sedrickkeh commited on
Commit
38340d7
·
verified ·
1 Parent(s): 7e15a77

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 sha256:51cf127615d757efee1e29c3e73a7e76f4b88bd2a2e7b385ce6b2cc5df1be3f7
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f987fba0b8924f2e503fa52659c4df136bbc81b1e9180e409923923bc064ae5b
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:b46ec1ebd0412177bec08de468657eae6e7fef870dee73155a330c1f74a423d5
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbcf1ec2c625a4656fdec89fb88cf4b739ee795ef06689ef299279eb2d11e322
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15a2fa6e1186479655d84c6eb31f6ce5897f21b491b92e72ac00b25e8911d361
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81cace9956df9e5c7314efab61e8b84afa972a415813685dc42121c92c70ac0c
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:484917bc923450416fabd11a1ac56a1f20e57d593f697747d0c981e16ec11f65
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edd23c26d9abf5750ee90043b34c619cc9fe543966ea66a7b89d0e3e626ccec7
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -117,3 +117,61 @@
117
  {"current_steps": 1160, "total_steps": 1755, "loss": 0.7651, "lr": 5e-06, "epoch": 1.9816357036087977, "percentage": 66.1, "elapsed_time": "18:50:33", "remaining_time": "9:39:54"}
118
  {"current_steps": 1170, "total_steps": 1755, "loss": 0.7679, "lr": 5e-06, "epoch": 1.9987187700192184, "percentage": 66.67, "elapsed_time": "19:00:11", "remaining_time": "9:30:05"}
119
  {"current_steps": 1170, "total_steps": 1755, "eval_loss": 0.8001261949539185, "epoch": 1.9987187700192184, "percentage": 66.67, "elapsed_time": "19:11:14", "remaining_time": "9:35:37"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
117
  {"current_steps": 1160, "total_steps": 1755, "loss": 0.7651, "lr": 5e-06, "epoch": 1.9816357036087977, "percentage": 66.1, "elapsed_time": "18:50:33", "remaining_time": "9:39:54"}
118
  {"current_steps": 1170, "total_steps": 1755, "loss": 0.7679, "lr": 5e-06, "epoch": 1.9987187700192184, "percentage": 66.67, "elapsed_time": "19:00:11", "remaining_time": "9:30:05"}
119
  {"current_steps": 1170, "total_steps": 1755, "eval_loss": 0.8001261949539185, "epoch": 1.9987187700192184, "percentage": 66.67, "elapsed_time": "19:11:14", "remaining_time": "9:35:37"}
120
+ {"current_steps": 1180, "total_steps": 1755, "loss": 0.7761, "lr": 5e-06, "epoch": 2.015801836429639, "percentage": 67.24, "elapsed_time": "19:21:25", "remaining_time": "9:25:57"}
121
+ {"current_steps": 1190, "total_steps": 1755, "loss": 0.7251, "lr": 5e-06, "epoch": 2.0328849028400597, "percentage": 67.81, "elapsed_time": "19:31:03", "remaining_time": "9:16:00"}
122
+ {"current_steps": 1200, "total_steps": 1755, "loss": 0.7275, "lr": 5e-06, "epoch": 2.0499679692504804, "percentage": 68.38, "elapsed_time": "19:40:42", "remaining_time": "9:06:04"}
123
+ {"current_steps": 1210, "total_steps": 1755, "loss": 0.7222, "lr": 5e-06, "epoch": 2.067051035660901, "percentage": 68.95, "elapsed_time": "19:50:21", "remaining_time": "8:56:09"}
124
+ {"current_steps": 1220, "total_steps": 1755, "loss": 0.7265, "lr": 5e-06, "epoch": 2.0841341020713218, "percentage": 69.52, "elapsed_time": "20:00:01", "remaining_time": "8:46:14"}
125
+ {"current_steps": 1230, "total_steps": 1755, "loss": 0.7253, "lr": 5e-06, "epoch": 2.1012171684817424, "percentage": 70.09, "elapsed_time": "20:09:40", "remaining_time": "8:36:19"}
126
+ {"current_steps": 1240, "total_steps": 1755, "loss": 0.7237, "lr": 5e-06, "epoch": 2.118300234892163, "percentage": 70.66, "elapsed_time": "20:19:19", "remaining_time": "8:26:24"}
127
+ {"current_steps": 1250, "total_steps": 1755, "loss": 0.7281, "lr": 5e-06, "epoch": 2.135383301302584, "percentage": 71.23, "elapsed_time": "20:28:57", "remaining_time": "8:16:30"}
128
+ {"current_steps": 1260, "total_steps": 1755, "loss": 0.7328, "lr": 5e-06, "epoch": 2.1524663677130045, "percentage": 71.79, "elapsed_time": "20:38:37", "remaining_time": "8:06:35"}
129
+ {"current_steps": 1270, "total_steps": 1755, "loss": 0.7295, "lr": 5e-06, "epoch": 2.169549434123425, "percentage": 72.36, "elapsed_time": "20:48:16", "remaining_time": "7:56:42"}
130
+ {"current_steps": 1280, "total_steps": 1755, "loss": 0.7337, "lr": 5e-06, "epoch": 2.186632500533846, "percentage": 72.93, "elapsed_time": "20:57:56", "remaining_time": "7:46:48"}
131
+ {"current_steps": 1290, "total_steps": 1755, "loss": 0.7257, "lr": 5e-06, "epoch": 2.2037155669442665, "percentage": 73.5, "elapsed_time": "21:07:33", "remaining_time": "7:36:54"}
132
+ {"current_steps": 1300, "total_steps": 1755, "loss": 0.7295, "lr": 5e-06, "epoch": 2.220798633354687, "percentage": 74.07, "elapsed_time": "21:17:11", "remaining_time": "7:27:01"}
133
+ {"current_steps": 1310, "total_steps": 1755, "loss": 0.7258, "lr": 5e-06, "epoch": 2.237881699765108, "percentage": 74.64, "elapsed_time": "21:26:52", "remaining_time": "7:17:08"}
134
+ {"current_steps": 1320, "total_steps": 1755, "loss": 0.7282, "lr": 5e-06, "epoch": 2.2549647661755285, "percentage": 75.21, "elapsed_time": "21:36:31", "remaining_time": "7:07:15"}
135
+ {"current_steps": 1330, "total_steps": 1755, "loss": 0.7289, "lr": 5e-06, "epoch": 2.2720478325859492, "percentage": 75.78, "elapsed_time": "21:46:09", "remaining_time": "6:57:22"}
136
+ {"current_steps": 1340, "total_steps": 1755, "loss": 0.7261, "lr": 5e-06, "epoch": 2.28913089899637, "percentage": 76.35, "elapsed_time": "21:55:46", "remaining_time": "6:47:29"}
137
+ {"current_steps": 1350, "total_steps": 1755, "loss": 0.7274, "lr": 5e-06, "epoch": 2.3062139654067906, "percentage": 76.92, "elapsed_time": "22:05:25", "remaining_time": "6:37:37"}
138
+ {"current_steps": 1360, "total_steps": 1755, "loss": 0.7295, "lr": 5e-06, "epoch": 2.3232970318172113, "percentage": 77.49, "elapsed_time": "22:15:04", "remaining_time": "6:27:45"}
139
+ {"current_steps": 1370, "total_steps": 1755, "loss": 0.7283, "lr": 5e-06, "epoch": 2.340380098227632, "percentage": 78.06, "elapsed_time": "22:24:41", "remaining_time": "6:17:53"}
140
+ {"current_steps": 1380, "total_steps": 1755, "loss": 0.7296, "lr": 5e-06, "epoch": 2.3574631646380526, "percentage": 78.63, "elapsed_time": "22:34:21", "remaining_time": "6:08:01"}
141
+ {"current_steps": 1390, "total_steps": 1755, "loss": 0.7248, "lr": 5e-06, "epoch": 2.3745462310484733, "percentage": 79.2, "elapsed_time": "22:44:00", "remaining_time": "5:58:10"}
142
+ {"current_steps": 1400, "total_steps": 1755, "loss": 0.7318, "lr": 5e-06, "epoch": 2.391629297458894, "percentage": 79.77, "elapsed_time": "22:53:37", "remaining_time": "5:48:18"}
143
+ {"current_steps": 1410, "total_steps": 1755, "loss": 0.7272, "lr": 5e-06, "epoch": 2.4087123638693146, "percentage": 80.34, "elapsed_time": "23:03:17", "remaining_time": "5:38:27"}
144
+ {"current_steps": 1420, "total_steps": 1755, "loss": 0.7277, "lr": 5e-06, "epoch": 2.4257954302797353, "percentage": 80.91, "elapsed_time": "23:12:55", "remaining_time": "5:28:36"}
145
+ {"current_steps": 1430, "total_steps": 1755, "loss": 0.7307, "lr": 5e-06, "epoch": 2.442878496690156, "percentage": 81.48, "elapsed_time": "23:22:33", "remaining_time": "5:18:45"}
146
+ {"current_steps": 1440, "total_steps": 1755, "loss": 0.7313, "lr": 5e-06, "epoch": 2.4599615631005767, "percentage": 82.05, "elapsed_time": "23:32:11", "remaining_time": "5:08:54"}
147
+ {"current_steps": 1450, "total_steps": 1755, "loss": 0.7304, "lr": 5e-06, "epoch": 2.4770446295109974, "percentage": 82.62, "elapsed_time": "23:41:51", "remaining_time": "4:59:04"}
148
+ {"current_steps": 1460, "total_steps": 1755, "loss": 0.7301, "lr": 5e-06, "epoch": 2.494127695921418, "percentage": 83.19, "elapsed_time": "23:51:32", "remaining_time": "4:49:14"}
149
+ {"current_steps": 1470, "total_steps": 1755, "loss": 0.7279, "lr": 5e-06, "epoch": 2.5112107623318387, "percentage": 83.76, "elapsed_time": "1 day, 0:01:10", "remaining_time": "4:39:24"}
150
+ {"current_steps": 1480, "total_steps": 1755, "loss": 0.728, "lr": 5e-06, "epoch": 2.5282938287422594, "percentage": 84.33, "elapsed_time": "1 day, 0:10:48", "remaining_time": "4:29:34"}
151
+ {"current_steps": 1490, "total_steps": 1755, "loss": 0.727, "lr": 5e-06, "epoch": 2.54537689515268, "percentage": 84.9, "elapsed_time": "1 day, 0:20:25", "remaining_time": "4:19:44"}
152
+ {"current_steps": 1500, "total_steps": 1755, "loss": 0.7326, "lr": 5e-06, "epoch": 2.5624599615631007, "percentage": 85.47, "elapsed_time": "1 day, 0:30:05", "remaining_time": "4:09:54"}
153
+ {"current_steps": 1510, "total_steps": 1755, "loss": 0.7316, "lr": 5e-06, "epoch": 2.5795430279735214, "percentage": 86.04, "elapsed_time": "1 day, 0:39:42", "remaining_time": "4:00:05"}
154
+ {"current_steps": 1520, "total_steps": 1755, "loss": 0.7312, "lr": 5e-06, "epoch": 2.596626094383942, "percentage": 86.61, "elapsed_time": "1 day, 0:49:19", "remaining_time": "3:50:15"}
155
+ {"current_steps": 1530, "total_steps": 1755, "loss": 0.729, "lr": 5e-06, "epoch": 2.6137091607943628, "percentage": 87.18, "elapsed_time": "1 day, 0:58:58", "remaining_time": "3:40:26"}
156
+ {"current_steps": 1540, "total_steps": 1755, "loss": 0.7282, "lr": 5e-06, "epoch": 2.6307922272047835, "percentage": 87.75, "elapsed_time": "1 day, 1:08:37", "remaining_time": "3:30:37"}
157
+ {"current_steps": 1550, "total_steps": 1755, "loss": 0.7316, "lr": 5e-06, "epoch": 2.647875293615204, "percentage": 88.32, "elapsed_time": "1 day, 1:18:15", "remaining_time": "3:20:48"}
158
+ {"current_steps": 1560, "total_steps": 1755, "loss": 0.7311, "lr": 5e-06, "epoch": 2.664958360025625, "percentage": 88.89, "elapsed_time": "1 day, 1:27:51", "remaining_time": "3:10:58"}
159
+ {"current_steps": 1570, "total_steps": 1755, "loss": 0.7317, "lr": 5e-06, "epoch": 2.6820414264360455, "percentage": 89.46, "elapsed_time": "1 day, 1:37:28", "remaining_time": "3:01:10"}
160
+ {"current_steps": 1580, "total_steps": 1755, "loss": 0.7308, "lr": 5e-06, "epoch": 2.699124492846466, "percentage": 90.03, "elapsed_time": "1 day, 1:47:06", "remaining_time": "2:51:21"}
161
+ {"current_steps": 1590, "total_steps": 1755, "loss": 0.7322, "lr": 5e-06, "epoch": 2.716207559256887, "percentage": 90.6, "elapsed_time": "1 day, 1:56:42", "remaining_time": "2:41:32"}
162
+ {"current_steps": 1600, "total_steps": 1755, "loss": 0.7299, "lr": 5e-06, "epoch": 2.7332906256673075, "percentage": 91.17, "elapsed_time": "1 day, 2:06:20", "remaining_time": "2:31:44"}
163
+ {"current_steps": 1610, "total_steps": 1755, "loss": 0.7311, "lr": 5e-06, "epoch": 2.750373692077728, "percentage": 91.74, "elapsed_time": "1 day, 2:15:58", "remaining_time": "2:21:56"}
164
+ {"current_steps": 1620, "total_steps": 1755, "loss": 0.7326, "lr": 5e-06, "epoch": 2.767456758488149, "percentage": 92.31, "elapsed_time": "1 day, 2:25:36", "remaining_time": "2:12:08"}
165
+ {"current_steps": 1630, "total_steps": 1755, "loss": 0.7283, "lr": 5e-06, "epoch": 2.7845398248985695, "percentage": 92.88, "elapsed_time": "1 day, 2:35:16", "remaining_time": "2:02:20"}
166
+ {"current_steps": 1640, "total_steps": 1755, "loss": 0.7322, "lr": 5e-06, "epoch": 2.8016228913089902, "percentage": 93.45, "elapsed_time": "1 day, 2:44:54", "remaining_time": "1:52:32"}
167
+ {"current_steps": 1650, "total_steps": 1755, "loss": 0.7305, "lr": 5e-06, "epoch": 2.818705957719411, "percentage": 94.02, "elapsed_time": "1 day, 2:54:34", "remaining_time": "1:42:44"}
168
+ {"current_steps": 1660, "total_steps": 1755, "loss": 0.7318, "lr": 5e-06, "epoch": 2.8357890241298316, "percentage": 94.59, "elapsed_time": "1 day, 3:04:13", "remaining_time": "1:32:57"}
169
+ {"current_steps": 1670, "total_steps": 1755, "loss": 0.7261, "lr": 5e-06, "epoch": 2.852872090540252, "percentage": 95.16, "elapsed_time": "1 day, 3:13:52", "remaining_time": "1:23:09"}
170
+ {"current_steps": 1680, "total_steps": 1755, "loss": 0.7326, "lr": 5e-06, "epoch": 2.8699551569506725, "percentage": 95.73, "elapsed_time": "1 day, 3:23:33", "remaining_time": "1:13:22"}
171
+ {"current_steps": 1690, "total_steps": 1755, "loss": 0.7267, "lr": 5e-06, "epoch": 2.887038223361093, "percentage": 96.3, "elapsed_time": "1 day, 3:33:12", "remaining_time": "1:03:35"}
172
+ {"current_steps": 1700, "total_steps": 1755, "loss": 0.7304, "lr": 5e-06, "epoch": 2.904121289771514, "percentage": 96.87, "elapsed_time": "1 day, 3:42:48", "remaining_time": "0:53:47"}
173
+ {"current_steps": 1710, "total_steps": 1755, "loss": 0.7337, "lr": 5e-06, "epoch": 2.9212043561819345, "percentage": 97.44, "elapsed_time": "1 day, 3:52:28", "remaining_time": "0:44:00"}
174
+ {"current_steps": 1720, "total_steps": 1755, "loss": 0.7305, "lr": 5e-06, "epoch": 2.938287422592355, "percentage": 98.01, "elapsed_time": "1 day, 4:02:06", "remaining_time": "0:34:13"}
175
+ {"current_steps": 1730, "total_steps": 1755, "loss": 0.7255, "lr": 5e-06, "epoch": 2.955370489002776, "percentage": 98.58, "elapsed_time": "1 day, 4:11:46", "remaining_time": "0:24:26"}
176
+ {"current_steps": 1740, "total_steps": 1755, "loss": 0.7299, "lr": 5e-06, "epoch": 2.9724535554131966, "percentage": 99.15, "elapsed_time": "1 day, 4:21:24", "remaining_time": "0:14:40"}
177
+ {"current_steps": 1750, "total_steps": 1755, "loss": 0.7294, "lr": 5e-06, "epoch": 2.9895366218236172, "percentage": 99.72, "elapsed_time": "1 day, 4:31:04", "remaining_time": "0:04:53"}