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 sha256:2bca969b0189be9b6dddbaf5fb7411c32b16182bead609a9e107847d8a2b5a51
|
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 sha256:80ebcfaf233773625a3a17512f858d7f93ce38884196b2260c07159c34d1eaef
|
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:c23f8eb5747a5f9fada579d73a49e868f9e7b490c1d9e1ad58e5df9c3ac3362d
|
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 sha256:11d687d2336cc8816f8b5486e7994030ec0627693c0ef8aff89d05bfef3d757d
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -57,3 +57,60 @@
|
|
57 |
{"current_steps": 57, "total_steps": 168, "loss": 1.2307, "lr": 8.366216519365623e-06, "epoch": 1.0133333333333334, "percentage": 33.93, "elapsed_time": "0:44:37", "remaining_time": "1:26:54"}
|
58 |
{"current_steps": 58, "total_steps": 168, "loss": 0.6984, "lr": 8.288574353009164e-06, "epoch": 1.031111111111111, "percentage": 34.52, "elapsed_time": "0:45:29", "remaining_time": "1:26:17"}
|
59 |
{"current_steps": 59, "total_steps": 168, "loss": 0.8081, "lr": 8.20950875096333e-06, "epoch": 1.048888888888889, "percentage": 35.12, "elapsed_time": "0:46:20", "remaining_time": "1:25:36"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
{"current_steps": 57, "total_steps": 168, "loss": 1.2307, "lr": 8.366216519365623e-06, "epoch": 1.0133333333333334, "percentage": 33.93, "elapsed_time": "0:44:37", "remaining_time": "1:26:54"}
|
58 |
{"current_steps": 58, "total_steps": 168, "loss": 0.6984, "lr": 8.288574353009164e-06, "epoch": 1.031111111111111, "percentage": 34.52, "elapsed_time": "0:45:29", "remaining_time": "1:26:17"}
|
59 |
{"current_steps": 59, "total_steps": 168, "loss": 0.8081, "lr": 8.20950875096333e-06, "epoch": 1.048888888888889, "percentage": 35.12, "elapsed_time": "0:46:20", "remaining_time": "1:25:36"}
|
60 |
+
{"current_steps": 60, "total_steps": 168, "loss": 0.7388, "lr": 8.129053936203688e-06, "epoch": 1.0666666666666667, "percentage": 35.71, "elapsed_time": "0:46:54", "remaining_time": "1:24:26"}
|
61 |
+
{"current_steps": 61, "total_steps": 168, "loss": 0.8232, "lr": 8.04724473301652e-06, "epoch": 1.0844444444444445, "percentage": 36.31, "elapsed_time": "0:47:42", "remaining_time": "1:23:40"}
|
62 |
+
{"current_steps": 62, "total_steps": 168, "loss": 0.6424, "lr": 7.964116551925365e-06, "epoch": 1.1022222222222222, "percentage": 36.9, "elapsed_time": "0:48:18", "remaining_time": "1:22:36"}
|
63 |
+
{"current_steps": 63, "total_steps": 168, "loss": 0.743, "lr": 7.879705374363831e-06, "epoch": 1.12, "percentage": 37.5, "elapsed_time": "0:49:08", "remaining_time": "1:21:54"}
|
64 |
+
{"current_steps": 64, "total_steps": 168, "loss": 0.6329, "lr": 7.794047737101298e-06, "epoch": 1.1377777777777778, "percentage": 38.1, "elapsed_time": "0:49:54", "remaining_time": "1:21:06"}
|
65 |
+
{"current_steps": 65, "total_steps": 168, "loss": 0.7648, "lr": 7.707180716428237e-06, "epoch": 1.1555555555555554, "percentage": 38.69, "elapsed_time": "0:50:44", "remaining_time": "1:20:24"}
|
66 |
+
{"current_steps": 66, "total_steps": 168, "loss": 0.9037, "lr": 7.619141912108008e-06, "epoch": 1.1733333333333333, "percentage": 39.29, "elapsed_time": "0:51:37", "remaining_time": "1:19:46"}
|
67 |
+
{"current_steps": 67, "total_steps": 168, "loss": 0.7325, "lr": 7.529969431102063e-06, "epoch": 1.1911111111111112, "percentage": 39.88, "elapsed_time": "0:52:26", "remaining_time": "1:19:02"}
|
68 |
+
{"current_steps": 68, "total_steps": 168, "loss": 0.6517, "lr": 7.4397018710756415e-06, "epoch": 1.208888888888889, "percentage": 40.48, "elapsed_time": "0:53:09", "remaining_time": "1:18:10"}
|
69 |
+
{"current_steps": 69, "total_steps": 168, "loss": 0.6863, "lr": 7.34837830369103e-06, "epoch": 1.2266666666666666, "percentage": 41.07, "elapsed_time": "0:53:56", "remaining_time": "1:17:23"}
|
70 |
+
{"current_steps": 70, "total_steps": 168, "loss": 0.7334, "lr": 7.2560382576956875e-06, "epoch": 1.2444444444444445, "percentage": 41.67, "elapsed_time": "0:54:47", "remaining_time": "1:16:42"}
|
71 |
+
{"current_steps": 71, "total_steps": 168, "loss": 0.6825, "lr": 7.162721701812506e-06, "epoch": 1.2622222222222224, "percentage": 42.26, "elapsed_time": "0:55:29", "remaining_time": "1:15:49"}
|
72 |
+
{"current_steps": 72, "total_steps": 168, "loss": 0.7138, "lr": 7.068469027439642e-06, "epoch": 1.28, "percentage": 42.86, "elapsed_time": "0:56:19", "remaining_time": "1:15:05"}
|
73 |
+
{"current_steps": 73, "total_steps": 168, "loss": 0.7004, "lr": 6.9733210311673826e-06, "epoch": 1.2977777777777777, "percentage": 43.45, "elapsed_time": "0:57:03", "remaining_time": "1:14:15"}
|
74 |
+
{"current_steps": 74, "total_steps": 168, "loss": 0.6926, "lr": 6.8773188971196515e-06, "epoch": 1.3155555555555556, "percentage": 44.05, "elapsed_time": "0:57:46", "remaining_time": "1:13:23"}
|
75 |
+
{"current_steps": 75, "total_steps": 168, "loss": 0.7251, "lr": 6.780504179127735e-06, "epoch": 1.3333333333333333, "percentage": 44.64, "elapsed_time": "0:58:27", "remaining_time": "1:12:29"}
|
76 |
+
{"current_steps": 76, "total_steps": 168, "loss": 0.6315, "lr": 6.682918782744033e-06, "epoch": 1.3511111111111112, "percentage": 45.24, "elapsed_time": "0:59:07", "remaining_time": "1:11:34"}
|
77 |
+
{"current_steps": 77, "total_steps": 168, "loss": 0.8246, "lr": 6.584604947103515e-06, "epoch": 1.3688888888888888, "percentage": 45.83, "elapsed_time": "1:00:00", "remaining_time": "1:10:55"}
|
78 |
+
{"current_steps": 78, "total_steps": 168, "loss": 0.6918, "lr": 6.4856052266408375e-06, "epoch": 1.3866666666666667, "percentage": 46.43, "elapsed_time": "1:00:44", "remaining_time": "1:10:04"}
|
79 |
+
{"current_steps": 79, "total_steps": 168, "loss": 0.7386, "lr": 6.385962472670953e-06, "epoch": 1.4044444444444444, "percentage": 47.02, "elapsed_time": "1:01:35", "remaining_time": "1:09:23"}
|
80 |
+
{"current_steps": 80, "total_steps": 168, "loss": 0.6715, "lr": 6.28571981484123e-06, "epoch": 1.4222222222222223, "percentage": 47.62, "elapsed_time": "1:02:20", "remaining_time": "1:08:35"}
|
81 |
+
{"current_steps": 81, "total_steps": 168, "loss": 0.662, "lr": 6.184920642463095e-06, "epoch": 1.44, "percentage": 48.21, "elapsed_time": "1:03:09", "remaining_time": "1:07:50"}
|
82 |
+
{"current_steps": 82, "total_steps": 168, "loss": 0.7322, "lr": 6.083608585731283e-06, "epoch": 1.4577777777777778, "percentage": 48.81, "elapsed_time": "1:04:09", "remaining_time": "1:07:17"}
|
83 |
+
{"current_steps": 83, "total_steps": 168, "loss": 0.6793, "lr": 5.9818274968388225e-06, "epoch": 1.4755555555555555, "percentage": 49.4, "elapsed_time": "1:04:44", "remaining_time": "1:06:17"}
|
84 |
+
{"current_steps": 84, "total_steps": 168, "loss": 0.6983, "lr": 5.879621430995927e-06, "epoch": 1.4933333333333334, "percentage": 50.0, "elapsed_time": "1:05:32", "remaining_time": "1:05:32"}
|
85 |
+
{"current_steps": 85, "total_steps": 168, "loss": 0.7993, "lr": 5.777034627361025e-06, "epoch": 1.511111111111111, "percentage": 50.6, "elapsed_time": "1:06:14", "remaining_time": "1:04:41"}
|
86 |
+
{"current_steps": 86, "total_steps": 168, "loss": 0.6955, "lr": 5.674111489892144e-06, "epoch": 1.528888888888889, "percentage": 51.19, "elapsed_time": "1:07:00", "remaining_time": "1:03:53"}
|
87 |
+
{"current_steps": 87, "total_steps": 168, "loss": 0.694, "lr": 5.570896568126994e-06, "epoch": 1.5466666666666666, "percentage": 51.79, "elapsed_time": "1:07:47", "remaining_time": "1:03:07"}
|
88 |
+
{"current_steps": 88, "total_steps": 168, "loss": 0.6934, "lr": 5.4674345379e-06, "epoch": 1.5644444444444443, "percentage": 52.38, "elapsed_time": "1:08:31", "remaining_time": "1:02:18"}
|
89 |
+
{"current_steps": 89, "total_steps": 168, "loss": 0.7066, "lr": 5.36377018200472e-06, "epoch": 1.5822222222222222, "percentage": 52.98, "elapsed_time": "1:09:13", "remaining_time": "1:01:26"}
|
90 |
+
{"current_steps": 90, "total_steps": 168, "loss": 0.608, "lr": 5.259948370809902e-06, "epoch": 1.6, "percentage": 53.57, "elapsed_time": "1:09:54", "remaining_time": "1:00:34"}
|
91 |
+
{"current_steps": 91, "total_steps": 168, "loss": 0.762, "lr": 5.156014042837696e-06, "epoch": 1.6177777777777778, "percentage": 54.17, "elapsed_time": "1:10:37", "remaining_time": "0:59:45"}
|
92 |
+
{"current_steps": 92, "total_steps": 168, "loss": 0.6945, "lr": 5.052012185312322e-06, "epoch": 1.6355555555555554, "percentage": 54.76, "elapsed_time": "1:11:35", "remaining_time": "0:59:08"}
|
93 |
+
{"current_steps": 93, "total_steps": 168, "loss": 0.6902, "lr": 4.94798781468768e-06, "epoch": 1.6533333333333333, "percentage": 55.36, "elapsed_time": "1:12:21", "remaining_time": "0:58:21"}
|
94 |
+
{"current_steps": 94, "total_steps": 168, "loss": 0.8185, "lr": 4.843985957162304e-06, "epoch": 1.6711111111111112, "percentage": 55.95, "elapsed_time": "1:13:09", "remaining_time": "0:57:35"}
|
95 |
+
{"current_steps": 95, "total_steps": 168, "loss": 0.6987, "lr": 4.740051629190099e-06, "epoch": 1.6888888888888889, "percentage": 56.55, "elapsed_time": "1:13:55", "remaining_time": "0:56:48"}
|
96 |
+
{"current_steps": 96, "total_steps": 168, "loss": 0.759, "lr": 4.636229817995281e-06, "epoch": 1.7066666666666666, "percentage": 57.14, "elapsed_time": "1:14:47", "remaining_time": "0:56:05"}
|
97 |
+
{"current_steps": 97, "total_steps": 168, "loss": 0.7005, "lr": 4.532565462099999e-06, "epoch": 1.7244444444444444, "percentage": 57.74, "elapsed_time": "1:15:37", "remaining_time": "0:55:21"}
|
98 |
+
{"current_steps": 98, "total_steps": 168, "loss": 0.6753, "lr": 4.429103431873009e-06, "epoch": 1.7422222222222223, "percentage": 58.33, "elapsed_time": "1:16:15", "remaining_time": "0:54:28"}
|
99 |
+
{"current_steps": 99, "total_steps": 168, "loss": 0.6962, "lr": 4.3258885101078565e-06, "epoch": 1.76, "percentage": 58.93, "elapsed_time": "1:17:02", "remaining_time": "0:53:41"}
|
100 |
+
{"current_steps": 100, "total_steps": 168, "loss": 0.7709, "lr": 4.2229653726389765e-06, "epoch": 1.7777777777777777, "percentage": 59.52, "elapsed_time": "1:17:48", "remaining_time": "0:52:54"}
|
101 |
+
{"current_steps": 101, "total_steps": 168, "loss": 0.6639, "lr": 4.120378569004074e-06, "epoch": 1.7955555555555556, "percentage": 60.12, "elapsed_time": "1:18:30", "remaining_time": "0:52:05"}
|
102 |
+
{"current_steps": 102, "total_steps": 168, "loss": 0.679, "lr": 4.018172503161179e-06, "epoch": 1.8133333333333335, "percentage": 60.71, "elapsed_time": "1:19:16", "remaining_time": "0:51:17"}
|
103 |
+
{"current_steps": 103, "total_steps": 168, "loss": 0.7619, "lr": 3.9163914142687185e-06, "epoch": 1.8311111111111111, "percentage": 61.31, "elapsed_time": "1:20:03", "remaining_time": "0:50:31"}
|
104 |
+
{"current_steps": 104, "total_steps": 168, "loss": 0.5876, "lr": 3.815079357536907e-06, "epoch": 1.8488888888888888, "percentage": 61.9, "elapsed_time": "1:20:41", "remaining_time": "0:49:39"}
|
105 |
+
{"current_steps": 105, "total_steps": 168, "loss": 0.7726, "lr": 3.714280185158771e-06, "epoch": 1.8666666666666667, "percentage": 62.5, "elapsed_time": "1:21:28", "remaining_time": "0:48:53"}
|
106 |
+
{"current_steps": 106, "total_steps": 168, "loss": 0.7155, "lr": 3.614037527329048e-06, "epoch": 1.8844444444444446, "percentage": 63.1, "elapsed_time": "1:22:22", "remaining_time": "0:48:11"}
|
107 |
+
{"current_steps": 107, "total_steps": 168, "loss": 0.7175, "lr": 3.5143947733591633e-06, "epoch": 1.9022222222222223, "percentage": 63.69, "elapsed_time": "1:23:06", "remaining_time": "0:47:22"}
|
108 |
+
{"current_steps": 108, "total_steps": 168, "loss": 0.6943, "lr": 3.4153950528964867e-06, "epoch": 1.92, "percentage": 64.29, "elapsed_time": "1:23:51", "remaining_time": "0:46:35"}
|
109 |
+
{"current_steps": 109, "total_steps": 168, "loss": 0.7555, "lr": 3.3170812172559695e-06, "epoch": 1.9377777777777778, "percentage": 64.88, "elapsed_time": "1:24:40", "remaining_time": "0:45:50"}
|
110 |
+
{"current_steps": 110, "total_steps": 168, "loss": 0.6852, "lr": 3.2194958208722656e-06, "epoch": 1.9555555555555557, "percentage": 65.48, "elapsed_time": "1:25:21", "remaining_time": "0:45:00"}
|
111 |
+
{"current_steps": 111, "total_steps": 168, "loss": 0.7171, "lr": 3.1226811028803514e-06, "epoch": 1.9733333333333334, "percentage": 66.07, "elapsed_time": "1:26:14", "remaining_time": "0:44:17"}
|
112 |
+
{"current_steps": 112, "total_steps": 168, "loss": 0.6122, "lr": 3.0266789688326187e-06, "epoch": 1.991111111111111, "percentage": 66.67, "elapsed_time": "1:26:53", "remaining_time": "0:43:26"}
|
113 |
+
{"current_steps": 113, "total_steps": 168, "loss": 1.3572, "lr": 2.9315309725603596e-06, "epoch": 2.008888888888889, "percentage": 67.26, "elapsed_time": "1:28:40", "remaining_time": "0:43:09"}
|
114 |
+
{"current_steps": 114, "total_steps": 168, "loss": 0.7745, "lr": 2.8372782981874964e-06, "epoch": 2.026666666666667, "percentage": 67.86, "elapsed_time": "1:29:34", "remaining_time": "0:42:25"}
|
115 |
+
{"current_steps": 115, "total_steps": 168, "loss": 0.6196, "lr": 2.7439617423043146e-06, "epoch": 2.0444444444444443, "percentage": 68.45, "elapsed_time": "1:30:17", "remaining_time": "0:41:36"}
|
116 |
+
{"current_steps": 116, "total_steps": 168, "loss": 0.5975, "lr": 2.6516216963089698e-06, "epoch": 2.062222222222222, "percentage": 69.05, "elapsed_time": "1:30:58", "remaining_time": "0:40:46"}
|