Training in progress, step 1200
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 sha256:2af6a8cbd45d0bba842d94a405b6405243433654239c8671db5459d2e7b8707d
|
| 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 sha256:62992e6b84eab9f869728ef10588cc20f588d0d5bb25792b92f2aa8498240617
|
| 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:d0a7b9eb37800ccc57fa06a67c94e1fb2a621c4a751031e14d776399b4a39a73
|
| 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:fe7ebe46fd91b4691d9a1a9cf5636617e0268a747be348afe720743710d9a05c
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -201,3 +201,42 @@
|
|
| 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"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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"}
|
| 204 |
+
{"current_steps": 1020, "total_steps": 3850, "loss": 0.2836, "lr": 3.678574570665181e-05, "epoch": 1.8553230209281164, "percentage": 26.49, "elapsed_time": "6:52:08", "remaining_time": "19:03:28"}
|
| 205 |
+
{"current_steps": 1025, "total_steps": 3850, "loss": 0.2953, "lr": 3.673627911271586e-05, "epoch": 1.86442220200182, "percentage": 26.62, "elapsed_time": "6:54:12", "remaining_time": "19:01:36"}
|
| 206 |
+
{"current_steps": 1030, "total_steps": 3850, "loss": 0.3157, "lr": 3.668646857184591e-05, "epoch": 1.873521383075523, "percentage": 26.75, "elapsed_time": "6:56:01", "remaining_time": "18:59:00"}
|
| 207 |
+
{"current_steps": 1035, "total_steps": 3850, "loss": 0.3093, "lr": 3.663631510769739e-05, "epoch": 1.8826205641492266, "percentage": 26.88, "elapsed_time": "6:58:00", "remaining_time": "18:56:55"}
|
| 208 |
+
{"current_steps": 1040, "total_steps": 3850, "loss": 0.3016, "lr": 3.658581975097311e-05, "epoch": 1.89171974522293, "percentage": 27.01, "elapsed_time": "6:59:50", "remaining_time": "18:54:22"}
|
| 209 |
+
{"current_steps": 1045, "total_steps": 3850, "loss": 0.2961, "lr": 3.653498353940215e-05, "epoch": 1.9008189262966333, "percentage": 27.14, "elapsed_time": "7:01:48", "remaining_time": "18:52:12"}
|
| 210 |
+
{"current_steps": 1050, "total_steps": 3850, "loss": 0.2948, "lr": 3.648380751771846e-05, "epoch": 1.9099181073703366, "percentage": 27.27, "elapsed_time": "7:03:35", "remaining_time": "18:49:35"}
|
| 211 |
+
{"current_steps": 1055, "total_steps": 3850, "loss": 0.2813, "lr": 3.6432292737639426e-05, "epoch": 1.91901728844404, "percentage": 27.4, "elapsed_time": "7:05:38", "remaining_time": "18:47:37"}
|
| 212 |
+
{"current_steps": 1060, "total_steps": 3850, "loss": 0.2946, "lr": 3.638044025784425e-05, "epoch": 1.9281164695177435, "percentage": 27.53, "elapsed_time": "7:07:29", "remaining_time": "18:45:10"}
|
| 213 |
+
{"current_steps": 1065, "total_steps": 3850, "loss": 0.2967, "lr": 3.63282511439522e-05, "epoch": 1.9372156505914466, "percentage": 27.66, "elapsed_time": "7:09:23", "remaining_time": "18:42:51"}
|
| 214 |
+
{"current_steps": 1070, "total_steps": 3850, "loss": 0.296, "lr": 3.627572646850069e-05, "epoch": 1.9463148316651502, "percentage": 27.79, "elapsed_time": "7:11:23", "remaining_time": "18:40:49"}
|
| 215 |
+
{"current_steps": 1075, "total_steps": 3850, "loss": 0.3, "lr": 3.6222867310923296e-05, "epoch": 1.9554140127388535, "percentage": 27.92, "elapsed_time": "7:13:17", "remaining_time": "18:38:30"}
|
| 216 |
+
{"current_steps": 1080, "total_steps": 3850, "loss": 0.2869, "lr": 3.6169674757527466e-05, "epoch": 1.9645131938125568, "percentage": 28.05, "elapsed_time": "7:15:07", "remaining_time": "18:36:02"}
|
| 217 |
+
{"current_steps": 1085, "total_steps": 3850, "loss": 0.2896, "lr": 3.61161499014723e-05, "epoch": 1.9736123748862604, "percentage": 28.18, "elapsed_time": "7:17:08", "remaining_time": "18:34:01"}
|
| 218 |
+
{"current_steps": 1090, "total_steps": 3850, "loss": 0.2915, "lr": 3.606229384274604e-05, "epoch": 1.9827115559599635, "percentage": 28.31, "elapsed_time": "7:19:07", "remaining_time": "18:31:55"}
|
| 219 |
+
{"current_steps": 1095, "total_steps": 3850, "loss": 0.2972, "lr": 3.600810768814345e-05, "epoch": 1.991810737033667, "percentage": 28.44, "elapsed_time": "7:21:01", "remaining_time": "18:29:35"}
|
| 220 |
+
{"current_steps": 1100, "total_steps": 3850, "loss": 0.3044, "lr": 3.595359255124311e-05, "epoch": 2.0, "percentage": 28.57, "elapsed_time": "7:22:57", "remaining_time": "18:27:23"}
|
| 221 |
+
{"current_steps": 1105, "total_steps": 3850, "loss": 0.2748, "lr": 3.589874955238449e-05, "epoch": 2.0090991810737036, "percentage": 28.7, "elapsed_time": "7:25:00", "remaining_time": "18:25:27"}
|
| 222 |
+
{"current_steps": 1110, "total_steps": 3850, "loss": 0.2744, "lr": 3.5843579818644956e-05, "epoch": 2.0181983621474067, "percentage": 28.83, "elapsed_time": "7:26:48", "remaining_time": "18:22:56"}
|
| 223 |
+
{"current_steps": 1115, "total_steps": 3850, "loss": 0.2697, "lr": 3.5788084483816587e-05, "epoch": 2.02729754322111, "percentage": 28.96, "elapsed_time": "7:28:49", "remaining_time": "18:20:56"}
|
| 224 |
+
{"current_steps": 1120, "total_steps": 3850, "loss": 0.2756, "lr": 3.573226468838289e-05, "epoch": 2.0363967242948133, "percentage": 29.09, "elapsed_time": "7:30:44", "remaining_time": "18:18:41"}
|
| 225 |
+
{"current_steps": 1125, "total_steps": 3850, "loss": 0.2764, "lr": 3.567612157949536e-05, "epoch": 2.045495905368517, "percentage": 29.22, "elapsed_time": "7:32:34", "remaining_time": "18:16:14"}
|
| 226 |
+
{"current_steps": 1130, "total_steps": 3850, "loss": 0.2759, "lr": 3.561965631094988e-05, "epoch": 2.05459508644222, "percentage": 29.35, "elapsed_time": "7:34:33", "remaining_time": "18:14:08"}
|
| 227 |
+
{"current_steps": 1135, "total_steps": 3850, "loss": 0.2375, "lr": 3.556287004316305e-05, "epoch": 2.0636942675159236, "percentage": 29.48, "elapsed_time": "7:36:34", "remaining_time": "18:12:10"}
|
| 228 |
+
{"current_steps": 1140, "total_steps": 3850, "loss": 0.2636, "lr": 3.5505763943148324e-05, "epoch": 2.072793448589627, "percentage": 29.61, "elapsed_time": "7:38:29", "remaining_time": "18:09:56"}
|
| 229 |
+
{"current_steps": 1145, "total_steps": 3850, "loss": 0.2538, "lr": 3.544833918449199e-05, "epoch": 2.08189262966333, "percentage": 29.74, "elapsed_time": "7:40:24", "remaining_time": "18:07:41"}
|
| 230 |
+
{"current_steps": 1150, "total_steps": 3850, "loss": 0.2615, "lr": 3.5390596947329124e-05, "epoch": 2.0909918107370338, "percentage": 29.87, "elapsed_time": "7:42:31", "remaining_time": "18:05:55"}
|
| 231 |
+
{"current_steps": 1155, "total_steps": 3850, "loss": 0.2609, "lr": 3.5332538418319254e-05, "epoch": 2.100090991810737, "percentage": 30.0, "elapsed_time": "7:44:19", "remaining_time": "18:03:26"}
|
| 232 |
+
{"current_steps": 1160, "total_steps": 3850, "loss": 0.2721, "lr": 3.527416479062205e-05, "epoch": 2.1091901728844404, "percentage": 30.13, "elapsed_time": "7:46:09", "remaining_time": "18:00:59"}
|
| 233 |
+
{"current_steps": 1165, "total_steps": 3850, "loss": 0.2635, "lr": 3.521547726387275e-05, "epoch": 2.1182893539581436, "percentage": 30.26, "elapsed_time": "7:48:22", "remaining_time": "17:59:27"}
|
| 234 |
+
{"current_steps": 1170, "total_steps": 3850, "loss": 0.2672, "lr": 3.515647704415754e-05, "epoch": 2.127388535031847, "percentage": 30.39, "elapsed_time": "7:50:16", "remaining_time": "17:57:13"}
|
| 235 |
+
{"current_steps": 1175, "total_steps": 3850, "loss": 0.2813, "lr": 3.509716534398873e-05, "epoch": 2.1364877161055507, "percentage": 30.52, "elapsed_time": "7:52:14", "remaining_time": "17:55:06"}
|
| 236 |
+
{"current_steps": 1180, "total_steps": 3850, "loss": 0.2779, "lr": 3.503754338227989e-05, "epoch": 2.1455868971792538, "percentage": 30.65, "elapsed_time": "7:54:06", "remaining_time": "17:52:46"}
|
| 237 |
+
{"current_steps": 1185, "total_steps": 3850, "loss": 0.2708, "lr": 3.497761238432073e-05, "epoch": 2.1546860782529573, "percentage": 30.78, "elapsed_time": "7:55:51", "remaining_time": "17:50:10"}
|
| 238 |
+
{"current_steps": 1190, "total_steps": 3850, "loss": 0.2539, "lr": 3.4917373581752e-05, "epoch": 2.1637852593266604, "percentage": 30.91, "elapsed_time": "7:57:46", "remaining_time": "17:47:58"}
|
| 239 |
+
{"current_steps": 1195, "total_steps": 3850, "loss": 0.2577, "lr": 3.4856828212540094e-05, "epoch": 2.172884440400364, "percentage": 31.04, "elapsed_time": "7:59:37", "remaining_time": "17:45:35"}
|
| 240 |
+
{"current_steps": 1200, "total_steps": 3850, "loss": 0.2593, "lr": 3.4795977520951684e-05, "epoch": 2.1819836214740675, "percentage": 31.17, "elapsed_time": "8:01:41", "remaining_time": "17:43:44"}
|
| 241 |
+
{"current_steps": 1205, "total_steps": 3850, "loss": 0.2545, "lr": 3.47348227575281e-05, "epoch": 2.1910828025477707, "percentage": 31.3, "elapsed_time": "8:04:39", "remaining_time": "17:43:51"}
|
| 242 |
+
{"current_steps": 1210, "total_steps": 3850, "loss": 0.2596, "lr": 3.467336517905966e-05, "epoch": 2.200181983621474, "percentage": 31.43, "elapsed_time": "8:06:52", "remaining_time": "17:42:15"}
|