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:
|
3 |
size 4877660776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be7cc5508e95413cbd684a748df3664f87db5a1319f073eab123be863893b29f
|
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:
|
3 |
size 4932751008
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac5195ca241eec511897509d39000356dfc440d72c56d83e347e72a2363fc603
|
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:
|
3 |
size 4330865200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6673b65eec0e8bb6bad786d766cf5147dc24abd1b8fdf8315ab6bb6b524698e
|
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:
|
3 |
size 1089994880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:579c8ad24e39ea7f51085ee1894cd060b550a103f2c903114ec8eae0c3aa233b
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -113,3 +113,54 @@
|
|
113 |
{"current_steps": 113, "total_steps": 165, "loss": 0.4873, "lr": 2.748981275911633e-06, "epoch": 2.029940119760479, "percentage": 68.48, "elapsed_time": "1:10:30", "remaining_time": "0:32:26"}
|
114 |
{"current_steps": 114, "total_steps": 165, "loss": 0.5312, "lr": 2.6547249258818162e-06, "epoch": 2.0479041916167664, "percentage": 69.09, "elapsed_time": "1:11:06", "remaining_time": "0:31:48"}
|
115 |
{"current_steps": 115, "total_steps": 165, "loss": 0.4992, "lr": 2.5615252809318287e-06, "epoch": 2.065868263473054, "percentage": 69.7, "elapsed_time": "1:11:42", "remaining_time": "0:31:10"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
113 |
{"current_steps": 113, "total_steps": 165, "loss": 0.4873, "lr": 2.748981275911633e-06, "epoch": 2.029940119760479, "percentage": 68.48, "elapsed_time": "1:10:30", "remaining_time": "0:32:26"}
|
114 |
{"current_steps": 114, "total_steps": 165, "loss": 0.5312, "lr": 2.6547249258818162e-06, "epoch": 2.0479041916167664, "percentage": 69.09, "elapsed_time": "1:11:06", "remaining_time": "0:31:48"}
|
115 |
{"current_steps": 115, "total_steps": 165, "loss": 0.4992, "lr": 2.5615252809318287e-06, "epoch": 2.065868263473054, "percentage": 69.7, "elapsed_time": "1:11:42", "remaining_time": "0:31:10"}
|
116 |
+
{"current_steps": 116, "total_steps": 165, "loss": 0.4958, "lr": 2.469424333806718e-06, "epoch": 2.0838323353293413, "percentage": 70.3, "elapsed_time": "1:12:18", "remaining_time": "0:30:32"}
|
117 |
+
{"current_steps": 117, "total_steps": 165, "loss": 0.519, "lr": 2.3784635822138424e-06, "epoch": 2.1017964071856285, "percentage": 70.91, "elapsed_time": "1:12:54", "remaining_time": "0:29:54"}
|
118 |
+
{"current_steps": 118, "total_steps": 165, "loss": 0.5243, "lr": 2.288684010125325e-06, "epoch": 2.1197604790419162, "percentage": 71.52, "elapsed_time": "1:13:30", "remaining_time": "0:29:16"}
|
119 |
+
{"current_steps": 119, "total_steps": 165, "loss": 0.5216, "lr": 2.2001260693120236e-06, "epoch": 2.1377245508982035, "percentage": 72.12, "elapsed_time": "1:14:06", "remaining_time": "0:28:38"}
|
120 |
+
{"current_steps": 120, "total_steps": 165, "loss": 0.4988, "lr": 2.1128296611172593e-06, "epoch": 2.155688622754491, "percentage": 72.73, "elapsed_time": "1:14:42", "remaining_time": "0:28:00"}
|
121 |
+
{"current_steps": 121, "total_steps": 165, "loss": 0.5164, "lr": 2.0268341184785674e-06, "epoch": 2.1736526946107784, "percentage": 73.33, "elapsed_time": "1:15:18", "remaining_time": "0:27:23"}
|
122 |
+
{"current_steps": 122, "total_steps": 165, "loss": 0.5073, "lr": 1.9421781882055447e-06, "epoch": 2.191616766467066, "percentage": 73.94, "elapsed_time": "1:15:54", "remaining_time": "0:26:45"}
|
123 |
+
{"current_steps": 123, "total_steps": 165, "loss": 0.5105, "lr": 1.8589000135217882e-06, "epoch": 2.2095808383233533, "percentage": 74.55, "elapsed_time": "1:16:30", "remaining_time": "0:26:07"}
|
124 |
+
{"current_steps": 124, "total_steps": 165, "loss": 0.5354, "lr": 1.7770371168788042e-06, "epoch": 2.2275449101796405, "percentage": 75.15, "elapsed_time": "1:17:06", "remaining_time": "0:25:29"}
|
125 |
+
{"current_steps": 125, "total_steps": 165, "loss": 0.512, "lr": 1.6966263830495939e-06, "epoch": 2.245508982035928, "percentage": 75.76, "elapsed_time": "1:17:42", "remaining_time": "0:24:51"}
|
126 |
+
{"current_steps": 126, "total_steps": 165, "loss": 0.5068, "lr": 1.6177040425095664e-06, "epoch": 2.2634730538922154, "percentage": 76.36, "elapsed_time": "1:18:18", "remaining_time": "0:24:14"}
|
127 |
+
{"current_steps": 127, "total_steps": 165, "loss": 0.5145, "lr": 1.5403056551122697e-06, "epoch": 2.281437125748503, "percentage": 76.97, "elapsed_time": "1:18:54", "remaining_time": "0:23:36"}
|
128 |
+
{"current_steps": 128, "total_steps": 165, "loss": 0.52, "lr": 1.4644660940672628e-06, "epoch": 2.2994011976047903, "percentage": 77.58, "elapsed_time": "1:19:30", "remaining_time": "0:22:58"}
|
129 |
+
{"current_steps": 129, "total_steps": 165, "loss": 0.4946, "lr": 1.390219530227378e-06, "epoch": 2.317365269461078, "percentage": 78.18, "elapsed_time": "1:20:06", "remaining_time": "0:22:21"}
|
130 |
+
{"current_steps": 130, "total_steps": 165, "loss": 0.4993, "lr": 1.3175994166924394e-06, "epoch": 2.3353293413173652, "percentage": 78.79, "elapsed_time": "1:20:42", "remaining_time": "0:21:43"}
|
131 |
+
{"current_steps": 131, "total_steps": 165, "loss": 0.4848, "lr": 1.246638473736378e-06, "epoch": 2.3532934131736525, "percentage": 79.39, "elapsed_time": "1:21:18", "remaining_time": "0:21:06"}
|
132 |
+
{"current_steps": 132, "total_steps": 165, "loss": 0.4965, "lr": 1.1773686740645384e-06, "epoch": 2.37125748502994, "percentage": 80.0, "elapsed_time": "1:21:54", "remaining_time": "0:20:28"}
|
133 |
+
{"current_steps": 133, "total_steps": 165, "loss": 0.5105, "lr": 1.1098212284078037e-06, "epoch": 2.3892215568862274, "percentage": 80.61, "elapsed_time": "1:22:29", "remaining_time": "0:19:50"}
|
134 |
+
{"current_steps": 134, "total_steps": 165, "loss": 0.5367, "lr": 1.0440265714600573e-06, "epoch": 2.407185628742515, "percentage": 81.21, "elapsed_time": "1:23:05", "remaining_time": "0:19:13"}
|
135 |
+
{"current_steps": 135, "total_steps": 165, "loss": 0.537, "lr": 9.80014348165298e-07, "epoch": 2.4251497005988023, "percentage": 81.82, "elapsed_time": "1:23:41", "remaining_time": "0:18:35"}
|
136 |
+
{"current_steps": 136, "total_steps": 165, "loss": 0.5125, "lr": 9.178134003605721e-07, "epoch": 2.44311377245509, "percentage": 82.42, "elapsed_time": "1:24:17", "remaining_time": "0:17:58"}
|
137 |
+
{"current_steps": 137, "total_steps": 165, "loss": 0.5166, "lr": 8.574517537807897e-07, "epoch": 2.461077844311377, "percentage": 83.03, "elapsed_time": "1:24:53", "remaining_time": "0:17:21"}
|
138 |
+
{"current_steps": 138, "total_steps": 165, "loss": 0.4882, "lr": 7.989566054312286e-07, "epoch": 2.479041916167665, "percentage": 83.64, "elapsed_time": "1:25:29", "remaining_time": "0:16:43"}
|
139 |
+
{"current_steps": 139, "total_steps": 165, "loss": 0.4973, "lr": 7.423543113334436e-07, "epoch": 2.497005988023952, "percentage": 84.24, "elapsed_time": "1:26:05", "remaining_time": "0:16:06"}
|
140 |
+
{"current_steps": 140, "total_steps": 165, "loss": 0.4993, "lr": 6.876703746500984e-07, "epoch": 2.5149700598802394, "percentage": 84.85, "elapsed_time": "1:26:41", "remaining_time": "0:15:28"}
|
141 |
+
{"current_steps": 141, "total_steps": 165, "loss": 0.5045, "lr": 6.349294341940593e-07, "epoch": 2.532934131736527, "percentage": 85.45, "elapsed_time": "1:27:17", "remaining_time": "0:14:51"}
|
142 |
+
{"current_steps": 142, "total_steps": 165, "loss": 0.5181, "lr": 5.841552533269534e-07, "epoch": 2.5508982035928143, "percentage": 86.06, "elapsed_time": "1:27:53", "remaining_time": "0:14:14"}
|
143 |
+
{"current_steps": 143, "total_steps": 165, "loss": 0.513, "lr": 5.353707092521581e-07, "epoch": 2.568862275449102, "percentage": 86.67, "elapsed_time": "1:28:28", "remaining_time": "0:13:36"}
|
144 |
+
{"current_steps": 144, "total_steps": 165, "loss": 0.5237, "lr": 4.885977827070748e-07, "epoch": 2.586826347305389, "percentage": 87.27, "elapsed_time": "1:29:04", "remaining_time": "0:12:59"}
|
145 |
+
{"current_steps": 145, "total_steps": 165, "loss": 0.4919, "lr": 4.43857548059321e-07, "epoch": 2.6047904191616764, "percentage": 87.88, "elapsed_time": "1:29:40", "remaining_time": "0:12:22"}
|
146 |
+
{"current_steps": 146, "total_steps": 165, "loss": 0.5173, "lr": 4.0117016381130636e-07, "epoch": 2.622754491017964, "percentage": 88.48, "elapsed_time": "1:30:16", "remaining_time": "0:11:44"}
|
147 |
+
{"current_steps": 147, "total_steps": 165, "loss": 0.4952, "lr": 3.6055486351745327e-07, "epoch": 2.6407185628742518, "percentage": 89.09, "elapsed_time": "1:30:52", "remaining_time": "0:11:07"}
|
148 |
+
{"current_steps": 148, "total_steps": 165, "loss": 0.5057, "lr": 3.220299471181898e-07, "epoch": 2.658682634730539, "percentage": 89.7, "elapsed_time": "1:31:28", "remaining_time": "0:10:30"}
|
149 |
+
{"current_steps": 149, "total_steps": 165, "loss": 0.5042, "lr": 2.85612772694579e-07, "epoch": 2.6766467065868262, "percentage": 90.3, "elapsed_time": "1:32:04", "remaining_time": "0:09:53"}
|
150 |
+
{"current_steps": 150, "total_steps": 165, "loss": 0.5111, "lr": 2.5131974864734063e-07, "epoch": 2.694610778443114, "percentage": 90.91, "elapsed_time": "1:32:40", "remaining_time": "0:09:16"}
|
151 |
+
{"current_steps": 151, "total_steps": 165, "loss": 0.5156, "lr": 2.1916632630374579e-07, "epoch": 2.712574850299401, "percentage": 91.52, "elapsed_time": "1:33:16", "remaining_time": "0:08:38"}
|
152 |
+
{"current_steps": 152, "total_steps": 165, "loss": 0.5084, "lr": 1.8916699295575324e-07, "epoch": 2.730538922155689, "percentage": 92.12, "elapsed_time": "1:33:52", "remaining_time": "0:08:01"}
|
153 |
+
{"current_steps": 153, "total_steps": 165, "loss": 0.5165, "lr": 1.6133526533250566e-07, "epoch": 2.748502994011976, "percentage": 92.73, "elapsed_time": "1:34:28", "remaining_time": "0:07:24"}
|
154 |
+
{"current_steps": 154, "total_steps": 165, "loss": 0.5252, "lr": 1.3568368351012718e-07, "epoch": 2.7664670658682633, "percentage": 93.33, "elapsed_time": "1:35:04", "remaining_time": "0:06:47"}
|
155 |
+
{"current_steps": 155, "total_steps": 165, "loss": 0.4864, "lr": 1.1222380526156929e-07, "epoch": 2.784431137724551, "percentage": 93.94, "elapsed_time": "1:35:40", "remaining_time": "0:06:10"}
|
156 |
+
{"current_steps": 156, "total_steps": 165, "loss": 0.4982, "lr": 9.096620084905472e-08, "epoch": 2.802395209580838, "percentage": 94.55, "elapsed_time": "1:36:16", "remaining_time": "0:05:33"}
|
157 |
+
{"current_steps": 157, "total_steps": 165, "loss": 0.5048, "lr": 7.192044826145772e-08, "epoch": 2.820359281437126, "percentage": 95.15, "elapsed_time": "1:36:52", "remaining_time": "0:04:56"}
|
158 |
+
{"current_steps": 158, "total_steps": 165, "loss": 0.4932, "lr": 5.509512889877333e-08, "epoch": 2.838323353293413, "percentage": 95.76, "elapsed_time": "1:37:28", "remaining_time": "0:04:19"}
|
159 |
+
{"current_steps": 159, "total_steps": 165, "loss": 0.5108, "lr": 4.0497823705615836e-08, "epoch": 2.8562874251497004, "percentage": 96.36, "elapsed_time": "1:38:04", "remaining_time": "0:03:42"}
|
160 |
+
{"current_steps": 160, "total_steps": 165, "loss": 0.5127, "lr": 2.8135109755487723e-08, "epoch": 2.874251497005988, "percentage": 96.97, "elapsed_time": "1:38:40", "remaining_time": "0:03:05"}
|
161 |
+
{"current_steps": 161, "total_steps": 165, "loss": 0.5033, "lr": 1.8012557287367394e-08, "epoch": 2.8922155688622757, "percentage": 97.58, "elapsed_time": "1:39:16", "remaining_time": "0:02:27"}
|
162 |
+
{"current_steps": 162, "total_steps": 165, "loss": 0.5082, "lr": 1.0134727195937332e-08, "epoch": 2.910179640718563, "percentage": 98.18, "elapsed_time": "1:39:52", "remaining_time": "0:01:50"}
|
163 |
+
{"current_steps": 163, "total_steps": 165, "loss": 0.5003, "lr": 4.505168976592922e-09, "epoch": 2.92814371257485, "percentage": 98.79, "elapsed_time": "1:40:28", "remaining_time": "0:01:13"}
|
164 |
+
{"current_steps": 164, "total_steps": 165, "loss": 0.4874, "lr": 1.1264191261528557e-09, "epoch": 2.946107784431138, "percentage": 99.39, "elapsed_time": "1:41:04", "remaining_time": "0:00:36"}
|
165 |
+
{"current_steps": 165, "total_steps": 165, "loss": 0.5015, "lr": 0.0, "epoch": 2.964071856287425, "percentage": 100.0, "elapsed_time": "1:41:40", "remaining_time": "0:00:00"}
|
166 |
+
{"current_steps": 165, "total_steps": 165, "epoch": 2.964071856287425, "percentage": 100.0, "elapsed_time": "1:43:13", "remaining_time": "0:00:00"}
|