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:ddae2f72f1b4da14ab50747cb106e6249f4fc3316eb104fe5b5b68fcfd620447
|
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 sha256:0879114090270cf53ae770a00e7ca61df97562536cade41a455d5d0583b23bd9
|
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:d8923c2cca366da67039d90f4728b1caaf6a19cea57a2bccd99915c2ccc61a2d
|
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 sha256:4d734eaf2f02c58d33d13b7db5e28ba9f2005d146e6686425129709764c37e30
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -57,3 +57,59 @@
|
|
57 |
{"current_steps": 57, "total_steps": 165, "loss": 0.529, "lr": 8.303373616950408e-06, "epoch": 1.0239520958083832, "percentage": 34.55, "elapsed_time": "0:35:46", "remaining_time": "1:07:47"}
|
58 |
{"current_steps": 58, "total_steps": 165, "loss": 0.5694, "lr": 8.222962883121196e-06, "epoch": 1.0419161676646707, "percentage": 35.15, "elapsed_time": "0:36:22", "remaining_time": "1:07:06"}
|
59 |
{"current_steps": 59, "total_steps": 165, "loss": 0.5217, "lr": 8.141099986478212e-06, "epoch": 1.0598802395209581, "percentage": 35.76, "elapsed_time": "0:36:58", "remaining_time": "1:06:26"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
{"current_steps": 57, "total_steps": 165, "loss": 0.529, "lr": 8.303373616950408e-06, "epoch": 1.0239520958083832, "percentage": 34.55, "elapsed_time": "0:35:46", "remaining_time": "1:07:47"}
|
58 |
{"current_steps": 58, "total_steps": 165, "loss": 0.5694, "lr": 8.222962883121196e-06, "epoch": 1.0419161676646707, "percentage": 35.15, "elapsed_time": "0:36:22", "remaining_time": "1:07:06"}
|
59 |
{"current_steps": 59, "total_steps": 165, "loss": 0.5217, "lr": 8.141099986478212e-06, "epoch": 1.0598802395209581, "percentage": 35.76, "elapsed_time": "0:36:58", "remaining_time": "1:06:26"}
|
60 |
+
{"current_steps": 60, "total_steps": 165, "loss": 0.5433, "lr": 8.057821811794457e-06, "epoch": 1.0778443113772456, "percentage": 36.36, "elapsed_time": "0:37:34", "remaining_time": "1:05:45"}
|
61 |
+
{"current_steps": 61, "total_steps": 165, "loss": 0.5449, "lr": 7.973165881521435e-06, "epoch": 1.095808383233533, "percentage": 36.97, "elapsed_time": "0:38:10", "remaining_time": "1:05:05"}
|
62 |
+
{"current_steps": 62, "total_steps": 165, "loss": 0.5623, "lr": 7.887170338882742e-06, "epoch": 1.1137724550898203, "percentage": 37.58, "elapsed_time": "0:38:46", "remaining_time": "1:04:25"}
|
63 |
+
{"current_steps": 63, "total_steps": 165, "loss": 0.5364, "lr": 7.799873930687979e-06, "epoch": 1.1317365269461077, "percentage": 38.18, "elapsed_time": "0:39:22", "remaining_time": "1:03:45"}
|
64 |
+
{"current_steps": 64, "total_steps": 165, "loss": 0.5368, "lr": 7.711315989874677e-06, "epoch": 1.1497005988023952, "percentage": 38.79, "elapsed_time": "0:39:58", "remaining_time": "1:03:05"}
|
65 |
+
{"current_steps": 65, "total_steps": 165, "loss": 0.5571, "lr": 7.621536417786159e-06, "epoch": 1.1676646706586826, "percentage": 39.39, "elapsed_time": "0:40:34", "remaining_time": "1:02:25"}
|
66 |
+
{"current_steps": 66, "total_steps": 165, "loss": 0.5436, "lr": 7.530575666193283e-06, "epoch": 1.18562874251497, "percentage": 40.0, "elapsed_time": "0:41:10", "remaining_time": "1:01:45"}
|
67 |
+
{"current_steps": 67, "total_steps": 165, "loss": 0.5397, "lr": 7.438474719068174e-06, "epoch": 1.2035928143712575, "percentage": 40.61, "elapsed_time": "0:41:46", "remaining_time": "1:01:05"}
|
68 |
+
{"current_steps": 68, "total_steps": 165, "loss": 0.5328, "lr": 7.3452750741181855e-06, "epoch": 1.221556886227545, "percentage": 41.21, "elapsed_time": "0:42:21", "remaining_time": "1:00:26"}
|
69 |
+
{"current_steps": 69, "total_steps": 165, "loss": 0.5679, "lr": 7.251018724088367e-06, "epoch": 1.2395209580838324, "percentage": 41.82, "elapsed_time": "0:42:57", "remaining_time": "0:59:46"}
|
70 |
+
{"current_steps": 70, "total_steps": 165, "loss": 0.5657, "lr": 7.155748137840892e-06, "epoch": 1.2574850299401197, "percentage": 42.42, "elapsed_time": "0:43:33", "remaining_time": "0:59:07"}
|
71 |
+
{"current_steps": 71, "total_steps": 165, "loss": 0.5394, "lr": 7.059506241219964e-06, "epoch": 1.2754491017964071, "percentage": 43.03, "elapsed_time": "0:44:09", "remaining_time": "0:58:27"}
|
72 |
+
{"current_steps": 72, "total_steps": 165, "loss": 0.5307, "lr": 6.962336397710819e-06, "epoch": 1.2934131736526946, "percentage": 43.64, "elapsed_time": "0:44:45", "remaining_time": "0:57:48"}
|
73 |
+
{"current_steps": 73, "total_steps": 165, "loss": 0.5484, "lr": 6.864282388901544e-06, "epoch": 1.311377245508982, "percentage": 44.24, "elapsed_time": "0:45:21", "remaining_time": "0:57:09"}
|
74 |
+
{"current_steps": 74, "total_steps": 165, "loss": 0.5306, "lr": 6.765388394756504e-06, "epoch": 1.3293413173652695, "percentage": 44.85, "elapsed_time": "0:45:57", "remaining_time": "0:56:30"}
|
75 |
+
{"current_steps": 75, "total_steps": 165, "loss": 0.5203, "lr": 6.665698973710289e-06, "epoch": 1.347305389221557, "percentage": 45.45, "elapsed_time": "0:46:33", "remaining_time": "0:55:51"}
|
76 |
+
{"current_steps": 76, "total_steps": 165, "loss": 0.5303, "lr": 6.565259042591112e-06, "epoch": 1.3652694610778444, "percentage": 46.06, "elapsed_time": "0:47:09", "remaining_time": "0:55:13"}
|
77 |
+
{"current_steps": 77, "total_steps": 165, "loss": 0.5199, "lr": 6.464113856382752e-06, "epoch": 1.3832335329341316, "percentage": 46.67, "elapsed_time": "0:47:45", "remaining_time": "0:54:34"}
|
78 |
+
{"current_steps": 78, "total_steps": 165, "loss": 0.5178, "lr": 6.3623089878341146e-06, "epoch": 1.401197604790419, "percentage": 47.27, "elapsed_time": "0:48:21", "remaining_time": "0:53:55"}
|
79 |
+
{"current_steps": 79, "total_steps": 165, "loss": 0.534, "lr": 6.259890306925627e-06, "epoch": 1.4191616766467066, "percentage": 47.88, "elapsed_time": "0:48:57", "remaining_time": "0:53:17"}
|
80 |
+
{"current_steps": 80, "total_steps": 165, "loss": 0.5446, "lr": 6.156903960201709e-06, "epoch": 1.437125748502994, "percentage": 48.48, "elapsed_time": "0:49:33", "remaining_time": "0:52:38"}
|
81 |
+
{"current_steps": 81, "total_steps": 165, "loss": 0.5439, "lr": 6.053396349978632e-06, "epoch": 1.4550898203592815, "percentage": 49.09, "elapsed_time": "0:50:08", "remaining_time": "0:52:00"}
|
82 |
+
{"current_steps": 82, "total_steps": 165, "loss": 0.5215, "lr": 5.949414113437142e-06, "epoch": 1.473053892215569, "percentage": 49.7, "elapsed_time": "0:50:44", "remaining_time": "0:51:22"}
|
83 |
+
{"current_steps": 83, "total_steps": 165, "loss": 0.5409, "lr": 5.8450041016092465e-06, "epoch": 1.4910179640718564, "percentage": 50.3, "elapsed_time": "0:51:20", "remaining_time": "0:50:43"}
|
84 |
+
{"current_steps": 84, "total_steps": 165, "loss": 0.5231, "lr": 5.740213358268658e-06, "epoch": 1.5089820359281436, "percentage": 50.91, "elapsed_time": "0:51:56", "remaining_time": "0:50:05"}
|
85 |
+
{"current_steps": 85, "total_steps": 165, "loss": 0.5277, "lr": 5.635089098734394e-06, "epoch": 1.5269461077844313, "percentage": 51.52, "elapsed_time": "0:52:32", "remaining_time": "0:49:27"}
|
86 |
+
{"current_steps": 86, "total_steps": 165, "loss": 0.5071, "lr": 5.529678688597081e-06, "epoch": 1.5449101796407185, "percentage": 52.12, "elapsed_time": "0:53:08", "remaining_time": "0:48:49"}
|
87 |
+
{"current_steps": 87, "total_steps": 165, "loss": 0.5471, "lr": 5.4240296223775465e-06, "epoch": 1.562874251497006, "percentage": 52.73, "elapsed_time": "0:53:44", "remaining_time": "0:48:11"}
|
88 |
+
{"current_steps": 88, "total_steps": 165, "loss": 0.5373, "lr": 5.318189502127332e-06, "epoch": 1.5808383233532934, "percentage": 53.33, "elapsed_time": "0:54:20", "remaining_time": "0:47:33"}
|
89 |
+
{"current_steps": 89, "total_steps": 165, "loss": 0.5135, "lr": 5.212206015980742e-06, "epoch": 1.5988023952095807, "percentage": 53.94, "elapsed_time": "0:54:56", "remaining_time": "0:46:55"}
|
90 |
+
{"current_steps": 90, "total_steps": 165, "loss": 0.5305, "lr": 5.106126916668118e-06, "epoch": 1.6167664670658684, "percentage": 54.55, "elapsed_time": "0:55:32", "remaining_time": "0:46:17"}
|
91 |
+
{"current_steps": 91, "total_steps": 165, "loss": 0.5095, "lr": 5e-06, "epoch": 1.6347305389221556, "percentage": 55.15, "elapsed_time": "0:56:08", "remaining_time": "0:45:39"}
|
92 |
+
{"current_steps": 92, "total_steps": 165, "loss": 0.5135, "lr": 4.8938730833318825e-06, "epoch": 1.6526946107784433, "percentage": 55.76, "elapsed_time": "0:56:44", "remaining_time": "0:45:01"}
|
93 |
+
{"current_steps": 93, "total_steps": 165, "loss": 0.5251, "lr": 4.78779398401926e-06, "epoch": 1.6706586826347305, "percentage": 56.36, "elapsed_time": "0:57:20", "remaining_time": "0:44:23"}
|
94 |
+
{"current_steps": 94, "total_steps": 165, "loss": 0.5613, "lr": 4.6818104978726685e-06, "epoch": 1.688622754491018, "percentage": 56.97, "elapsed_time": "0:57:56", "remaining_time": "0:43:46"}
|
95 |
+
{"current_steps": 95, "total_steps": 165, "loss": 0.5226, "lr": 4.575970377622456e-06, "epoch": 1.7065868263473054, "percentage": 57.58, "elapsed_time": "0:58:32", "remaining_time": "0:43:08"}
|
96 |
+
{"current_steps": 96, "total_steps": 165, "loss": 0.4925, "lr": 4.47032131140292e-06, "epoch": 1.7245508982035929, "percentage": 58.18, "elapsed_time": "0:59:08", "remaining_time": "0:42:30"}
|
97 |
+
{"current_steps": 97, "total_steps": 165, "loss": 0.5124, "lr": 4.364910901265607e-06, "epoch": 1.7425149700598803, "percentage": 58.79, "elapsed_time": "0:59:44", "remaining_time": "0:41:52"}
|
98 |
+
{"current_steps": 98, "total_steps": 165, "loss": 0.5387, "lr": 4.259786641731344e-06, "epoch": 1.7604790419161676, "percentage": 59.39, "elapsed_time": "1:00:20", "remaining_time": "0:41:15"}
|
99 |
+
{"current_steps": 99, "total_steps": 165, "loss": 0.53, "lr": 4.154995898390756e-06, "epoch": 1.7784431137724552, "percentage": 60.0, "elapsed_time": "1:00:56", "remaining_time": "0:40:37"}
|
100 |
+
{"current_steps": 100, "total_steps": 165, "loss": 0.5288, "lr": 4.050585886562858e-06, "epoch": 1.7964071856287425, "percentage": 60.61, "elapsed_time": "1:01:32", "remaining_time": "0:40:00"}
|
101 |
+
{"current_steps": 101, "total_steps": 165, "loss": 0.5436, "lr": 3.94660365002137e-06, "epoch": 1.81437125748503, "percentage": 61.21, "elapsed_time": "1:02:08", "remaining_time": "0:39:22"}
|
102 |
+
{"current_steps": 102, "total_steps": 165, "loss": 0.5493, "lr": 3.843096039798293e-06, "epoch": 1.8323353293413174, "percentage": 61.82, "elapsed_time": "1:02:44", "remaining_time": "0:38:45"}
|
103 |
+
{"current_steps": 103, "total_steps": 165, "loss": 0.5229, "lr": 3.7401096930743753e-06, "epoch": 1.8502994011976048, "percentage": 62.42, "elapsed_time": "1:03:20", "remaining_time": "0:38:07"}
|
104 |
+
{"current_steps": 104, "total_steps": 165, "loss": 0.5174, "lr": 3.6376910121658867e-06, "epoch": 1.8682634730538923, "percentage": 63.03, "elapsed_time": "1:03:56", "remaining_time": "0:37:30"}
|
105 |
+
{"current_steps": 105, "total_steps": 165, "loss": 0.5526, "lr": 3.5358861436172487e-06, "epoch": 1.8862275449101795, "percentage": 63.64, "elapsed_time": "1:04:32", "remaining_time": "0:36:52"}
|
106 |
+
{"current_steps": 106, "total_steps": 165, "loss": 0.5359, "lr": 3.4347409574088896e-06, "epoch": 1.9041916167664672, "percentage": 64.24, "elapsed_time": "1:05:08", "remaining_time": "0:36:15"}
|
107 |
+
{"current_steps": 107, "total_steps": 165, "loss": 0.5106, "lr": 3.3343010262897125e-06, "epoch": 1.9221556886227544, "percentage": 64.85, "elapsed_time": "1:05:44", "remaining_time": "0:35:38"}
|
108 |
+
{"current_steps": 108, "total_steps": 165, "loss": 0.5109, "lr": 3.234611605243496e-06, "epoch": 1.9401197604790419, "percentage": 65.45, "elapsed_time": "1:06:20", "remaining_time": "0:35:00"}
|
109 |
+
{"current_steps": 109, "total_steps": 165, "loss": 0.5442, "lr": 3.1357176110984578e-06, "epoch": 1.9580838323353293, "percentage": 66.06, "elapsed_time": "1:06:56", "remaining_time": "0:34:23"}
|
110 |
+
{"current_steps": 110, "total_steps": 165, "loss": 0.5115, "lr": 3.0376636022891813e-06, "epoch": 1.9760479041916168, "percentage": 66.67, "elapsed_time": "1:07:31", "remaining_time": "0:33:45"}
|
111 |
+
{"current_steps": 111, "total_steps": 165, "loss": 0.6078, "lr": 2.9404937587800374e-06, "epoch": 1.9940119760479043, "percentage": 67.27, "elapsed_time": "1:08:07", "remaining_time": "0:33:08"}
|
112 |
+
{"current_steps": 112, "total_steps": 165, "loss": 0.5972, "lr": 2.8442518621591085e-06, "epoch": 2.0119760479041915, "percentage": 67.88, "elapsed_time": "1:09:54", "remaining_time": "0:33:05"}
|
113 |
+
{"current_steps": 113, "total_steps": 165, "loss": 0.4873, "lr": 2.748981275911633e-06, "epoch": 2.029940119760479, "percentage": 68.48, "elapsed_time": "1:10:30", "remaining_time": "0:32:26"}
|
114 |
+
{"current_steps": 114, "total_steps": 165, "loss": 0.5312, "lr": 2.6547249258818162e-06, "epoch": 2.0479041916167664, "percentage": 69.09, "elapsed_time": "1:11:06", "remaining_time": "0:31:48"}
|
115 |
+
{"current_steps": 115, "total_steps": 165, "loss": 0.4992, "lr": 2.5615252809318287e-06, "epoch": 2.065868263473054, "percentage": 69.7, "elapsed_time": "1:11:42", "remaining_time": "0:31:10"}
|