Training in progress, epoch 1
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 sha256:2ef5a9423e276f87c6e7db10f61cdf028731dbb7bba0b1c935017866eedfe399
|
| 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 sha256:4398d2a6cedbce4ccbc524694ff552dc750ffcf5b91ac04226be1afb5d1886a6
|
| 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 sha256:26917aa46c8d88ecbdddff91c1dc2dbd88407bddad83f0e4cf1c773f8b9e763c
|
| 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 sha256:64a1cd3a5640d99f2561623418abcf3bae2dc8113890bef6a6649d9d546ecf57
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -69,3 +69,53 @@
|
|
| 69 |
{"current_steps": 69, "total_steps": 156, "loss": 0.7508, "lr": 6.8614682920097265e-06, "epoch": 1.3184713375796178, "percentage": 44.23, "elapsed_time": "0:13:29", "remaining_time": "0:17:01"}
|
| 70 |
{"current_steps": 70, "total_steps": 156, "loss": 0.6699, "lr": 6.7568741204067145e-06, "epoch": 1.3375796178343948, "percentage": 44.87, "elapsed_time": "0:13:50", "remaining_time": "0:17:00"}
|
| 71 |
{"current_steps": 71, "total_steps": 156, "loss": 0.7125, "lr": 6.651395309775837e-06, "epoch": 1.356687898089172, "percentage": 45.51, "elapsed_time": "0:14:01", "remaining_time": "0:16:47"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
{"current_steps": 69, "total_steps": 156, "loss": 0.7508, "lr": 6.8614682920097265e-06, "epoch": 1.3184713375796178, "percentage": 44.23, "elapsed_time": "0:13:29", "remaining_time": "0:17:01"}
|
| 70 |
{"current_steps": 70, "total_steps": 156, "loss": 0.6699, "lr": 6.7568741204067145e-06, "epoch": 1.3375796178343948, "percentage": 44.87, "elapsed_time": "0:13:50", "remaining_time": "0:17:00"}
|
| 71 |
{"current_steps": 71, "total_steps": 156, "loss": 0.7125, "lr": 6.651395309775837e-06, "epoch": 1.356687898089172, "percentage": 45.51, "elapsed_time": "0:14:01", "remaining_time": "0:16:47"}
|
| 72 |
+
{"current_steps": 72, "total_steps": 156, "loss": 0.6811, "lr": 6.545084971874738e-06, "epoch": 1.3757961783439492, "percentage": 46.15, "elapsed_time": "0:14:14", "remaining_time": "0:16:36"}
|
| 73 |
+
{"current_steps": 73, "total_steps": 156, "loss": 0.7014, "lr": 6.437996637160086e-06, "epoch": 1.394904458598726, "percentage": 46.79, "elapsed_time": "0:14:26", "remaining_time": "0:16:25"}
|
| 74 |
+
{"current_steps": 74, "total_steps": 156, "loss": 0.6723, "lr": 6.330184227833376e-06, "epoch": 1.4140127388535033, "percentage": 47.44, "elapsed_time": "0:14:39", "remaining_time": "0:16:14"}
|
| 75 |
+
{"current_steps": 75, "total_steps": 156, "loss": 0.6753, "lr": 6.2217020306894705e-06, "epoch": 1.4331210191082802, "percentage": 48.08, "elapsed_time": "0:14:48", "remaining_time": "0:15:59"}
|
| 76 |
+
{"current_steps": 76, "total_steps": 156, "loss": 0.703, "lr": 6.112604669781572e-06, "epoch": 1.4522292993630574, "percentage": 48.72, "elapsed_time": "0:15:17", "remaining_time": "0:16:05"}
|
| 77 |
+
{"current_steps": 77, "total_steps": 156, "loss": 0.7443, "lr": 6.002947078916365e-06, "epoch": 1.4713375796178343, "percentage": 49.36, "elapsed_time": "0:15:28", "remaining_time": "0:15:52"}
|
| 78 |
+
{"current_steps": 78, "total_steps": 156, "loss": 0.6685, "lr": 5.892784473993184e-06, "epoch": 1.4904458598726116, "percentage": 50.0, "elapsed_time": "0:15:35", "remaining_time": "0:15:35"}
|
| 79 |
+
{"current_steps": 79, "total_steps": 156, "loss": 0.6591, "lr": 5.782172325201155e-06, "epoch": 1.5095541401273884, "percentage": 50.64, "elapsed_time": "0:15:43", "remaining_time": "0:15:19"}
|
| 80 |
+
{"current_steps": 80, "total_steps": 156, "loss": 0.6936, "lr": 5.671166329088278e-06, "epoch": 1.5286624203821657, "percentage": 51.28, "elapsed_time": "0:15:56", "remaining_time": "0:15:08"}
|
| 81 |
+
{"current_steps": 81, "total_steps": 156, "loss": 0.6929, "lr": 5.559822380516539e-06, "epoch": 1.5477707006369426, "percentage": 51.92, "elapsed_time": "0:16:02", "remaining_time": "0:14:51"}
|
| 82 |
+
{"current_steps": 82, "total_steps": 156, "loss": 0.7198, "lr": 5.448196544517168e-06, "epoch": 1.5668789808917198, "percentage": 52.56, "elapsed_time": "0:16:12", "remaining_time": "0:14:37"}
|
| 83 |
+
{"current_steps": 83, "total_steps": 156, "loss": 0.7355, "lr": 5.336345028060199e-06, "epoch": 1.5859872611464967, "percentage": 53.21, "elapsed_time": "0:16:24", "remaining_time": "0:14:26"}
|
| 84 |
+
{"current_steps": 84, "total_steps": 156, "loss": 0.6984, "lr": 5.224324151752575e-06, "epoch": 1.605095541401274, "percentage": 53.85, "elapsed_time": "0:16:38", "remaining_time": "0:14:16"}
|
| 85 |
+
{"current_steps": 85, "total_steps": 156, "loss": 0.7028, "lr": 5.112190321479026e-06, "epoch": 1.6242038216560508, "percentage": 54.49, "elapsed_time": "0:16:46", "remaining_time": "0:14:00"}
|
| 86 |
+
{"current_steps": 86, "total_steps": 156, "loss": 0.666, "lr": 5e-06, "epoch": 1.643312101910828, "percentage": 55.13, "elapsed_time": "0:16:56", "remaining_time": "0:13:47"}
|
| 87 |
+
{"current_steps": 87, "total_steps": 156, "loss": 0.7537, "lr": 4.887809678520976e-06, "epoch": 1.662420382165605, "percentage": 55.77, "elapsed_time": "0:17:05", "remaining_time": "0:13:33"}
|
| 88 |
+
{"current_steps": 88, "total_steps": 156, "loss": 0.7102, "lr": 4.775675848247427e-06, "epoch": 1.6815286624203822, "percentage": 56.41, "elapsed_time": "0:17:17", "remaining_time": "0:13:21"}
|
| 89 |
+
{"current_steps": 89, "total_steps": 156, "loss": 0.6781, "lr": 4.663654971939802e-06, "epoch": 1.700636942675159, "percentage": 57.05, "elapsed_time": "0:17:24", "remaining_time": "0:13:06"}
|
| 90 |
+
{"current_steps": 90, "total_steps": 156, "loss": 0.7141, "lr": 4.551803455482833e-06, "epoch": 1.7197452229299364, "percentage": 57.69, "elapsed_time": "0:17:35", "remaining_time": "0:12:53"}
|
| 91 |
+
{"current_steps": 91, "total_steps": 156, "loss": 0.7032, "lr": 4.4401776194834615e-06, "epoch": 1.7388535031847132, "percentage": 58.33, "elapsed_time": "0:17:45", "remaining_time": "0:12:40"}
|
| 92 |
+
{"current_steps": 92, "total_steps": 156, "loss": 0.7434, "lr": 4.3288336709117246e-06, "epoch": 1.7579617834394905, "percentage": 58.97, "elapsed_time": "0:17:55", "remaining_time": "0:12:28"}
|
| 93 |
+
{"current_steps": 93, "total_steps": 156, "loss": 0.68, "lr": 4.217827674798845e-06, "epoch": 1.7770700636942676, "percentage": 59.62, "elapsed_time": "0:18:05", "remaining_time": "0:12:15"}
|
| 94 |
+
{"current_steps": 94, "total_steps": 156, "loss": 0.6568, "lr": 4.107215526006818e-06, "epoch": 1.7961783439490446, "percentage": 60.26, "elapsed_time": "0:18:14", "remaining_time": "0:12:02"}
|
| 95 |
+
{"current_steps": 95, "total_steps": 156, "loss": 0.7393, "lr": 3.997052921083637e-06, "epoch": 1.8152866242038217, "percentage": 60.9, "elapsed_time": "0:18:25", "remaining_time": "0:11:49"}
|
| 96 |
+
{"current_steps": 96, "total_steps": 156, "loss": 0.6979, "lr": 3.887395330218429e-06, "epoch": 1.8343949044585988, "percentage": 61.54, "elapsed_time": "0:18:36", "remaining_time": "0:11:37"}
|
| 97 |
+
{"current_steps": 97, "total_steps": 156, "loss": 0.7, "lr": 3.778297969310529e-06, "epoch": 1.8535031847133758, "percentage": 62.18, "elapsed_time": "0:18:46", "remaining_time": "0:11:25"}
|
| 98 |
+
{"current_steps": 98, "total_steps": 156, "loss": 0.7173, "lr": 3.669815772166625e-06, "epoch": 1.872611464968153, "percentage": 62.82, "elapsed_time": "0:18:55", "remaining_time": "0:11:11"}
|
| 99 |
+
{"current_steps": 99, "total_steps": 156, "loss": 0.6773, "lr": 3.562003362839914e-06, "epoch": 1.89171974522293, "percentage": 63.46, "elapsed_time": "0:19:06", "remaining_time": "0:10:59"}
|
| 100 |
+
{"current_steps": 100, "total_steps": 156, "loss": 0.6369, "lr": 3.4549150281252635e-06, "epoch": 1.910828025477707, "percentage": 64.1, "elapsed_time": "0:19:12", "remaining_time": "0:10:45"}
|
| 101 |
+
{"current_steps": 101, "total_steps": 156, "loss": 0.7553, "lr": 3.3486046902241663e-06, "epoch": 1.929936305732484, "percentage": 64.74, "elapsed_time": "0:19:24", "remaining_time": "0:10:33"}
|
| 102 |
+
{"current_steps": 102, "total_steps": 156, "loss": 0.6749, "lr": 3.2431258795932863e-06, "epoch": 1.9490445859872612, "percentage": 65.38, "elapsed_time": "0:19:31", "remaining_time": "0:10:20"}
|
| 103 |
+
{"current_steps": 103, "total_steps": 156, "loss": 0.6918, "lr": 3.1385317079902743e-06, "epoch": 1.9681528662420382, "percentage": 66.03, "elapsed_time": "0:19:45", "remaining_time": "0:10:10"}
|
| 104 |
+
{"current_steps": 104, "total_steps": 156, "loss": 0.6841, "lr": 3.0348748417303826e-06, "epoch": 1.9872611464968153, "percentage": 66.67, "elapsed_time": "0:19:58", "remaining_time": "0:09:59"}
|
| 105 |
+
{"current_steps": 105, "total_steps": 156, "loss": 1.1013, "lr": 2.932207475167398e-06, "epoch": 2.0063694267515926, "percentage": 67.31, "elapsed_time": "0:20:57", "remaining_time": "0:10:10"}
|
| 106 |
+
{"current_steps": 106, "total_steps": 156, "loss": 0.6537, "lr": 2.83058130441221e-06, "epoch": 2.0254777070063694, "percentage": 67.95, "elapsed_time": "0:21:10", "remaining_time": "0:09:59"}
|
| 107 |
+
{"current_steps": 107, "total_steps": 156, "loss": 0.5645, "lr": 2.7300475013022666e-06, "epoch": 2.0445859872611467, "percentage": 68.59, "elapsed_time": "0:21:18", "remaining_time": "0:09:45"}
|
| 108 |
+
{"current_steps": 108, "total_steps": 156, "loss": 0.5989, "lr": 2.6306566876350072e-06, "epoch": 2.0636942675159236, "percentage": 69.23, "elapsed_time": "0:21:30", "remaining_time": "0:09:33"}
|
| 109 |
+
{"current_steps": 109, "total_steps": 156, "loss": 0.574, "lr": 2.532458909678266e-06, "epoch": 2.082802547770701, "percentage": 69.87, "elapsed_time": "0:21:41", "remaining_time": "0:09:21"}
|
| 110 |
+
{"current_steps": 110, "total_steps": 156, "loss": 0.6267, "lr": 2.43550361297047e-06, "epoch": 2.1019108280254777, "percentage": 70.51, "elapsed_time": "0:21:48", "remaining_time": "0:09:07"}
|
| 111 |
+
{"current_steps": 111, "total_steps": 156, "loss": 0.635, "lr": 2.339839617423318e-06, "epoch": 2.121019108280255, "percentage": 71.15, "elapsed_time": "0:22:01", "remaining_time": "0:08:55"}
|
| 112 |
+
{"current_steps": 112, "total_steps": 156, "loss": 0.6011, "lr": 2.245515092739488e-06, "epoch": 2.140127388535032, "percentage": 71.79, "elapsed_time": "0:22:13", "remaining_time": "0:08:43"}
|
| 113 |
+
{"current_steps": 113, "total_steps": 156, "loss": 0.6377, "lr": 2.1525775341577404e-06, "epoch": 2.159235668789809, "percentage": 72.44, "elapsed_time": "0:22:25", "remaining_time": "0:08:32"}
|
| 114 |
+
{"current_steps": 114, "total_steps": 156, "loss": 0.5621, "lr": 2.061073738537635e-06, "epoch": 2.178343949044586, "percentage": 73.08, "elapsed_time": "0:22:37", "remaining_time": "0:08:20"}
|
| 115 |
+
{"current_steps": 115, "total_steps": 156, "loss": 0.5837, "lr": 1.971049780795901e-06, "epoch": 2.1974522292993632, "percentage": 73.72, "elapsed_time": "0:22:45", "remaining_time": "0:08:06"}
|
| 116 |
+
{"current_steps": 116, "total_steps": 156, "loss": 0.5976, "lr": 1.8825509907063328e-06, "epoch": 2.21656050955414, "percentage": 74.36, "elapsed_time": "0:22:53", "remaining_time": "0:07:53"}
|
| 117 |
+
{"current_steps": 117, "total_steps": 156, "loss": 0.6231, "lr": 1.7956219300748796e-06, "epoch": 2.2356687898089174, "percentage": 75.0, "elapsed_time": "0:23:05", "remaining_time": "0:07:41"}
|
| 118 |
+
{"current_steps": 118, "total_steps": 156, "loss": 0.5705, "lr": 1.7103063703014372e-06, "epoch": 2.254777070063694, "percentage": 75.64, "elapsed_time": "0:23:16", "remaining_time": "0:07:29"}
|
| 119 |
+
{"current_steps": 119, "total_steps": 156, "loss": 0.6073, "lr": 1.6266472703396286e-06, "epoch": 2.2738853503184715, "percentage": 76.28, "elapsed_time": "0:23:26", "remaining_time": "0:07:17"}
|
| 120 |
+
{"current_steps": 120, "total_steps": 156, "loss": 0.6255, "lr": 1.544686755065677e-06, "epoch": 2.2929936305732483, "percentage": 76.92, "elapsed_time": "0:23:34", "remaining_time": "0:07:04"}
|
| 121 |
+
{"current_steps": 121, "total_steps": 156, "loss": 0.5905, "lr": 1.4644660940672628e-06, "epoch": 2.3121019108280256, "percentage": 77.56, "elapsed_time": "0:23:41", "remaining_time": "0:06:51"}
|