Training in progress, step 800
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 4902257696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1051fba19e3553e454fac7fc848ce95c5ec024cb1d29b81cbf79e9186e53e4d
|
| 3 |
size 4902257696
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915960368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9c250bb76077bee01b32b4cda827fcf80b0a750c2875c35ba98f95bd5d6df37
|
| 3 |
size 4915960368
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4983068496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:353b116d05b1683790d5a27e30921eec7b255a729613b5edffa85ccea9fb53c4
|
| 3 |
size 4983068496
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1580230264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71cfb5d41cabe6d02f3c323debe2c607c4c546f937317b03268ba69374d0f833
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -123,3 +123,43 @@
|
|
| 123 |
{"current_steps": 615, "total_steps": 3850, "loss": 0.3032, "lr": 3.9570460093825664e-05, "epoch": 1.1182893539581438, "percentage": 15.97, "elapsed_time": "4:08:09", "remaining_time": "21:45:22"}
|
| 124 |
{"current_steps": 620, "total_steps": 3850, "loss": 0.3105, "lr": 3.9551569292201536e-05, "epoch": 1.127388535031847, "percentage": 16.1, "elapsed_time": "4:09:57", "remaining_time": "21:42:13"}
|
| 125 |
{"current_steps": 625, "total_steps": 3850, "loss": 0.2998, "lr": 3.9532276686671804e-05, "epoch": 1.1364877161055504, "percentage": 16.23, "elapsed_time": "4:12:09", "remaining_time": "21:41:10"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 123 |
{"current_steps": 615, "total_steps": 3850, "loss": 0.3032, "lr": 3.9570460093825664e-05, "epoch": 1.1182893539581438, "percentage": 15.97, "elapsed_time": "4:08:09", "remaining_time": "21:45:22"}
|
| 124 |
{"current_steps": 620, "total_steps": 3850, "loss": 0.3105, "lr": 3.9551569292201536e-05, "epoch": 1.127388535031847, "percentage": 16.1, "elapsed_time": "4:09:57", "remaining_time": "21:42:13"}
|
| 125 |
{"current_steps": 625, "total_steps": 3850, "loss": 0.2998, "lr": 3.9532276686671804e-05, "epoch": 1.1364877161055504, "percentage": 16.23, "elapsed_time": "4:12:09", "remaining_time": "21:41:10"}
|
| 126 |
+
{"current_steps": 630, "total_steps": 3850, "loss": 0.3012, "lr": 3.951258267371841e-05, "epoch": 1.1455868971792538, "percentage": 16.36, "elapsed_time": "4:14:04", "remaining_time": "21:38:34"}
|
| 127 |
+
{"current_steps": 635, "total_steps": 3850, "loss": 0.3091, "lr": 3.9492487658072615e-05, "epoch": 1.1546860782529573, "percentage": 16.49, "elapsed_time": "4:15:56", "remaining_time": "21:35:47"}
|
| 128 |
+
{"current_steps": 640, "total_steps": 3850, "loss": 0.2936, "lr": 3.947199205270668e-05, "epoch": 1.1637852593266607, "percentage": 16.62, "elapsed_time": "4:17:50", "remaining_time": "21:33:13"}
|
| 129 |
+
{"current_steps": 645, "total_steps": 3850, "loss": 0.2938, "lr": 3.9451096278825386e-05, "epoch": 1.172884440400364, "percentage": 16.75, "elapsed_time": "4:20:12", "remaining_time": "21:33:00"}
|
| 130 |
+
{"current_steps": 650, "total_steps": 3850, "loss": 0.2944, "lr": 3.942980076585735e-05, "epoch": 1.1819836214740673, "percentage": 16.88, "elapsed_time": "4:22:10", "remaining_time": "21:30:42"}
|
| 131 |
+
{"current_steps": 655, "total_steps": 3850, "loss": 0.3258, "lr": 3.940810595144624e-05, "epoch": 1.1910828025477707, "percentage": 17.01, "elapsed_time": "4:24:06", "remaining_time": "21:28:18"}
|
| 132 |
+
{"current_steps": 660, "total_steps": 3850, "loss": 0.3017, "lr": 3.938601228144173e-05, "epoch": 1.200181983621474, "percentage": 17.14, "elapsed_time": "4:26:04", "remaining_time": "21:26:03"}
|
| 133 |
+
{"current_steps": 665, "total_steps": 3850, "loss": 0.3122, "lr": 3.9363520209890405e-05, "epoch": 1.2092811646951773, "percentage": 17.27, "elapsed_time": "4:28:07", "remaining_time": "21:24:09"}
|
| 134 |
+
{"current_steps": 670, "total_steps": 3850, "loss": 0.3121, "lr": 3.9340630199026365e-05, "epoch": 1.2183803457688809, "percentage": 17.4, "elapsed_time": "4:30:14", "remaining_time": "21:22:39"}
|
| 135 |
+
{"current_steps": 675, "total_steps": 3850, "loss": 0.2952, "lr": 3.931734271926176e-05, "epoch": 1.2274795268425842, "percentage": 17.53, "elapsed_time": "4:32:11", "remaining_time": "21:20:20"}
|
| 136 |
+
{"current_steps": 680, "total_steps": 3850, "loss": 0.3211, "lr": 3.929365824917712e-05, "epoch": 1.2365787079162875, "percentage": 17.66, "elapsed_time": "4:34:06", "remaining_time": "21:17:49"}
|
| 137 |
+
{"current_steps": 685, "total_steps": 3850, "loss": 0.2986, "lr": 3.9269577275511504e-05, "epoch": 1.2456778889899909, "percentage": 17.79, "elapsed_time": "4:35:50", "remaining_time": "21:14:31"}
|
| 138 |
+
{"current_steps": 690, "total_steps": 3850, "loss": 0.2955, "lr": 3.924510029315253e-05, "epoch": 1.2547770700636942, "percentage": 17.92, "elapsed_time": "4:37:44", "remaining_time": "21:11:58"}
|
| 139 |
+
{"current_steps": 695, "total_steps": 3850, "loss": 0.3092, "lr": 3.922022780512614e-05, "epoch": 1.2638762511373978, "percentage": 18.05, "elapsed_time": "4:39:22", "remaining_time": "21:08:12"}
|
| 140 |
+
{"current_steps": 700, "total_steps": 3850, "loss": 0.2925, "lr": 3.919496032258637e-05, "epoch": 1.2729754322111009, "percentage": 18.18, "elapsed_time": "4:41:10", "remaining_time": "21:05:18"}
|
| 141 |
+
{"current_steps": 705, "total_steps": 3850, "loss": 0.2998, "lr": 3.9169298364804716e-05, "epoch": 1.2820746132848044, "percentage": 18.31, "elapsed_time": "4:43:01", "remaining_time": "21:02:35"}
|
| 142 |
+
{"current_steps": 710, "total_steps": 3850, "loss": 0.3088, "lr": 3.914324245915956e-05, "epoch": 1.2911737943585078, "percentage": 18.44, "elapsed_time": "4:44:52", "remaining_time": "20:59:50"}
|
| 143 |
+
{"current_steps": 715, "total_steps": 3850, "loss": 0.3107, "lr": 3.91167931411253e-05, "epoch": 1.300272975432211, "percentage": 18.57, "elapsed_time": "4:46:37", "remaining_time": "20:56:44"}
|
| 144 |
+
{"current_steps": 720, "total_steps": 3850, "loss": 0.3044, "lr": 3.908995095426134e-05, "epoch": 1.3093721565059144, "percentage": 18.7, "elapsed_time": "4:48:40", "remaining_time": "20:54:58"}
|
| 145 |
+
{"current_steps": 725, "total_steps": 3850, "loss": 0.2943, "lr": 3.90627164502009e-05, "epoch": 1.3184713375796178, "percentage": 18.83, "elapsed_time": "4:50:46", "remaining_time": "20:53:18"}
|
| 146 |
+
{"current_steps": 730, "total_steps": 3850, "loss": 0.3189, "lr": 3.903509018863974e-05, "epoch": 1.3275705186533213, "percentage": 18.96, "elapsed_time": "4:52:55", "remaining_time": "20:51:59"}
|
| 147 |
+
{"current_steps": 735, "total_steps": 3850, "loss": 0.3137, "lr": 3.90070727373246e-05, "epoch": 1.3366696997270244, "percentage": 19.09, "elapsed_time": "4:54:51", "remaining_time": "20:49:37"}
|
| 148 |
+
{"current_steps": 740, "total_steps": 3850, "loss": 0.3039, "lr": 3.897866467204155e-05, "epoch": 1.345768880800728, "percentage": 19.22, "elapsed_time": "4:56:42", "remaining_time": "20:46:57"}
|
| 149 |
+
{"current_steps": 745, "total_steps": 3850, "loss": 0.3086, "lr": 3.894986657660418e-05, "epoch": 1.3548680618744313, "percentage": 19.35, "elapsed_time": "4:58:41", "remaining_time": "20:44:54"}
|
| 150 |
+
{"current_steps": 750, "total_steps": 3850, "loss": 0.2966, "lr": 3.892067904284154e-05, "epoch": 1.3639672429481347, "percentage": 19.48, "elapsed_time": "5:00:53", "remaining_time": "20:43:41"}
|
| 151 |
+
{"current_steps": 755, "total_steps": 3850, "loss": 0.3042, "lr": 3.889110267058608e-05, "epoch": 1.373066424021838, "percentage": 19.61, "elapsed_time": "5:02:46", "remaining_time": "20:41:11"}
|
| 152 |
+
{"current_steps": 760, "total_steps": 3850, "loss": 0.3039, "lr": 3.886113806766121e-05, "epoch": 1.3821656050955413, "percentage": 19.74, "elapsed_time": "5:04:51", "remaining_time": "20:39:27"}
|
| 153 |
+
{"current_steps": 765, "total_steps": 3850, "loss": 0.3024, "lr": 3.883078584986888e-05, "epoch": 1.3912647861692449, "percentage": 19.87, "elapsed_time": "5:06:52", "remaining_time": "20:37:33"}
|
| 154 |
+
{"current_steps": 770, "total_steps": 3850, "loss": 0.3073, "lr": 3.8800046640976916e-05, "epoch": 1.4003639672429482, "percentage": 20.0, "elapsed_time": "5:08:50", "remaining_time": "20:35:21"}
|
| 155 |
+
{"current_steps": 775, "total_steps": 3850, "loss": 0.3087, "lr": 3.876892107270616e-05, "epoch": 1.4094631483166515, "percentage": 20.13, "elapsed_time": "5:10:43", "remaining_time": "20:32:51"}
|
| 156 |
+
{"current_steps": 780, "total_steps": 3850, "loss": 0.3101, "lr": 3.873740978471755e-05, "epoch": 1.4185623293903549, "percentage": 20.26, "elapsed_time": "5:12:52", "remaining_time": "20:31:25"}
|
| 157 |
+
{"current_steps": 785, "total_steps": 3850, "loss": 0.3037, "lr": 3.8705513424598934e-05, "epoch": 1.4276615104640582, "percentage": 20.39, "elapsed_time": "5:14:54", "remaining_time": "20:29:34"}
|
| 158 |
+
{"current_steps": 790, "total_steps": 3850, "loss": 0.3022, "lr": 3.8673232647851756e-05, "epoch": 1.4367606915377615, "percentage": 20.52, "elapsed_time": "5:17:00", "remaining_time": "20:27:55"}
|
| 159 |
+
{"current_steps": 795, "total_steps": 3850, "loss": 0.2825, "lr": 3.8640568117877594e-05, "epoch": 1.4458598726114649, "percentage": 20.65, "elapsed_time": "5:19:09", "remaining_time": "20:26:25"}
|
| 160 |
+
{"current_steps": 800, "total_steps": 3850, "loss": 0.3015, "lr": 3.8607520505964574e-05, "epoch": 1.4549590536851684, "percentage": 20.78, "elapsed_time": "5:21:17", "remaining_time": "20:24:57"}
|
| 161 |
+
{"current_steps": 805, "total_steps": 3850, "loss": 0.3207, "lr": 3.857409049127348e-05, "epoch": 1.4640582347588718, "percentage": 20.91, "elapsed_time": "5:24:41", "remaining_time": "20:28:09"}
|
| 162 |
+
{"current_steps": 810, "total_steps": 3850, "loss": 0.3036, "lr": 3.8540278760823866e-05, "epoch": 1.473157415832575, "percentage": 21.04, "elapsed_time": "5:26:27", "remaining_time": "20:25:12"}
|
| 163 |
+
{"current_steps": 815, "total_steps": 3850, "loss": 0.2996, "lr": 3.8506086009479934e-05, "epoch": 1.4822565969062784, "percentage": 21.17, "elapsed_time": "5:28:28", "remaining_time": "20:23:14"}
|
| 164 |
+
{"current_steps": 820, "total_steps": 3850, "loss": 0.2944, "lr": 3.8471512939936224e-05, "epoch": 1.4913557779799818, "percentage": 21.3, "elapsed_time": "5:30:13", "remaining_time": "20:20:14"}
|
| 165 |
+
{"current_steps": 825, "total_steps": 3850, "loss": 0.2899, "lr": 3.843656026270319e-05, "epoch": 1.5004549590536853, "percentage": 21.43, "elapsed_time": "5:32:15", "remaining_time": "20:18:15"}
|