sedrickkeh commited on
Commit
0742e35
·
verified ·
1 Parent(s): 9a9e077

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:bae1cd407f4662f20e98cfecccb55e799a9c399a3e4bb5e947f701d59ce189fe
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:977e1a8fa02787ac872129767b928f1051e04ed291baa9e1751214c0df8875ff
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07ea8f471dc2f59b39255706b1fa010df36847d74de25644562279ac6c005bec
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b19bf76841caccbd02c425af4363741c2c978f5bc67b5a5867ceeaeb5e8568c0
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30d5ed5cc94a64db14f662ddc102f43b01400587611f2b3b13672aa80342dc83
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0772e740b7cef9b6ea6a89b72f6de09bfc6464f95425c27e43b8f22090676a77
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ff98ee15dc712acea84b0e223506a48f03c325aad48d4dd58283cd0f09e9403
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7767b14e06f158461a004d1275e5e59b6fc2ece7245017b607b69b8c1465d0f
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -108,3 +108,57 @@
108
  {"current_steps": 1070, "total_steps": 1629, "loss": 0.7731, "lr": 5e-06, "epoch": 1.9696272434422457, "percentage": 65.68, "elapsed_time": "17:18:07", "remaining_time": "9:02:20"}
109
  {"current_steps": 1080, "total_steps": 1629, "loss": 0.7689, "lr": 5e-06, "epoch": 1.9880349746893695, "percentage": 66.3, "elapsed_time": "17:27:44", "remaining_time": "8:52:36"}
110
  {"current_steps": 1086, "total_steps": 1629, "eval_loss": 0.8038221001625061, "epoch": 1.9990796134376438, "percentage": 66.67, "elapsed_time": "17:43:35", "remaining_time": "8:51:47"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
108
  {"current_steps": 1070, "total_steps": 1629, "loss": 0.7731, "lr": 5e-06, "epoch": 1.9696272434422457, "percentage": 65.68, "elapsed_time": "17:18:07", "remaining_time": "9:02:20"}
109
  {"current_steps": 1080, "total_steps": 1629, "loss": 0.7689, "lr": 5e-06, "epoch": 1.9880349746893695, "percentage": 66.3, "elapsed_time": "17:27:44", "remaining_time": "8:52:36"}
110
  {"current_steps": 1086, "total_steps": 1629, "eval_loss": 0.8038221001625061, "epoch": 1.9990796134376438, "percentage": 66.67, "elapsed_time": "17:43:35", "remaining_time": "8:51:47"}
111
+ {"current_steps": 1090, "total_steps": 1629, "loss": 0.8114, "lr": 5e-06, "epoch": 2.0064427059364935, "percentage": 66.91, "elapsed_time": "17:48:12", "remaining_time": "8:48:13"}
112
+ {"current_steps": 1100, "total_steps": 1629, "loss": 0.7261, "lr": 5e-06, "epoch": 2.024850437183617, "percentage": 67.53, "elapsed_time": "17:57:50", "remaining_time": "8:38:20"}
113
+ {"current_steps": 1110, "total_steps": 1629, "loss": 0.7268, "lr": 5e-06, "epoch": 2.0432581684307407, "percentage": 68.14, "elapsed_time": "18:07:28", "remaining_time": "8:28:27"}
114
+ {"current_steps": 1120, "total_steps": 1629, "loss": 0.7268, "lr": 5e-06, "epoch": 2.0616658996778647, "percentage": 68.75, "elapsed_time": "18:17:06", "remaining_time": "8:18:35"}
115
+ {"current_steps": 1130, "total_steps": 1629, "loss": 0.7284, "lr": 5e-06, "epoch": 2.0800736309249883, "percentage": 69.37, "elapsed_time": "18:26:44", "remaining_time": "8:08:43"}
116
+ {"current_steps": 1140, "total_steps": 1629, "loss": 0.725, "lr": 5e-06, "epoch": 2.0984813621721123, "percentage": 69.98, "elapsed_time": "18:36:21", "remaining_time": "7:58:51"}
117
+ {"current_steps": 1150, "total_steps": 1629, "loss": 0.7303, "lr": 5e-06, "epoch": 2.116889093419236, "percentage": 70.6, "elapsed_time": "18:45:58", "remaining_time": "7:48:59"}
118
+ {"current_steps": 1160, "total_steps": 1629, "loss": 0.7289, "lr": 5e-06, "epoch": 2.13529682466636, "percentage": 71.21, "elapsed_time": "18:55:35", "remaining_time": "7:39:07"}
119
+ {"current_steps": 1170, "total_steps": 1629, "loss": 0.7279, "lr": 5e-06, "epoch": 2.1537045559134835, "percentage": 71.82, "elapsed_time": "19:05:11", "remaining_time": "7:29:15"}
120
+ {"current_steps": 1180, "total_steps": 1629, "loss": 0.726, "lr": 5e-06, "epoch": 2.1721122871606076, "percentage": 72.44, "elapsed_time": "19:14:48", "remaining_time": "7:19:24"}
121
+ {"current_steps": 1190, "total_steps": 1629, "loss": 0.7298, "lr": 5e-06, "epoch": 2.190520018407731, "percentage": 73.05, "elapsed_time": "19:24:26", "remaining_time": "7:09:34"}
122
+ {"current_steps": 1200, "total_steps": 1629, "loss": 0.7287, "lr": 5e-06, "epoch": 2.208927749654855, "percentage": 73.66, "elapsed_time": "19:34:03", "remaining_time": "6:59:43"}
123
+ {"current_steps": 1210, "total_steps": 1629, "loss": 0.7344, "lr": 5e-06, "epoch": 2.2273354809019787, "percentage": 74.28, "elapsed_time": "19:43:40", "remaining_time": "6:49:53"}
124
+ {"current_steps": 1220, "total_steps": 1629, "loss": 0.7267, "lr": 5e-06, "epoch": 2.2457432121491028, "percentage": 74.89, "elapsed_time": "19:53:17", "remaining_time": "6:40:02"}
125
+ {"current_steps": 1230, "total_steps": 1629, "loss": 0.7263, "lr": 5e-06, "epoch": 2.2641509433962264, "percentage": 75.51, "elapsed_time": "20:02:54", "remaining_time": "6:30:12"}
126
+ {"current_steps": 1240, "total_steps": 1629, "loss": 0.7313, "lr": 5e-06, "epoch": 2.2825586746433504, "percentage": 76.12, "elapsed_time": "20:12:32", "remaining_time": "6:20:23"}
127
+ {"current_steps": 1250, "total_steps": 1629, "loss": 0.7304, "lr": 5e-06, "epoch": 2.300966405890474, "percentage": 76.73, "elapsed_time": "20:22:09", "remaining_time": "6:10:33"}
128
+ {"current_steps": 1260, "total_steps": 1629, "loss": 0.7272, "lr": 5e-06, "epoch": 2.319374137137598, "percentage": 77.35, "elapsed_time": "20:31:47", "remaining_time": "6:00:44"}
129
+ {"current_steps": 1270, "total_steps": 1629, "loss": 0.7282, "lr": 5e-06, "epoch": 2.3377818683847216, "percentage": 77.96, "elapsed_time": "20:41:25", "remaining_time": "5:50:55"}
130
+ {"current_steps": 1280, "total_steps": 1629, "loss": 0.7269, "lr": 5e-06, "epoch": 2.356189599631845, "percentage": 78.58, "elapsed_time": "20:51:01", "remaining_time": "5:41:06"}
131
+ {"current_steps": 1290, "total_steps": 1629, "loss": 0.7339, "lr": 5e-06, "epoch": 2.374597330878969, "percentage": 79.19, "elapsed_time": "21:00:39", "remaining_time": "5:31:17"}
132
+ {"current_steps": 1300, "total_steps": 1629, "loss": 0.7345, "lr": 5e-06, "epoch": 2.393005062126093, "percentage": 79.8, "elapsed_time": "21:10:16", "remaining_time": "5:21:28"}
133
+ {"current_steps": 1310, "total_steps": 1629, "loss": 0.7337, "lr": 5e-06, "epoch": 2.411412793373217, "percentage": 80.42, "elapsed_time": "21:19:54", "remaining_time": "5:11:40"}
134
+ {"current_steps": 1320, "total_steps": 1629, "loss": 0.7302, "lr": 5e-06, "epoch": 2.4298205246203404, "percentage": 81.03, "elapsed_time": "21:29:33", "remaining_time": "5:01:52"}
135
+ {"current_steps": 1330, "total_steps": 1629, "loss": 0.7326, "lr": 5e-06, "epoch": 2.4482282558674644, "percentage": 81.65, "elapsed_time": "21:39:11", "remaining_time": "4:52:04"}
136
+ {"current_steps": 1340, "total_steps": 1629, "loss": 0.7341, "lr": 5e-06, "epoch": 2.466635987114588, "percentage": 82.26, "elapsed_time": "21:48:49", "remaining_time": "4:42:16"}
137
+ {"current_steps": 1350, "total_steps": 1629, "loss": 0.7307, "lr": 5e-06, "epoch": 2.485043718361712, "percentage": 82.87, "elapsed_time": "21:58:26", "remaining_time": "4:32:28"}
138
+ {"current_steps": 1360, "total_steps": 1629, "loss": 0.7267, "lr": 5e-06, "epoch": 2.5034514496088356, "percentage": 83.49, "elapsed_time": "22:08:03", "remaining_time": "4:22:40"}
139
+ {"current_steps": 1370, "total_steps": 1629, "loss": 0.7313, "lr": 5e-06, "epoch": 2.5218591808559596, "percentage": 84.1, "elapsed_time": "22:17:41", "remaining_time": "4:12:53"}
140
+ {"current_steps": 1380, "total_steps": 1629, "loss": 0.7306, "lr": 5e-06, "epoch": 2.540266912103083, "percentage": 84.71, "elapsed_time": "22:27:19", "remaining_time": "4:03:06"}
141
+ {"current_steps": 1390, "total_steps": 1629, "loss": 0.7307, "lr": 5e-06, "epoch": 2.5586746433502072, "percentage": 85.33, "elapsed_time": "22:36:58", "remaining_time": "3:53:19"}
142
+ {"current_steps": 1400, "total_steps": 1629, "loss": 0.7301, "lr": 5e-06, "epoch": 2.577082374597331, "percentage": 85.94, "elapsed_time": "22:46:36", "remaining_time": "3:43:32"}
143
+ {"current_steps": 1410, "total_steps": 1629, "loss": 0.7303, "lr": 5e-06, "epoch": 2.595490105844455, "percentage": 86.56, "elapsed_time": "22:56:13", "remaining_time": "3:33:45"}
144
+ {"current_steps": 1420, "total_steps": 1629, "loss": 0.7334, "lr": 5e-06, "epoch": 2.6138978370915784, "percentage": 87.17, "elapsed_time": "23:05:50", "remaining_time": "3:23:58"}
145
+ {"current_steps": 1430, "total_steps": 1629, "loss": 0.7304, "lr": 5e-06, "epoch": 2.632305568338702, "percentage": 87.78, "elapsed_time": "23:15:28", "remaining_time": "3:14:11"}
146
+ {"current_steps": 1440, "total_steps": 1629, "loss": 0.7312, "lr": 5e-06, "epoch": 2.650713299585826, "percentage": 88.4, "elapsed_time": "23:25:05", "remaining_time": "3:04:25"}
147
+ {"current_steps": 1450, "total_steps": 1629, "loss": 0.7286, "lr": 5e-06, "epoch": 2.66912103083295, "percentage": 89.01, "elapsed_time": "23:34:41", "remaining_time": "2:54:38"}
148
+ {"current_steps": 1460, "total_steps": 1629, "loss": 0.7333, "lr": 5e-06, "epoch": 2.6875287620800736, "percentage": 89.63, "elapsed_time": "23:44:19", "remaining_time": "2:44:52"}
149
+ {"current_steps": 1470, "total_steps": 1629, "loss": 0.7346, "lr": 5e-06, "epoch": 2.705936493327197, "percentage": 90.24, "elapsed_time": "23:53:55", "remaining_time": "2:35:05"}
150
+ {"current_steps": 1480, "total_steps": 1629, "loss": 0.7323, "lr": 5e-06, "epoch": 2.7243442245743212, "percentage": 90.85, "elapsed_time": "1 day, 0:03:33", "remaining_time": "2:25:19"}
151
+ {"current_steps": 1490, "total_steps": 1629, "loss": 0.7379, "lr": 5e-06, "epoch": 2.7427519558214453, "percentage": 91.47, "elapsed_time": "1 day, 0:13:10", "remaining_time": "2:15:33"}
152
+ {"current_steps": 1500, "total_steps": 1629, "loss": 0.7304, "lr": 5e-06, "epoch": 2.761159687068569, "percentage": 92.08, "elapsed_time": "1 day, 0:22:47", "remaining_time": "2:05:48"}
153
+ {"current_steps": 1510, "total_steps": 1629, "loss": 0.7279, "lr": 5e-06, "epoch": 2.7795674183156924, "percentage": 92.69, "elapsed_time": "1 day, 0:32:24", "remaining_time": "1:56:02"}
154
+ {"current_steps": 1520, "total_steps": 1629, "loss": 0.7285, "lr": 5e-06, "epoch": 2.7979751495628165, "percentage": 93.31, "elapsed_time": "1 day, 0:41:59", "remaining_time": "1:46:16"}
155
+ {"current_steps": 1530, "total_steps": 1629, "loss": 0.7327, "lr": 5e-06, "epoch": 2.81638288080994, "percentage": 93.92, "elapsed_time": "1 day, 0:51:35", "remaining_time": "1:36:30"}
156
+ {"current_steps": 1540, "total_steps": 1629, "loss": 0.7359, "lr": 5e-06, "epoch": 2.834790612057064, "percentage": 94.54, "elapsed_time": "1 day, 1:01:11", "remaining_time": "1:26:45"}
157
+ {"current_steps": 1550, "total_steps": 1629, "loss": 0.7314, "lr": 5e-06, "epoch": 2.8531983433041876, "percentage": 95.15, "elapsed_time": "1 day, 1:10:49", "remaining_time": "1:17:00"}
158
+ {"current_steps": 1560, "total_steps": 1629, "loss": 0.7305, "lr": 5e-06, "epoch": 2.8716060745513117, "percentage": 95.76, "elapsed_time": "1 day, 1:20:26", "remaining_time": "1:07:15"}
159
+ {"current_steps": 1570, "total_steps": 1629, "loss": 0.7316, "lr": 5e-06, "epoch": 2.8900138057984353, "percentage": 96.38, "elapsed_time": "1 day, 1:30:04", "remaining_time": "0:57:29"}
160
+ {"current_steps": 1580, "total_steps": 1629, "loss": 0.7288, "lr": 5e-06, "epoch": 2.9084215370455593, "percentage": 96.99, "elapsed_time": "1 day, 1:39:42", "remaining_time": "0:47:45"}
161
+ {"current_steps": 1590, "total_steps": 1629, "loss": 0.7371, "lr": 5e-06, "epoch": 2.926829268292683, "percentage": 97.61, "elapsed_time": "1 day, 1:49:20", "remaining_time": "0:38:00"}
162
+ {"current_steps": 1600, "total_steps": 1629, "loss": 0.7342, "lr": 5e-06, "epoch": 2.945236999539807, "percentage": 98.22, "elapsed_time": "1 day, 1:58:57", "remaining_time": "0:28:15"}
163
+ {"current_steps": 1610, "total_steps": 1629, "loss": 0.7313, "lr": 5e-06, "epoch": 2.9636447307869305, "percentage": 98.83, "elapsed_time": "1 day, 2:08:34", "remaining_time": "0:18:30"}
164
+ {"current_steps": 1620, "total_steps": 1629, "loss": 0.7326, "lr": 5e-06, "epoch": 2.982052462034054, "percentage": 99.45, "elapsed_time": "1 day, 2:18:13", "remaining_time": "0:08:46"}