Training in progress, epoch 4
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 sha256:5d3c8732bfc72aa06cf084eafb5bc3313b98932f84a16a0c406e014835a864a8
|
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:cc06365135e70534f05efcca40d89f223f291ca488185ee26bba9c80a11ecd60
|
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 sha256:775a07dc81da03f415b9832dcaf7df477e349e22a3559ec3814af94ba907f5aa
|
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:ae3cc0b5397c442806b704ad576876c1001907ff15f6be1122ad2423856fa0a5
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -106,3 +106,36 @@
|
|
106 |
{"current_steps": 106, "total_steps": 231, "loss": 0.1865, "lr": 1.3205411116710973e-05, "epoch": 3.212121212121212, "percentage": 45.89, "elapsed_time": "0:39:06", "remaining_time": "0:46:07"}
|
107 |
{"current_steps": 107, "total_steps": 231, "loss": 0.196, "lr": 1.3061287809011243e-05, "epoch": 3.242424242424242, "percentage": 46.32, "elapsed_time": "0:39:28", "remaining_time": "0:45:44"}
|
108 |
{"current_steps": 108, "total_steps": 231, "loss": 0.2, "lr": 1.291645939454825e-05, "epoch": 3.2727272727272725, "percentage": 46.75, "elapsed_time": "0:39:41", "remaining_time": "0:45:12"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
106 |
{"current_steps": 106, "total_steps": 231, "loss": 0.1865, "lr": 1.3205411116710973e-05, "epoch": 3.212121212121212, "percentage": 45.89, "elapsed_time": "0:39:06", "remaining_time": "0:46:07"}
|
107 |
{"current_steps": 107, "total_steps": 231, "loss": 0.196, "lr": 1.3061287809011243e-05, "epoch": 3.242424242424242, "percentage": 46.32, "elapsed_time": "0:39:28", "remaining_time": "0:45:44"}
|
108 |
{"current_steps": 108, "total_steps": 231, "loss": 0.2, "lr": 1.291645939454825e-05, "epoch": 3.2727272727272725, "percentage": 46.75, "elapsed_time": "0:39:41", "remaining_time": "0:45:12"}
|
109 |
+
{"current_steps": 109, "total_steps": 231, "loss": 0.1913, "lr": 1.277095923166689e-05, "epoch": 3.303030303030303, "percentage": 47.19, "elapsed_time": "0:40:01", "remaining_time": "0:44:47"}
|
110 |
+
{"current_steps": 110, "total_steps": 231, "loss": 0.1795, "lr": 1.2624820833435939e-05, "epoch": 3.3333333333333335, "percentage": 47.62, "elapsed_time": "0:40:19", "remaining_time": "0:44:21"}
|
111 |
+
{"current_steps": 111, "total_steps": 231, "loss": 0.2025, "lr": 1.2478077859929e-05, "epoch": 3.3636363636363638, "percentage": 48.05, "elapsed_time": "0:40:38", "remaining_time": "0:43:55"}
|
112 |
+
{"current_steps": 112, "total_steps": 231, "loss": 0.1864, "lr": 1.2330764110471567e-05, "epoch": 3.393939393939394, "percentage": 48.48, "elapsed_time": "0:40:57", "remaining_time": "0:43:30"}
|
113 |
+
{"current_steps": 113, "total_steps": 231, "loss": 0.2132, "lr": 1.2182913515856016e-05, "epoch": 3.4242424242424243, "percentage": 48.92, "elapsed_time": "0:41:19", "remaining_time": "0:43:09"}
|
114 |
+
{"current_steps": 114, "total_steps": 231, "loss": 0.1869, "lr": 1.2034560130526341e-05, "epoch": 3.4545454545454546, "percentage": 49.35, "elapsed_time": "0:41:39", "remaining_time": "0:42:44"}
|
115 |
+
{"current_steps": 115, "total_steps": 231, "loss": 0.2048, "lr": 1.1885738124734359e-05, "epoch": 3.484848484848485, "percentage": 49.78, "elapsed_time": "0:41:59", "remaining_time": "0:42:21"}
|
116 |
+
{"current_steps": 116, "total_steps": 231, "loss": 0.1764, "lr": 1.1736481776669307e-05, "epoch": 3.515151515151515, "percentage": 50.22, "elapsed_time": "0:42:16", "remaining_time": "0:41:54"}
|
117 |
+
{"current_steps": 117, "total_steps": 231, "loss": 0.1923, "lr": 1.1586825464562515e-05, "epoch": 3.5454545454545454, "percentage": 50.65, "elapsed_time": "0:42:34", "remaining_time": "0:41:29"}
|
118 |
+
{"current_steps": 118, "total_steps": 231, "loss": 0.2146, "lr": 1.1436803658769082e-05, "epoch": 3.5757575757575757, "percentage": 51.08, "elapsed_time": "0:42:54", "remaining_time": "0:41:05"}
|
119 |
+
{"current_steps": 119, "total_steps": 231, "loss": 0.1865, "lr": 1.1286450913828313e-05, "epoch": 3.606060606060606, "percentage": 51.52, "elapsed_time": "0:43:12", "remaining_time": "0:40:40"}
|
120 |
+
{"current_steps": 120, "total_steps": 231, "loss": 0.1683, "lr": 1.113580186050475e-05, "epoch": 3.6363636363636362, "percentage": 51.95, "elapsed_time": "0:43:31", "remaining_time": "0:40:15"}
|
121 |
+
{"current_steps": 121, "total_steps": 231, "loss": 0.1964, "lr": 1.0984891197811686e-05, "epoch": 3.6666666666666665, "percentage": 52.38, "elapsed_time": "0:43:53", "remaining_time": "0:39:53"}
|
122 |
+
{"current_steps": 122, "total_steps": 231, "loss": 0.1801, "lr": 1.0833753685018935e-05, "epoch": 3.6969696969696972, "percentage": 52.81, "elapsed_time": "0:44:14", "remaining_time": "0:39:31"}
|
123 |
+
{"current_steps": 123, "total_steps": 231, "loss": 0.194, "lr": 1.0682424133646712e-05, "epoch": 3.7272727272727275, "percentage": 53.25, "elapsed_time": "0:44:31", "remaining_time": "0:39:06"}
|
124 |
+
{"current_steps": 124, "total_steps": 231, "loss": 0.2023, "lr": 1.0530937399447496e-05, "epoch": 3.757575757575758, "percentage": 53.68, "elapsed_time": "0:44:49", "remaining_time": "0:38:40"}
|
125 |
+
{"current_steps": 125, "total_steps": 231, "loss": 0.1875, "lr": 1.0379328374377715e-05, "epoch": 3.787878787878788, "percentage": 54.11, "elapsed_time": "0:45:09", "remaining_time": "0:38:17"}
|
126 |
+
{"current_steps": 126, "total_steps": 231, "loss": 0.1871, "lr": 1.0227631978561057e-05, "epoch": 3.8181818181818183, "percentage": 54.55, "elapsed_time": "0:45:28", "remaining_time": "0:37:53"}
|
127 |
+
{"current_steps": 127, "total_steps": 231, "loss": 0.1965, "lr": 1.0075883152245334e-05, "epoch": 3.8484848484848486, "percentage": 54.98, "elapsed_time": "0:45:47", "remaining_time": "0:37:30"}
|
128 |
+
{"current_steps": 128, "total_steps": 231, "loss": 0.175, "lr": 9.92411684775467e-06, "epoch": 3.878787878787879, "percentage": 55.41, "elapsed_time": "0:46:03", "remaining_time": "0:37:03"}
|
129 |
+
{"current_steps": 129, "total_steps": 231, "loss": 0.1948, "lr": 9.772368021438943e-06, "epoch": 3.909090909090909, "percentage": 55.84, "elapsed_time": "0:46:25", "remaining_time": "0:36:42"}
|
130 |
+
{"current_steps": 130, "total_steps": 231, "loss": 0.1834, "lr": 9.620671625622287e-06, "epoch": 3.9393939393939394, "percentage": 56.28, "elapsed_time": "0:46:40", "remaining_time": "0:36:15"}
|
131 |
+
{"current_steps": 131, "total_steps": 231, "loss": 0.1738, "lr": 9.469062600552509e-06, "epoch": 3.9696969696969697, "percentage": 56.71, "elapsed_time": "0:46:55", "remaining_time": "0:35:49"}
|
132 |
+
{"current_steps": 132, "total_steps": 231, "loss": 0.1941, "lr": 9.317575866353293e-06, "epoch": 4.0, "percentage": 57.14, "elapsed_time": "0:47:16", "remaining_time": "0:35:27"}
|
133 |
+
{"current_steps": 133, "total_steps": 231, "loss": 0.1367, "lr": 9.166246314981066e-06, "epoch": 4.03030303030303, "percentage": 57.58, "elapsed_time": "0:49:22", "remaining_time": "0:36:23"}
|
134 |
+
{"current_steps": 134, "total_steps": 231, "loss": 0.1309, "lr": 9.015108802188314e-06, "epoch": 4.0606060606060606, "percentage": 58.01, "elapsed_time": "0:49:42", "remaining_time": "0:35:58"}
|
135 |
+
{"current_steps": 135, "total_steps": 231, "loss": 0.149, "lr": 8.86419813949525e-06, "epoch": 4.090909090909091, "percentage": 58.44, "elapsed_time": "0:50:02", "remaining_time": "0:35:34"}
|
136 |
+
{"current_steps": 136, "total_steps": 231, "loss": 0.1533, "lr": 8.71354908617169e-06, "epoch": 4.121212121212121, "percentage": 58.87, "elapsed_time": "0:50:16", "remaining_time": "0:35:07"}
|
137 |
+
{"current_steps": 137, "total_steps": 231, "loss": 0.1437, "lr": 8.56319634123092e-06, "epoch": 4.151515151515151, "percentage": 59.31, "elapsed_time": "0:50:38", "remaining_time": "0:34:44"}
|
138 |
+
{"current_steps": 138, "total_steps": 231, "loss": 0.1489, "lr": 8.413174535437486e-06, "epoch": 4.181818181818182, "percentage": 59.74, "elapsed_time": "0:50:54", "remaining_time": "0:34:18"}
|
139 |
+
{"current_steps": 139, "total_steps": 231, "loss": 0.1261, "lr": 8.263518223330698e-06, "epoch": 4.212121212121212, "percentage": 60.17, "elapsed_time": "0:51:12", "remaining_time": "0:33:53"}
|
140 |
+
{"current_steps": 140, "total_steps": 231, "loss": 0.1255, "lr": 8.114261875265643e-06, "epoch": 4.242424242424242, "percentage": 60.61, "elapsed_time": "0:51:29", "remaining_time": "0:33:28"}
|
141 |
+
{"current_steps": 141, "total_steps": 231, "loss": 0.1543, "lr": 7.965439869473664e-06, "epoch": 4.2727272727272725, "percentage": 61.04, "elapsed_time": "0:51:48", "remaining_time": "0:33:04"}
|