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:f2c324e9b9e5083cc9d657c7195548efc3ffffa90102d799bafc308124061a46
|
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 sha256:69266cd3449678b1bb113375e3e8f36930ee451a384e20cc3a269e17903b23c0
|
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:c5b327fca2ce86cfad98b54282a1ce3e5a3dc2b8eefac3f57ae60c82095e5b51
|
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 sha256:12f10edce9749c45868c0d146d7982a041d4f49711d63cfcebffd6c62cf5d4fe
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -62,3 +62,55 @@
|
|
62 |
{"current_steps": 62, "total_steps": 364, "loss": 0.2587, "lr": 1.9712944769464862e-07, "epoch": 1.1847133757961783, "percentage": 17.03, "elapsed_time": "0:15:28", "remaining_time": "1:15:20"}
|
63 |
{"current_steps": 63, "total_steps": 364, "loss": 0.2538, "lr": 1.9689642954609806e-07, "epoch": 1.2038216560509554, "percentage": 17.31, "elapsed_time": "0:15:40", "remaining_time": "1:14:51"}
|
64 |
{"current_steps": 64, "total_steps": 364, "loss": 0.2527, "lr": 1.966544678736044e-07, "epoch": 1.2229299363057324, "percentage": 17.58, "elapsed_time": "0:15:52", "remaining_time": "1:14:23"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
62 |
{"current_steps": 62, "total_steps": 364, "loss": 0.2587, "lr": 1.9712944769464862e-07, "epoch": 1.1847133757961783, "percentage": 17.03, "elapsed_time": "0:15:28", "remaining_time": "1:15:20"}
|
63 |
{"current_steps": 63, "total_steps": 364, "loss": 0.2538, "lr": 1.9689642954609806e-07, "epoch": 1.2038216560509554, "percentage": 17.31, "elapsed_time": "0:15:40", "remaining_time": "1:14:51"}
|
64 |
{"current_steps": 64, "total_steps": 364, "loss": 0.2527, "lr": 1.966544678736044e-07, "epoch": 1.2229299363057324, "percentage": 17.58, "elapsed_time": "0:15:52", "remaining_time": "1:14:23"}
|
65 |
+
{"current_steps": 65, "total_steps": 364, "loss": 0.2479, "lr": 1.9640358501018882e-07, "epoch": 1.2420382165605095, "percentage": 17.86, "elapsed_time": "0:16:05", "remaining_time": "1:14:00"}
|
66 |
+
{"current_steps": 66, "total_steps": 364, "loss": 0.2482, "lr": 1.961438041122969e-07, "epoch": 1.2611464968152866, "percentage": 18.13, "elapsed_time": "0:16:17", "remaining_time": "1:13:35"}
|
67 |
+
{"current_steps": 67, "total_steps": 364, "loss": 0.253, "lr": 1.9587514915766122e-07, "epoch": 1.2802547770700636, "percentage": 18.41, "elapsed_time": "0:16:31", "remaining_time": "1:13:15"}
|
68 |
+
{"current_steps": 68, "total_steps": 364, "loss": 0.2457, "lr": 1.9559764494308834e-07, "epoch": 1.2993630573248407, "percentage": 18.68, "elapsed_time": "0:16:42", "remaining_time": "1:12:44"}
|
69 |
+
{"current_steps": 69, "total_steps": 364, "loss": 0.2554, "lr": 1.9531131708217004e-07, "epoch": 1.3184713375796178, "percentage": 18.96, "elapsed_time": "0:16:54", "remaining_time": "1:12:19"}
|
70 |
+
{"current_steps": 70, "total_steps": 364, "loss": 0.2561, "lr": 1.9501619200291905e-07, "epoch": 1.3375796178343948, "percentage": 19.23, "elapsed_time": "0:17:07", "remaining_time": "1:11:54"}
|
71 |
+
{"current_steps": 71, "total_steps": 364, "loss": 0.264, "lr": 1.9471229694533e-07, "epoch": 1.356687898089172, "percentage": 19.51, "elapsed_time": "0:17:21", "remaining_time": "1:11:37"}
|
72 |
+
{"current_steps": 72, "total_steps": 364, "loss": 0.2579, "lr": 1.9439965995886488e-07, "epoch": 1.3757961783439492, "percentage": 19.78, "elapsed_time": "0:17:35", "remaining_time": "1:11:19"}
|
73 |
+
{"current_steps": 73, "total_steps": 364, "loss": 0.2515, "lr": 1.9407830989986428e-07, "epoch": 1.394904458598726, "percentage": 20.05, "elapsed_time": "0:17:48", "remaining_time": "1:11:00"}
|
74 |
+
{"current_steps": 74, "total_steps": 364, "loss": 0.2592, "lr": 1.9374827642888395e-07, "epoch": 1.4140127388535033, "percentage": 20.33, "elapsed_time": "0:18:01", "remaining_time": "1:10:40"}
|
75 |
+
{"current_steps": 75, "total_steps": 364, "loss": 0.2559, "lr": 1.9340959000795706e-07, "epoch": 1.4331210191082802, "percentage": 20.6, "elapsed_time": "0:18:16", "remaining_time": "1:10:25"}
|
76 |
+
{"current_steps": 76, "total_steps": 364, "loss": 0.2658, "lr": 1.9306228189778253e-07, "epoch": 1.4522292993630574, "percentage": 20.88, "elapsed_time": "0:18:31", "remaining_time": "1:10:10"}
|
77 |
+
{"current_steps": 77, "total_steps": 364, "loss": 0.2646, "lr": 1.927063841548398e-07, "epoch": 1.4713375796178343, "percentage": 21.15, "elapsed_time": "0:18:42", "remaining_time": "1:09:44"}
|
78 |
+
{"current_steps": 78, "total_steps": 364, "loss": 0.2581, "lr": 1.923419296284299e-07, "epoch": 1.4904458598726116, "percentage": 21.43, "elapsed_time": "0:18:54", "remaining_time": "1:09:20"}
|
79 |
+
{"current_steps": 79, "total_steps": 364, "loss": 0.2567, "lr": 1.919689519576436e-07, "epoch": 1.5095541401273884, "percentage": 21.7, "elapsed_time": "0:19:05", "remaining_time": "1:08:52"}
|
80 |
+
{"current_steps": 80, "total_steps": 364, "loss": 0.253, "lr": 1.9158748556825634e-07, "epoch": 1.5286624203821657, "percentage": 21.98, "elapsed_time": "0:19:19", "remaining_time": "1:08:36"}
|
81 |
+
{"current_steps": 81, "total_steps": 364, "loss": 0.2584, "lr": 1.911975656695509e-07, "epoch": 1.5477707006369426, "percentage": 22.25, "elapsed_time": "0:19:30", "remaining_time": "1:08:10"}
|
82 |
+
{"current_steps": 82, "total_steps": 364, "loss": 0.2605, "lr": 1.907992282510675e-07, "epoch": 1.5668789808917198, "percentage": 22.53, "elapsed_time": "0:19:45", "remaining_time": "1:07:58"}
|
83 |
+
{"current_steps": 83, "total_steps": 364, "loss": 0.2548, "lr": 1.90392510079282e-07, "epoch": 1.5859872611464967, "percentage": 22.8, "elapsed_time": "0:19:59", "remaining_time": "1:07:39"}
|
84 |
+
{"current_steps": 84, "total_steps": 364, "loss": 0.2354, "lr": 1.8997744869421245e-07, "epoch": 1.605095541401274, "percentage": 23.08, "elapsed_time": "0:20:07", "remaining_time": "1:07:04"}
|
85 |
+
{"current_steps": 85, "total_steps": 364, "loss": 0.2441, "lr": 1.8955408240595392e-07, "epoch": 1.6242038216560508, "percentage": 23.35, "elapsed_time": "0:20:23", "remaining_time": "1:06:56"}
|
86 |
+
{"current_steps": 86, "total_steps": 364, "loss": 0.2503, "lr": 1.8912245029114278e-07, "epoch": 1.643312101910828, "percentage": 23.63, "elapsed_time": "0:20:39", "remaining_time": "1:06:46"}
|
87 |
+
{"current_steps": 87, "total_steps": 364, "loss": 0.2529, "lr": 1.8868259218934966e-07, "epoch": 1.662420382165605, "percentage": 23.9, "elapsed_time": "0:20:53", "remaining_time": "1:06:32"}
|
88 |
+
{"current_steps": 88, "total_steps": 364, "loss": 0.2492, "lr": 1.882345486994024e-07, "epoch": 1.6815286624203822, "percentage": 24.18, "elapsed_time": "0:21:09", "remaining_time": "1:06:21"}
|
89 |
+
{"current_steps": 89, "total_steps": 364, "loss": 0.2657, "lr": 1.877783611756389e-07, "epoch": 1.700636942675159, "percentage": 24.45, "elapsed_time": "0:21:22", "remaining_time": "1:06:03"}
|
90 |
+
{"current_steps": 90, "total_steps": 364, "loss": 0.2503, "lr": 1.8731407172408987e-07, "epoch": 1.7197452229299364, "percentage": 24.73, "elapsed_time": "0:21:36", "remaining_time": "1:05:48"}
|
91 |
+
{"current_steps": 91, "total_steps": 364, "loss": 0.2553, "lr": 1.8684172319859257e-07, "epoch": 1.7388535031847132, "percentage": 25.0, "elapsed_time": "0:21:50", "remaining_time": "1:05:31"}
|
92 |
+
{"current_steps": 92, "total_steps": 364, "loss": 0.2572, "lr": 1.863613591968355e-07, "epoch": 1.7579617834394905, "percentage": 25.27, "elapsed_time": "0:22:03", "remaining_time": "1:05:13"}
|
93 |
+
{"current_steps": 93, "total_steps": 364, "loss": 0.2527, "lr": 1.8587302405633417e-07, "epoch": 1.7770700636942676, "percentage": 25.55, "elapsed_time": "0:22:17", "remaining_time": "1:04:56"}
|
94 |
+
{"current_steps": 94, "total_steps": 364, "loss": 0.2595, "lr": 1.8537676285033885e-07, "epoch": 1.7961783439490446, "percentage": 25.82, "elapsed_time": "0:22:31", "remaining_time": "1:04:42"}
|
95 |
+
{"current_steps": 95, "total_steps": 364, "loss": 0.2577, "lr": 1.848726213836744e-07, "epoch": 1.8152866242038217, "percentage": 26.1, "elapsed_time": "0:22:46", "remaining_time": "1:04:29"}
|
96 |
+
{"current_steps": 96, "total_steps": 364, "loss": 0.2521, "lr": 1.8436064618851224e-07, "epoch": 1.8343949044585988, "percentage": 26.37, "elapsed_time": "0:23:00", "remaining_time": "1:04:13"}
|
97 |
+
{"current_steps": 97, "total_steps": 364, "loss": 0.2502, "lr": 1.8384088452007576e-07, "epoch": 1.8535031847133758, "percentage": 26.65, "elapsed_time": "0:23:13", "remaining_time": "1:03:54"}
|
98 |
+
{"current_steps": 98, "total_steps": 364, "loss": 0.2586, "lr": 1.8331338435227837e-07, "epoch": 1.872611464968153, "percentage": 26.92, "elapsed_time": "0:23:25", "remaining_time": "1:03:34"}
|
99 |
+
{"current_steps": 99, "total_steps": 364, "loss": 0.267, "lr": 1.8277819437329574e-07, "epoch": 1.89171974522293, "percentage": 27.2, "elapsed_time": "0:23:37", "remaining_time": "1:03:13"}
|
100 |
+
{"current_steps": 100, "total_steps": 364, "loss": 0.2485, "lr": 1.8223536398107174e-07, "epoch": 1.910828025477707, "percentage": 27.47, "elapsed_time": "0:23:50", "remaining_time": "1:02:57"}
|
101 |
+
{"current_steps": 101, "total_steps": 364, "loss": 0.2499, "lr": 1.8168494327875916e-07, "epoch": 1.929936305732484, "percentage": 27.75, "elapsed_time": "0:24:04", "remaining_time": "1:02:41"}
|
102 |
+
{"current_steps": 102, "total_steps": 364, "loss": 0.2505, "lr": 1.8112698307009504e-07, "epoch": 1.9490445859872612, "percentage": 28.02, "elapsed_time": "0:24:15", "remaining_time": "1:02:17"}
|
103 |
+
{"current_steps": 103, "total_steps": 364, "loss": 0.2668, "lr": 1.8056153485471165e-07, "epoch": 1.9681528662420382, "percentage": 28.3, "elapsed_time": "0:24:30", "remaining_time": "1:02:06"}
|
104 |
+
{"current_steps": 104, "total_steps": 364, "loss": 0.2565, "lr": 1.7998865082338287e-07, "epoch": 1.9872611464968153, "percentage": 28.57, "elapsed_time": "0:24:43", "remaining_time": "1:01:48"}
|
105 |
+
{"current_steps": 105, "total_steps": 364, "loss": 0.2533, "lr": 1.7940838385320732e-07, "epoch": 2.0063694267515926, "percentage": 28.85, "elapsed_time": "0:26:39", "remaining_time": "1:05:45"}
|
106 |
+
{"current_steps": 106, "total_steps": 364, "loss": 0.2525, "lr": 1.788207875027274e-07, "epoch": 2.0254777070063694, "percentage": 29.12, "elapsed_time": "0:26:51", "remaining_time": "1:05:22"}
|
107 |
+
{"current_steps": 107, "total_steps": 364, "loss": 0.2532, "lr": 1.7822591600698629e-07, "epoch": 2.0445859872611467, "percentage": 29.4, "elapsed_time": "0:27:00", "remaining_time": "1:04:51"}
|
108 |
+
{"current_steps": 108, "total_steps": 364, "loss": 0.2573, "lr": 1.7762382427252165e-07, "epoch": 2.0636942675159236, "percentage": 29.67, "elapsed_time": "0:27:15", "remaining_time": "1:04:37"}
|
109 |
+
{"current_steps": 109, "total_steps": 364, "loss": 0.2602, "lr": 1.7701456787229803e-07, "epoch": 2.082802547770701, "percentage": 29.95, "elapsed_time": "0:27:31", "remaining_time": "1:04:23"}
|
110 |
+
{"current_steps": 110, "total_steps": 364, "loss": 0.2554, "lr": 1.7639820304057742e-07, "epoch": 2.1019108280254777, "percentage": 30.22, "elapsed_time": "0:27:46", "remaining_time": "1:04:09"}
|
111 |
+
{"current_steps": 111, "total_steps": 364, "loss": 0.253, "lr": 1.7577478666772882e-07, "epoch": 2.121019108280255, "percentage": 30.49, "elapsed_time": "0:28:02", "remaining_time": "1:03:54"}
|
112 |
+
{"current_steps": 112, "total_steps": 364, "loss": 0.2488, "lr": 1.7514437629497717e-07, "epoch": 2.140127388535032, "percentage": 30.77, "elapsed_time": "0:28:16", "remaining_time": "1:03:37"}
|
113 |
+
{"current_steps": 113, "total_steps": 364, "loss": 0.2562, "lr": 1.7450703010909262e-07, "epoch": 2.159235668789809, "percentage": 31.04, "elapsed_time": "0:28:29", "remaining_time": "1:03:16"}
|
114 |
+
{"current_steps": 114, "total_steps": 364, "loss": 0.2607, "lr": 1.738628069370195e-07, "epoch": 2.178343949044586, "percentage": 31.32, "elapsed_time": "0:28:46", "remaining_time": "1:03:05"}
|
115 |
+
{"current_steps": 115, "total_steps": 364, "loss": 0.2503, "lr": 1.7321176624044687e-07, "epoch": 2.1974522292993632, "percentage": 31.59, "elapsed_time": "0:28:57", "remaining_time": "1:02:42"}
|
116 |
+
{"current_steps": 116, "total_steps": 364, "loss": 0.2509, "lr": 1.7255396811032013e-07, "epoch": 2.21656050955414, "percentage": 31.87, "elapsed_time": "0:29:12", "remaining_time": "1:02:26"}
|