Training in progress, step 600
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 sha256:17292ccb7eeb9c2b274ac88dfc9ed52a621b67ca0f4359266997a65b0316eedc
|
| 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:f4848e0e748087c907dc262c66163f8ec541f98aef7388a087711e1afa8b8339
|
| 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 sha256:11b147a70c7d42f6a6ac61949d37d58709d904d6fe8dad2bd3925ae6bbbdca35
|
| 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 sha256:0a653eacbe46250912f01d4a473391e0d70d412923e7eb97f2b97e17d7d64998
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -80,3 +80,46 @@
|
|
| 80 |
{"current_steps": 400, "total_steps": 3850, "loss": 0.3347, "lr": 3.999838882205719e-05, "epoch": 0.7279344858962693, "percentage": 10.39, "elapsed_time": "2:41:02", "remaining_time": "23:08:56"}
|
| 81 |
{"current_steps": 405, "total_steps": 3850, "loss": 0.3471, "lr": 3.999703250682087e-05, "epoch": 0.7370336669699727, "percentage": 10.52, "elapsed_time": "2:44:05", "remaining_time": "23:15:49"}
|
| 82 |
{"current_steps": 410, "total_steps": 3850, "loss": 0.321, "lr": 3.9995265232973414e-05, "epoch": 0.7461328480436761, "percentage": 10.65, "elapsed_time": "2:46:16", "remaining_time": "23:15:05"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
{"current_steps": 400, "total_steps": 3850, "loss": 0.3347, "lr": 3.999838882205719e-05, "epoch": 0.7279344858962693, "percentage": 10.39, "elapsed_time": "2:41:02", "remaining_time": "23:08:56"}
|
| 81 |
{"current_steps": 405, "total_steps": 3850, "loss": 0.3471, "lr": 3.999703250682087e-05, "epoch": 0.7370336669699727, "percentage": 10.52, "elapsed_time": "2:44:05", "remaining_time": "23:15:49"}
|
| 82 |
{"current_steps": 410, "total_steps": 3850, "loss": 0.321, "lr": 3.9995265232973414e-05, "epoch": 0.7461328480436761, "percentage": 10.65, "elapsed_time": "2:46:16", "remaining_time": "23:15:05"}
|
| 83 |
+
{"current_steps": 415, "total_steps": 3850, "loss": 0.3242, "lr": 3.9993087036834034e-05, "epoch": 0.7552320291173794, "percentage": 10.78, "elapsed_time": "2:48:14", "remaining_time": "23:12:34"}
|
| 84 |
+
{"current_steps": 420, "total_steps": 3850, "loss": 0.3329, "lr": 3.9990497963166797e-05, "epoch": 0.7643312101910829, "percentage": 10.91, "elapsed_time": "2:50:02", "remaining_time": "23:08:42"}
|
| 85 |
+
{"current_steps": 425, "total_steps": 3850, "loss": 0.3283, "lr": 3.99874980651797e-05, "epoch": 0.7734303912647862, "percentage": 11.04, "elapsed_time": "2:52:06", "remaining_time": "23:06:57"}
|
| 86 |
+
{"current_steps": 430, "total_steps": 3850, "loss": 0.3288, "lr": 3.998408740452359e-05, "epoch": 0.7825295723384895, "percentage": 11.17, "elapsed_time": "2:54:05", "remaining_time": "23:04:39"}
|
| 87 |
+
{"current_steps": 435, "total_steps": 3850, "loss": 0.342, "lr": 3.998026605129088e-05, "epoch": 0.7916287534121929, "percentage": 11.3, "elapsed_time": "2:56:06", "remaining_time": "23:02:34"}
|
| 88 |
+
{"current_steps": 440, "total_steps": 3850, "loss": 0.3378, "lr": 3.997603408401413e-05, "epoch": 0.8007279344858963, "percentage": 11.43, "elapsed_time": "2:58:15", "remaining_time": "23:01:27"}
|
| 89 |
+
{"current_steps": 445, "total_steps": 3850, "loss": 0.3335, "lr": 3.997139158966441e-05, "epoch": 0.8098271155595996, "percentage": 11.56, "elapsed_time": "3:00:10", "remaining_time": "22:58:38"}
|
| 90 |
+
{"current_steps": 450, "total_steps": 3850, "loss": 0.3274, "lr": 3.996633866364953e-05, "epoch": 0.818926296633303, "percentage": 11.69, "elapsed_time": "3:02:22", "remaining_time": "22:57:55"}
|
| 91 |
+
{"current_steps": 455, "total_steps": 3850, "loss": 0.3392, "lr": 3.996087540981206e-05, "epoch": 0.8280254777070064, "percentage": 11.82, "elapsed_time": "3:04:23", "remaining_time": "22:55:53"}
|
| 92 |
+
{"current_steps": 460, "total_steps": 3850, "loss": 0.3385, "lr": 3.9955001940427236e-05, "epoch": 0.8371246587807097, "percentage": 11.95, "elapsed_time": "3:06:21", "remaining_time": "22:53:20"}
|
| 93 |
+
{"current_steps": 465, "total_steps": 3850, "loss": 0.308, "lr": 3.99487183762006e-05, "epoch": 0.8462238398544131, "percentage": 12.08, "elapsed_time": "3:08:13", "remaining_time": "22:50:09"}
|
| 94 |
+
{"current_steps": 470, "total_steps": 3850, "loss": 0.3267, "lr": 3.994202484626555e-05, "epoch": 0.8553230209281165, "percentage": 12.21, "elapsed_time": "3:10:04", "remaining_time": "22:46:51"}
|
| 95 |
+
{"current_steps": 475, "total_steps": 3850, "loss": 0.3302, "lr": 3.993492148818069e-05, "epoch": 0.8644222020018199, "percentage": 12.34, "elapsed_time": "3:12:08", "remaining_time": "22:45:12"}
|
| 96 |
+
{"current_steps": 480, "total_steps": 3850, "loss": 0.3269, "lr": 3.992740844792699e-05, "epoch": 0.8735213830755232, "percentage": 12.47, "elapsed_time": "3:14:08", "remaining_time": "22:42:59"}
|
| 97 |
+
{"current_steps": 485, "total_steps": 3850, "loss": 0.338, "lr": 3.991948587990479e-05, "epoch": 0.8826205641492265, "percentage": 12.6, "elapsed_time": "3:16:09", "remaining_time": "22:40:57"}
|
| 98 |
+
{"current_steps": 490, "total_steps": 3850, "loss": 0.3351, "lr": 3.991115394693061e-05, "epoch": 0.89171974522293, "percentage": 12.73, "elapsed_time": "3:18:05", "remaining_time": "22:38:18"}
|
| 99 |
+
{"current_steps": 495, "total_steps": 3850, "loss": 0.3066, "lr": 3.990241282023385e-05, "epoch": 0.9008189262966333, "percentage": 12.86, "elapsed_time": "3:20:07", "remaining_time": "22:36:25"}
|
| 100 |
+
{"current_steps": 500, "total_steps": 3850, "loss": 0.3338, "lr": 3.989326267945323e-05, "epoch": 0.9099181073703366, "percentage": 12.99, "elapsed_time": "3:22:08", "remaining_time": "22:34:18"}
|
| 101 |
+
{"current_steps": 505, "total_steps": 3850, "loss": 0.3366, "lr": 3.98837037126331e-05, "epoch": 0.9190172884440401, "percentage": 13.12, "elapsed_time": "3:24:22", "remaining_time": "22:33:42"}
|
| 102 |
+
{"current_steps": 510, "total_steps": 3850, "loss": 0.349, "lr": 3.98737361162196e-05, "epoch": 0.9281164695177434, "percentage": 13.25, "elapsed_time": "3:26:24", "remaining_time": "22:31:46"}
|
| 103 |
+
{"current_steps": 515, "total_steps": 3850, "loss": 0.3, "lr": 3.986336009505659e-05, "epoch": 0.9372156505914467, "percentage": 13.38, "elapsed_time": "3:28:31", "remaining_time": "22:30:20"}
|
| 104 |
+
{"current_steps": 520, "total_steps": 3850, "loss": 0.3458, "lr": 3.985257586238149e-05, "epoch": 0.9463148316651502, "percentage": 13.51, "elapsed_time": "3:30:28", "remaining_time": "22:27:51"}
|
| 105 |
+
{"current_steps": 525, "total_steps": 3850, "loss": 0.3403, "lr": 3.984138363982084e-05, "epoch": 0.9554140127388535, "percentage": 13.64, "elapsed_time": "3:32:20", "remaining_time": "22:24:52"}
|
| 106 |
+
{"current_steps": 530, "total_steps": 3850, "loss": 0.3148, "lr": 3.982978365738578e-05, "epoch": 0.9645131938125568, "percentage": 13.77, "elapsed_time": "3:34:08", "remaining_time": "22:21:25"}
|
| 107 |
+
{"current_steps": 535, "total_steps": 3850, "loss": 0.3209, "lr": 3.981777615346731e-05, "epoch": 0.9736123748862603, "percentage": 13.9, "elapsed_time": "3:35:57", "remaining_time": "22:18:09"}
|
| 108 |
+
{"current_steps": 540, "total_steps": 3850, "loss": 0.3326, "lr": 3.980536137483141e-05, "epoch": 0.9827115559599636, "percentage": 14.03, "elapsed_time": "3:37:40", "remaining_time": "22:14:17"}
|
| 109 |
+
{"current_steps": 545, "total_steps": 3850, "loss": 0.3276, "lr": 3.9792539576613934e-05, "epoch": 0.991810737033667, "percentage": 14.16, "elapsed_time": "3:39:37", "remaining_time": "22:11:50"}
|
| 110 |
+
{"current_steps": 550, "total_steps": 3850, "loss": 0.334, "lr": 3.9779311022315405e-05, "epoch": 1.0, "percentage": 14.29, "elapsed_time": "3:41:26", "remaining_time": "22:08:39"}
|
| 111 |
+
{"current_steps": 555, "total_steps": 3850, "loss": 0.3199, "lr": 3.976567598379558e-05, "epoch": 1.0090991810737033, "percentage": 14.42, "elapsed_time": "3:43:16", "remaining_time": "22:05:31"}
|
| 112 |
+
{"current_steps": 560, "total_steps": 3850, "loss": 0.314, "lr": 3.975163474126785e-05, "epoch": 1.0181983621474067, "percentage": 14.55, "elapsed_time": "3:45:14", "remaining_time": "22:03:16"}
|
| 113 |
+
{"current_steps": 565, "total_steps": 3850, "loss": 0.302, "lr": 3.9737187583293505e-05, "epoch": 1.02729754322111, "percentage": 14.68, "elapsed_time": "3:47:16", "remaining_time": "22:01:23"}
|
| 114 |
+
{"current_steps": 570, "total_steps": 3850, "loss": 0.3217, "lr": 3.9722334806775806e-05, "epoch": 1.0363967242948136, "percentage": 14.81, "elapsed_time": "3:49:22", "remaining_time": "21:59:57"}
|
| 115 |
+
{"current_steps": 575, "total_steps": 3850, "loss": 0.3028, "lr": 3.9707076716953866e-05, "epoch": 1.0454959053685169, "percentage": 14.94, "elapsed_time": "3:51:26", "remaining_time": "21:58:10"}
|
| 116 |
+
{"current_steps": 580, "total_steps": 3850, "loss": 0.2955, "lr": 3.969141362739636e-05, "epoch": 1.0545950864422202, "percentage": 15.06, "elapsed_time": "3:53:27", "remaining_time": "21:56:13"}
|
| 117 |
+
{"current_steps": 585, "total_steps": 3850, "loss": 0.3154, "lr": 3.967534585999515e-05, "epoch": 1.0636942675159236, "percentage": 15.19, "elapsed_time": "3:55:21", "remaining_time": "21:53:36"}
|
| 118 |
+
{"current_steps": 590, "total_steps": 3850, "loss": 0.2855, "lr": 3.965887374495859e-05, "epoch": 1.0727934485896269, "percentage": 15.32, "elapsed_time": "3:57:27", "remaining_time": "21:52:00"}
|
| 119 |
+
{"current_steps": 595, "total_steps": 3850, "loss": 0.3086, "lr": 3.964199762080478e-05, "epoch": 1.0818926296633302, "percentage": 15.45, "elapsed_time": "3:59:20", "remaining_time": "21:49:22"}
|
| 120 |
+
{"current_steps": 600, "total_steps": 3850, "loss": 0.3112, "lr": 3.9624717834354606e-05, "epoch": 1.0909918107370338, "percentage": 15.58, "elapsed_time": "4:01:01", "remaining_time": "21:45:34"}
|
| 121 |
+
{"current_steps": 605, "total_steps": 3850, "loss": 0.3046, "lr": 3.9607034740724615e-05, "epoch": 1.100090991810737, "percentage": 15.71, "elapsed_time": "4:04:12", "remaining_time": "21:49:48"}
|
| 122 |
+
{"current_steps": 610, "total_steps": 3850, "loss": 0.3029, "lr": 3.958894870331971e-05, "epoch": 1.1091901728844404, "percentage": 15.84, "elapsed_time": "4:06:11", "remaining_time": "21:47:40"}
|
| 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"}
|