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 sha256:23e1febe08632b91f6577f6eee889397e3f5291bb21995418b7c9c89ae4e9302
|
| 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 sha256:16c3ab5e9d7eaff3c6b55a511752416294e3557448da4c6278d81951efc2e00f
|
| 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:f9946600f7020c757ce53f636916ad5ff6fee20c29449d7d1439f50791ab6bf1
|
| 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 sha256:53bb995d017074067b5a5457d68704a5c4b0972d98265bacd50d695e1d64441c
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -67,3 +67,55 @@
|
|
| 67 |
{"current_steps": 67, "total_steps": 156, "loss": 0.7498, "lr": 7.067792524832604e-06, "epoch": 1.2802547770700636, "percentage": 42.95, "elapsed_time": "0:13:04", "remaining_time": "0:17:21"}
|
| 68 |
{"current_steps": 68, "total_steps": 156, "loss": 0.6954, "lr": 6.965125158269619e-06, "epoch": 1.2993630573248407, "percentage": 43.59, "elapsed_time": "0:13:13", "remaining_time": "0:17:06"}
|
| 69 |
{"current_steps": 69, "total_steps": 156, "loss": 0.756, "lr": 6.8614682920097265e-06, "epoch": 1.3184713375796178, "percentage": 44.23, "elapsed_time": "0:13:24", "remaining_time": "0:16:53"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
{"current_steps": 67, "total_steps": 156, "loss": 0.7498, "lr": 7.067792524832604e-06, "epoch": 1.2802547770700636, "percentage": 42.95, "elapsed_time": "0:13:04", "remaining_time": "0:17:21"}
|
| 68 |
{"current_steps": 68, "total_steps": 156, "loss": 0.6954, "lr": 6.965125158269619e-06, "epoch": 1.2993630573248407, "percentage": 43.59, "elapsed_time": "0:13:13", "remaining_time": "0:17:06"}
|
| 69 |
{"current_steps": 69, "total_steps": 156, "loss": 0.756, "lr": 6.8614682920097265e-06, "epoch": 1.3184713375796178, "percentage": 44.23, "elapsed_time": "0:13:24", "remaining_time": "0:16:53"}
|
| 70 |
+
{"current_steps": 70, "total_steps": 156, "loss": 0.681, "lr": 6.7568741204067145e-06, "epoch": 1.3375796178343948, "percentage": 44.87, "elapsed_time": "0:13:43", "remaining_time": "0:16:51"}
|
| 71 |
+
{"current_steps": 71, "total_steps": 156, "loss": 0.725, "lr": 6.651395309775837e-06, "epoch": 1.356687898089172, "percentage": 45.51, "elapsed_time": "0:13:54", "remaining_time": "0:16:38"}
|
| 72 |
+
{"current_steps": 72, "total_steps": 156, "loss": 0.6893, "lr": 6.545084971874738e-06, "epoch": 1.3757961783439492, "percentage": 46.15, "elapsed_time": "0:14:06", "remaining_time": "0:16:27"}
|
| 73 |
+
{"current_steps": 73, "total_steps": 156, "loss": 0.709, "lr": 6.437996637160086e-06, "epoch": 1.394904458598726, "percentage": 46.79, "elapsed_time": "0:14:18", "remaining_time": "0:16:16"}
|
| 74 |
+
{"current_steps": 74, "total_steps": 156, "loss": 0.6778, "lr": 6.330184227833376e-06, "epoch": 1.4140127388535033, "percentage": 47.44, "elapsed_time": "0:14:31", "remaining_time": "0:16:05"}
|
| 75 |
+
{"current_steps": 75, "total_steps": 156, "loss": 0.6839, "lr": 6.2217020306894705e-06, "epoch": 1.4331210191082802, "percentage": 48.08, "elapsed_time": "0:14:40", "remaining_time": "0:15:50"}
|
| 76 |
+
{"current_steps": 76, "total_steps": 156, "loss": 0.7109, "lr": 6.112604669781572e-06, "epoch": 1.4522292993630574, "percentage": 48.72, "elapsed_time": "0:15:05", "remaining_time": "0:15:53"}
|
| 77 |
+
{"current_steps": 77, "total_steps": 156, "loss": 0.7523, "lr": 6.002947078916365e-06, "epoch": 1.4713375796178343, "percentage": 49.36, "elapsed_time": "0:15:16", "remaining_time": "0:15:40"}
|
| 78 |
+
{"current_steps": 78, "total_steps": 156, "loss": 0.6795, "lr": 5.892784473993184e-06, "epoch": 1.4904458598726116, "percentage": 50.0, "elapsed_time": "0:15:23", "remaining_time": "0:15:23"}
|
| 79 |
+
{"current_steps": 79, "total_steps": 156, "loss": 0.666, "lr": 5.782172325201155e-06, "epoch": 1.5095541401273884, "percentage": 50.64, "elapsed_time": "0:15:31", "remaining_time": "0:15:08"}
|
| 80 |
+
{"current_steps": 80, "total_steps": 156, "loss": 0.701, "lr": 5.671166329088278e-06, "epoch": 1.5286624203821657, "percentage": 51.28, "elapsed_time": "0:15:44", "remaining_time": "0:14:56"}
|
| 81 |
+
{"current_steps": 81, "total_steps": 156, "loss": 0.7023, "lr": 5.559822380516539e-06, "epoch": 1.5477707006369426, "percentage": 51.92, "elapsed_time": "0:15:50", "remaining_time": "0:14:39"}
|
| 82 |
+
{"current_steps": 82, "total_steps": 156, "loss": 0.7271, "lr": 5.448196544517168e-06, "epoch": 1.5668789808917198, "percentage": 52.56, "elapsed_time": "0:15:59", "remaining_time": "0:14:25"}
|
| 83 |
+
{"current_steps": 83, "total_steps": 156, "loss": 0.7432, "lr": 5.336345028060199e-06, "epoch": 1.5859872611464967, "percentage": 53.21, "elapsed_time": "0:16:11", "remaining_time": "0:14:14"}
|
| 84 |
+
{"current_steps": 84, "total_steps": 156, "loss": 0.7103, "lr": 5.224324151752575e-06, "epoch": 1.605095541401274, "percentage": 53.85, "elapsed_time": "0:16:25", "remaining_time": "0:14:04"}
|
| 85 |
+
{"current_steps": 85, "total_steps": 156, "loss": 0.7116, "lr": 5.112190321479026e-06, "epoch": 1.6242038216560508, "percentage": 54.49, "elapsed_time": "0:16:32", "remaining_time": "0:13:49"}
|
| 86 |
+
{"current_steps": 86, "total_steps": 156, "loss": 0.6722, "lr": 5e-06, "epoch": 1.643312101910828, "percentage": 55.13, "elapsed_time": "0:16:43", "remaining_time": "0:13:36"}
|
| 87 |
+
{"current_steps": 87, "total_steps": 156, "loss": 0.7636, "lr": 4.887809678520976e-06, "epoch": 1.662420382165605, "percentage": 55.77, "elapsed_time": "0:16:51", "remaining_time": "0:13:22"}
|
| 88 |
+
{"current_steps": 88, "total_steps": 156, "loss": 0.7164, "lr": 4.775675848247427e-06, "epoch": 1.6815286624203822, "percentage": 56.41, "elapsed_time": "0:17:03", "remaining_time": "0:13:10"}
|
| 89 |
+
{"current_steps": 89, "total_steps": 156, "loss": 0.6914, "lr": 4.663654971939802e-06, "epoch": 1.700636942675159, "percentage": 57.05, "elapsed_time": "0:17:10", "remaining_time": "0:12:55"}
|
| 90 |
+
{"current_steps": 90, "total_steps": 156, "loss": 0.7241, "lr": 4.551803455482833e-06, "epoch": 1.7197452229299364, "percentage": 57.69, "elapsed_time": "0:17:20", "remaining_time": "0:12:43"}
|
| 91 |
+
{"current_steps": 91, "total_steps": 156, "loss": 0.7143, "lr": 4.4401776194834615e-06, "epoch": 1.7388535031847132, "percentage": 58.33, "elapsed_time": "0:17:30", "remaining_time": "0:12:30"}
|
| 92 |
+
{"current_steps": 92, "total_steps": 156, "loss": 0.7519, "lr": 4.3288336709117246e-06, "epoch": 1.7579617834394905, "percentage": 58.97, "elapsed_time": "0:17:40", "remaining_time": "0:12:17"}
|
| 93 |
+
{"current_steps": 93, "total_steps": 156, "loss": 0.689, "lr": 4.217827674798845e-06, "epoch": 1.7770700636942676, "percentage": 59.62, "elapsed_time": "0:17:49", "remaining_time": "0:12:04"}
|
| 94 |
+
{"current_steps": 94, "total_steps": 156, "loss": 0.6654, "lr": 4.107215526006818e-06, "epoch": 1.7961783439490446, "percentage": 60.26, "elapsed_time": "0:17:59", "remaining_time": "0:11:51"}
|
| 95 |
+
{"current_steps": 95, "total_steps": 156, "loss": 0.7507, "lr": 3.997052921083637e-06, "epoch": 1.8152866242038217, "percentage": 60.9, "elapsed_time": "0:18:09", "remaining_time": "0:11:39"}
|
| 96 |
+
{"current_steps": 96, "total_steps": 156, "loss": 0.7146, "lr": 3.887395330218429e-06, "epoch": 1.8343949044585988, "percentage": 61.54, "elapsed_time": "0:18:20", "remaining_time": "0:11:27"}
|
| 97 |
+
{"current_steps": 97, "total_steps": 156, "loss": 0.7085, "lr": 3.778297969310529e-06, "epoch": 1.8535031847133758, "percentage": 62.18, "elapsed_time": "0:18:30", "remaining_time": "0:11:15"}
|
| 98 |
+
{"current_steps": 98, "total_steps": 156, "loss": 0.7262, "lr": 3.669815772166625e-06, "epoch": 1.872611464968153, "percentage": 62.82, "elapsed_time": "0:18:38", "remaining_time": "0:11:02"}
|
| 99 |
+
{"current_steps": 99, "total_steps": 156, "loss": 0.691, "lr": 3.562003362839914e-06, "epoch": 1.89171974522293, "percentage": 63.46, "elapsed_time": "0:18:49", "remaining_time": "0:10:50"}
|
| 100 |
+
{"current_steps": 100, "total_steps": 156, "loss": 0.6462, "lr": 3.4549150281252635e-06, "epoch": 1.910828025477707, "percentage": 64.1, "elapsed_time": "0:18:56", "remaining_time": "0:10:36"}
|
| 101 |
+
{"current_steps": 101, "total_steps": 156, "loss": 0.7647, "lr": 3.3486046902241663e-06, "epoch": 1.929936305732484, "percentage": 64.74, "elapsed_time": "0:19:06", "remaining_time": "0:10:24"}
|
| 102 |
+
{"current_steps": 102, "total_steps": 156, "loss": 0.6822, "lr": 3.2431258795932863e-06, "epoch": 1.9490445859872612, "percentage": 65.38, "elapsed_time": "0:19:14", "remaining_time": "0:10:10"}
|
| 103 |
+
{"current_steps": 103, "total_steps": 156, "loss": 0.7024, "lr": 3.1385317079902743e-06, "epoch": 1.9681528662420382, "percentage": 66.03, "elapsed_time": "0:19:28", "remaining_time": "0:10:01"}
|
| 104 |
+
{"current_steps": 104, "total_steps": 156, "loss": 0.6904, "lr": 3.0348748417303826e-06, "epoch": 1.9872611464968153, "percentage": 66.67, "elapsed_time": "0:19:39", "remaining_time": "0:09:49"}
|
| 105 |
+
{"current_steps": 105, "total_steps": 156, "loss": 1.1124, "lr": 2.932207475167398e-06, "epoch": 2.0063694267515926, "percentage": 67.31, "elapsed_time": "0:20:39", "remaining_time": "0:10:01"}
|
| 106 |
+
{"current_steps": 106, "total_steps": 156, "loss": 0.6577, "lr": 2.83058130441221e-06, "epoch": 2.0254777070063694, "percentage": 67.95, "elapsed_time": "0:20:51", "remaining_time": "0:09:50"}
|
| 107 |
+
{"current_steps": 107, "total_steps": 156, "loss": 0.5686, "lr": 2.7300475013022666e-06, "epoch": 2.0445859872611467, "percentage": 68.59, "elapsed_time": "0:20:59", "remaining_time": "0:09:36"}
|
| 108 |
+
{"current_steps": 108, "total_steps": 156, "loss": 0.6029, "lr": 2.6306566876350072e-06, "epoch": 2.0636942675159236, "percentage": 69.23, "elapsed_time": "0:21:10", "remaining_time": "0:09:24"}
|
| 109 |
+
{"current_steps": 109, "total_steps": 156, "loss": 0.5759, "lr": 2.532458909678266e-06, "epoch": 2.082802547770701, "percentage": 69.87, "elapsed_time": "0:21:19", "remaining_time": "0:09:11"}
|
| 110 |
+
{"current_steps": 110, "total_steps": 156, "loss": 0.6313, "lr": 2.43550361297047e-06, "epoch": 2.1019108280254777, "percentage": 70.51, "elapsed_time": "0:21:27", "remaining_time": "0:08:58"}
|
| 111 |
+
{"current_steps": 111, "total_steps": 156, "loss": 0.642, "lr": 2.339839617423318e-06, "epoch": 2.121019108280255, "percentage": 71.15, "elapsed_time": "0:21:40", "remaining_time": "0:08:47"}
|
| 112 |
+
{"current_steps": 112, "total_steps": 156, "loss": 0.6071, "lr": 2.245515092739488e-06, "epoch": 2.140127388535032, "percentage": 71.79, "elapsed_time": "0:21:51", "remaining_time": "0:08:35"}
|
| 113 |
+
{"current_steps": 113, "total_steps": 156, "loss": 0.6389, "lr": 2.1525775341577404e-06, "epoch": 2.159235668789809, "percentage": 72.44, "elapsed_time": "0:22:03", "remaining_time": "0:08:23"}
|
| 114 |
+
{"current_steps": 114, "total_steps": 156, "loss": 0.5686, "lr": 2.061073738537635e-06, "epoch": 2.178343949044586, "percentage": 73.08, "elapsed_time": "0:22:14", "remaining_time": "0:08:11"}
|
| 115 |
+
{"current_steps": 115, "total_steps": 156, "loss": 0.5922, "lr": 1.971049780795901e-06, "epoch": 2.1974522292993632, "percentage": 73.72, "elapsed_time": "0:22:23", "remaining_time": "0:07:58"}
|
| 116 |
+
{"current_steps": 116, "total_steps": 156, "loss": 0.6002, "lr": 1.8825509907063328e-06, "epoch": 2.21656050955414, "percentage": 74.36, "elapsed_time": "0:22:30", "remaining_time": "0:07:45"}
|
| 117 |
+
{"current_steps": 117, "total_steps": 156, "loss": 0.6249, "lr": 1.7956219300748796e-06, "epoch": 2.2356687898089174, "percentage": 75.0, "elapsed_time": "0:22:42", "remaining_time": "0:07:34"}
|
| 118 |
+
{"current_steps": 118, "total_steps": 156, "loss": 0.5775, "lr": 1.7103063703014372e-06, "epoch": 2.254777070063694, "percentage": 75.64, "elapsed_time": "0:22:53", "remaining_time": "0:07:22"}
|
| 119 |
+
{"current_steps": 119, "total_steps": 156, "loss": 0.6113, "lr": 1.6266472703396286e-06, "epoch": 2.2738853503184715, "percentage": 76.28, "elapsed_time": "0:23:03", "remaining_time": "0:07:10"}
|
| 120 |
+
{"current_steps": 120, "total_steps": 156, "loss": 0.6283, "lr": 1.544686755065677e-06, "epoch": 2.2929936305732483, "percentage": 76.92, "elapsed_time": "0:23:11", "remaining_time": "0:06:57"}
|
| 121 |
+
{"current_steps": 121, "total_steps": 156, "loss": 0.5991, "lr": 1.4644660940672628e-06, "epoch": 2.3121019108280256, "percentage": 77.56, "elapsed_time": "0:23:18", "remaining_time": "0:06:44"}
|