Training in progress, epoch 2
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 4976698672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e87d1c0063506020430e7b4781607e969aa1f4df221e0ad372546c857dd2dcc6
|
3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999802720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aef76beee6c6cc2fb97a0b4ceb4d4e88df4e62642a7c924ecc49de1e301fc70f
|
3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4915916176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b04c2207c8543dfb9b460c8df6adcbf6b0493cdcedb31cdfa9f3227723fe5b35
|
3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1168138808
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c400787f66737f98631881e289aad4d39e3e56056926f11c186ae004dbe1f09
|
3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
@@ -67,3 +67,36 @@
|
|
67 |
{"current_steps": 660, "total_steps": 1002, "loss": 0.5557, "lr": 5e-06, "epoch": 1.973124300111982, "percentage": 65.87, "elapsed_time": "5:58:32", "remaining_time": "3:05:47"}
|
68 |
{"current_steps": 668, "total_steps": 1002, "eval_loss": 0.5998166799545288, "epoch": 1.9970138111235536, "percentage": 66.67, "elapsed_time": "6:06:47", "remaining_time": "3:03:23"}
|
69 |
{"current_steps": 670, "total_steps": 1002, "loss": 0.594, "lr": 5e-06, "epoch": 2.005225830533781, "percentage": 66.87, "elapsed_time": "6:09:03", "remaining_time": "3:02:52"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
{"current_steps": 660, "total_steps": 1002, "loss": 0.5557, "lr": 5e-06, "epoch": 1.973124300111982, "percentage": 65.87, "elapsed_time": "5:58:32", "remaining_time": "3:05:47"}
|
68 |
{"current_steps": 668, "total_steps": 1002, "eval_loss": 0.5998166799545288, "epoch": 1.9970138111235536, "percentage": 66.67, "elapsed_time": "6:06:47", "remaining_time": "3:03:23"}
|
69 |
{"current_steps": 670, "total_steps": 1002, "loss": 0.594, "lr": 5e-06, "epoch": 2.005225830533781, "percentage": 66.87, "elapsed_time": "6:09:03", "remaining_time": "3:02:52"}
|
70 |
+
{"current_steps": 680, "total_steps": 1002, "loss": 0.5113, "lr": 5e-06, "epoch": 2.0350877192982457, "percentage": 67.86, "elapsed_time": "6:14:24", "remaining_time": "2:57:17"}
|
71 |
+
{"current_steps": 690, "total_steps": 1002, "loss": 0.5055, "lr": 5e-06, "epoch": 2.06494960806271, "percentage": 68.86, "elapsed_time": "6:19:46", "remaining_time": "2:51:43"}
|
72 |
+
{"current_steps": 700, "total_steps": 1002, "loss": 0.5033, "lr": 5e-06, "epoch": 2.0948114968271745, "percentage": 69.86, "elapsed_time": "6:25:09", "remaining_time": "2:46:10"}
|
73 |
+
{"current_steps": 710, "total_steps": 1002, "loss": 0.5057, "lr": 5e-06, "epoch": 2.1246733855916387, "percentage": 70.86, "elapsed_time": "6:30:33", "remaining_time": "2:40:37"}
|
74 |
+
{"current_steps": 720, "total_steps": 1002, "loss": 0.5043, "lr": 5e-06, "epoch": 2.1545352743561033, "percentage": 71.86, "elapsed_time": "6:35:57", "remaining_time": "2:35:05"}
|
75 |
+
{"current_steps": 730, "total_steps": 1002, "loss": 0.5007, "lr": 5e-06, "epoch": 2.1843971631205674, "percentage": 72.85, "elapsed_time": "6:41:19", "remaining_time": "2:29:32"}
|
76 |
+
{"current_steps": 740, "total_steps": 1002, "loss": 0.5059, "lr": 5e-06, "epoch": 2.2142590518850316, "percentage": 73.85, "elapsed_time": "6:46:40", "remaining_time": "2:23:59"}
|
77 |
+
{"current_steps": 750, "total_steps": 1002, "loss": 0.5063, "lr": 5e-06, "epoch": 2.244120940649496, "percentage": 74.85, "elapsed_time": "6:52:01", "remaining_time": "2:18:26"}
|
78 |
+
{"current_steps": 760, "total_steps": 1002, "loss": 0.5037, "lr": 5e-06, "epoch": 2.2739828294139603, "percentage": 75.85, "elapsed_time": "6:57:23", "remaining_time": "2:12:54"}
|
79 |
+
{"current_steps": 770, "total_steps": 1002, "loss": 0.5028, "lr": 5e-06, "epoch": 2.303844718178425, "percentage": 76.85, "elapsed_time": "7:02:43", "remaining_time": "2:07:22"}
|
80 |
+
{"current_steps": 780, "total_steps": 1002, "loss": 0.5059, "lr": 5e-06, "epoch": 2.333706606942889, "percentage": 77.84, "elapsed_time": "7:08:06", "remaining_time": "2:01:50"}
|
81 |
+
{"current_steps": 790, "total_steps": 1002, "loss": 0.5071, "lr": 5e-06, "epoch": 2.3635684957073533, "percentage": 78.84, "elapsed_time": "7:13:28", "remaining_time": "1:56:19"}
|
82 |
+
{"current_steps": 800, "total_steps": 1002, "loss": 0.5043, "lr": 5e-06, "epoch": 2.393430384471818, "percentage": 79.84, "elapsed_time": "7:18:51", "remaining_time": "1:50:48"}
|
83 |
+
{"current_steps": 810, "total_steps": 1002, "loss": 0.5106, "lr": 5e-06, "epoch": 2.423292273236282, "percentage": 80.84, "elapsed_time": "7:24:13", "remaining_time": "1:45:17"}
|
84 |
+
{"current_steps": 820, "total_steps": 1002, "loss": 0.5115, "lr": 5e-06, "epoch": 2.4531541620007467, "percentage": 81.84, "elapsed_time": "7:29:37", "remaining_time": "1:39:47"}
|
85 |
+
{"current_steps": 830, "total_steps": 1002, "loss": 0.5028, "lr": 5e-06, "epoch": 2.483016050765211, "percentage": 82.83, "elapsed_time": "7:34:59", "remaining_time": "1:34:17"}
|
86 |
+
{"current_steps": 840, "total_steps": 1002, "loss": 0.5047, "lr": 5e-06, "epoch": 2.512877939529675, "percentage": 83.83, "elapsed_time": "7:40:22", "remaining_time": "1:28:47"}
|
87 |
+
{"current_steps": 850, "total_steps": 1002, "loss": 0.5092, "lr": 5e-06, "epoch": 2.5427398282941396, "percentage": 84.83, "elapsed_time": "7:45:47", "remaining_time": "1:23:17"}
|
88 |
+
{"current_steps": 860, "total_steps": 1002, "loss": 0.502, "lr": 5e-06, "epoch": 2.572601717058604, "percentage": 85.83, "elapsed_time": "7:51:07", "remaining_time": "1:17:47"}
|
89 |
+
{"current_steps": 870, "total_steps": 1002, "loss": 0.5055, "lr": 5e-06, "epoch": 2.6024636058230683, "percentage": 86.83, "elapsed_time": "7:56:30", "remaining_time": "1:12:17"}
|
90 |
+
{"current_steps": 880, "total_steps": 1002, "loss": 0.5094, "lr": 5e-06, "epoch": 2.6323254945875325, "percentage": 87.82, "elapsed_time": "8:01:52", "remaining_time": "1:06:48"}
|
91 |
+
{"current_steps": 890, "total_steps": 1002, "loss": 0.5103, "lr": 5e-06, "epoch": 2.662187383351997, "percentage": 88.82, "elapsed_time": "8:07:15", "remaining_time": "1:01:19"}
|
92 |
+
{"current_steps": 900, "total_steps": 1002, "loss": 0.5072, "lr": 5e-06, "epoch": 2.6920492721164613, "percentage": 89.82, "elapsed_time": "8:12:36", "remaining_time": "0:55:49"}
|
93 |
+
{"current_steps": 910, "total_steps": 1002, "loss": 0.5118, "lr": 5e-06, "epoch": 2.721911160880926, "percentage": 90.82, "elapsed_time": "8:17:59", "remaining_time": "0:50:20"}
|
94 |
+
{"current_steps": 920, "total_steps": 1002, "loss": 0.5062, "lr": 5e-06, "epoch": 2.75177304964539, "percentage": 91.82, "elapsed_time": "8:23:20", "remaining_time": "0:44:51"}
|
95 |
+
{"current_steps": 930, "total_steps": 1002, "loss": 0.5123, "lr": 5e-06, "epoch": 2.781634938409854, "percentage": 92.81, "elapsed_time": "8:28:42", "remaining_time": "0:39:23"}
|
96 |
+
{"current_steps": 940, "total_steps": 1002, "loss": 0.5027, "lr": 5e-06, "epoch": 2.811496827174319, "percentage": 93.81, "elapsed_time": "8:34:04", "remaining_time": "0:33:54"}
|
97 |
+
{"current_steps": 950, "total_steps": 1002, "loss": 0.5113, "lr": 5e-06, "epoch": 2.841358715938783, "percentage": 94.81, "elapsed_time": "8:39:28", "remaining_time": "0:28:26"}
|
98 |
+
{"current_steps": 960, "total_steps": 1002, "loss": 0.5113, "lr": 5e-06, "epoch": 2.8712206047032476, "percentage": 95.81, "elapsed_time": "8:44:52", "remaining_time": "0:22:57"}
|
99 |
+
{"current_steps": 970, "total_steps": 1002, "loss": 0.5109, "lr": 5e-06, "epoch": 2.9010824934677117, "percentage": 96.81, "elapsed_time": "8:50:15", "remaining_time": "0:17:29"}
|
100 |
+
{"current_steps": 980, "total_steps": 1002, "loss": 0.5098, "lr": 5e-06, "epoch": 2.9309443822321763, "percentage": 97.8, "elapsed_time": "8:55:39", "remaining_time": "0:12:01"}
|
101 |
+
{"current_steps": 990, "total_steps": 1002, "loss": 0.5103, "lr": 5e-06, "epoch": 2.9608062709966405, "percentage": 98.8, "elapsed_time": "9:01:02", "remaining_time": "0:06:33"}
|
102 |
+
{"current_steps": 1000, "total_steps": 1002, "loss": 0.5009, "lr": 5e-06, "epoch": 2.990668159761105, "percentage": 99.8, "elapsed_time": "9:06:25", "remaining_time": "0:01:05"}
|