time": "0:36:22"}
96
+ {"current_steps": 940, "total_steps": 1281, "loss": 0.4586, "lr": 5e-06, "epoch": 2.201405152224824, "percentage": 73.38, "elapsed_time": "1:37:23", "remaining_time": "0:35:19"}
97
+ {"current_steps": 950, "total_steps": 1281, "loss": 0.4669, "lr": 5e-06, "epoch": 2.2248243559718968, "percentage": 74.16, "elapsed_time": "1:38:22", "remaining_time": "0:34:16"}
98
+ {"current_steps": 960, "total_steps": 1281, "loss": 0.4665, "lr": 5e-06, "epoch": 2.2482435597189694, "percentage": 74.94, "elapsed_time": "1:39:21", "remaining_time": "0:33:13"}
99
+ {"current_steps": 970, "total_steps": 1281, "loss": 0.4665, "lr": 5e-06, "epoch": 2.271662763466042, "percentage": 75.72, "elapsed_time": "1:40:21", "remaining_time": "0:32:10"}
100
+ {"current_steps": 980, "total_steps": 1281, "loss": 0.4662, "lr": 5e-06, "epoch": 2.2950819672131146, "percentage": 76.5, "elapsed_time": "1:41:21", "remaining_time": "0:31:07"}
101
+ {"current_steps": 990, "total_steps": 1281, "loss": 0.4646, "lr": 5e-06, "epoch": 2.3185011709601873, "percentage": 77.28, "elapsed_time": "1:42:22", "remaining_time": "0:30:05"}
102
+ {"current_steps": 1000, "total_steps": 1281, "loss": 0.4647, "lr": 5e-06, "epoch": 2.34192037470726, "percentage": 78.06, "elapsed_time": "1:43:22", "remaining_time": "0:29:02"}
103
+ {"current_steps": 1010, "total_steps": 1281, "loss": 0.4659, "lr": 5e-06, "epoch": 2.3653395784543325, "percentage": 78.84, "elapsed_time": "1:44:21", "remaining_time": "0:28:00"}
104
+ {"current_steps": 1020, "total_steps": 1281, "loss": 0.4663, "lr": 5e-06, "epoch": 2.388758782201405, "percentage": 79.63, "elapsed_time": "1:45:21", "remaining_time": "0:26:57"}
105
+ {"current_steps": 1030, "total_steps": 1281, "loss": 0.4676, "lr": 5e-06, "epoch": 2.4121779859484778, "percentage": 80.41, "elapsed_time": "1:46:20", "remaining_time": "0:25:54"}
106
+ {"current_steps": 1040, "total_steps": 1281, "loss": 0.4673, "lr": 5e-06, "epoch": 2.4355971896955504, "percentage": 81.19, "elapsed_time": "1:47:20", "remaining_time": "0:24:52"}
107
+ {"current_steps": 1050, "total_steps": 1281, "loss": 0.4654, "lr": 5e-06, "epoch": 2.459016393442623, "percentage": 81.97, "elapsed_time": "1:48:19", "remaining_time": "0:23:49"}
108
+ {"current_steps": 1060, "total_steps": 1281, "loss": 0.469, "lr": 5e-06, "epoch": 2.4824355971896956, "percentage": 82.75, "elapsed_time": "1:49:18", "remaining_time": "0:22:47"}
109
+ {"current_steps": 1070, "total_steps": 1281, "loss": 0.47, "lr": 5e-06, "epoch": 2.5058548009367683, "percentage": 83.53, "elapsed_time": "1:50:18", "remaining_time": "0:21:45"}
110
+ {"current_steps": 1080, "total_steps": 1281, "loss": 0.4685, "lr": 5e-06, "epoch": 2.529274004683841, "percentage": 84.31, "elapsed_time": "1:51:17", "remaining_time": "0:20:42"}
111
+ {"current_steps": 1090, "total_steps": 1281, "loss": 0.4677, "lr": 5e-06, "epoch": 2.552693208430913, "percentage": 85.09, "elapsed_time": "1:52:17", "remaining_time": "0:19:40"}
112
+ {"current_steps": 1100, "total_steps": 1281, "loss": 0.4695, "lr": 5e-06, "epoch": 2.576112412177986, "percentage": 85.87, "elapsed_time": "1:53:17", "remaining_time": "0:18:38"}
113
+ {"current_steps": 1110, "total_steps": 1281, "loss": 0.4677, "lr": 5e-06, "epoch": 2.5995316159250583, "percentage": 86.65, "elapsed_time": "1:54:16", "remaining_time": "0:17:36"}
114
+ {"current_steps": 1120, "total_steps": 1281, "loss": 0.4696, "lr": 5e-06, "epoch": 2.6229508196721314, "percentage": 87.43, "elapsed_time": "1:55:16", "remaining_time": "0:16:34"}
115
+ {"current_steps": 1130, "total_steps": 1281, "loss": 0.4664, "lr": 5e-06, "epoch": 2.6463700234192036, "percentage": 88.21, "elapsed_time": "1:56:15", "remaining_time": "0:15:32"}
116
+ {"current_steps": 1140, "total_steps": 1281, "loss": 0.4693, "lr": 5e-06, "epoch": 2.669789227166276, "percentage": 88.99, "elapsed_time": "1:57:14", "remaining_time": "0:14:30"}
117
+ {"current_steps": 1150, "total_steps": 1281, "loss": 0.4692, "lr": 5e-06, "epoch": 2.693208430913349, "percentage": 89.77, "elapsed_time": "1:58:14", "remaining_time": "0:13:28"}
118
+ {"current_steps": 1160, "total_steps": 1281, "loss": 0.4704, "lr": 5e-06, "epoch": 2.7166276346604215, "percentage": 90.55, "elapsed_time": "1:59:13", "remaining_time": "0:12:26"}
119
+ {"current_steps": 1170, "total_steps": 1281, "loss": 0.4648, "lr": 5e-06, "epoch": 2.740046838407494, "percentage": 91.33, "elapsed_time": "2:00:13", "remaining_time": "0:11:24"}
120
+ {"current_steps": 1180, "total_steps": 1281, "loss": 0.4629, "lr": 5e-06, "epoch": 2.7634660421545667, "percentage": 92.12, "elapsed_time": "2:01:12", "remaining_time": "0:10:22"}
121
+ {"current_steps": 1190, "total_steps": 1281, "loss": 0.4704, "lr": 5e-06, "epoch": 2.7868852459016393, "percentage": 92.9, "elapsed_time": "2:02:11", "remaining_time": "0:09:20"}
122
+ {"current_steps": 1200, "total_steps": 1281, "loss": 0.4707, "lr": 5e-06, "epoch": 2.810304449648712, "percentage": 93.68, "elapsed_time": "2:03:11", "remaining_time": "0:08:18"}
123
+ {"current_steps": 1210, "total_steps": 1281, "loss": 0.4679, "lr": 5e-06, "epoch": 2.8337236533957846, "percentage": 94.46, "elapsed_time": "2:04:10", "remaining_time": "0:07:17"}