Training in progress, step 1000
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 sha256:1bcab777d646385a6e0dfcd1caa828666fb6f29385933f4428ac261cced37b00
|
| 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:fe7af14279f1f57e6d02986d0928b9c9f45b772a6f8d5c9ba2f1acb30e8de5ed
|
| 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 sha256:7c78913c98210ca9ea4e81ac7bbc192d0bce9741c9d01998f84208ec9339e6d9
|
| 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 sha256:5bde0d7c811b2c755e8cbb6f48a9cdc8b4af8f14c0877feb2736fd25f1d3ea9a
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -163,3 +163,41 @@
|
|
| 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"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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"}
|
| 166 |
+
{"current_steps": 830, "total_steps": 3850, "loss": 0.2962, "lr": 3.840122869609258e-05, "epoch": 1.5095541401273884, "percentage": 21.56, "elapsed_time": "5:34:03", "remaining_time": "20:15:31"}
|
| 167 |
+
{"current_steps": 835, "total_steps": 3850, "loss": 0.2793, "lr": 3.8365518966202724e-05, "epoch": 1.518653321201092, "percentage": 21.69, "elapsed_time": "5:36:05", "remaining_time": "20:13:33"}
|
| 168 |
+
{"current_steps": 840, "total_steps": 3850, "loss": 0.2836, "lr": 3.832943180690356e-05, "epoch": 1.5277525022747953, "percentage": 21.82, "elapsed_time": "5:38:12", "remaining_time": "20:11:56"}
|
| 169 |
+
{"current_steps": 845, "total_steps": 3850, "loss": 0.303, "lr": 3.829296795982156e-05, "epoch": 1.5368516833484986, "percentage": 21.95, "elapsed_time": "5:40:22", "remaining_time": "20:10:25"}
|
| 170 |
+
{"current_steps": 850, "total_steps": 3850, "loss": 0.292, "lr": 3.8256128174324515e-05, "epoch": 1.545950864422202, "percentage": 22.08, "elapsed_time": "5:42:35", "remaining_time": "20:09:09"}
|
| 171 |
+
{"current_steps": 855, "total_steps": 3850, "loss": 0.2833, "lr": 3.82189132075061e-05, "epoch": 1.5550500454959053, "percentage": 22.21, "elapsed_time": "5:44:37", "remaining_time": "20:07:12"}
|
| 172 |
+
{"current_steps": 860, "total_steps": 3850, "loss": 0.2962, "lr": 3.818132382417037e-05, "epoch": 1.5641492265696089, "percentage": 22.34, "elapsed_time": "5:46:32", "remaining_time": "20:04:49"}
|
| 173 |
+
{"current_steps": 865, "total_steps": 3850, "loss": 0.3039, "lr": 3.8143360796815964e-05, "epoch": 1.573248407643312, "percentage": 22.47, "elapsed_time": "5:48:22", "remaining_time": "20:02:12"}
|
| 174 |
+
{"current_steps": 870, "total_steps": 3850, "loss": 0.2879, "lr": 3.81050249056203e-05, "epoch": 1.5823475887170155, "percentage": 22.6, "elapsed_time": "5:50:27", "remaining_time": "20:00:25"}
|
| 175 |
+
{"current_steps": 875, "total_steps": 3850, "loss": 0.2997, "lr": 3.8066316938423495e-05, "epoch": 1.5914467697907189, "percentage": 22.73, "elapsed_time": "5:52:33", "remaining_time": "19:58:41"}
|
| 176 |
+
{"current_steps": 880, "total_steps": 3850, "loss": 0.3098, "lr": 3.8027237690712206e-05, "epoch": 1.6005459508644222, "percentage": 22.86, "elapsed_time": "5:54:24", "remaining_time": "19:56:07"}
|
| 177 |
+
{"current_steps": 885, "total_steps": 3850, "loss": 0.2901, "lr": 3.798778796560326e-05, "epoch": 1.6096451319381255, "percentage": 22.99, "elapsed_time": "5:56:10", "remaining_time": "19:53:16"}
|
| 178 |
+
{"current_steps": 890, "total_steps": 3850, "loss": 0.2978, "lr": 3.794796857382717e-05, "epoch": 1.6187443130118289, "percentage": 23.12, "elapsed_time": "5:58:11", "remaining_time": "19:51:18"}
|
| 179 |
+
{"current_steps": 895, "total_steps": 3850, "loss": 0.3023, "lr": 3.790778033371145e-05, "epoch": 1.6278434940855324, "percentage": 23.25, "elapsed_time": "6:00:21", "remaining_time": "19:49:48"}
|
| 180 |
+
{"current_steps": 900, "total_steps": 3850, "loss": 0.3085, "lr": 3.786722407116379e-05, "epoch": 1.6369426751592355, "percentage": 23.38, "elapsed_time": "6:02:29", "remaining_time": "19:48:09"}
|
| 181 |
+
{"current_steps": 905, "total_steps": 3850, "loss": 0.3064, "lr": 3.782630061965515e-05, "epoch": 1.646041856232939, "percentage": 23.51, "elapsed_time": "6:04:24", "remaining_time": "19:45:49"}
|
| 182 |
+
{"current_steps": 910, "total_steps": 3850, "loss": 0.261, "lr": 3.778501082020255e-05, "epoch": 1.6551410373066424, "percentage": 23.64, "elapsed_time": "6:06:41", "remaining_time": "19:44:41"}
|
| 183 |
+
{"current_steps": 915, "total_steps": 3850, "loss": 0.2758, "lr": 3.7743355521351814e-05, "epoch": 1.6642402183803457, "percentage": 23.77, "elapsed_time": "6:08:47", "remaining_time": "19:42:58"}
|
| 184 |
+
{"current_steps": 920, "total_steps": 3850, "loss": 0.2961, "lr": 3.7701335579160147e-05, "epoch": 1.673339399454049, "percentage": 23.9, "elapsed_time": "6:10:44", "remaining_time": "19:40:42"}
|
| 185 |
+
{"current_steps": 925, "total_steps": 3850, "loss": 0.3086, "lr": 3.7658951857178544e-05, "epoch": 1.6824385805277524, "percentage": 24.03, "elapsed_time": "6:12:31", "remaining_time": "19:37:57"}
|
| 186 |
+
{"current_steps": 930, "total_steps": 3850, "loss": 0.2772, "lr": 3.7616205226434005e-05, "epoch": 1.691537761601456, "percentage": 24.16, "elapsed_time": "6:14:43", "remaining_time": "19:36:32"}
|
| 187 |
+
{"current_steps": 935, "total_steps": 3850, "loss": 0.2902, "lr": 3.7573096565411694e-05, "epoch": 1.700636942675159, "percentage": 24.29, "elapsed_time": "6:16:48", "remaining_time": "19:34:44"}
|
| 188 |
+
{"current_steps": 940, "total_steps": 3850, "loss": 0.3026, "lr": 3.7529626760036814e-05, "epoch": 1.7097361237488626, "percentage": 24.42, "elapsed_time": "6:18:35", "remaining_time": "19:32:02"}
|
| 189 |
+
{"current_steps": 945, "total_steps": 3850, "loss": 0.301, "lr": 3.7485796703656475e-05, "epoch": 1.718835304822566, "percentage": 24.55, "elapsed_time": "6:20:39", "remaining_time": "19:30:10"}
|
| 190 |
+
{"current_steps": 950, "total_steps": 3850, "loss": 0.3127, "lr": 3.7441607297021254e-05, "epoch": 1.7279344858962693, "percentage": 24.68, "elapsed_time": "6:22:30", "remaining_time": "19:27:39"}
|
| 191 |
+
{"current_steps": 955, "total_steps": 3850, "loss": 0.2877, "lr": 3.7397059448266786e-05, "epoch": 1.7370336669699729, "percentage": 24.81, "elapsed_time": "6:24:33", "remaining_time": "19:25:43"}
|
| 192 |
+
{"current_steps": 960, "total_steps": 3850, "loss": 0.2944, "lr": 3.735215407289498e-05, "epoch": 1.746132848043676, "percentage": 24.94, "elapsed_time": "6:26:26", "remaining_time": "19:23:20"}
|
| 193 |
+
{"current_steps": 965, "total_steps": 3850, "loss": 0.3011, "lr": 3.730689209375533e-05, "epoch": 1.7552320291173795, "percentage": 25.06, "elapsed_time": "6:28:28", "remaining_time": "19:21:24"}
|
| 194 |
+
{"current_steps": 970, "total_steps": 3850, "loss": 0.2814, "lr": 3.726127444102583e-05, "epoch": 1.7643312101910829, "percentage": 25.19, "elapsed_time": "6:30:28", "remaining_time": "19:19:21"}
|
| 195 |
+
{"current_steps": 975, "total_steps": 3850, "loss": 0.271, "lr": 3.721530205219395e-05, "epoch": 1.7734303912647862, "percentage": 25.32, "elapsed_time": "6:32:43", "remaining_time": "19:18:01"}
|
| 196 |
+
{"current_steps": 980, "total_steps": 3850, "loss": 0.2907, "lr": 3.716897587203733e-05, "epoch": 1.7825295723384895, "percentage": 25.45, "elapsed_time": "6:34:53", "remaining_time": "19:16:28"}
|
| 197 |
+
{"current_steps": 985, "total_steps": 3850, "loss": 0.3063, "lr": 3.712229685260434e-05, "epoch": 1.7916287534121929, "percentage": 25.58, "elapsed_time": "6:36:51", "remaining_time": "19:14:20"}
|
| 198 |
+
{"current_steps": 990, "total_steps": 3850, "loss": 0.2958, "lr": 3.707526595319459e-05, "epoch": 1.8007279344858964, "percentage": 25.71, "elapsed_time": "6:38:55", "remaining_time": "19:12:25"}
|
| 199 |
+
{"current_steps": 995, "total_steps": 3850, "loss": 0.2965, "lr": 3.7027884140339144e-05, "epoch": 1.8098271155595995, "percentage": 25.84, "elapsed_time": "6:40:55", "remaining_time": "19:10:24"}
|
| 200 |
+
{"current_steps": 1000, "total_steps": 3850, "loss": 0.2801, "lr": 3.698015238778066e-05, "epoch": 1.818926296633303, "percentage": 25.97, "elapsed_time": "6:43:05", "remaining_time": "19:08:47"}
|
| 201 |
+
{"current_steps": 1005, "total_steps": 3850, "loss": 0.2814, "lr": 3.693207167645344e-05, "epoch": 1.8280254777070064, "percentage": 26.1, "elapsed_time": "6:46:20", "remaining_time": "19:10:18"}
|
| 202 |
+
{"current_steps": 1010, "total_steps": 3850, "loss": 0.2925, "lr": 3.6883642994463194e-05, "epoch": 1.8371246587807097, "percentage": 26.23, "elapsed_time": "6:48:26", "remaining_time": "19:08:28"}
|
| 203 |
+
{"current_steps": 1015, "total_steps": 3850, "loss": 0.2974, "lr": 3.6834867337066805e-05, "epoch": 1.846223839854413, "percentage": 26.36, "elapsed_time": "6:50:13", "remaining_time": "19:05:46"}
|