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 sha256:718651a184f0a981fc566e0c54c26dad6d1ef2af8f0d189db8f9a1c5a167a44f
|
| 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:f1a97133a8481a68a638b58ee5445f8cf694382c65f308a1dc379004f0c94251
|
| 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:d2752e4539a49e999b03c4eeedd1a1d517cf0f0bb229d7dbaaa51a5a3b3df34e
|
| 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 sha256:68d999b791d33cd8895afcee9fa89346349e88021772849f4327bf4a9d7270e5
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -126,3 +126,50 @@
|
|
| 126 |
{"current_steps": 126, "total_steps": 174, "loss": 0.7541, "lr": 2.159676266344222e-06, "epoch": 2.147727272727273, "percentage": 72.41, "elapsed_time": "0:31:33", "remaining_time": "0:12:01"}
|
| 127 |
{"current_steps": 127, "total_steps": 174, "loss": 0.5964, "lr": 2.077389851950557e-06, "epoch": 2.164772727272727, "percentage": 72.99, "elapsed_time": "0:31:46", "remaining_time": "0:11:45"}
|
| 128 |
{"current_steps": 128, "total_steps": 174, "loss": 0.6619, "lr": 1.996288678810105e-06, "epoch": 2.1818181818181817, "percentage": 73.56, "elapsed_time": "0:31:58", "remaining_time": "0:11:29"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 126 |
{"current_steps": 126, "total_steps": 174, "loss": 0.7541, "lr": 2.159676266344222e-06, "epoch": 2.147727272727273, "percentage": 72.41, "elapsed_time": "0:31:33", "remaining_time": "0:12:01"}
|
| 127 |
{"current_steps": 127, "total_steps": 174, "loss": 0.5964, "lr": 2.077389851950557e-06, "epoch": 2.164772727272727, "percentage": 72.99, "elapsed_time": "0:31:46", "remaining_time": "0:11:45"}
|
| 128 |
{"current_steps": 128, "total_steps": 174, "loss": 0.6619, "lr": 1.996288678810105e-06, "epoch": 2.1818181818181817, "percentage": 73.56, "elapsed_time": "0:31:58", "remaining_time": "0:11:29"}
|
| 129 |
+
{"current_steps": 129, "total_steps": 174, "loss": 0.6833, "lr": 1.9164056368572847e-06, "epoch": 2.1988636363636362, "percentage": 74.14, "elapsed_time": "0:32:11", "remaining_time": "0:11:13"}
|
| 130 |
+
{"current_steps": 130, "total_steps": 174, "loss": 0.6855, "lr": 1.8377731220231144e-06, "epoch": 2.215909090909091, "percentage": 74.71, "elapsed_time": "0:32:23", "remaining_time": "0:10:57"}
|
| 131 |
+
{"current_steps": 131, "total_steps": 174, "loss": 0.6424, "lr": 1.7604230230973068e-06, "epoch": 2.2329545454545454, "percentage": 75.29, "elapsed_time": "0:32:35", "remaining_time": "0:10:41"}
|
| 132 |
+
{"current_steps": 132, "total_steps": 174, "loss": 0.6231, "lr": 1.6843867087960252e-06, "epoch": 2.25, "percentage": 75.86, "elapsed_time": "0:32:47", "remaining_time": "0:10:26"}
|
| 133 |
+
{"current_steps": 133, "total_steps": 174, "loss": 0.5598, "lr": 1.6096950150405454e-06, "epoch": 2.2670454545454546, "percentage": 76.44, "elapsed_time": "0:32:57", "remaining_time": "0:10:09"}
|
| 134 |
+
{"current_steps": 134, "total_steps": 174, "loss": 0.7221, "lr": 1.5363782324520033e-06, "epoch": 2.284090909090909, "percentage": 77.01, "elapsed_time": "0:33:10", "remaining_time": "0:09:54"}
|
| 135 |
+
{"current_steps": 135, "total_steps": 174, "loss": 0.6413, "lr": 1.4644660940672628e-06, "epoch": 2.3011363636363638, "percentage": 77.59, "elapsed_time": "0:33:24", "remaining_time": "0:09:38"}
|
| 136 |
+
{"current_steps": 136, "total_steps": 174, "loss": 0.6992, "lr": 1.3939877632809279e-06, "epoch": 2.3181818181818183, "percentage": 78.16, "elapsed_time": "0:33:40", "remaining_time": "0:09:24"}
|
| 137 |
+
{"current_steps": 137, "total_steps": 174, "loss": 0.6878, "lr": 1.3249718220183583e-06, "epoch": 2.3352272727272725, "percentage": 78.74, "elapsed_time": "0:33:53", "remaining_time": "0:09:09"}
|
| 138 |
+
{"current_steps": 138, "total_steps": 174, "loss": 0.6385, "lr": 1.257446259144494e-06, "epoch": 2.3522727272727275, "percentage": 79.31, "elapsed_time": "0:34:07", "remaining_time": "0:08:54"}
|
| 139 |
+
{"current_steps": 139, "total_steps": 174, "loss": 0.7421, "lr": 1.1914384591132045e-06, "epoch": 2.3693181818181817, "percentage": 79.89, "elapsed_time": "0:34:25", "remaining_time": "0:08:39"}
|
| 140 |
+
{"current_steps": 140, "total_steps": 174, "loss": 0.647, "lr": 1.1269751908617277e-06, "epoch": 2.3863636363636362, "percentage": 80.46, "elapsed_time": "0:34:40", "remaining_time": "0:08:25"}
|
| 141 |
+
{"current_steps": 141, "total_steps": 174, "loss": 0.6702, "lr": 1.0640825969547498e-06, "epoch": 2.403409090909091, "percentage": 81.03, "elapsed_time": "0:34:56", "remaining_time": "0:08:10"}
|
| 142 |
+
{"current_steps": 142, "total_steps": 174, "loss": 0.5888, "lr": 1.0027861829824953e-06, "epoch": 2.4204545454545454, "percentage": 81.61, "elapsed_time": "0:35:12", "remaining_time": "0:07:56"}
|
| 143 |
+
{"current_steps": 143, "total_steps": 174, "loss": 0.7405, "lr": 9.431108072171346e-07, "epoch": 2.4375, "percentage": 82.18, "elapsed_time": "0:35:29", "remaining_time": "0:07:41"}
|
| 144 |
+
{"current_steps": 144, "total_steps": 174, "loss": 0.6819, "lr": 8.850806705317183e-07, "epoch": 2.4545454545454546, "percentage": 82.76, "elapsed_time": "0:35:43", "remaining_time": "0:07:26"}
|
| 145 |
+
{"current_steps": 145, "total_steps": 174, "loss": 0.6332, "lr": 8.287193065856936e-07, "epoch": 2.471590909090909, "percentage": 83.33, "elapsed_time": "0:35:55", "remaining_time": "0:07:11"}
|
| 146 |
+
{"current_steps": 146, "total_steps": 174, "loss": 0.676, "lr": 7.740495722810271e-07, "epoch": 2.4886363636363638, "percentage": 83.91, "elapsed_time": "0:36:07", "remaining_time": "0:06:55"}
|
| 147 |
+
{"current_steps": 147, "total_steps": 174, "loss": 0.7018, "lr": 7.210936384927631e-07, "epoch": 2.5056818181818183, "percentage": 84.48, "elapsed_time": "0:36:23", "remaining_time": "0:06:41"}
|
| 148 |
+
{"current_steps": 148, "total_steps": 174, "loss": 0.6894, "lr": 6.698729810778065e-07, "epoch": 2.5227272727272725, "percentage": 85.06, "elapsed_time": "0:36:39", "remaining_time": "0:06:26"}
|
| 149 |
+
{"current_steps": 149, "total_steps": 174, "loss": 0.645, "lr": 6.204083721655607e-07, "epoch": 2.5397727272727275, "percentage": 85.63, "elapsed_time": "0:36:53", "remaining_time": "0:06:11"}
|
| 150 |
+
{"current_steps": 150, "total_steps": 174, "loss": 0.7111, "lr": 5.727198717339511e-07, "epoch": 2.5568181818181817, "percentage": 86.21, "elapsed_time": "0:37:07", "remaining_time": "0:05:56"}
|
| 151 |
+
{"current_steps": 151, "total_steps": 174, "loss": 0.7216, "lr": 5.268268194742638e-07, "epoch": 2.5738636363636362, "percentage": 86.78, "elapsed_time": "0:37:23", "remaining_time": "0:05:41"}
|
| 152 |
+
{"current_steps": 152, "total_steps": 174, "loss": 0.621, "lr": 4.827478269480895e-07, "epoch": 2.590909090909091, "percentage": 87.36, "elapsed_time": "0:37:37", "remaining_time": "0:05:26"}
|
| 153 |
+
{"current_steps": 153, "total_steps": 174, "loss": 0.7521, "lr": 4.405007700395497e-07, "epoch": 2.6079545454545454, "percentage": 87.93, "elapsed_time": "0:37:52", "remaining_time": "0:05:11"}
|
| 154 |
+
{"current_steps": 154, "total_steps": 174, "loss": 0.6145, "lr": 4.001027817058789e-07, "epoch": 2.625, "percentage": 88.51, "elapsed_time": "0:38:09", "remaining_time": "0:04:57"}
|
| 155 |
+
{"current_steps": 155, "total_steps": 174, "loss": 0.6278, "lr": 3.615702450292857e-07, "epoch": 2.6420454545454546, "percentage": 89.08, "elapsed_time": "0:38:22", "remaining_time": "0:04:42"}
|
| 156 |
+
{"current_steps": 156, "total_steps": 174, "loss": 0.7472, "lr": 3.2491878657292643e-07, "epoch": 2.659090909090909, "percentage": 89.66, "elapsed_time": "0:38:34", "remaining_time": "0:04:27"}
|
| 157 |
+
{"current_steps": 157, "total_steps": 174, "loss": 0.6258, "lr": 2.901632700436757e-07, "epoch": 2.6761363636363638, "percentage": 90.23, "elapsed_time": "0:38:44", "remaining_time": "0:04:11"}
|
| 158 |
+
{"current_steps": 158, "total_steps": 174, "loss": 0.6839, "lr": 2.573177902642726e-07, "epoch": 2.6931818181818183, "percentage": 90.8, "elapsed_time": "0:38:58", "remaining_time": "0:03:56"}
|
| 159 |
+
{"current_steps": 159, "total_steps": 174, "loss": 0.6734, "lr": 2.2639566745727203e-07, "epoch": 2.7102272727272725, "percentage": 91.38, "elapsed_time": "0:39:12", "remaining_time": "0:03:41"}
|
| 160 |
+
{"current_steps": 160, "total_steps": 174, "loss": 0.6367, "lr": 1.9740944184313882e-07, "epoch": 2.7272727272727275, "percentage": 91.95, "elapsed_time": "0:39:25", "remaining_time": "0:03:27"}
|
| 161 |
+
{"current_steps": 161, "total_steps": 174, "loss": 0.632, "lr": 1.7037086855465902e-07, "epoch": 2.7443181818181817, "percentage": 92.53, "elapsed_time": "0:39:41", "remaining_time": "0:03:12"}
|
| 162 |
+
{"current_steps": 162, "total_steps": 174, "loss": 0.6924, "lr": 1.4529091286973994e-07, "epoch": 2.7613636363636362, "percentage": 93.1, "elapsed_time": "0:39:56", "remaining_time": "0:02:57"}
|
| 163 |
+
{"current_steps": 163, "total_steps": 174, "loss": 0.7466, "lr": 1.2217974576453072e-07, "epoch": 2.778409090909091, "percentage": 93.68, "elapsed_time": "0:40:11", "remaining_time": "0:02:42"}
|
| 164 |
+
{"current_steps": 164, "total_steps": 174, "loss": 0.6057, "lr": 1.0104673978866164e-07, "epoch": 2.7954545454545454, "percentage": 94.25, "elapsed_time": "0:40:23", "remaining_time": "0:02:27"}
|
| 165 |
+
{"current_steps": 165, "total_steps": 174, "loss": 0.663, "lr": 8.190046526428241e-08, "epoch": 2.8125, "percentage": 94.83, "elapsed_time": "0:40:40", "remaining_time": "0:02:13"}
|
| 166 |
+
{"current_steps": 166, "total_steps": 174, "loss": 0.6762, "lr": 6.474868681043578e-08, "epoch": 2.8295454545454546, "percentage": 95.4, "elapsed_time": "0:40:53", "remaining_time": "0:01:58"}
|
| 167 |
+
{"current_steps": 167, "total_steps": 174, "loss": 0.6105, "lr": 4.959836019417963e-08, "epoch": 2.846590909090909, "percentage": 95.98, "elapsed_time": "0:41:04", "remaining_time": "0:01:43"}
|
| 168 |
+
{"current_steps": 168, "total_steps": 174, "loss": 0.7567, "lr": 3.645562950973014e-08, "epoch": 2.8636363636363638, "percentage": 96.55, "elapsed_time": "0:41:17", "remaining_time": "0:01:28"}
|
| 169 |
+
{"current_steps": 169, "total_steps": 174, "loss": 0.6174, "lr": 2.5325824686772138e-08, "epoch": 2.8806818181818183, "percentage": 97.13, "elapsed_time": "0:41:31", "remaining_time": "0:01:13"}
|
| 170 |
+
{"current_steps": 170, "total_steps": 174, "loss": 0.5918, "lr": 1.6213459328950355e-08, "epoch": 2.8977272727272725, "percentage": 97.7, "elapsed_time": "0:41:43", "remaining_time": "0:00:58"}
|
| 171 |
+
{"current_steps": 171, "total_steps": 174, "loss": 0.693, "lr": 9.12222888341252e-09, "epoch": 2.9147727272727275, "percentage": 98.28, "elapsed_time": "0:42:01", "remaining_time": "0:00:44"}
|
| 172 |
+
{"current_steps": 172, "total_steps": 174, "loss": 0.6132, "lr": 4.055009142152066e-09, "epoch": 2.9318181818181817, "percentage": 98.85, "elapsed_time": "0:42:17", "remaining_time": "0:00:29"}
|
| 173 |
+
{"current_steps": 173, "total_steps": 174, "loss": 0.6515, "lr": 1.0138550757493592e-09, "epoch": 2.9488636363636362, "percentage": 99.43, "elapsed_time": "0:42:29", "remaining_time": "0:00:14"}
|
| 174 |
+
{"current_steps": 174, "total_steps": 174, "loss": 0.7362, "lr": 0.0, "epoch": 2.965909090909091, "percentage": 100.0, "elapsed_time": "0:42:41", "remaining_time": "0:00:00"}
|
| 175 |
+
{"current_steps": 174, "total_steps": 174, "epoch": 2.965909090909091, "percentage": 100.0, "elapsed_time": "0:44:56", "remaining_time": "0:00:00"}
|