sedrickkeh commited on
Commit
de6fec3
·
verified ·
1 Parent(s): 0037392

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 sha256:6cfe3b3d7ce5fa70e8b3c9d63ea02a5f6e4e0c60ed838816b842f26001445b8a
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50c1e70fa37344d3fd96656b7af74a4e7a30ac6610422b56aa6561c685637bf3
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:b6ee3643fac178ce79a77df727ec852b5af08f3273fd088fa30e480620070efc
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc824c4bcec7a0d085f6eb5483e4a464ed80988c241c3379a864ece1488670c
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:db2e2b9a07cfd0d764e99c48341dc607ac2e4f3adac4b5294bf88e2ab17659fe
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d06f70595cc9ccca5bd323a01f07d0c84708fd3dd72ce81832333fcdb7e9f978
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cfa1a52b7f24e148ed181b705430f8bee82238fc14538acdaddc010e197e8a5
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7712797ffbd749a57f6db43c70fc7285f197f7acfb2f159b81791e0c20248549
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -115,3 +115,60 @@
115
  {"current_steps": 1140, "total_steps": 1722, "loss": 0.6807, "lr": 5e-06, "epoch": 1.985630306988896, "percentage": 66.2, "elapsed_time": "10:14:00", "remaining_time": "5:13:28"}
116
  {"current_steps": 1148, "total_steps": 1722, "eval_loss": 0.7203673124313354, "epoch": 1.9995645547572392, "percentage": 66.67, "elapsed_time": "10:24:57", "remaining_time": "5:12:28"}
117
  {"current_steps": 1150, "total_steps": 1722, "loss": 0.7309, "lr": 5e-06, "epoch": 2.003048116699325, "percentage": 66.78, "elapsed_time": "10:27:12", "remaining_time": "5:11:58"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
115
  {"current_steps": 1140, "total_steps": 1722, "loss": 0.6807, "lr": 5e-06, "epoch": 1.985630306988896, "percentage": 66.2, "elapsed_time": "10:14:00", "remaining_time": "5:13:28"}
116
  {"current_steps": 1148, "total_steps": 1722, "eval_loss": 0.7203673124313354, "epoch": 1.9995645547572392, "percentage": 66.67, "elapsed_time": "10:24:57", "remaining_time": "5:12:28"}
117
  {"current_steps": 1150, "total_steps": 1722, "loss": 0.7309, "lr": 5e-06, "epoch": 2.003048116699325, "percentage": 66.78, "elapsed_time": "10:27:12", "remaining_time": "5:11:58"}
118
+ {"current_steps": 1160, "total_steps": 1722, "loss": 0.6325, "lr": 5e-06, "epoch": 2.020465926409754, "percentage": 67.36, "elapsed_time": "10:32:29", "remaining_time": "5:06:26"}
119
+ {"current_steps": 1170, "total_steps": 1722, "loss": 0.6307, "lr": 5e-06, "epoch": 2.037883736120183, "percentage": 67.94, "elapsed_time": "10:37:46", "remaining_time": "5:00:54"}
120
+ {"current_steps": 1180, "total_steps": 1722, "loss": 0.6337, "lr": 5e-06, "epoch": 2.055301545830612, "percentage": 68.52, "elapsed_time": "10:43:05", "remaining_time": "4:55:23"}
121
+ {"current_steps": 1190, "total_steps": 1722, "loss": 0.6291, "lr": 5e-06, "epoch": 2.072719355541041, "percentage": 69.11, "elapsed_time": "10:48:24", "remaining_time": "4:49:52"}
122
+ {"current_steps": 1200, "total_steps": 1722, "loss": 0.6303, "lr": 5e-06, "epoch": 2.0901371652514698, "percentage": 69.69, "elapsed_time": "10:53:43", "remaining_time": "4:44:22"}
123
+ {"current_steps": 1210, "total_steps": 1722, "loss": 0.63, "lr": 5e-06, "epoch": 2.1075549749618987, "percentage": 70.27, "elapsed_time": "10:59:02", "remaining_time": "4:38:52"}
124
+ {"current_steps": 1220, "total_steps": 1722, "loss": 0.6319, "lr": 5e-06, "epoch": 2.1249727846723276, "percentage": 70.85, "elapsed_time": "11:04:21", "remaining_time": "4:33:21"}
125
+ {"current_steps": 1230, "total_steps": 1722, "loss": 0.6338, "lr": 5e-06, "epoch": 2.142390594382756, "percentage": 71.43, "elapsed_time": "11:09:40", "remaining_time": "4:27:52"}
126
+ {"current_steps": 1240, "total_steps": 1722, "loss": 0.6315, "lr": 5e-06, "epoch": 2.159808404093185, "percentage": 72.01, "elapsed_time": "11:14:58", "remaining_time": "4:22:22"}
127
+ {"current_steps": 1250, "total_steps": 1722, "loss": 0.6307, "lr": 5e-06, "epoch": 2.177226213803614, "percentage": 72.59, "elapsed_time": "11:20:17", "remaining_time": "4:16:52"}
128
+ {"current_steps": 1260, "total_steps": 1722, "loss": 0.635, "lr": 5e-06, "epoch": 2.194644023514043, "percentage": 73.17, "elapsed_time": "11:25:35", "remaining_time": "4:11:23"}
129
+ {"current_steps": 1270, "total_steps": 1722, "loss": 0.6328, "lr": 5e-06, "epoch": 2.212061833224472, "percentage": 73.75, "elapsed_time": "11:30:52", "remaining_time": "4:05:53"}
130
+ {"current_steps": 1280, "total_steps": 1722, "loss": 0.6392, "lr": 5e-06, "epoch": 2.229479642934901, "percentage": 74.33, "elapsed_time": "11:36:10", "remaining_time": "4:00:23"}
131
+ {"current_steps": 1290, "total_steps": 1722, "loss": 0.6347, "lr": 5e-06, "epoch": 2.24689745264533, "percentage": 74.91, "elapsed_time": "11:41:29", "remaining_time": "3:54:55"}
132
+ {"current_steps": 1300, "total_steps": 1722, "loss": 0.6304, "lr": 5e-06, "epoch": 2.2643152623557588, "percentage": 75.49, "elapsed_time": "11:46:47", "remaining_time": "3:49:26"}
133
+ {"current_steps": 1310, "total_steps": 1722, "loss": 0.6354, "lr": 5e-06, "epoch": 2.2817330720661877, "percentage": 76.07, "elapsed_time": "11:52:04", "remaining_time": "3:43:56"}
134
+ {"current_steps": 1320, "total_steps": 1722, "loss": 0.6319, "lr": 5e-06, "epoch": 2.2991508817766166, "percentage": 76.66, "elapsed_time": "11:57:22", "remaining_time": "3:38:28"}
135
+ {"current_steps": 1330, "total_steps": 1722, "loss": 0.6361, "lr": 5e-06, "epoch": 2.3165686914870456, "percentage": 77.24, "elapsed_time": "12:02:42", "remaining_time": "3:33:00"}
136
+ {"current_steps": 1340, "total_steps": 1722, "loss": 0.6363, "lr": 5e-06, "epoch": 2.3339865011974745, "percentage": 77.82, "elapsed_time": "12:08:01", "remaining_time": "3:27:32"}
137
+ {"current_steps": 1350, "total_steps": 1722, "loss": 0.6408, "lr": 5e-06, "epoch": 2.3514043109079035, "percentage": 78.4, "elapsed_time": "12:13:19", "remaining_time": "3:22:04"}
138
+ {"current_steps": 1360, "total_steps": 1722, "loss": 0.6333, "lr": 5e-06, "epoch": 2.3688221206183324, "percentage": 78.98, "elapsed_time": "12:18:37", "remaining_time": "3:16:36"}
139
+ {"current_steps": 1370, "total_steps": 1722, "loss": 0.6328, "lr": 5e-06, "epoch": 2.3862399303287614, "percentage": 79.56, "elapsed_time": "12:23:54", "remaining_time": "3:11:08"}
140
+ {"current_steps": 1380, "total_steps": 1722, "loss": 0.6413, "lr": 5e-06, "epoch": 2.40365774003919, "percentage": 80.14, "elapsed_time": "12:29:11", "remaining_time": "3:05:40"}
141
+ {"current_steps": 1390, "total_steps": 1722, "loss": 0.6362, "lr": 5e-06, "epoch": 2.421075549749619, "percentage": 80.72, "elapsed_time": "12:34:30", "remaining_time": "3:00:12"}
142
+ {"current_steps": 1400, "total_steps": 1722, "loss": 0.6354, "lr": 5e-06, "epoch": 2.4384933594600477, "percentage": 81.3, "elapsed_time": "12:39:48", "remaining_time": "2:54:45"}
143
+ {"current_steps": 1410, "total_steps": 1722, "loss": 0.6364, "lr": 5e-06, "epoch": 2.4559111691704767, "percentage": 81.88, "elapsed_time": "12:45:07", "remaining_time": "2:49:18"}
144
+ {"current_steps": 1420, "total_steps": 1722, "loss": 0.6347, "lr": 5e-06, "epoch": 2.4733289788809056, "percentage": 82.46, "elapsed_time": "12:50:26", "remaining_time": "2:43:51"}
145
+ {"current_steps": 1430, "total_steps": 1722, "loss": 0.6375, "lr": 5e-06, "epoch": 2.4907467885913346, "percentage": 83.04, "elapsed_time": "12:55:44", "remaining_time": "2:38:24"}
146
+ {"current_steps": 1440, "total_steps": 1722, "loss": 0.638, "lr": 5e-06, "epoch": 2.5081645983017635, "percentage": 83.62, "elapsed_time": "13:01:03", "remaining_time": "2:32:57"}
147
+ {"current_steps": 1450, "total_steps": 1722, "loss": 0.6356, "lr": 5e-06, "epoch": 2.5255824080121925, "percentage": 84.2, "elapsed_time": "13:06:21", "remaining_time": "2:27:30"}
148
+ {"current_steps": 1460, "total_steps": 1722, "loss": 0.64, "lr": 5e-06, "epoch": 2.5430002177226214, "percentage": 84.79, "elapsed_time": "13:11:40", "remaining_time": "2:22:04"}
149
+ {"current_steps": 1470, "total_steps": 1722, "loss": 0.6392, "lr": 5e-06, "epoch": 2.5604180274330504, "percentage": 85.37, "elapsed_time": "13:16:59", "remaining_time": "2:16:37"}
150
+ {"current_steps": 1480, "total_steps": 1722, "loss": 0.638, "lr": 5e-06, "epoch": 2.5778358371434793, "percentage": 85.95, "elapsed_time": "13:22:18", "remaining_time": "2:11:11"}
151
+ {"current_steps": 1490, "total_steps": 1722, "loss": 0.6418, "lr": 5e-06, "epoch": 2.5952536468539082, "percentage": 86.53, "elapsed_time": "13:27:36", "remaining_time": "2:05:44"}
152
+ {"current_steps": 1500, "total_steps": 1722, "loss": 0.637, "lr": 5e-06, "epoch": 2.612671456564337, "percentage": 87.11, "elapsed_time": "13:32:55", "remaining_time": "2:00:18"}
153
+ {"current_steps": 1510, "total_steps": 1722, "loss": 0.6359, "lr": 5e-06, "epoch": 2.6300892662747657, "percentage": 87.69, "elapsed_time": "13:38:14", "remaining_time": "1:54:52"}
154
+ {"current_steps": 1520, "total_steps": 1722, "loss": 0.6372, "lr": 5e-06, "epoch": 2.647507075985195, "percentage": 88.27, "elapsed_time": "13:43:34", "remaining_time": "1:49:26"}
155
+ {"current_steps": 1530, "total_steps": 1722, "loss": 0.6393, "lr": 5e-06, "epoch": 2.6649248856956236, "percentage": 88.85, "elapsed_time": "13:48:53", "remaining_time": "1:44:01"}
156
+ {"current_steps": 1540, "total_steps": 1722, "loss": 0.6399, "lr": 5e-06, "epoch": 2.6823426954060525, "percentage": 89.43, "elapsed_time": "13:54:11", "remaining_time": "1:38:35"}
157
+ {"current_steps": 1550, "total_steps": 1722, "loss": 0.6348, "lr": 5e-06, "epoch": 2.6997605051164815, "percentage": 90.01, "elapsed_time": "13:59:30", "remaining_time": "1:33:09"}
158
+ {"current_steps": 1560, "total_steps": 1722, "loss": 0.6358, "lr": 5e-06, "epoch": 2.7171783148269104, "percentage": 90.59, "elapsed_time": "14:04:49", "remaining_time": "1:27:43"}
159
+ {"current_steps": 1570, "total_steps": 1722, "loss": 0.6416, "lr": 5e-06, "epoch": 2.7345961245373394, "percentage": 91.17, "elapsed_time": "14:10:09", "remaining_time": "1:22:18"}
160
+ {"current_steps": 1580, "total_steps": 1722, "loss": 0.6312, "lr": 5e-06, "epoch": 2.7520139342477683, "percentage": 91.75, "elapsed_time": "14:15:27", "remaining_time": "1:16:52"}
161
+ {"current_steps": 1590, "total_steps": 1722, "loss": 0.6369, "lr": 5e-06, "epoch": 2.7694317439581972, "percentage": 92.33, "elapsed_time": "14:20:46", "remaining_time": "1:11:27"}
162
+ {"current_steps": 1600, "total_steps": 1722, "loss": 0.6376, "lr": 5e-06, "epoch": 2.786849553668626, "percentage": 92.92, "elapsed_time": "14:26:03", "remaining_time": "1:06:02"}
163
+ {"current_steps": 1610, "total_steps": 1722, "loss": 0.638, "lr": 5e-06, "epoch": 2.804267363379055, "percentage": 93.5, "elapsed_time": "14:31:21", "remaining_time": "1:00:36"}
164
+ {"current_steps": 1620, "total_steps": 1722, "loss": 0.6363, "lr": 5e-06, "epoch": 2.821685173089484, "percentage": 94.08, "elapsed_time": "14:36:40", "remaining_time": "0:55:11"}
165
+ {"current_steps": 1630, "total_steps": 1722, "loss": 0.6392, "lr": 5e-06, "epoch": 2.839102982799913, "percentage": 94.66, "elapsed_time": "14:41:58", "remaining_time": "0:49:46"}
166
+ {"current_steps": 1640, "total_steps": 1722, "loss": 0.6369, "lr": 5e-06, "epoch": 2.856520792510342, "percentage": 95.24, "elapsed_time": "14:47:17", "remaining_time": "0:44:21"}
167
+ {"current_steps": 1650, "total_steps": 1722, "loss": 0.636, "lr": 5e-06, "epoch": 2.873938602220771, "percentage": 95.82, "elapsed_time": "14:52:36", "remaining_time": "0:38:57"}
168
+ {"current_steps": 1660, "total_steps": 1722, "loss": 0.6376, "lr": 5e-06, "epoch": 2.8913564119311994, "percentage": 96.4, "elapsed_time": "14:57:55", "remaining_time": "0:33:32"}
169
+ {"current_steps": 1670, "total_steps": 1722, "loss": 0.6386, "lr": 5e-06, "epoch": 2.908774221641629, "percentage": 96.98, "elapsed_time": "15:03:14", "remaining_time": "0:28:07"}
170
+ {"current_steps": 1680, "total_steps": 1722, "loss": 0.6378, "lr": 5e-06, "epoch": 2.9261920313520573, "percentage": 97.56, "elapsed_time": "15:08:34", "remaining_time": "0:22:42"}
171
+ {"current_steps": 1690, "total_steps": 1722, "loss": 0.6392, "lr": 5e-06, "epoch": 2.9436098410624862, "percentage": 98.14, "elapsed_time": "15:13:53", "remaining_time": "0:17:18"}
172
+ {"current_steps": 1700, "total_steps": 1722, "loss": 0.642, "lr": 5e-06, "epoch": 2.961027650772915, "percentage": 98.72, "elapsed_time": "15:19:12", "remaining_time": "0:11:53"}
173
+ {"current_steps": 1710, "total_steps": 1722, "loss": 0.6381, "lr": 5e-06, "epoch": 2.978445460483344, "percentage": 99.3, "elapsed_time": "15:24:31", "remaining_time": "0:06:29"}
174
+ {"current_steps": 1720, "total_steps": 1722, "loss": 0.638, "lr": 5e-06, "epoch": 2.995863270193773, "percentage": 99.88, "elapsed_time": "15:29:50", "remaining_time": "0:01:04"}