Training in progress, step 100
Browse files- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- trainer_log.jsonl +103 -103
- training_args.bin +1 -1
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 sha256:8ff14c806c54eea392cc70aee8393f3e8be1f575e68d609fbd79721fda1d4ff0
|
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:ee60585155fd0127ebfe940d6e596c220c5a7bc8728f9be0c5afefea7b65144a
|
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:ee4117ce8205faef1e357f807ae707f67b8d701723179d951645138a28fdf877
|
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:da34789feb3ec7a798556e6ad0eb6e585e2b5c3beb1f3f75bad5b583990bcc30
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -1,103 +1,103 @@
|
|
1 |
-
{"current_steps": 1, "total_steps": 5415, "loss": 0.8713, "lr": 1.845018450184502e-08, "epoch": 0.0005537609598523304, "percentage": 0.02, "elapsed_time": "0:00:
|
2 |
-
{"current_steps": 2, "total_steps": 5415, "loss": 0.854, "lr": 3.690036900369004e-08, "epoch": 0.0011075219197046607, "percentage": 0.04, "elapsed_time": "0:01:
|
3 |
-
{"current_steps": 3, "total_steps": 5415, "loss": 0.
|
4 |
-
{"current_steps": 4, "total_steps": 5415, "loss": 0.8932, "lr": 7.380073800738008e-08, "epoch": 0.0022150438394093214, "percentage": 0.07, "elapsed_time": "0:02:
|
5 |
-
{"current_steps": 5, "total_steps": 5415, "loss": 0.
|
6 |
-
{"current_steps": 6, "total_steps": 5415, "loss": 0.
|
7 |
-
{"current_steps": 7, "total_steps": 5415, "loss": 0.
|
8 |
-
{"current_steps": 8, "total_steps": 5415, "loss": 0.874, "lr": 1.4760147601476016e-07, "epoch": 0.004430087678818643, "percentage": 0.15, "elapsed_time": "0:04:
|
9 |
-
{"current_steps": 9, "total_steps": 5415, "loss": 0.
|
10 |
-
{"current_steps": 10, "total_steps": 5415, "loss": 0.
|
11 |
-
{"current_steps": 11, "total_steps": 5415, "loss": 0.
|
12 |
-
{"current_steps": 12, "total_steps": 5415, "loss": 0.
|
13 |
-
{"current_steps": 13, "total_steps": 5415, "loss": 0.
|
14 |
-
{"current_steps": 14, "total_steps": 5415, "loss": 0.
|
15 |
-
{"current_steps": 15, "total_steps": 5415, "loss": 0.
|
16 |
-
{"current_steps": 16, "total_steps": 5415, "loss": 0.
|
17 |
-
{"current_steps": 17, "total_steps": 5415, "loss": 0.8633, "lr": 3.136531365313653e-07, "epoch": 0.009413936317489617, "percentage": 0.31, "elapsed_time": "0:10:
|
18 |
-
{"current_steps": 18, "total_steps": 5415, "loss": 0.
|
19 |
-
{"current_steps": 19, "total_steps": 5415, "loss": 0.
|
20 |
-
{"current_steps": 20, "total_steps": 5415, "loss": 0.
|
21 |
-
{"current_steps": 21, "total_steps": 5415, "loss": 0.
|
22 |
-
{"current_steps": 22, "total_steps": 5415, "loss": 0.
|
23 |
-
{"current_steps": 23, "total_steps": 5415, "loss": 0.
|
24 |
-
{"current_steps": 24, "total_steps": 5415, "loss": 0.
|
25 |
-
{"current_steps": 25, "total_steps": 5415, "loss": 0.
|
26 |
-
{"current_steps": 26, "total_steps": 5415, "loss": 0.
|
27 |
-
{"current_steps": 27, "total_steps": 5415, "loss": 0.
|
28 |
-
{"current_steps": 28, "total_steps": 5415, "loss": 0.
|
29 |
-
{"current_steps": 29, "total_steps": 5415, "loss": 0.
|
30 |
-
{"current_steps": 30, "total_steps": 5415, "loss": 0.
|
31 |
-
{"current_steps": 31, "total_steps": 5415, "loss": 0.
|
32 |
-
{"current_steps": 32, "total_steps": 5415, "loss": 0.
|
33 |
-
{"current_steps": 33, "total_steps": 5415, "loss": 0.7777, "lr": 6.088560885608857e-07, "epoch": 0.018274111675126905, "percentage": 0.61, "elapsed_time": "0:20:
|
34 |
-
{"current_steps": 34, "total_steps": 5415, "loss": 0.7835, "lr": 6.273062730627306e-07, "epoch": 0.018827872634979235, "percentage": 0.63, "elapsed_time": "0:
|
35 |
-
{"current_steps": 35, "total_steps": 5415, "loss": 0.7691, "lr": 6.457564575645757e-07, "epoch": 0.019381633594831565, "percentage": 0.65, "elapsed_time": "0:21:
|
36 |
-
{"current_steps": 36, "total_steps": 5415, "loss": 0.7705, "lr": 6.642066420664207e-07, "epoch": 0.019935394554683895, "percentage": 0.66, "elapsed_time": "0:22:
|
37 |
-
{"current_steps": 37, "total_steps": 5415, "loss": 0.716, "lr": 6.826568265682657e-07, "epoch": 0.020489155514536225, "percentage": 0.68, "elapsed_time": "0:22:
|
38 |
-
{"current_steps": 38, "total_steps": 5415, "loss": 0.7769, "lr": 7.011070110701107e-07, "epoch": 0.021042916474388555, "percentage": 0.7, "elapsed_time": "0:23:
|
39 |
-
{"current_steps": 39, "total_steps": 5415, "loss": 0.
|
40 |
-
{"current_steps": 40, "total_steps": 5415, "loss": 0.7325, "lr": 7.380073800738008e-07, "epoch": 0.022150438394093218, "percentage": 0.74, "elapsed_time": "0:24:
|
41 |
-
{"current_steps": 41, "total_steps": 5415, "loss": 0.7488, "lr": 7.564575645756458e-07, "epoch": 0.022704199353945548, "percentage": 0.76, "elapsed_time": "0:25:
|
42 |
-
{"current_steps": 42, "total_steps": 5415, "loss": 0.751, "lr": 7.749077490774908e-07, "epoch": 0.023257960313797878, "percentage": 0.78, "elapsed_time": "0:25:
|
43 |
-
{"current_steps": 43, "total_steps": 5415, "loss": 0.7274, "lr": 7.933579335793358e-07, "epoch": 0.023811721273650208, "percentage": 0.79, "elapsed_time": "0:26:
|
44 |
-
{"current_steps": 44, "total_steps": 5415, "loss": 0.7461, "lr": 8.118081180811808e-07, "epoch": 0.024365482233502538, "percentage": 0.81, "elapsed_time": "0:
|
45 |
-
{"current_steps": 45, "total_steps": 5415, "loss": 0.7651, "lr": 8.302583025830259e-07, "epoch": 0.024919243193354867, "percentage": 0.83, "elapsed_time": "0:27:
|
46 |
-
{"current_steps": 46, "total_steps": 5415, "loss": 0.
|
47 |
-
{"current_steps": 47, "total_steps": 5415, "loss": 0.7399, "lr": 8.671586715867159e-07, "epoch": 0.02602676511305953, "percentage": 0.87, "elapsed_time": "0:28:
|
48 |
-
{"current_steps": 48, "total_steps": 5415, "loss": 0.
|
49 |
-
{"current_steps": 49, "total_steps": 5415, "loss": 0.7224, "lr": 9.040590405904059e-07, "epoch": 0.02713428703276419, "percentage": 0.9, "elapsed_time": "0:30:
|
50 |
-
{"current_steps": 50, "total_steps": 5415, "loss": 0.
|
51 |
-
{"current_steps": 51, "total_steps": 5415, "loss": 0.6827, "lr": 9.40959409594096e-07, "epoch": 0.02824180895246885, "percentage": 0.94, "elapsed_time": "0:31:
|
52 |
-
{"current_steps": 52, "total_steps": 5415, "loss": 0.
|
53 |
-
{"current_steps": 53, "total_steps": 5415, "loss": 0.6763, "lr": 9.77859778597786e-07, "epoch": 0.02934933087217351, "percentage": 0.98, "elapsed_time": "0:32:
|
54 |
-
{"current_steps": 54, "total_steps": 5415, "loss": 0.7397, "lr": 9.963099630996311e-07, "epoch": 0.029903091832025844, "percentage": 1.0, "elapsed_time": "0:33:
|
55 |
-
{"current_steps": 55, "total_steps": 5415, "loss": 0.
|
56 |
-
{"current_steps": 56, "total_steps": 5415, "loss": 0.6997, "lr": 1.0332103321033212e-06, "epoch": 0.031010613751730504, "percentage": 1.03, "elapsed_time": "0:34:
|
57 |
-
{"current_steps": 57, "total_steps": 5415, "loss": 0.675, "lr": 1.0516605166051662e-06, "epoch": 0.031564374711582834, "percentage": 1.05, "elapsed_time": "0:
|
58 |
-
{"current_steps": 58, "total_steps": 5415, "loss": 0.6631, "lr": 1.070110701107011e-06, "epoch": 0.03211813567143516, "percentage": 1.07, "elapsed_time": "0:35:
|
59 |
-
{"current_steps": 59, "total_steps": 5415, "loss": 0.
|
60 |
-
{"current_steps": 60, "total_steps": 5415, "loss": 0.6647, "lr": 1.1070110701107011e-06, "epoch": 0.03322565759113982, "percentage": 1.11, "elapsed_time": "0:
|
61 |
-
{"current_steps": 61, "total_steps": 5415, "loss": 0.6661, "lr": 1.1254612546125462e-06, "epoch": 0.03377941855099215, "percentage": 1.13, "elapsed_time": "0:37:
|
62 |
-
{"current_steps": 62, "total_steps": 5415, "loss": 0.6934, "lr": 1.1439114391143912e-06, "epoch": 0.03433317951084448, "percentage": 1.14, "elapsed_time": "0:38:
|
63 |
-
{"current_steps": 63, "total_steps": 5415, "loss": 0.6344, "lr": 1.1623616236162363e-06, "epoch": 0.03488694047069681, "percentage": 1.16, "elapsed_time": "0:38:
|
64 |
-
{"current_steps": 64, "total_steps": 5415, "loss": 0.6576, "lr": 1.1808118081180813e-06, "epoch": 0.03544070143054914, "percentage": 1.18, "elapsed_time": "0:39:
|
65 |
-
{"current_steps": 65, "total_steps": 5415, "loss": 0.6484, "lr": 1.1992619926199263e-06, "epoch": 0.03599446239040148, "percentage": 1.2, "elapsed_time": "0:39:
|
66 |
-
{"current_steps": 66, "total_steps": 5415, "loss": 0.
|
67 |
-
{"current_steps": 67, "total_steps": 5415, "loss": 0.6424, "lr": 1.2361623616236164e-06, "epoch": 0.03710198431010614, "percentage": 1.24, "elapsed_time": "0:
|
68 |
-
{"current_steps": 68, "total_steps": 5415, "loss": 0.635, "lr": 1.2546125461254613e-06, "epoch": 0.03765574526995847, "percentage": 1.26, "elapsed_time": "0:41:
|
69 |
-
{"current_steps": 69, "total_steps": 5415, "loss": 0.
|
70 |
-
{"current_steps": 70, "total_steps": 5415, "loss": 0.6262, "lr": 1.2915129151291513e-06, "epoch": 0.03876326718966313, "percentage": 1.29, "elapsed_time": "0:
|
71 |
-
{"current_steps": 71, "total_steps": 5415, "loss": 0.6374, "lr": 1.3099630996309964e-06, "epoch": 0.03931702814951546, "percentage": 1.31, "elapsed_time": "0:43:
|
72 |
-
{"current_steps": 72, "total_steps": 5415, "loss": 0.639, "lr": 1.3284132841328414e-06, "epoch": 0.03987078910936779, "percentage": 1.33, "elapsed_time": "0:44:
|
73 |
-
{"current_steps": 73, "total_steps": 5415, "loss": 0.6392, "lr": 1.3468634686346865e-06, "epoch": 0.04042455006922012, "percentage": 1.35, "elapsed_time": "0:
|
74 |
-
{"current_steps": 74, "total_steps": 5415, "loss": 0.
|
75 |
-
{"current_steps": 75, "total_steps": 5415, "loss": 0.6401, "lr": 1.3837638376383765e-06, "epoch": 0.04153207198892478, "percentage": 1.39, "elapsed_time": "0:46:
|
76 |
-
{"current_steps": 76, "total_steps": 5415, "loss": 0.6399, "lr": 1.4022140221402214e-06, "epoch": 0.04208583294877711, "percentage": 1.4, "elapsed_time": "0:46:
|
77 |
-
{"current_steps": 77, "total_steps": 5415, "loss": 0.
|
78 |
-
{"current_steps": 78, "total_steps": 5415, "loss": 0.
|
79 |
-
{"current_steps": 79, "total_steps": 5415, "loss": 0.
|
80 |
-
{"current_steps": 80, "total_steps": 5415, "loss": 0.601, "lr": 1.4760147601476015e-06, "epoch": 0.044300876788186436, "percentage": 1.48, "elapsed_time": "0:49:
|
81 |
-
{"current_steps": 81, "total_steps": 5415, "loss": 0.6615, "lr": 1.4944649446494466e-06, "epoch": 0.044854637748038766, "percentage": 1.5, "elapsed_time": "0:
|
82 |
-
{"current_steps": 82, "total_steps": 5415, "loss": 0.6234, "lr": 1.5129151291512916e-06, "epoch": 0.045408398707891096, "percentage": 1.51, "elapsed_time": "0:50:
|
83 |
-
{"current_steps": 83, "total_steps": 5415, "loss": 0.
|
84 |
-
{"current_steps": 84, "total_steps": 5415, "loss": 0.6297, "lr": 1.5498154981549817e-06, "epoch": 0.046515920627595755, "percentage": 1.55, "elapsed_time": "0:
|
85 |
-
{"current_steps": 85, "total_steps": 5415, "loss": 0.
|
86 |
-
{"current_steps": 86, "total_steps": 5415, "loss": 0.
|
87 |
-
{"current_steps": 87, "total_steps": 5415, "loss": 0.
|
88 |
-
{"current_steps": 88, "total_steps": 5415, "loss": 0.6138, "lr": 1.6236162361623616e-06, "epoch": 0.048730964467005075, "percentage": 1.63, "elapsed_time": "0:54:
|
89 |
-
{"current_steps": 89, "total_steps": 5415, "loss": 0.6175, "lr": 1.6420664206642067e-06, "epoch": 0.049284725426857405, "percentage": 1.64, "elapsed_time": "0:54:
|
90 |
-
{"current_steps": 90, "total_steps": 5415, "loss": 0.6114, "lr": 1.6605166051660517e-06, "epoch": 0.049838486386709735, "percentage": 1.66, "elapsed_time": "0:55:
|
91 |
-
{"current_steps": 91, "total_steps": 5415, "loss": 0.6082, "lr": 1.6789667896678968e-06, "epoch": 0.050392247346562065, "percentage": 1.68, "elapsed_time": "0:
|
92 |
-
{"current_steps": 92, "total_steps": 5415, "loss": 0.602, "lr": 1.6974169741697418e-06, "epoch": 0.050946008306414395, "percentage": 1.7, "elapsed_time": "0:56:
|
93 |
-
{"current_steps": 93, "total_steps": 5415, "loss": 0.6168, "lr": 1.7158671586715868e-06, "epoch": 0.051499769266266725, "percentage": 1.72, "elapsed_time": "0:57:
|
94 |
-
{"current_steps": 94, "total_steps": 5415, "loss": 0.6096, "lr": 1.7343173431734319e-06, "epoch": 0.05205353022611906, "percentage": 1.74, "elapsed_time": "0:
|
95 |
-
{"current_steps": 95, "total_steps": 5415, "loss": 0.6246, "lr": 1.752767527675277e-06, "epoch": 0.05260729118597139, "percentage": 1.75, "elapsed_time": "0:58:
|
96 |
-
{"current_steps": 96, "total_steps": 5415, "loss": 0.
|
97 |
-
{"current_steps": 97, "total_steps": 5415, "loss": 0.
|
98 |
-
{"current_steps": 98, "total_steps": 5415, "loss": 0.5739, "lr": 1.8081180811808118e-06, "epoch": 0.05426857406552838, "percentage": 1.81, "elapsed_time": "1:00:
|
99 |
-
{"current_steps": 99, "total_steps": 5415, "loss": 0.6209, "lr": 1.8265682656826569e-06, "epoch": 0.05482233502538071, "percentage": 1.83, "elapsed_time": "1:
|
100 |
-
{"current_steps": 100, "total_steps": 5415, "loss": 0.6282, "lr": 1.845018450184502e-06, "epoch": 0.05537609598523304, "percentage": 1.85, "elapsed_time": "1:01:
|
101 |
-
{"current_steps": 101, "total_steps": 5415, "loss": 0.6178, "lr": 1.863468634686347e-06, "epoch": 0.05592985694508537, "percentage": 1.87, "elapsed_time": "1:
|
102 |
-
{"current_steps": 102, "total_steps": 5415, "loss": 0.5922, "lr": 1.881918819188192e-06, "epoch": 0.0564836179049377, "percentage": 1.88, "elapsed_time": "1:03:
|
103 |
-
{"current_steps": 103, "total_steps": 5415, "loss": 0.
|
|
|
1 |
+
{"current_steps": 1, "total_steps": 5415, "loss": 0.8713, "lr": 1.845018450184502e-08, "epoch": 0.0005537609598523304, "percentage": 0.02, "elapsed_time": "0:00:48", "remaining_time": "3 days, 0:36:07"}
|
2 |
+
{"current_steps": 2, "total_steps": 5415, "loss": 0.854, "lr": 3.690036900369004e-08, "epoch": 0.0011075219197046607, "percentage": 0.04, "elapsed_time": "0:01:20", "remaining_time": "2 days, 12:41:00"}
|
3 |
+
{"current_steps": 3, "total_steps": 5415, "loss": 0.846, "lr": 5.5350553505535055e-08, "epoch": 0.0016612828795569913, "percentage": 0.06, "elapsed_time": "0:02:03", "remaining_time": "2 days, 13:40:31"}
|
4 |
+
{"current_steps": 4, "total_steps": 5415, "loss": 0.8932, "lr": 7.380073800738008e-08, "epoch": 0.0022150438394093214, "percentage": 0.07, "elapsed_time": "0:02:38", "remaining_time": "2 days, 11:35:39"}
|
5 |
+
{"current_steps": 5, "total_steps": 5415, "loss": 0.8431, "lr": 9.22509225092251e-08, "epoch": 0.0027688047992616522, "percentage": 0.09, "elapsed_time": "0:03:14", "remaining_time": "2 days, 10:27:55"}
|
6 |
+
{"current_steps": 6, "total_steps": 5415, "loss": 0.8839, "lr": 1.1070110701107011e-07, "epoch": 0.0033225657591139826, "percentage": 0.11, "elapsed_time": "0:03:40", "remaining_time": "2 days, 7:11:51"}
|
7 |
+
{"current_steps": 7, "total_steps": 5415, "loss": 0.8815, "lr": 1.2915129151291515e-07, "epoch": 0.003876326718966313, "percentage": 0.13, "elapsed_time": "0:04:13", "remaining_time": "2 days, 6:20:56"}
|
8 |
+
{"current_steps": 8, "total_steps": 5415, "loss": 0.874, "lr": 1.4760147601476016e-07, "epoch": 0.004430087678818643, "percentage": 0.15, "elapsed_time": "0:04:54", "remaining_time": "2 days, 7:19:30"}
|
9 |
+
{"current_steps": 9, "total_steps": 5415, "loss": 0.9231, "lr": 1.6605166051660518e-07, "epoch": 0.004983848638670974, "percentage": 0.17, "elapsed_time": "0:05:30", "remaining_time": "2 days, 7:13:39"}
|
10 |
+
{"current_steps": 10, "total_steps": 5415, "loss": 0.8484, "lr": 1.845018450184502e-07, "epoch": 0.0055376095985233045, "percentage": 0.18, "elapsed_time": "0:06:05", "remaining_time": "2 days, 6:56:28"}
|
11 |
+
{"current_steps": 11, "total_steps": 5415, "loss": 0.853, "lr": 2.029520295202952e-07, "epoch": 0.006091370558375634, "percentage": 0.2, "elapsed_time": "0:06:39", "remaining_time": "2 days, 6:29:45"}
|
12 |
+
{"current_steps": 12, "total_steps": 5415, "loss": 0.8651, "lr": 2.2140221402214022e-07, "epoch": 0.006645131518227965, "percentage": 0.22, "elapsed_time": "0:07:14", "remaining_time": "2 days, 6:23:10"}
|
13 |
+
{"current_steps": 13, "total_steps": 5415, "loss": 0.8969, "lr": 2.3985239852398526e-07, "epoch": 0.007198892478080295, "percentage": 0.24, "elapsed_time": "0:07:53", "remaining_time": "2 days, 6:39:12"}
|
14 |
+
{"current_steps": 14, "total_steps": 5415, "loss": 0.8537, "lr": 2.583025830258303e-07, "epoch": 0.007752653437932626, "percentage": 0.26, "elapsed_time": "0:08:32", "remaining_time": "2 days, 6:52:07"}
|
15 |
+
{"current_steps": 15, "total_steps": 5415, "loss": 0.882, "lr": 2.767527675276753e-07, "epoch": 0.008306414397784956, "percentage": 0.28, "elapsed_time": "0:09:12", "remaining_time": "2 days, 7:13:52"}
|
16 |
+
{"current_steps": 16, "total_steps": 5415, "loss": 0.871, "lr": 2.9520295202952033e-07, "epoch": 0.008860175357637286, "percentage": 0.3, "elapsed_time": "0:09:52", "remaining_time": "2 days, 7:29:30"}
|
17 |
+
{"current_steps": 17, "total_steps": 5415, "loss": 0.8633, "lr": 3.136531365313653e-07, "epoch": 0.009413936317489617, "percentage": 0.31, "elapsed_time": "0:10:32", "remaining_time": "2 days, 7:45:50"}
|
18 |
+
{"current_steps": 18, "total_steps": 5415, "loss": 0.8545, "lr": 3.3210332103321035e-07, "epoch": 0.009967697277341947, "percentage": 0.33, "elapsed_time": "0:11:06", "remaining_time": "2 days, 7:28:54"}
|
19 |
+
{"current_steps": 19, "total_steps": 5415, "loss": 0.8947, "lr": 3.5055350553505534e-07, "epoch": 0.010521458237194277, "percentage": 0.35, "elapsed_time": "0:11:42", "remaining_time": "2 days, 7:26:57"}
|
20 |
+
{"current_steps": 20, "total_steps": 5415, "loss": 0.8717, "lr": 3.690036900369004e-07, "epoch": 0.011075219197046609, "percentage": 0.37, "elapsed_time": "0:12:15", "remaining_time": "2 days, 7:05:55"}
|
21 |
+
{"current_steps": 21, "total_steps": 5415, "loss": 0.8536, "lr": 3.874538745387454e-07, "epoch": 0.011628980156898939, "percentage": 0.39, "elapsed_time": "0:12:54", "remaining_time": "2 days, 7:14:47"}
|
22 |
+
{"current_steps": 22, "total_steps": 5415, "loss": 0.8057, "lr": 4.059040590405904e-07, "epoch": 0.012182741116751269, "percentage": 0.41, "elapsed_time": "0:13:27", "remaining_time": "2 days, 7:00:50"}
|
23 |
+
{"current_steps": 23, "total_steps": 5415, "loss": 0.7965, "lr": 4.2435424354243545e-07, "epoch": 0.012736502076603599, "percentage": 0.42, "elapsed_time": "0:14:03", "remaining_time": "2 days, 6:56:06"}
|
24 |
+
{"current_steps": 24, "total_steps": 5415, "loss": 0.8122, "lr": 4.4280442804428044e-07, "epoch": 0.01329026303645593, "percentage": 0.44, "elapsed_time": "0:14:44", "remaining_time": "2 days, 7:12:54"}
|
25 |
+
{"current_steps": 25, "total_steps": 5415, "loss": 0.8019, "lr": 4.612546125461255e-07, "epoch": 0.01384402399630826, "percentage": 0.46, "elapsed_time": "0:15:22", "remaining_time": "2 days, 7:13:04"}
|
26 |
+
{"current_steps": 26, "total_steps": 5415, "loss": 0.784, "lr": 4.797047970479705e-07, "epoch": 0.01439778495616059, "percentage": 0.48, "elapsed_time": "0:15:50", "remaining_time": "2 days, 6:44:59"}
|
27 |
+
{"current_steps": 27, "total_steps": 5415, "loss": 0.8578, "lr": 4.981549815498156e-07, "epoch": 0.014951545916012922, "percentage": 0.5, "elapsed_time": "0:16:28", "remaining_time": "2 days, 6:46:32"}
|
28 |
+
{"current_steps": 28, "total_steps": 5415, "loss": 0.798, "lr": 5.166051660516606e-07, "epoch": 0.015505306875865252, "percentage": 0.52, "elapsed_time": "0:17:05", "remaining_time": "2 days, 6:49:32"}
|
29 |
+
{"current_steps": 29, "total_steps": 5415, "loss": 0.8157, "lr": 5.350553505535055e-07, "epoch": 0.01605906783571758, "percentage": 0.54, "elapsed_time": "0:17:43", "remaining_time": "2 days, 6:50:28"}
|
30 |
+
{"current_steps": 30, "total_steps": 5415, "loss": 0.8143, "lr": 5.535055350553506e-07, "epoch": 0.01661282879556991, "percentage": 0.55, "elapsed_time": "0:18:24", "remaining_time": "2 days, 7:05:27"}
|
31 |
+
{"current_steps": 31, "total_steps": 5415, "loss": 0.7409, "lr": 5.719557195571956e-07, "epoch": 0.01716658975542224, "percentage": 0.57, "elapsed_time": "0:19:02", "remaining_time": "2 days, 7:06:09"}
|
32 |
+
{"current_steps": 32, "total_steps": 5415, "loss": 0.7887, "lr": 5.904059040590407e-07, "epoch": 0.01772035071527457, "percentage": 0.59, "elapsed_time": "0:19:40", "remaining_time": "2 days, 7:09:23"}
|
33 |
+
{"current_steps": 33, "total_steps": 5415, "loss": 0.7777, "lr": 6.088560885608857e-07, "epoch": 0.018274111675126905, "percentage": 0.61, "elapsed_time": "0:20:17", "remaining_time": "2 days, 7:10:34"}
|
34 |
+
{"current_steps": 34, "total_steps": 5415, "loss": 0.7835, "lr": 6.273062730627306e-07, "epoch": 0.018827872634979235, "percentage": 0.63, "elapsed_time": "0:21:00", "remaining_time": "2 days, 7:24:01"}
|
35 |
+
{"current_steps": 35, "total_steps": 5415, "loss": 0.7691, "lr": 6.457564575645757e-07, "epoch": 0.019381633594831565, "percentage": 0.65, "elapsed_time": "0:21:36", "remaining_time": "2 days, 7:20:49"}
|
36 |
+
{"current_steps": 36, "total_steps": 5415, "loss": 0.7705, "lr": 6.642066420664207e-07, "epoch": 0.019935394554683895, "percentage": 0.66, "elapsed_time": "0:22:14", "remaining_time": "2 days, 7:23:03"}
|
37 |
+
{"current_steps": 37, "total_steps": 5415, "loss": 0.716, "lr": 6.826568265682657e-07, "epoch": 0.020489155514536225, "percentage": 0.68, "elapsed_time": "0:22:53", "remaining_time": "2 days, 7:26:57"}
|
38 |
+
{"current_steps": 38, "total_steps": 5415, "loss": 0.7769, "lr": 7.011070110701107e-07, "epoch": 0.021042916474388555, "percentage": 0.7, "elapsed_time": "0:23:32", "remaining_time": "2 days, 7:31:52"}
|
39 |
+
{"current_steps": 39, "total_steps": 5415, "loss": 0.7487, "lr": 7.195571955719557e-07, "epoch": 0.021596677434240884, "percentage": 0.72, "elapsed_time": "0:24:13", "remaining_time": "2 days, 7:38:44"}
|
40 |
+
{"current_steps": 40, "total_steps": 5415, "loss": 0.7325, "lr": 7.380073800738008e-07, "epoch": 0.022150438394093218, "percentage": 0.74, "elapsed_time": "0:24:49", "remaining_time": "2 days, 7:35:30"}
|
41 |
+
{"current_steps": 41, "total_steps": 5415, "loss": 0.7488, "lr": 7.564575645756458e-07, "epoch": 0.022704199353945548, "percentage": 0.76, "elapsed_time": "0:25:19", "remaining_time": "2 days, 7:19:21"}
|
42 |
+
{"current_steps": 42, "total_steps": 5415, "loss": 0.751, "lr": 7.749077490774908e-07, "epoch": 0.023257960313797878, "percentage": 0.78, "elapsed_time": "0:25:50", "remaining_time": "2 days, 7:06:17"}
|
43 |
+
{"current_steps": 43, "total_steps": 5415, "loss": 0.7274, "lr": 7.933579335793358e-07, "epoch": 0.023811721273650208, "percentage": 0.79, "elapsed_time": "0:26:26", "remaining_time": "2 days, 7:02:24"}
|
44 |
+
{"current_steps": 44, "total_steps": 5415, "loss": 0.7461, "lr": 8.118081180811808e-07, "epoch": 0.024365482233502538, "percentage": 0.81, "elapsed_time": "0:27:01", "remaining_time": "2 days, 6:59:14"}
|
45 |
+
{"current_steps": 45, "total_steps": 5415, "loss": 0.7651, "lr": 8.302583025830259e-07, "epoch": 0.024919243193354867, "percentage": 0.83, "elapsed_time": "0:27:37", "remaining_time": "2 days, 6:57:20"}
|
46 |
+
{"current_steps": 46, "total_steps": 5415, "loss": 0.7048, "lr": 8.487084870848709e-07, "epoch": 0.025473004153207197, "percentage": 0.85, "elapsed_time": "0:28:17", "remaining_time": "2 days, 7:02:24"}
|
47 |
+
{"current_steps": 47, "total_steps": 5415, "loss": 0.7399, "lr": 8.671586715867159e-07, "epoch": 0.02602676511305953, "percentage": 0.87, "elapsed_time": "0:28:56", "remaining_time": "2 days, 7:04:41"}
|
48 |
+
{"current_steps": 48, "total_steps": 5415, "loss": 0.7263, "lr": 8.856088560885609e-07, "epoch": 0.02658052607291186, "percentage": 0.89, "elapsed_time": "0:29:34", "remaining_time": "2 days, 7:07:06"}
|
49 |
+
{"current_steps": 49, "total_steps": 5415, "loss": 0.7224, "lr": 9.040590405904059e-07, "epoch": 0.02713428703276419, "percentage": 0.9, "elapsed_time": "0:30:13", "remaining_time": "2 days, 7:09:28"}
|
50 |
+
{"current_steps": 50, "total_steps": 5415, "loss": 0.6946, "lr": 9.22509225092251e-07, "epoch": 0.02768804799261652, "percentage": 0.92, "elapsed_time": "0:30:46", "remaining_time": "2 days, 7:02:58"}
|
51 |
+
{"current_steps": 51, "total_steps": 5415, "loss": 0.6827, "lr": 9.40959409594096e-07, "epoch": 0.02824180895246885, "percentage": 0.94, "elapsed_time": "0:31:22", "remaining_time": "2 days, 7:00:00"}
|
52 |
+
{"current_steps": 52, "total_steps": 5415, "loss": 0.6775, "lr": 9.59409594095941e-07, "epoch": 0.02879556991232118, "percentage": 0.96, "elapsed_time": "0:32:03", "remaining_time": "2 days, 7:06:37"}
|
53 |
+
{"current_steps": 53, "total_steps": 5415, "loss": 0.6763, "lr": 9.77859778597786e-07, "epoch": 0.02934933087217351, "percentage": 0.98, "elapsed_time": "0:32:41", "remaining_time": "2 days, 7:08:05"}
|
54 |
+
{"current_steps": 54, "total_steps": 5415, "loss": 0.7397, "lr": 9.963099630996311e-07, "epoch": 0.029903091832025844, "percentage": 1.0, "elapsed_time": "0:33:19", "remaining_time": "2 days, 7:08:51"}
|
55 |
+
{"current_steps": 55, "total_steps": 5415, "loss": 0.6848, "lr": 1.0147601476014762e-06, "epoch": 0.030456852791878174, "percentage": 1.02, "elapsed_time": "0:33:55", "remaining_time": "2 days, 7:06:47"}
|
56 |
+
{"current_steps": 56, "total_steps": 5415, "loss": 0.6997, "lr": 1.0332103321033212e-06, "epoch": 0.031010613751730504, "percentage": 1.03, "elapsed_time": "0:34:31", "remaining_time": "2 days, 7:04:03"}
|
57 |
+
{"current_steps": 57, "total_steps": 5415, "loss": 0.675, "lr": 1.0516605166051662e-06, "epoch": 0.031564374711582834, "percentage": 1.05, "elapsed_time": "0:35:11", "remaining_time": "2 days, 7:08:27"}
|
58 |
+
{"current_steps": 58, "total_steps": 5415, "loss": 0.6631, "lr": 1.070110701107011e-06, "epoch": 0.03211813567143516, "percentage": 1.07, "elapsed_time": "0:35:50", "remaining_time": "2 days, 7:11:00"}
|
59 |
+
{"current_steps": 59, "total_steps": 5415, "loss": 0.7203, "lr": 1.088560885608856e-06, "epoch": 0.03267189663128749, "percentage": 1.09, "elapsed_time": "0:36:28", "remaining_time": "2 days, 7:10:31"}
|
60 |
+
{"current_steps": 60, "total_steps": 5415, "loss": 0.6647, "lr": 1.1070110701107011e-06, "epoch": 0.03322565759113982, "percentage": 1.11, "elapsed_time": "0:37:04", "remaining_time": "2 days, 7:08:42"}
|
61 |
+
{"current_steps": 61, "total_steps": 5415, "loss": 0.6661, "lr": 1.1254612546125462e-06, "epoch": 0.03377941855099215, "percentage": 1.13, "elapsed_time": "0:37:40", "remaining_time": "2 days, 7:06:08"}
|
62 |
+
{"current_steps": 62, "total_steps": 5415, "loss": 0.6934, "lr": 1.1439114391143912e-06, "epoch": 0.03433317951084448, "percentage": 1.14, "elapsed_time": "0:38:14", "remaining_time": "2 days, 7:01:31"}
|
63 |
+
{"current_steps": 63, "total_steps": 5415, "loss": 0.6344, "lr": 1.1623616236162363e-06, "epoch": 0.03488694047069681, "percentage": 1.16, "elapsed_time": "0:38:47", "remaining_time": "2 days, 6:56:03"}
|
64 |
+
{"current_steps": 64, "total_steps": 5415, "loss": 0.6576, "lr": 1.1808118081180813e-06, "epoch": 0.03544070143054914, "percentage": 1.18, "elapsed_time": "0:39:23", "remaining_time": "2 days, 6:52:56"}
|
65 |
+
{"current_steps": 65, "total_steps": 5415, "loss": 0.6484, "lr": 1.1992619926199263e-06, "epoch": 0.03599446239040148, "percentage": 1.2, "elapsed_time": "0:39:56", "remaining_time": "2 days, 6:47:47"}
|
66 |
+
{"current_steps": 66, "total_steps": 5415, "loss": 0.6581, "lr": 1.2177121771217714e-06, "epoch": 0.03654822335025381, "percentage": 1.22, "elapsed_time": "0:40:35", "remaining_time": "2 days, 6:49:16"}
|
67 |
+
{"current_steps": 67, "total_steps": 5415, "loss": 0.6424, "lr": 1.2361623616236164e-06, "epoch": 0.03710198431010614, "percentage": 1.24, "elapsed_time": "0:41:13", "remaining_time": "2 days, 6:50:49"}
|
68 |
+
{"current_steps": 68, "total_steps": 5415, "loss": 0.635, "lr": 1.2546125461254613e-06, "epoch": 0.03765574526995847, "percentage": 1.26, "elapsed_time": "0:41:43", "remaining_time": "2 days, 6:40:20"}
|
69 |
+
{"current_steps": 69, "total_steps": 5415, "loss": 0.6422, "lr": 1.2730627306273063e-06, "epoch": 0.0382095062298108, "percentage": 1.27, "elapsed_time": "0:42:25", "remaining_time": "2 days, 6:46:48"}
|
70 |
+
{"current_steps": 70, "total_steps": 5415, "loss": 0.6262, "lr": 1.2915129151291513e-06, "epoch": 0.03876326718966313, "percentage": 1.29, "elapsed_time": "0:43:04", "remaining_time": "2 days, 6:48:29"}
|
71 |
+
{"current_steps": 71, "total_steps": 5415, "loss": 0.6374, "lr": 1.3099630996309964e-06, "epoch": 0.03931702814951546, "percentage": 1.31, "elapsed_time": "0:43:42", "remaining_time": "2 days, 6:49:43"}
|
72 |
+
{"current_steps": 72, "total_steps": 5415, "loss": 0.639, "lr": 1.3284132841328414e-06, "epoch": 0.03987078910936779, "percentage": 1.33, "elapsed_time": "0:44:22", "remaining_time": "2 days, 6:52:43"}
|
73 |
+
{"current_steps": 73, "total_steps": 5415, "loss": 0.6392, "lr": 1.3468634686346865e-06, "epoch": 0.04042455006922012, "percentage": 1.35, "elapsed_time": "0:45:02", "remaining_time": "2 days, 6:55:41"}
|
74 |
+
{"current_steps": 74, "total_steps": 5415, "loss": 0.6157, "lr": 1.3653136531365315e-06, "epoch": 0.04097831102907245, "percentage": 1.37, "elapsed_time": "0:45:40", "remaining_time": "2 days, 6:57:02"}
|
75 |
+
{"current_steps": 75, "total_steps": 5415, "loss": 0.6401, "lr": 1.3837638376383765e-06, "epoch": 0.04153207198892478, "percentage": 1.39, "elapsed_time": "0:46:20", "remaining_time": "2 days, 6:59:32"}
|
76 |
+
{"current_steps": 76, "total_steps": 5415, "loss": 0.6399, "lr": 1.4022140221402214e-06, "epoch": 0.04208583294877711, "percentage": 1.4, "elapsed_time": "0:46:59", "remaining_time": "2 days, 7:01:29"}
|
77 |
+
{"current_steps": 77, "total_steps": 5415, "loss": 0.6117, "lr": 1.4206642066420664e-06, "epoch": 0.04263959390862944, "percentage": 1.42, "elapsed_time": "0:47:37", "remaining_time": "2 days, 7:01:37"}
|
78 |
+
{"current_steps": 78, "total_steps": 5415, "loss": 0.627, "lr": 1.4391143911439114e-06, "epoch": 0.04319335486848177, "percentage": 1.44, "elapsed_time": "0:48:17", "remaining_time": "2 days, 7:04:23"}
|
79 |
+
{"current_steps": 79, "total_steps": 5415, "loss": 0.641, "lr": 1.4575645756457565e-06, "epoch": 0.043747115828334106, "percentage": 1.46, "elapsed_time": "0:48:54", "remaining_time": "2 days, 7:03:15"}
|
80 |
+
{"current_steps": 80, "total_steps": 5415, "loss": 0.601, "lr": 1.4760147601476015e-06, "epoch": 0.044300876788186436, "percentage": 1.48, "elapsed_time": "0:49:26", "remaining_time": "2 days, 6:56:55"}
|
81 |
+
{"current_steps": 81, "total_steps": 5415, "loss": 0.6615, "lr": 1.4944649446494466e-06, "epoch": 0.044854637748038766, "percentage": 1.5, "elapsed_time": "0:50:05", "remaining_time": "2 days, 6:58:40"}
|
82 |
+
{"current_steps": 82, "total_steps": 5415, "loss": 0.6234, "lr": 1.5129151291512916e-06, "epoch": 0.045408398707891096, "percentage": 1.51, "elapsed_time": "0:50:47", "remaining_time": "2 days, 7:03:03"}
|
83 |
+
{"current_steps": 83, "total_steps": 5415, "loss": 0.5905, "lr": 1.5313653136531366e-06, "epoch": 0.045962159667743425, "percentage": 1.53, "elapsed_time": "0:51:23", "remaining_time": "2 days, 7:01:55"}
|
84 |
+
{"current_steps": 84, "total_steps": 5415, "loss": 0.6297, "lr": 1.5498154981549817e-06, "epoch": 0.046515920627595755, "percentage": 1.55, "elapsed_time": "0:52:00", "remaining_time": "2 days, 7:00:57"}
|
85 |
+
{"current_steps": 85, "total_steps": 5415, "loss": 0.6547, "lr": 1.5682656826568267e-06, "epoch": 0.047069681587448085, "percentage": 1.57, "elapsed_time": "0:52:38", "remaining_time": "2 days, 7:00:33"}
|
86 |
+
{"current_steps": 86, "total_steps": 5415, "loss": 0.6146, "lr": 1.5867158671586716e-06, "epoch": 0.047623442547300415, "percentage": 1.59, "elapsed_time": "0:53:17", "remaining_time": "2 days, 7:01:55"}
|
87 |
+
{"current_steps": 87, "total_steps": 5415, "loss": 0.5941, "lr": 1.6051660516605166e-06, "epoch": 0.048177203507152745, "percentage": 1.61, "elapsed_time": "0:53:52", "remaining_time": "2 days, 6:59:08"}
|
88 |
+
{"current_steps": 88, "total_steps": 5415, "loss": 0.6138, "lr": 1.6236162361623616e-06, "epoch": 0.048730964467005075, "percentage": 1.63, "elapsed_time": "0:54:26", "remaining_time": "2 days, 6:55:22"}
|
89 |
+
{"current_steps": 89, "total_steps": 5415, "loss": 0.6175, "lr": 1.6420664206642067e-06, "epoch": 0.049284725426857405, "percentage": 1.64, "elapsed_time": "0:54:58", "remaining_time": "2 days, 6:50:11"}
|
90 |
+
{"current_steps": 90, "total_steps": 5415, "loss": 0.6114, "lr": 1.6605166051660517e-06, "epoch": 0.049838486386709735, "percentage": 1.66, "elapsed_time": "0:55:33", "remaining_time": "2 days, 6:47:17"}
|
91 |
+
{"current_steps": 91, "total_steps": 5415, "loss": 0.6082, "lr": 1.6789667896678968e-06, "epoch": 0.050392247346562065, "percentage": 1.68, "elapsed_time": "0:56:10", "remaining_time": "2 days, 6:46:13"}
|
92 |
+
{"current_steps": 92, "total_steps": 5415, "loss": 0.602, "lr": 1.6974169741697418e-06, "epoch": 0.050946008306414395, "percentage": 1.7, "elapsed_time": "0:56:49", "remaining_time": "2 days, 6:47:58"}
|
93 |
+
{"current_steps": 93, "total_steps": 5415, "loss": 0.6168, "lr": 1.7158671586715868e-06, "epoch": 0.051499769266266725, "percentage": 1.72, "elapsed_time": "0:57:27", "remaining_time": "2 days, 6:48:31"}
|
94 |
+
{"current_steps": 94, "total_steps": 5415, "loss": 0.6096, "lr": 1.7343173431734319e-06, "epoch": 0.05205353022611906, "percentage": 1.74, "elapsed_time": "0:58:02", "remaining_time": "2 days, 6:45:22"}
|
95 |
+
{"current_steps": 95, "total_steps": 5415, "loss": 0.6246, "lr": 1.752767527675277e-06, "epoch": 0.05260729118597139, "percentage": 1.75, "elapsed_time": "0:58:40", "remaining_time": "2 days, 6:45:30"}
|
96 |
+
{"current_steps": 96, "total_steps": 5415, "loss": 0.5874, "lr": 1.7712177121771217e-06, "epoch": 0.05316105214582372, "percentage": 1.77, "elapsed_time": "0:59:16", "remaining_time": "2 days, 6:44:10"}
|
97 |
+
{"current_steps": 97, "total_steps": 5415, "loss": 0.5989, "lr": 1.7896678966789668e-06, "epoch": 0.05371481310567605, "percentage": 1.79, "elapsed_time": "0:59:55", "remaining_time": "2 days, 6:45:17"}
|
98 |
+
{"current_steps": 98, "total_steps": 5415, "loss": 0.5739, "lr": 1.8081180811808118e-06, "epoch": 0.05426857406552838, "percentage": 1.81, "elapsed_time": "1:00:33", "remaining_time": "2 days, 6:45:53"}
|
99 |
+
{"current_steps": 99, "total_steps": 5415, "loss": 0.6209, "lr": 1.8265682656826569e-06, "epoch": 0.05482233502538071, "percentage": 1.83, "elapsed_time": "1:01:09", "remaining_time": "2 days, 6:44:27"}
|
100 |
+
{"current_steps": 100, "total_steps": 5415, "loss": 0.6282, "lr": 1.845018450184502e-06, "epoch": 0.05537609598523304, "percentage": 1.85, "elapsed_time": "1:01:52", "remaining_time": "2 days, 6:48:27"}
|
101 |
+
{"current_steps": 101, "total_steps": 5415, "loss": 0.6178, "lr": 1.863468634686347e-06, "epoch": 0.05592985694508537, "percentage": 1.87, "elapsed_time": "1:03:16", "remaining_time": "2 days, 7:29:15"}
|
102 |
+
{"current_steps": 102, "total_steps": 5415, "loss": 0.5922, "lr": 1.881918819188192e-06, "epoch": 0.0564836179049377, "percentage": 1.88, "elapsed_time": "1:03:58", "remaining_time": "2 days, 7:32:05"}
|
103 |
+
{"current_steps": 103, "total_steps": 5415, "loss": 0.5759, "lr": 1.900369003690037e-06, "epoch": 0.05703737886479003, "percentage": 1.9, "elapsed_time": "1:04:36", "remaining_time": "2 days, 7:32:06"}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7352
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65355cc9420f4806b1940dec7f7015f5356a562bda84786c666fcd3e8aa92c72
|
3 |
size 7352
|