gsmyrnis commited on
Commit
3d58e05
·
verified ·
1 Parent(s): b014198

Training in progress, epoch 1

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d46770e59a42e0601da5825e6e3731c7094974f48dbbbf89153dc0dc83a4692
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7af73746593b96d6afba9df3dd58e5fec81f644348e67e834d7eeb4efa0d4fdf
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3feb1c2604a01182063f0aa811c05faebedf7fd775749371facc120f3d882771
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b01c60f6a9f4c530e732e8413d15588820e10d0c913ec6561b709fafa2e6c22
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e824affc632dbd5dda678eb84f25115fa1190d134aff0eb1a0360aef77100488
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78c29daf3c03bdc8023e8f4ab09f1dd8f0cf9cb9f009c0a49bf59be9a876b33b
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71038d51d982f354158d4dbf87a91e07dcdd9b32fe711af29da71fac27c30d70
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecff724064526b09f8290dab5ecbe2dbfed508c2465d992a750de8dc06826127
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -86,3 +86,73 @@
86
  {"current_steps": 86, "total_steps": 216, "loss": 0.4211, "lr": 7.546600811643816e-06, "epoch": 1.1889400921658986, "percentage": 39.81, "elapsed_time": "0:16:28", "remaining_time": "0:24:54"}
87
  {"current_steps": 87, "total_steps": 216, "loss": 0.3704, "lr": 7.476589988449939e-06, "epoch": 1.2027649769585254, "percentage": 40.28, "elapsed_time": "0:16:38", "remaining_time": "0:24:40"}
88
  {"current_steps": 88, "total_steps": 216, "loss": 0.3912, "lr": 7.405929722454026e-06, "epoch": 1.2165898617511521, "percentage": 40.74, "elapsed_time": "0:16:46", "remaining_time": "0:24:23"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
86
  {"current_steps": 86, "total_steps": 216, "loss": 0.4211, "lr": 7.546600811643816e-06, "epoch": 1.1889400921658986, "percentage": 39.81, "elapsed_time": "0:16:28", "remaining_time": "0:24:54"}
87
  {"current_steps": 87, "total_steps": 216, "loss": 0.3704, "lr": 7.476589988449939e-06, "epoch": 1.2027649769585254, "percentage": 40.28, "elapsed_time": "0:16:38", "remaining_time": "0:24:40"}
88
  {"current_steps": 88, "total_steps": 216, "loss": 0.3912, "lr": 7.405929722454026e-06, "epoch": 1.2165898617511521, "percentage": 40.74, "elapsed_time": "0:16:46", "remaining_time": "0:24:23"}
89
+ {"current_steps": 89, "total_steps": 216, "loss": 0.3836, "lr": 7.334638543086203e-06, "epoch": 1.230414746543779, "percentage": 41.2, "elapsed_time": "0:17:00", "remaining_time": "0:24:15"}
90
+ {"current_steps": 90, "total_steps": 216, "loss": 0.3915, "lr": 7.262735145222696e-06, "epoch": 1.2442396313364055, "percentage": 41.67, "elapsed_time": "0:17:12", "remaining_time": "0:24:06"}
91
+ {"current_steps": 91, "total_steps": 216, "loss": 0.4005, "lr": 7.190238384283413e-06, "epoch": 1.2580645161290323, "percentage": 42.13, "elapsed_time": "0:17:20", "remaining_time": "0:23:49"}
92
+ {"current_steps": 92, "total_steps": 216, "loss": 0.3991, "lr": 7.117167271287453e-06, "epoch": 1.271889400921659, "percentage": 42.59, "elapsed_time": "0:17:30", "remaining_time": "0:23:35"}
93
+ {"current_steps": 93, "total_steps": 216, "loss": 0.3643, "lr": 7.043540967867782e-06, "epoch": 1.2857142857142856, "percentage": 43.06, "elapsed_time": "0:17:39", "remaining_time": "0:23:21"}
94
+ {"current_steps": 94, "total_steps": 216, "loss": 0.4334, "lr": 6.969378781246436e-06, "epoch": 1.2995391705069124, "percentage": 43.52, "elapsed_time": "0:17:50", "remaining_time": "0:23:09"}
95
+ {"current_steps": 95, "total_steps": 216, "loss": 0.415, "lr": 6.894700159171535e-06, "epoch": 1.3133640552995391, "percentage": 43.98, "elapsed_time": "0:18:03", "remaining_time": "0:22:59"}
96
+ {"current_steps": 96, "total_steps": 216, "loss": 0.407, "lr": 6.819524684817439e-06, "epoch": 1.327188940092166, "percentage": 44.44, "elapsed_time": "0:18:14", "remaining_time": "0:22:47"}
97
+ {"current_steps": 97, "total_steps": 216, "loss": 0.401, "lr": 6.743872071649411e-06, "epoch": 1.3410138248847927, "percentage": 44.91, "elapsed_time": "0:18:26", "remaining_time": "0:22:37"}
98
+ {"current_steps": 98, "total_steps": 216, "loss": 0.3713, "lr": 6.667762158254104e-06, "epoch": 1.3548387096774195, "percentage": 45.37, "elapsed_time": "0:18:37", "remaining_time": "0:22:25"}
99
+ {"current_steps": 99, "total_steps": 216, "loss": 0.389, "lr": 6.591214903137221e-06, "epoch": 1.368663594470046, "percentage": 45.83, "elapsed_time": "0:18:49", "remaining_time": "0:22:15"}
100
+ {"current_steps": 100, "total_steps": 216, "loss": 0.3954, "lr": 6.514250379489754e-06, "epoch": 1.3824884792626728, "percentage": 46.3, "elapsed_time": "0:18:58", "remaining_time": "0:22:01"}
101
+ {"current_steps": 101, "total_steps": 216, "loss": 0.3939, "lr": 6.436888769924142e-06, "epoch": 1.3963133640552996, "percentage": 46.76, "elapsed_time": "0:19:09", "remaining_time": "0:21:48"}
102
+ {"current_steps": 102, "total_steps": 216, "loss": 0.4076, "lr": 6.3591503611817155e-06, "epoch": 1.4101382488479262, "percentage": 47.22, "elapsed_time": "0:19:19", "remaining_time": "0:21:35"}
103
+ {"current_steps": 103, "total_steps": 216, "loss": 0.3604, "lr": 6.281055538812861e-06, "epoch": 1.423963133640553, "percentage": 47.69, "elapsed_time": "0:19:28", "remaining_time": "0:21:21"}
104
+ {"current_steps": 104, "total_steps": 216, "loss": 0.4067, "lr": 6.202624781831269e-06, "epoch": 1.4377880184331797, "percentage": 48.15, "elapsed_time": "0:19:39", "remaining_time": "0:21:10"}
105
+ {"current_steps": 105, "total_steps": 216, "loss": 0.4255, "lr": 6.123878657343648e-06, "epoch": 1.4516129032258065, "percentage": 48.61, "elapsed_time": "0:19:52", "remaining_time": "0:21:00"}
106
+ {"current_steps": 106, "total_steps": 216, "loss": 0.4074, "lr": 6.044837815156377e-06, "epoch": 1.4654377880184333, "percentage": 49.07, "elapsed_time": "0:20:01", "remaining_time": "0:20:46"}
107
+ {"current_steps": 107, "total_steps": 216, "loss": 0.3895, "lr": 5.965522982360441e-06, "epoch": 1.4792626728110598, "percentage": 49.54, "elapsed_time": "0:20:12", "remaining_time": "0:20:34"}
108
+ {"current_steps": 108, "total_steps": 216, "loss": 0.4086, "lr": 5.885954957896115e-06, "epoch": 1.4930875576036866, "percentage": 50.0, "elapsed_time": "0:20:21", "remaining_time": "0:20:21"}
109
+ {"current_steps": 109, "total_steps": 216, "loss": 0.3693, "lr": 5.806154607098799e-06, "epoch": 1.5069124423963134, "percentage": 50.46, "elapsed_time": "0:20:35", "remaining_time": "0:20:12"}
110
+ {"current_steps": 110, "total_steps": 216, "loss": 0.4299, "lr": 5.726142856227453e-06, "epoch": 1.52073732718894, "percentage": 50.93, "elapsed_time": "0:20:48", "remaining_time": "0:20:02"}
111
+ {"current_steps": 111, "total_steps": 216, "loss": 0.4148, "lr": 5.645940686977033e-06, "epoch": 1.5345622119815667, "percentage": 51.39, "elapsed_time": "0:20:57", "remaining_time": "0:19:49"}
112
+ {"current_steps": 112, "total_steps": 216, "loss": 0.3924, "lr": 5.5655691309764225e-06, "epoch": 1.5483870967741935, "percentage": 51.85, "elapsed_time": "0:21:11", "remaining_time": "0:19:41"}
113
+ {"current_steps": 113, "total_steps": 216, "loss": 0.3789, "lr": 5.485049264273241e-06, "epoch": 1.5622119815668203, "percentage": 52.31, "elapsed_time": "0:21:24", "remaining_time": "0:19:30"}
114
+ {"current_steps": 114, "total_steps": 216, "loss": 0.3609, "lr": 5.404402201807022e-06, "epoch": 1.576036866359447, "percentage": 52.78, "elapsed_time": "0:21:34", "remaining_time": "0:19:17"}
115
+ {"current_steps": 115, "total_steps": 216, "loss": 0.4271, "lr": 5.323649091872179e-06, "epoch": 1.5898617511520738, "percentage": 53.24, "elapsed_time": "0:21:48", "remaining_time": "0:19:09"}
116
+ {"current_steps": 116, "total_steps": 216, "loss": 0.3989, "lr": 5.242811110572243e-06, "epoch": 1.6036866359447006, "percentage": 53.7, "elapsed_time": "0:21:59", "remaining_time": "0:18:57"}
117
+ {"current_steps": 117, "total_steps": 216, "loss": 0.3814, "lr": 5.161909456266781e-06, "epoch": 1.6175115207373272, "percentage": 54.17, "elapsed_time": "0:22:12", "remaining_time": "0:18:47"}
118
+ {"current_steps": 118, "total_steps": 216, "loss": 0.3985, "lr": 5.080965344012509e-06, "epoch": 1.631336405529954, "percentage": 54.63, "elapsed_time": "0:22:26", "remaining_time": "0:18:38"}
119
+ {"current_steps": 119, "total_steps": 216, "loss": 0.3523, "lr": 5e-06, "epoch": 1.6451612903225805, "percentage": 55.09, "elapsed_time": "0:22:33", "remaining_time": "0:18:22"}
120
+ {"current_steps": 120, "total_steps": 216, "loss": 0.3977, "lr": 4.919034655987493e-06, "epoch": 1.6589861751152073, "percentage": 55.56, "elapsed_time": "0:22:39", "remaining_time": "0:18:07"}
121
+ {"current_steps": 121, "total_steps": 216, "loss": 0.4122, "lr": 4.838090543733222e-06, "epoch": 1.672811059907834, "percentage": 56.02, "elapsed_time": "0:22:50", "remaining_time": "0:17:55"}
122
+ {"current_steps": 122, "total_steps": 216, "loss": 0.3936, "lr": 4.757188889427761e-06, "epoch": 1.6866359447004609, "percentage": 56.48, "elapsed_time": "0:22:56", "remaining_time": "0:17:40"}
123
+ {"current_steps": 123, "total_steps": 216, "loss": 0.3812, "lr": 4.6763509081278215e-06, "epoch": 1.7004608294930876, "percentage": 56.94, "elapsed_time": "0:23:11", "remaining_time": "0:17:32"}
124
+ {"current_steps": 124, "total_steps": 216, "loss": 0.3744, "lr": 4.59559779819298e-06, "epoch": 1.7142857142857144, "percentage": 57.41, "elapsed_time": "0:23:21", "remaining_time": "0:17:19"}
125
+ {"current_steps": 125, "total_steps": 216, "loss": 0.4133, "lr": 4.51495073572676e-06, "epoch": 1.728110599078341, "percentage": 57.87, "elapsed_time": "0:23:31", "remaining_time": "0:17:07"}
126
+ {"current_steps": 126, "total_steps": 216, "loss": 0.4059, "lr": 4.434430869023579e-06, "epoch": 1.7419354838709677, "percentage": 58.33, "elapsed_time": "0:23:42", "remaining_time": "0:16:55"}
127
+ {"current_steps": 127, "total_steps": 216, "loss": 0.4058, "lr": 4.3540593130229695e-06, "epoch": 1.7557603686635943, "percentage": 58.8, "elapsed_time": "0:23:52", "remaining_time": "0:16:44"}
128
+ {"current_steps": 128, "total_steps": 216, "loss": 0.4261, "lr": 4.27385714377255e-06, "epoch": 1.769585253456221, "percentage": 59.26, "elapsed_time": "0:24:03", "remaining_time": "0:16:32"}
129
+ {"current_steps": 129, "total_steps": 216, "loss": 0.3799, "lr": 4.1938453929012014e-06, "epoch": 1.7834101382488479, "percentage": 59.72, "elapsed_time": "0:24:13", "remaining_time": "0:16:20"}
130
+ {"current_steps": 130, "total_steps": 216, "loss": 0.4027, "lr": 4.1140450421038865e-06, "epoch": 1.7972350230414746, "percentage": 60.19, "elapsed_time": "0:24:25", "remaining_time": "0:16:09"}
131
+ {"current_steps": 131, "total_steps": 216, "loss": 0.3414, "lr": 4.034477017639561e-06, "epoch": 1.8110599078341014, "percentage": 60.65, "elapsed_time": "0:24:33", "remaining_time": "0:15:56"}
132
+ {"current_steps": 132, "total_steps": 216, "loss": 0.4054, "lr": 3.955162184843625e-06, "epoch": 1.8248847926267282, "percentage": 61.11, "elapsed_time": "0:24:42", "remaining_time": "0:15:43"}
133
+ {"current_steps": 133, "total_steps": 216, "loss": 0.4111, "lr": 3.8761213426563546e-06, "epoch": 1.838709677419355, "percentage": 61.57, "elapsed_time": "0:24:54", "remaining_time": "0:15:32"}
134
+ {"current_steps": 134, "total_steps": 216, "loss": 0.3725, "lr": 3.7973752181687336e-06, "epoch": 1.8525345622119815, "percentage": 62.04, "elapsed_time": "0:25:04", "remaining_time": "0:15:20"}
135
+ {"current_steps": 135, "total_steps": 216, "loss": 0.3989, "lr": 3.7189444611871383e-06, "epoch": 1.8663594470046083, "percentage": 62.5, "elapsed_time": "0:25:18", "remaining_time": "0:15:11"}
136
+ {"current_steps": 136, "total_steps": 216, "loss": 0.456, "lr": 3.6408496388182857e-06, "epoch": 1.8801843317972349, "percentage": 62.96, "elapsed_time": "0:25:33", "remaining_time": "0:15:01"}
137
+ {"current_steps": 137, "total_steps": 216, "loss": 0.3442, "lr": 3.5631112300758595e-06, "epoch": 1.8940092165898617, "percentage": 63.43, "elapsed_time": "0:25:43", "remaining_time": "0:14:49"}
138
+ {"current_steps": 138, "total_steps": 216, "loss": 0.4418, "lr": 3.4857496205102475e-06, "epoch": 1.9078341013824884, "percentage": 63.89, "elapsed_time": "0:25:58", "remaining_time": "0:14:40"}
139
+ {"current_steps": 139, "total_steps": 216, "loss": 0.3882, "lr": 3.4087850968627823e-06, "epoch": 1.9216589861751152, "percentage": 64.35, "elapsed_time": "0:26:07", "remaining_time": "0:14:28"}
140
+ {"current_steps": 140, "total_steps": 216, "loss": 0.3947, "lr": 3.3322378417458985e-06, "epoch": 1.935483870967742, "percentage": 64.81, "elapsed_time": "0:26:19", "remaining_time": "0:14:17"}
141
+ {"current_steps": 141, "total_steps": 216, "loss": 0.3399, "lr": 3.2561279283505888e-06, "epoch": 1.9493087557603688, "percentage": 65.28, "elapsed_time": "0:26:27", "remaining_time": "0:14:04"}
142
+ {"current_steps": 142, "total_steps": 216, "loss": 0.405, "lr": 3.180475315182563e-06, "epoch": 1.9631336405529956, "percentage": 65.74, "elapsed_time": "0:26:41", "remaining_time": "0:13:54"}
143
+ {"current_steps": 143, "total_steps": 216, "loss": 0.4145, "lr": 3.1052998408284664e-06, "epoch": 1.976958525345622, "percentage": 66.2, "elapsed_time": "0:26:55", "remaining_time": "0:13:44"}
144
+ {"current_steps": 144, "total_steps": 216, "loss": 0.3988, "lr": 3.0306212187535653e-06, "epoch": 1.9907834101382489, "percentage": 66.67, "elapsed_time": "0:27:05", "remaining_time": "0:13:32"}
145
+ {"current_steps": 145, "total_steps": 216, "loss": 0.6161, "lr": 2.9564590321322206e-06, "epoch": 2.0046082949308754, "percentage": 67.13, "elapsed_time": "0:28:29", "remaining_time": "0:13:57"}
146
+ {"current_steps": 146, "total_steps": 216, "loss": 0.3328, "lr": 2.882832728712551e-06, "epoch": 2.0184331797235022, "percentage": 67.59, "elapsed_time": "0:28:39", "remaining_time": "0:13:44"}
147
+ {"current_steps": 147, "total_steps": 216, "loss": 0.3514, "lr": 2.8097616157165886e-06, "epoch": 2.032258064516129, "percentage": 68.06, "elapsed_time": "0:28:49", "remaining_time": "0:13:31"}
148
+ {"current_steps": 148, "total_steps": 216, "loss": 0.3663, "lr": 2.7372648547773063e-06, "epoch": 2.046082949308756, "percentage": 68.52, "elapsed_time": "0:29:02", "remaining_time": "0:13:20"}
149
+ {"current_steps": 149, "total_steps": 216, "loss": 0.3557, "lr": 2.665361456913797e-06, "epoch": 2.0599078341013826, "percentage": 68.98, "elapsed_time": "0:29:15", "remaining_time": "0:13:09"}
150
+ {"current_steps": 150, "total_steps": 216, "loss": 0.3325, "lr": 2.594070277545975e-06, "epoch": 2.0737327188940093, "percentage": 69.44, "elapsed_time": "0:29:26", "remaining_time": "0:12:57"}
151
+ {"current_steps": 151, "total_steps": 216, "loss": 0.3723, "lr": 2.5234100115500643e-06, "epoch": 2.087557603686636, "percentage": 69.91, "elapsed_time": "0:29:39", "remaining_time": "0:12:46"}
152
+ {"current_steps": 152, "total_steps": 216, "loss": 0.3454, "lr": 2.4533991883561868e-06, "epoch": 2.1013824884792625, "percentage": 70.37, "elapsed_time": "0:29:47", "remaining_time": "0:12:32"}
153
+ {"current_steps": 153, "total_steps": 216, "loss": 0.3491, "lr": 2.38405616708935e-06, "epoch": 2.1152073732718892, "percentage": 70.83, "elapsed_time": "0:30:01", "remaining_time": "0:12:21"}
154
+ {"current_steps": 154, "total_steps": 216, "loss": 0.3714, "lr": 2.315399131755081e-06, "epoch": 2.129032258064516, "percentage": 71.3, "elapsed_time": "0:30:14", "remaining_time": "0:12:10"}
155
+ {"current_steps": 155, "total_steps": 216, "loss": 0.341, "lr": 2.2474460864709825e-06, "epoch": 2.142857142857143, "percentage": 71.76, "elapsed_time": "0:30:27", "remaining_time": "0:11:59"}
156
+ {"current_steps": 156, "total_steps": 216, "loss": 0.3362, "lr": 2.1802148507454675e-06, "epoch": 2.1566820276497696, "percentage": 72.22, "elapsed_time": "0:30:38", "remaining_time": "0:11:47"}
157
+ {"current_steps": 157, "total_steps": 216, "loss": 0.3712, "lr": 2.1137230548049042e-06, "epoch": 2.1705069124423964, "percentage": 72.69, "elapsed_time": "0:30:51", "remaining_time": "0:11:35"}
158
+ {"current_steps": 158, "total_steps": 216, "loss": 0.3289, "lr": 2.0479881349703885e-06, "epoch": 2.184331797235023, "percentage": 73.15, "elapsed_time": "0:31:01", "remaining_time": "0:11:23"}