sedrickkeh commited on
Commit
099f3f7
·
verified ·
1 Parent(s): f12c3a8

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 sha256:93028c4ad9f23fe74f1c4cc050aa75224997398228e1fa7d01db38fa914c06cd
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8baee16f851ce04df12574eb764202317f11a23201438204216e0f88d942df0
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50bc87a9fe7dac9ec0d1ecc6156994accd57adf0fc419c3e5af0efb0bb341098
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1347a3494df4e510ca464085dcc7302a7481cf74f4ef931cedce518a3edd146
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0539f9d3676e64c39198f75cf53579ccc88a20835168fcc5ba571e84481f4e46
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dd7cb425076950af228c01521ca5f80f8ec3b933c594f574833343974d38bc6
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:cb4ab7118c1c57bf09a523c3f9b4dd337522df0f4bef1e2768009b21c4560400
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a0e9c467aa7ebee548170d9cd8ed84e8ff456a330f63bd5d2000d822cb3eba7
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -122,3 +122,63 @@
122
  {"current_steps": 1210, "total_steps": 1827, "loss": 0.7667, "lr": 5e-06, "epoch": 1.9860484201887567, "percentage": 66.23, "elapsed_time": "19:47:23", "remaining_time": "10:05:28"}
123
  {"current_steps": 1218, "total_steps": 1827, "eval_loss": 0.8003594875335693, "epoch": 1.9991793188346327, "percentage": 66.67, "elapsed_time": "20:06:24", "remaining_time": "10:03:12"}
124
  {"current_steps": 1220, "total_steps": 1827, "loss": 0.8157, "lr": 5e-06, "epoch": 2.002462043496102, "percentage": 66.78, "elapsed_time": "20:09:07", "remaining_time": "10:01:35"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
122
  {"current_steps": 1210, "total_steps": 1827, "loss": 0.7667, "lr": 5e-06, "epoch": 1.9860484201887567, "percentage": 66.23, "elapsed_time": "19:47:23", "remaining_time": "10:05:28"}
123
  {"current_steps": 1218, "total_steps": 1827, "eval_loss": 0.8003594875335693, "epoch": 1.9991793188346327, "percentage": 66.67, "elapsed_time": "20:06:24", "remaining_time": "10:03:12"}
124
  {"current_steps": 1220, "total_steps": 1827, "loss": 0.8157, "lr": 5e-06, "epoch": 2.002462043496102, "percentage": 66.78, "elapsed_time": "20:09:07", "remaining_time": "10:01:35"}
125
+ {"current_steps": 1230, "total_steps": 1827, "loss": 0.7226, "lr": 5e-06, "epoch": 2.0188756668034467, "percentage": 67.32, "elapsed_time": "20:18:50", "remaining_time": "9:51:35"}
126
+ {"current_steps": 1240, "total_steps": 1827, "loss": 0.723, "lr": 5e-06, "epoch": 2.035289290110792, "percentage": 67.87, "elapsed_time": "20:28:32", "remaining_time": "9:41:34"}
127
+ {"current_steps": 1250, "total_steps": 1827, "loss": 0.7279, "lr": 5e-06, "epoch": 2.0517029134181373, "percentage": 68.42, "elapsed_time": "20:38:14", "remaining_time": "9:31:34"}
128
+ {"current_steps": 1260, "total_steps": 1827, "loss": 0.7231, "lr": 5e-06, "epoch": 2.068116536725482, "percentage": 68.97, "elapsed_time": "20:47:55", "remaining_time": "9:21:33"}
129
+ {"current_steps": 1270, "total_steps": 1827, "loss": 0.7251, "lr": 5e-06, "epoch": 2.0845301600328274, "percentage": 69.51, "elapsed_time": "20:57:38", "remaining_time": "9:11:34"}
130
+ {"current_steps": 1280, "total_steps": 1827, "loss": 0.721, "lr": 5e-06, "epoch": 2.1009437833401723, "percentage": 70.06, "elapsed_time": "21:07:22", "remaining_time": "9:01:36"}
131
+ {"current_steps": 1290, "total_steps": 1827, "loss": 0.7247, "lr": 5e-06, "epoch": 2.1173574066475176, "percentage": 70.61, "elapsed_time": "21:17:06", "remaining_time": "8:51:37"}
132
+ {"current_steps": 1300, "total_steps": 1827, "loss": 0.7239, "lr": 5e-06, "epoch": 2.1337710299548625, "percentage": 71.15, "elapsed_time": "21:26:50", "remaining_time": "8:41:39"}
133
+ {"current_steps": 1310, "total_steps": 1827, "loss": 0.7265, "lr": 5e-06, "epoch": 2.1501846532622078, "percentage": 71.7, "elapsed_time": "21:36:33", "remaining_time": "8:31:41"}
134
+ {"current_steps": 1320, "total_steps": 1827, "loss": 0.7271, "lr": 5e-06, "epoch": 2.1665982765695526, "percentage": 72.25, "elapsed_time": "21:46:17", "remaining_time": "8:21:43"}
135
+ {"current_steps": 1330, "total_steps": 1827, "loss": 0.728, "lr": 5e-06, "epoch": 2.183011899876898, "percentage": 72.8, "elapsed_time": "21:56:01", "remaining_time": "8:11:46"}
136
+ {"current_steps": 1340, "total_steps": 1827, "loss": 0.7304, "lr": 5e-06, "epoch": 2.199425523184243, "percentage": 73.34, "elapsed_time": "22:05:45", "remaining_time": "8:01:49"}
137
+ {"current_steps": 1350, "total_steps": 1827, "loss": 0.7289, "lr": 5e-06, "epoch": 2.215839146491588, "percentage": 73.89, "elapsed_time": "22:15:29", "remaining_time": "7:51:52"}
138
+ {"current_steps": 1360, "total_steps": 1827, "loss": 0.7279, "lr": 5e-06, "epoch": 2.232252769798933, "percentage": 74.44, "elapsed_time": "22:25:12", "remaining_time": "7:41:55"}
139
+ {"current_steps": 1370, "total_steps": 1827, "loss": 0.7294, "lr": 5e-06, "epoch": 2.2486663931062782, "percentage": 74.99, "elapsed_time": "22:34:57", "remaining_time": "7:31:58"}
140
+ {"current_steps": 1380, "total_steps": 1827, "loss": 0.7282, "lr": 5e-06, "epoch": 2.2650800164136236, "percentage": 75.53, "elapsed_time": "22:44:39", "remaining_time": "7:22:01"}
141
+ {"current_steps": 1390, "total_steps": 1827, "loss": 0.7241, "lr": 5e-06, "epoch": 2.2814936397209684, "percentage": 76.08, "elapsed_time": "22:54:23", "remaining_time": "7:12:05"}
142
+ {"current_steps": 1400, "total_steps": 1827, "loss": 0.7318, "lr": 5e-06, "epoch": 2.2979072630283133, "percentage": 76.63, "elapsed_time": "23:04:06", "remaining_time": "7:02:09"}
143
+ {"current_steps": 1410, "total_steps": 1827, "loss": 0.726, "lr": 5e-06, "epoch": 2.3143208863356586, "percentage": 77.18, "elapsed_time": "23:13:48", "remaining_time": "6:52:12"}
144
+ {"current_steps": 1420, "total_steps": 1827, "loss": 0.7303, "lr": 5e-06, "epoch": 2.330734509643004, "percentage": 77.72, "elapsed_time": "23:23:31", "remaining_time": "6:42:16"}
145
+ {"current_steps": 1430, "total_steps": 1827, "loss": 0.7288, "lr": 5e-06, "epoch": 2.3471481329503487, "percentage": 78.27, "elapsed_time": "23:33:13", "remaining_time": "6:32:20"}
146
+ {"current_steps": 1440, "total_steps": 1827, "loss": 0.7296, "lr": 5e-06, "epoch": 2.363561756257694, "percentage": 78.82, "elapsed_time": "23:42:56", "remaining_time": "6:22:25"}
147
+ {"current_steps": 1450, "total_steps": 1827, "loss": 0.733, "lr": 5e-06, "epoch": 2.379975379565039, "percentage": 79.37, "elapsed_time": "23:52:41", "remaining_time": "6:12:29"}
148
+ {"current_steps": 1460, "total_steps": 1827, "loss": 0.7273, "lr": 5e-06, "epoch": 2.396389002872384, "percentage": 79.91, "elapsed_time": "1 day, 0:02:25", "remaining_time": "6:02:34"}
149
+ {"current_steps": 1470, "total_steps": 1827, "loss": 0.7315, "lr": 5e-06, "epoch": 2.412802626179729, "percentage": 80.46, "elapsed_time": "1 day, 0:12:10", "remaining_time": "5:52:40"}
150
+ {"current_steps": 1480, "total_steps": 1827, "loss": 0.7276, "lr": 5e-06, "epoch": 2.4292162494870744, "percentage": 81.01, "elapsed_time": "1 day, 0:21:53", "remaining_time": "5:42:45"}
151
+ {"current_steps": 1490, "total_steps": 1827, "loss": 0.7303, "lr": 5e-06, "epoch": 2.4456298727944192, "percentage": 81.55, "elapsed_time": "1 day, 0:31:37", "remaining_time": "5:32:50"}
152
+ {"current_steps": 1500, "total_steps": 1827, "loss": 0.7268, "lr": 5e-06, "epoch": 2.4620434961017645, "percentage": 82.1, "elapsed_time": "1 day, 0:41:19", "remaining_time": "5:22:55"}
153
+ {"current_steps": 1510, "total_steps": 1827, "loss": 0.7308, "lr": 5e-06, "epoch": 2.4784571194091094, "percentage": 82.65, "elapsed_time": "1 day, 0:51:03", "remaining_time": "5:13:01"}
154
+ {"current_steps": 1520, "total_steps": 1827, "loss": 0.7307, "lr": 5e-06, "epoch": 2.4948707427164547, "percentage": 83.2, "elapsed_time": "1 day, 1:00:46", "remaining_time": "5:03:07"}
155
+ {"current_steps": 1530, "total_steps": 1827, "loss": 0.7276, "lr": 5e-06, "epoch": 2.5112843660237996, "percentage": 83.74, "elapsed_time": "1 day, 1:10:32", "remaining_time": "4:53:13"}
156
+ {"current_steps": 1540, "total_steps": 1827, "loss": 0.7276, "lr": 5e-06, "epoch": 2.527697989331145, "percentage": 84.29, "elapsed_time": "1 day, 1:20:15", "remaining_time": "4:43:19"}
157
+ {"current_steps": 1550, "total_steps": 1827, "loss": 0.7302, "lr": 5e-06, "epoch": 2.54411161263849, "percentage": 84.84, "elapsed_time": "1 day, 1:29:58", "remaining_time": "4:33:25"}
158
+ {"current_steps": 1560, "total_steps": 1827, "loss": 0.7304, "lr": 5e-06, "epoch": 2.560525235945835, "percentage": 85.39, "elapsed_time": "1 day, 1:39:41", "remaining_time": "4:23:31"}
159
+ {"current_steps": 1570, "total_steps": 1827, "loss": 0.7288, "lr": 5e-06, "epoch": 2.57693885925318, "percentage": 85.93, "elapsed_time": "1 day, 1:49:25", "remaining_time": "4:13:37"}
160
+ {"current_steps": 1580, "total_steps": 1827, "loss": 0.7292, "lr": 5e-06, "epoch": 2.593352482560525, "percentage": 86.48, "elapsed_time": "1 day, 1:59:09", "remaining_time": "4:03:44"}
161
+ {"current_steps": 1590, "total_steps": 1827, "loss": 0.7329, "lr": 5e-06, "epoch": 2.6097661058678705, "percentage": 87.03, "elapsed_time": "1 day, 2:08:52", "remaining_time": "3:53:51"}
162
+ {"current_steps": 1600, "total_steps": 1827, "loss": 0.7289, "lr": 5e-06, "epoch": 2.6261797291752154, "percentage": 87.58, "elapsed_time": "1 day, 2:18:35", "remaining_time": "3:43:57"}
163
+ {"current_steps": 1610, "total_steps": 1827, "loss": 0.7331, "lr": 5e-06, "epoch": 2.6425933524825607, "percentage": 88.12, "elapsed_time": "1 day, 2:28:18", "remaining_time": "3:34:04"}
164
+ {"current_steps": 1620, "total_steps": 1827, "loss": 0.73, "lr": 5e-06, "epoch": 2.6590069757899055, "percentage": 88.67, "elapsed_time": "1 day, 2:38:02", "remaining_time": "3:24:11"}
165
+ {"current_steps": 1630, "total_steps": 1827, "loss": 0.7302, "lr": 5e-06, "epoch": 2.675420599097251, "percentage": 89.22, "elapsed_time": "1 day, 2:47:45", "remaining_time": "3:14:18"}
166
+ {"current_steps": 1640, "total_steps": 1827, "loss": 0.7326, "lr": 5e-06, "epoch": 2.6918342224045957, "percentage": 89.76, "elapsed_time": "1 day, 2:57:29", "remaining_time": "3:04:26"}
167
+ {"current_steps": 1650, "total_steps": 1827, "loss": 0.7316, "lr": 5e-06, "epoch": 2.708247845711941, "percentage": 90.31, "elapsed_time": "1 day, 3:07:15", "remaining_time": "2:54:33"}
168
+ {"current_steps": 1660, "total_steps": 1827, "loss": 0.7309, "lr": 5e-06, "epoch": 2.724661469019286, "percentage": 90.86, "elapsed_time": "1 day, 3:17:00", "remaining_time": "2:44:41"}
169
+ {"current_steps": 1670, "total_steps": 1827, "loss": 0.7348, "lr": 5e-06, "epoch": 2.741075092326631, "percentage": 91.41, "elapsed_time": "1 day, 3:26:45", "remaining_time": "2:34:48"}
170
+ {"current_steps": 1680, "total_steps": 1827, "loss": 0.7286, "lr": 5e-06, "epoch": 2.7574887156339765, "percentage": 91.95, "elapsed_time": "1 day, 3:36:27", "remaining_time": "2:24:56"}
171
+ {"current_steps": 1690, "total_steps": 1827, "loss": 0.7342, "lr": 5e-06, "epoch": 2.7739023389413213, "percentage": 92.5, "elapsed_time": "1 day, 3:46:11", "remaining_time": "2:15:04"}
172
+ {"current_steps": 1700, "total_steps": 1827, "loss": 0.7303, "lr": 5e-06, "epoch": 2.790315962248666, "percentage": 93.05, "elapsed_time": "1 day, 3:55:56", "remaining_time": "2:05:12"}
173
+ {"current_steps": 1710, "total_steps": 1827, "loss": 0.7292, "lr": 5e-06, "epoch": 2.8067295855560115, "percentage": 93.6, "elapsed_time": "1 day, 4:05:39", "remaining_time": "1:55:20"}
174
+ {"current_steps": 1720, "total_steps": 1827, "loss": 0.7255, "lr": 5e-06, "epoch": 2.823143208863357, "percentage": 94.14, "elapsed_time": "1 day, 4:15:22", "remaining_time": "1:45:28"}
175
+ {"current_steps": 1730, "total_steps": 1827, "loss": 0.7305, "lr": 5e-06, "epoch": 2.8395568321707017, "percentage": 94.69, "elapsed_time": "1 day, 4:25:06", "remaining_time": "1:35:36"}
176
+ {"current_steps": 1740, "total_steps": 1827, "loss": 0.7297, "lr": 5e-06, "epoch": 2.8559704554780465, "percentage": 95.24, "elapsed_time": "1 day, 4:34:49", "remaining_time": "1:25:44"}
177
+ {"current_steps": 1750, "total_steps": 1827, "loss": 0.7274, "lr": 5e-06, "epoch": 2.872384078785392, "percentage": 95.79, "elapsed_time": "1 day, 4:44:32", "remaining_time": "1:15:52"}
178
+ {"current_steps": 1760, "total_steps": 1827, "loss": 0.7321, "lr": 5e-06, "epoch": 2.888797702092737, "percentage": 96.33, "elapsed_time": "1 day, 4:54:15", "remaining_time": "1:06:01"}
179
+ {"current_steps": 1770, "total_steps": 1827, "loss": 0.7315, "lr": 5e-06, "epoch": 2.905211325400082, "percentage": 96.88, "elapsed_time": "1 day, 5:03:57", "remaining_time": "0:56:09"}
180
+ {"current_steps": 1780, "total_steps": 1827, "loss": 0.7266, "lr": 5e-06, "epoch": 2.9216249487074273, "percentage": 97.43, "elapsed_time": "1 day, 5:13:39", "remaining_time": "0:46:18"}
181
+ {"current_steps": 1790, "total_steps": 1827, "loss": 0.7326, "lr": 5e-06, "epoch": 2.938038572014772, "percentage": 97.97, "elapsed_time": "1 day, 5:23:24", "remaining_time": "0:36:27"}
182
+ {"current_steps": 1800, "total_steps": 1827, "loss": 0.7299, "lr": 5e-06, "epoch": 2.9544521953221174, "percentage": 98.52, "elapsed_time": "1 day, 5:33:06", "remaining_time": "0:26:35"}
183
+ {"current_steps": 1810, "total_steps": 1827, "loss": 0.7363, "lr": 5e-06, "epoch": 2.9708658186294623, "percentage": 99.07, "elapsed_time": "1 day, 5:42:50", "remaining_time": "0:16:44"}
184
+ {"current_steps": 1820, "total_steps": 1827, "loss": 0.7286, "lr": 5e-06, "epoch": 2.9872794419368076, "percentage": 99.62, "elapsed_time": "1 day, 5:52:35", "remaining_time": "0:06:53"}