ryanmarten commited on
Commit
78d3264
·
verified ·
1 Parent(s): 12e2653

Training in progress, epoch 0

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08d1ce7c2f373a790f4c81118e5b9e788de0d55b689e897d4f5530a42e8e044a
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37387affbee12d9e34db81444c1bf4bcdfdd7e2c2fd0fd242e1a3f3b15c255f8
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:cbca5b136a608573f896241ddde4c71e7cbcc55f7bcd050d8851828da7c26ee2
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e1b3347534abf91a430073f8459743801cc73a51d84262b838f5a98c81b8dfc
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86f74ff287c081f863e43fea597abb75d0b31f159e2c748e170efc116c5c5f1a
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a19034da43df8189988a157fb7f1e39060d047d8efc3f6db6ac872db016b719
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e000b765d1b3f627cd46ec7aeef999f17eca2ef0152f73224452e14d0f66c7f
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:277e695eeb3534f31bfaf4a381c7248bce9d396c75c11b3a1d586ebba4ad47e4
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -1,71 +1,12 @@
1
- {"current_steps": 1, "total_steps": 70, "loss": 1.2719, "lr": 2.8571428571428573e-06, "epoch": 0.096, "percentage": 1.43, "elapsed_time": "0:02:18", "remaining_time": "2:39:28"}
2
- {"current_steps": 2, "total_steps": 70, "loss": 1.2273, "lr": 5.7142857142857145e-06, "epoch": 0.192, "percentage": 2.86, "elapsed_time": "0:04:20", "remaining_time": "2:27:32"}
3
- {"current_steps": 3, "total_steps": 70, "loss": 1.2782, "lr": 8.571428571428571e-06, "epoch": 0.288, "percentage": 4.29, "elapsed_time": "0:06:15", "remaining_time": "2:19:55"}
4
- {"current_steps": 4, "total_steps": 70, "loss": 1.1462, "lr": 1.1428571428571429e-05, "epoch": 0.384, "percentage": 5.71, "elapsed_time": "0:08:13", "remaining_time": "2:15:39"}
5
- {"current_steps": 5, "total_steps": 70, "loss": 1.1577, "lr": 1.4285714285714287e-05, "epoch": 0.48, "percentage": 7.14, "elapsed_time": "0:10:15", "remaining_time": "2:13:25"}
6
- {"current_steps": 6, "total_steps": 70, "loss": 1.1802, "lr": 1.7142857142857142e-05, "epoch": 0.576, "percentage": 8.57, "elapsed_time": "0:12:06", "remaining_time": "2:09:06"}
7
- {"current_steps": 7, "total_steps": 70, "loss": 1.1361, "lr": 2e-05, "epoch": 0.672, "percentage": 10.0, "elapsed_time": "0:14:08", "remaining_time": "2:07:17"}
8
- {"current_steps": 8, "total_steps": 70, "loss": 1.0833, "lr": 1.9987569212189224e-05, "epoch": 0.768, "percentage": 11.43, "elapsed_time": "0:16:15", "remaining_time": "2:05:59"}
9
- {"current_steps": 9, "total_steps": 70, "loss": 1.0261, "lr": 1.9950307753654016e-05, "epoch": 0.864, "percentage": 12.86, "elapsed_time": "0:18:17", "remaining_time": "2:03:55"}
10
- {"current_steps": 10, "total_steps": 70, "loss": 1.019, "lr": 1.9888308262251286e-05, "epoch": 0.96, "percentage": 14.29, "elapsed_time": "0:20:16", "remaining_time": "2:01:39"}
11
- {"current_steps": 11, "total_steps": 70, "loss": 1.6489, "lr": 1.9801724878485438e-05, "epoch": 1.064, "percentage": 15.71, "elapsed_time": "0:23:17", "remaining_time": "2:04:53"}
12
- {"current_steps": 12, "total_steps": 70, "loss": 1.0, "lr": 1.969077286229078e-05, "epoch": 1.16, "percentage": 17.14, "elapsed_time": "0:25:19", "remaining_time": "2:02:25"}
13
- {"current_steps": 13, "total_steps": 70, "loss": 0.9872, "lr": 1.955572805786141e-05, "epoch": 1.256, "percentage": 18.57, "elapsed_time": "0:27:27", "remaining_time": "2:00:24"}
14
- {"current_steps": 14, "total_steps": 70, "loss": 0.9577, "lr": 1.9396926207859085e-05, "epoch": 1.3519999999999999, "percentage": 20.0, "elapsed_time": "0:29:28", "remaining_time": "1:57:53"}
15
- {"current_steps": 15, "total_steps": 70, "loss": 0.9674, "lr": 1.921476211870408e-05, "epoch": 1.448, "percentage": 21.43, "elapsed_time": "0:31:38", "remaining_time": "1:56:00"}
16
- {"current_steps": 16, "total_steps": 70, "loss": 0.97, "lr": 1.900968867902419e-05, "epoch": 1.544, "percentage": 22.86, "elapsed_time": "0:33:22", "remaining_time": "1:52:37"}
17
- {"current_steps": 17, "total_steps": 70, "loss": 0.9541, "lr": 1.8782215733702286e-05, "epoch": 1.6400000000000001, "percentage": 24.29, "elapsed_time": "0:35:28", "remaining_time": "1:50:34"}
18
- {"current_steps": 18, "total_steps": 70, "loss": 1.017, "lr": 1.8532908816321557e-05, "epoch": 1.736, "percentage": 25.71, "elapsed_time": "0:37:20", "remaining_time": "1:47:52"}
19
- {"current_steps": 19, "total_steps": 70, "loss": 0.8853, "lr": 1.826238774315995e-05, "epoch": 1.8319999999999999, "percentage": 27.14, "elapsed_time": "0:39:02", "remaining_time": "1:44:48"}
20
- {"current_steps": 20, "total_steps": 70, "loss": 0.9426, "lr": 1.7971325072229227e-05, "epoch": 1.928, "percentage": 28.57, "elapsed_time": "0:40:57", "remaining_time": "1:42:22"}
21
- {"current_steps": 21, "total_steps": 70, "loss": 1.5667, "lr": 1.766044443118978e-05, "epoch": 2.032, "percentage": 30.0, "elapsed_time": "0:44:04", "remaining_time": "1:42:51"}
22
- {"current_steps": 22, "total_steps": 70, "loss": 0.9308, "lr": 1.7330518718298263e-05, "epoch": 2.128, "percentage": 31.43, "elapsed_time": "0:45:59", "remaining_time": "1:40:20"}
23
- {"current_steps": 23, "total_steps": 70, "loss": 0.8726, "lr": 1.698236818086073e-05, "epoch": 2.224, "percentage": 32.86, "elapsed_time": "0:47:59", "remaining_time": "1:38:05"}
24
- {"current_steps": 24, "total_steps": 70, "loss": 0.8916, "lr": 1.6616858375968596e-05, "epoch": 2.32, "percentage": 34.29, "elapsed_time": "0:49:55", "remaining_time": "1:35:40"}
25
- {"current_steps": 25, "total_steps": 70, "loss": 0.8827, "lr": 1.6234898018587336e-05, "epoch": 2.416, "percentage": 35.71, "elapsed_time": "0:51:46", "remaining_time": "1:33:12"}
26
- {"current_steps": 26, "total_steps": 70, "loss": 0.9593, "lr": 1.5837436722347902e-05, "epoch": 2.512, "percentage": 37.14, "elapsed_time": "0:53:57", "remaining_time": "1:31:19"}
27
- {"current_steps": 27, "total_steps": 70, "loss": 0.7634, "lr": 1.5425462638657597e-05, "epoch": 2.608, "percentage": 38.57, "elapsed_time": "0:55:39", "remaining_time": "1:28:39"}
28
- {"current_steps": 28, "total_steps": 70, "loss": 0.9058, "lr": 1.5000000000000002e-05, "epoch": 2.7039999999999997, "percentage": 40.0, "elapsed_time": "0:57:31", "remaining_time": "1:26:16"}
29
- {"current_steps": 29, "total_steps": 70, "loss": 0.8964, "lr": 1.4562106573531632e-05, "epoch": 2.8, "percentage": 41.43, "elapsed_time": "0:59:41", "remaining_time": "1:24:23"}
30
- {"current_steps": 30, "total_steps": 70, "loss": 0.8493, "lr": 1.4112871031306118e-05, "epoch": 2.896, "percentage": 42.86, "elapsed_time": "1:01:53", "remaining_time": "1:22:31"}
31
- {"current_steps": 31, "total_steps": 70, "loss": 1.4997, "lr": 1.3653410243663953e-05, "epoch": 2.992, "percentage": 44.29, "elapsed_time": "1:04:10", "remaining_time": "1:20:43"}
32
- {"current_steps": 32, "total_steps": 70, "loss": 0.8486, "lr": 1.3184866502516846e-05, "epoch": 3.096, "percentage": 45.71, "elapsed_time": "1:07:22", "remaining_time": "1:20:01"}
33
- {"current_steps": 33, "total_steps": 70, "loss": 0.8693, "lr": 1.2708404681430054e-05, "epoch": 3.192, "percentage": 47.14, "elapsed_time": "1:09:23", "remaining_time": "1:17:48"}
34
- {"current_steps": 34, "total_steps": 70, "loss": 0.8269, "lr": 1.2225209339563144e-05, "epoch": 3.288, "percentage": 48.57, "elapsed_time": "1:11:20", "remaining_time": "1:15:32"}
35
- {"current_steps": 35, "total_steps": 70, "loss": 0.7745, "lr": 1.1736481776669307e-05, "epoch": 3.384, "percentage": 50.0, "elapsed_time": "1:13:19", "remaining_time": "1:13:19"}
36
- {"current_steps": 36, "total_steps": 70, "loss": 0.8454, "lr": 1.1243437046474854e-05, "epoch": 3.48, "percentage": 51.43, "elapsed_time": "1:15:29", "remaining_time": "1:11:18"}
37
- {"current_steps": 37, "total_steps": 70, "loss": 0.7832, "lr": 1.0747300935864245e-05, "epoch": 3.576, "percentage": 52.86, "elapsed_time": "1:17:30", "remaining_time": "1:09:07"}
38
- {"current_steps": 38, "total_steps": 70, "loss": 0.8042, "lr": 1.0249306917380731e-05, "epoch": 3.672, "percentage": 54.29, "elapsed_time": "1:19:35", "remaining_time": "1:07:01"}
39
- {"current_steps": 39, "total_steps": 70, "loss": 0.807, "lr": 9.750693082619274e-06, "epoch": 3.768, "percentage": 55.71, "elapsed_time": "1:21:43", "remaining_time": "1:04:57"}
40
- {"current_steps": 40, "total_steps": 70, "loss": 0.8172, "lr": 9.252699064135759e-06, "epoch": 3.864, "percentage": 57.14, "elapsed_time": "1:23:50", "remaining_time": "1:02:52"}
41
- {"current_steps": 41, "total_steps": 70, "loss": 0.833, "lr": 8.756562953525151e-06, "epoch": 3.96, "percentage": 58.57, "elapsed_time": "1:25:36", "remaining_time": "1:00:32"}
42
- {"current_steps": 42, "total_steps": 70, "loss": 1.2994, "lr": 8.263518223330698e-06, "epoch": 4.064, "percentage": 60.0, "elapsed_time": "1:28:49", "remaining_time": "0:59:13"}
43
- {"current_steps": 43, "total_steps": 70, "loss": 0.79, "lr": 7.774790660436857e-06, "epoch": 4.16, "percentage": 61.43, "elapsed_time": "1:30:48", "remaining_time": "0:57:01"}
44
- {"current_steps": 44, "total_steps": 70, "loss": 0.7785, "lr": 7.291595318569951e-06, "epoch": 4.256, "percentage": 62.86, "elapsed_time": "1:32:51", "remaining_time": "0:54:52"}
45
- {"current_steps": 45, "total_steps": 70, "loss": 0.7446, "lr": 6.815133497483157e-06, "epoch": 4.352, "percentage": 64.29, "elapsed_time": "1:34:50", "remaining_time": "0:52:41"}
46
- {"current_steps": 46, "total_steps": 70, "loss": 0.7455, "lr": 6.34658975633605e-06, "epoch": 4.448, "percentage": 65.71, "elapsed_time": "1:36:44", "remaining_time": "0:50:28"}
47
- {"current_steps": 47, "total_steps": 70, "loss": 0.7859, "lr": 5.887128968693887e-06, "epoch": 4.5440000000000005, "percentage": 67.14, "elapsed_time": "1:38:39", "remaining_time": "0:48:16"}
48
- {"current_steps": 48, "total_steps": 70, "loss": 0.6996, "lr": 5.43789342646837e-06, "epoch": 4.64, "percentage": 68.57, "elapsed_time": "1:40:30", "remaining_time": "0:46:03"}
49
- {"current_steps": 49, "total_steps": 70, "loss": 0.8119, "lr": 5.000000000000003e-06, "epoch": 4.736, "percentage": 70.0, "elapsed_time": "1:42:37", "remaining_time": "0:43:58"}
50
- {"current_steps": 50, "total_steps": 70, "loss": 0.7318, "lr": 4.5745373613424075e-06, "epoch": 4.832, "percentage": 71.43, "elapsed_time": "1:44:36", "remaining_time": "0:41:50"}
51
- {"current_steps": 51, "total_steps": 70, "loss": 0.776, "lr": 4.162563277652104e-06, "epoch": 4.928, "percentage": 72.86, "elapsed_time": "1:46:37", "remaining_time": "0:39:43"}
52
- {"current_steps": 52, "total_steps": 70, "loss": 1.283, "lr": 3.7651019814126656e-06, "epoch": 5.032, "percentage": 74.29, "elapsed_time": "1:49:45", "remaining_time": "0:37:59"}
53
- {"current_steps": 53, "total_steps": 70, "loss": 0.8399, "lr": 3.3831416240314085e-06, "epoch": 5.128, "percentage": 75.71, "elapsed_time": "1:51:44", "remaining_time": "0:35:50"}
54
- {"current_steps": 54, "total_steps": 70, "loss": 0.5846, "lr": 3.017631819139273e-06, "epoch": 5.224, "percentage": 77.14, "elapsed_time": "1:53:29", "remaining_time": "0:33:37"}
55
- {"current_steps": 55, "total_steps": 70, "loss": 0.7821, "lr": 2.669481281701739e-06, "epoch": 5.32, "percentage": 78.57, "elapsed_time": "1:55:43", "remaining_time": "0:31:33"}
56
- {"current_steps": 56, "total_steps": 70, "loss": 0.7378, "lr": 2.339555568810221e-06, "epoch": 5.416, "percentage": 80.0, "elapsed_time": "1:57:41", "remaining_time": "0:29:25"}
57
- {"current_steps": 57, "total_steps": 70, "loss": 0.7592, "lr": 2.0286749277707783e-06, "epoch": 5.5120000000000005, "percentage": 81.43, "elapsed_time": "1:59:40", "remaining_time": "0:27:17"}
58
- {"current_steps": 58, "total_steps": 70, "loss": 0.7171, "lr": 1.7376122568400533e-06, "epoch": 5.608, "percentage": 82.86, "elapsed_time": "2:01:33", "remaining_time": "0:25:08"}
59
- {"current_steps": 59, "total_steps": 70, "loss": 0.7126, "lr": 1.467091183678444e-06, "epoch": 5.704, "percentage": 84.29, "elapsed_time": "2:03:36", "remaining_time": "0:23:02"}
60
- {"current_steps": 60, "total_steps": 70, "loss": 0.7747, "lr": 1.2177842662977136e-06, "epoch": 5.8, "percentage": 85.71, "elapsed_time": "2:05:48", "remaining_time": "0:20:58"}
61
- {"current_steps": 61, "total_steps": 70, "loss": 0.7731, "lr": 9.903113209758098e-07, "epoch": 5.896, "percentage": 87.14, "elapsed_time": "2:07:49", "remaining_time": "0:18:51"}
62
- {"current_steps": 62, "total_steps": 70, "loss": 1.1821, "lr": 7.852378812959227e-07, "epoch": 5.992, "percentage": 88.57, "elapsed_time": "2:09:51", "remaining_time": "0:16:45"}
63
- {"current_steps": 63, "total_steps": 70, "loss": 0.7462, "lr": 6.030737921409169e-07, "epoch": 6.096, "percentage": 90.0, "elapsed_time": "2:12:52", "remaining_time": "0:14:45"}
64
- {"current_steps": 64, "total_steps": 70, "loss": 0.7164, "lr": 4.4427194213859216e-07, "epoch": 6.192, "percentage": 91.43, "elapsed_time": "2:14:52", "remaining_time": "0:12:38"}
65
- {"current_steps": 65, "total_steps": 70, "loss": 0.715, "lr": 3.0922713770922155e-07, "epoch": 6.288, "percentage": 92.86, "elapsed_time": "2:16:49", "remaining_time": "0:10:31"}
66
- {"current_steps": 66, "total_steps": 70, "loss": 0.7515, "lr": 1.9827512151456175e-07, "epoch": 6.384, "percentage": 94.29, "elapsed_time": "2:18:40", "remaining_time": "0:08:24"}
67
- {"current_steps": 67, "total_steps": 70, "loss": 0.7416, "lr": 1.1169173774871478e-07, "epoch": 6.48, "percentage": 95.71, "elapsed_time": "2:20:43", "remaining_time": "0:06:18"}
68
- {"current_steps": 68, "total_steps": 70, "loss": 0.7276, "lr": 4.9692246345985905e-08, "epoch": 6.576, "percentage": 97.14, "elapsed_time": "2:22:53", "remaining_time": "0:04:12"}
69
- {"current_steps": 69, "total_steps": 70, "loss": 0.7376, "lr": 1.2430787810776556e-08, "epoch": 6.672, "percentage": 98.57, "elapsed_time": "2:24:44", "remaining_time": "0:02:05"}
70
- {"current_steps": 70, "total_steps": 70, "loss": 0.7305, "lr": 0.0, "epoch": 6.768, "percentage": 100.0, "elapsed_time": "2:26:37", "remaining_time": "0:00:00"}
71
- {"current_steps": 70, "total_steps": 70, "epoch": 6.768, "percentage": 100.0, "elapsed_time": "2:28:58", "remaining_time": "0:00:00"}
 
1
+ {"current_steps": 1, "total_steps": 70, "loss": 1.2159, "lr": 2.8571428571428573e-06, "epoch": 0.096, "percentage": 1.43, "elapsed_time": "0:01:53", "remaining_time": "2:09:57"}
2
+ {"current_steps": 2, "total_steps": 70, "loss": 1.1803, "lr": 5.7142857142857145e-06, "epoch": 0.192, "percentage": 2.86, "elapsed_time": "0:03:36", "remaining_time": "2:02:24"}
3
+ {"current_steps": 3, "total_steps": 70, "loss": 1.2637, "lr": 8.571428571428571e-06, "epoch": 0.288, "percentage": 4.29, "elapsed_time": "0:05:19", "remaining_time": "1:58:58"}
4
+ {"current_steps": 4, "total_steps": 70, "loss": 1.0997, "lr": 1.1428571428571429e-05, "epoch": 0.384, "percentage": 5.71, "elapsed_time": "0:07:02", "remaining_time": "1:56:06"}
5
+ {"current_steps": 5, "total_steps": 70, "loss": 1.134, "lr": 1.4285714285714287e-05, "epoch": 0.48, "percentage": 7.14, "elapsed_time": "0:08:49", "remaining_time": "1:54:46"}
6
+ {"current_steps": 6, "total_steps": 70, "loss": 1.1521, "lr": 1.7142857142857142e-05, "epoch": 0.576, "percentage": 8.57, "elapsed_time": "0:10:30", "remaining_time": "1:52:01"}
7
+ {"current_steps": 7, "total_steps": 70, "loss": 1.0869, "lr": 2e-05, "epoch": 0.672, "percentage": 10.0, "elapsed_time": "0:12:16", "remaining_time": "1:50:25"}
8
+ {"current_steps": 8, "total_steps": 70, "loss": 1.0384, "lr": 1.9987569212189224e-05, "epoch": 0.768, "percentage": 11.43, "elapsed_time": "0:14:01", "remaining_time": "1:48:41"}
9
+ {"current_steps": 9, "total_steps": 70, "loss": 0.9982, "lr": 1.9950307753654016e-05, "epoch": 0.864, "percentage": 12.86, "elapsed_time": "0:15:50", "remaining_time": "1:47:25"}
10
+ {"current_steps": 10, "total_steps": 70, "loss": 0.9549, "lr": 1.9888308262251286e-05, "epoch": 0.96, "percentage": 14.29, "elapsed_time": "0:17:43", "remaining_time": "1:46:19"}
11
+ {"current_steps": 11, "total_steps": 70, "loss": 0.9849, "lr": 1.9801724878485438e-05, "epoch": 1.056, "percentage": 15.71, "elapsed_time": "0:20:15", "remaining_time": "1:48:40"}
12
+ {"current_steps": 12, "total_steps": 70, "loss": 0.9482, "lr": 1.969077286229078e-05, "epoch": 1.152, "percentage": 17.14, "elapsed_time": "0:21:59", "remaining_time": "1:46:17"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bca58713098e5e5b65394c265379bdb36fa8b53053e417366105cfd2214babfb
3
- size 7160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d6babea8910037c5eef84380cbe661a1244728984ae94468b361e529b34a0ec
3
+ size 7224