sedrickkeh commited on
Commit
0b4ff59
·
verified ·
1 Parent(s): b1cc5d5

Training in progress, epoch 3

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:532ad72726d5f1c8be77df56851b59c42c74a2491e2be144820fb619b7372541
3
  size 4903351912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d3cbc1acac011960e67baff31fa498a99957a48cfd921859ad37e7685a6dd9f
3
  size 4903351912
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cad05750d48ef87c113f06d2882d249543abb7b298a8da5fd984dfb708f19ab5
3
  size 4947570872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fea75179c5d206412c4dcd2d1137bbec91a626202b004df412a8387d1a6d675
3
  size 4947570872
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:907564fb4555a5ad241c27384689846a929c5529510b3d9e300f55f6dfce1907
3
  size 4962221464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d04071832e5298795ae42ee0c32043f454ddaeed4d60397dcb7437e881785d69
3
  size 4962221464
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:995494e66b59b8015e9323be0d79d481609e02f043011f38c70414597c9b8e60
3
  size 3670322200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bd5a651206f6cd9e563926fe2fd290fd1fe385dcd338183b879ab02731c0b96
3
  size 3670322200
trainer_log.jsonl CHANGED
@@ -101,3 +101,36 @@
101
  {"current_steps": 990, "total_steps": 1336, "loss": 0.5048, "lr": 5e-06, "epoch": 2.962962962962963, "percentage": 74.1, "elapsed_time": "12:40:27", "remaining_time": "4:25:46"}
102
  {"current_steps": 1000, "total_steps": 1336, "loss": 0.5047, "lr": 5e-06, "epoch": 2.992891881780771, "percentage": 74.85, "elapsed_time": "12:48:00", "remaining_time": "4:18:03"}
103
  {"current_steps": 1002, "total_steps": 1336, "eval_loss": 0.6354114413261414, "epoch": 2.9988776655443323, "percentage": 75.0, "elapsed_time": "12:54:16", "remaining_time": "4:18:05"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
101
  {"current_steps": 990, "total_steps": 1336, "loss": 0.5048, "lr": 5e-06, "epoch": 2.962962962962963, "percentage": 74.1, "elapsed_time": "12:40:27", "remaining_time": "4:25:46"}
102
  {"current_steps": 1000, "total_steps": 1336, "loss": 0.5047, "lr": 5e-06, "epoch": 2.992891881780771, "percentage": 74.85, "elapsed_time": "12:48:00", "remaining_time": "4:18:03"}
103
  {"current_steps": 1002, "total_steps": 1336, "eval_loss": 0.6354114413261414, "epoch": 2.9988776655443323, "percentage": 75.0, "elapsed_time": "12:54:16", "remaining_time": "4:18:05"}
104
+ {"current_steps": 1010, "total_steps": 1336, "loss": 0.4757, "lr": 5e-06, "epoch": 3.0228208005985784, "percentage": 75.6, "elapsed_time": "13:01:07", "remaining_time": "4:12:07"}
105
+ {"current_steps": 1020, "total_steps": 1336, "loss": 0.4189, "lr": 5e-06, "epoch": 3.052749719416386, "percentage": 76.35, "elapsed_time": "13:08:42", "remaining_time": "4:04:20"}
106
+ {"current_steps": 1030, "total_steps": 1336, "loss": 0.42, "lr": 5e-06, "epoch": 3.082678638234194, "percentage": 77.1, "elapsed_time": "13:16:18", "remaining_time": "3:56:34"}
107
+ {"current_steps": 1040, "total_steps": 1336, "loss": 0.4184, "lr": 5e-06, "epoch": 3.1126075570520015, "percentage": 77.84, "elapsed_time": "13:23:52", "remaining_time": "3:48:47"}
108
+ {"current_steps": 1050, "total_steps": 1336, "loss": 0.4173, "lr": 5e-06, "epoch": 3.142536475869809, "percentage": 78.59, "elapsed_time": "13:31:25", "remaining_time": "3:41:00"}
109
+ {"current_steps": 1060, "total_steps": 1336, "loss": 0.426, "lr": 5e-06, "epoch": 3.1724653946876167, "percentage": 79.34, "elapsed_time": "13:38:59", "remaining_time": "3:33:14"}
110
+ {"current_steps": 1070, "total_steps": 1336, "loss": 0.4192, "lr": 5e-06, "epoch": 3.2023943135054247, "percentage": 80.09, "elapsed_time": "13:46:33", "remaining_time": "3:25:28"}
111
+ {"current_steps": 1080, "total_steps": 1336, "loss": 0.4248, "lr": 5e-06, "epoch": 3.2323232323232323, "percentage": 80.84, "elapsed_time": "13:54:07", "remaining_time": "3:17:43"}
112
+ {"current_steps": 1090, "total_steps": 1336, "loss": 0.4309, "lr": 5e-06, "epoch": 3.2622521511410403, "percentage": 81.59, "elapsed_time": "14:01:42", "remaining_time": "3:09:57"}
113
+ {"current_steps": 1100, "total_steps": 1336, "loss": 0.4265, "lr": 5e-06, "epoch": 3.292181069958848, "percentage": 82.34, "elapsed_time": "14:09:16", "remaining_time": "3:02:12"}
114
+ {"current_steps": 1110, "total_steps": 1336, "loss": 0.4247, "lr": 5e-06, "epoch": 3.3221099887766554, "percentage": 83.08, "elapsed_time": "14:16:50", "remaining_time": "2:54:27"}
115
+ {"current_steps": 1120, "total_steps": 1336, "loss": 0.4247, "lr": 5e-06, "epoch": 3.352038907594463, "percentage": 83.83, "elapsed_time": "14:24:23", "remaining_time": "2:46:42"}
116
+ {"current_steps": 1130, "total_steps": 1336, "loss": 0.427, "lr": 5e-06, "epoch": 3.381967826412271, "percentage": 84.58, "elapsed_time": "14:31:58", "remaining_time": "2:38:57"}
117
+ {"current_steps": 1140, "total_steps": 1336, "loss": 0.4296, "lr": 5e-06, "epoch": 3.4118967452300786, "percentage": 85.33, "elapsed_time": "14:39:34", "remaining_time": "2:31:13"}
118
+ {"current_steps": 1150, "total_steps": 1336, "loss": 0.4272, "lr": 5e-06, "epoch": 3.441825664047886, "percentage": 86.08, "elapsed_time": "14:47:09", "remaining_time": "2:23:29"}
119
+ {"current_steps": 1160, "total_steps": 1336, "loss": 0.4298, "lr": 5e-06, "epoch": 3.471754582865694, "percentage": 86.83, "elapsed_time": "14:54:42", "remaining_time": "2:15:44"}
120
+ {"current_steps": 1170, "total_steps": 1336, "loss": 0.4299, "lr": 5e-06, "epoch": 3.5016835016835017, "percentage": 87.57, "elapsed_time": "15:02:17", "remaining_time": "2:08:01"}
121
+ {"current_steps": 1180, "total_steps": 1336, "loss": 0.4299, "lr": 5e-06, "epoch": 3.5316124205013093, "percentage": 88.32, "elapsed_time": "15:09:51", "remaining_time": "2:00:17"}
122
+ {"current_steps": 1190, "total_steps": 1336, "loss": 0.436, "lr": 5e-06, "epoch": 3.561541339319117, "percentage": 89.07, "elapsed_time": "15:17:26", "remaining_time": "1:52:33"}
123
+ {"current_steps": 1200, "total_steps": 1336, "loss": 0.4307, "lr": 5e-06, "epoch": 3.591470258136925, "percentage": 89.82, "elapsed_time": "15:25:01", "remaining_time": "1:44:50"}
124
+ {"current_steps": 1210, "total_steps": 1336, "loss": 0.435, "lr": 5e-06, "epoch": 3.6213991769547325, "percentage": 90.57, "elapsed_time": "15:32:36", "remaining_time": "1:37:06"}
125
+ {"current_steps": 1220, "total_steps": 1336, "loss": 0.4366, "lr": 5e-06, "epoch": 3.6513280957725405, "percentage": 91.32, "elapsed_time": "15:40:12", "remaining_time": "1:29:23"}
126
+ {"current_steps": 1230, "total_steps": 1336, "loss": 0.4328, "lr": 5e-06, "epoch": 3.681257014590348, "percentage": 92.07, "elapsed_time": "15:47:47", "remaining_time": "1:21:40"}
127
+ {"current_steps": 1240, "total_steps": 1336, "loss": 0.4423, "lr": 5e-06, "epoch": 3.7111859334081556, "percentage": 92.81, "elapsed_time": "15:55:22", "remaining_time": "1:13:57"}
128
+ {"current_steps": 1250, "total_steps": 1336, "loss": 0.4348, "lr": 5e-06, "epoch": 3.741114852225963, "percentage": 93.56, "elapsed_time": "16:02:57", "remaining_time": "1:06:15"}
129
+ {"current_steps": 1260, "total_steps": 1336, "loss": 0.4341, "lr": 5e-06, "epoch": 3.771043771043771, "percentage": 94.31, "elapsed_time": "16:10:32", "remaining_time": "0:58:32"}
130
+ {"current_steps": 1270, "total_steps": 1336, "loss": 0.4417, "lr": 5e-06, "epoch": 3.8009726898615788, "percentage": 95.06, "elapsed_time": "16:18:06", "remaining_time": "0:50:49"}
131
+ {"current_steps": 1280, "total_steps": 1336, "loss": 0.4385, "lr": 5e-06, "epoch": 3.8309016086793863, "percentage": 95.81, "elapsed_time": "16:25:41", "remaining_time": "0:43:07"}
132
+ {"current_steps": 1290, "total_steps": 1336, "loss": 0.4389, "lr": 5e-06, "epoch": 3.8608305274971944, "percentage": 96.56, "elapsed_time": "16:33:15", "remaining_time": "0:35:25"}
133
+ {"current_steps": 1300, "total_steps": 1336, "loss": 0.4371, "lr": 5e-06, "epoch": 3.890759446315002, "percentage": 97.31, "elapsed_time": "16:40:49", "remaining_time": "0:27:42"}
134
+ {"current_steps": 1310, "total_steps": 1336, "loss": 0.4394, "lr": 5e-06, "epoch": 3.9206883651328095, "percentage": 98.05, "elapsed_time": "16:48:22", "remaining_time": "0:20:00"}
135
+ {"current_steps": 1320, "total_steps": 1336, "loss": 0.4351, "lr": 5e-06, "epoch": 3.950617283950617, "percentage": 98.8, "elapsed_time": "16:55:56", "remaining_time": "0:12:18"}
136
+ {"current_steps": 1330, "total_steps": 1336, "loss": 0.4386, "lr": 5e-06, "epoch": 3.980546202768425, "percentage": 99.55, "elapsed_time": "17:03:30", "remaining_time": "0:04:37"}