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 sha256:932693bbcde0d4d15045c0db5446e10155f944b86ca4543c3a1ec6ead22fe1b8
|
| 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 sha256:1b533c8ede529526ffc51d062875a1d64a4c3cdf2febf6cfbaec763fe2bd1e0f
|
| 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:a6350e2536398f18d37afb18ef18ceff9828fb8643d1beed68dd0a46274c5b33
|
| 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:aa9e69252bbc3f9939695d1674a92b8e5620a0733538c2e7720671927d731408
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -60,3 +60,66 @@
|
|
| 60 |
{"current_steps": 60, "total_steps": 186, "loss": 0.4277, "lr": 6.868050422828812e-05, "epoch": 0.96, "percentage": 32.26, "elapsed_time": "3:38:34", "remaining_time": "7:38:59"}
|
| 61 |
{"current_steps": 61, "total_steps": 186, "loss": 0.4296, "lr": 6.815093849469446e-05, "epoch": 0.976, "percentage": 32.8, "elapsed_time": "3:42:11", "remaining_time": "7:35:19"}
|
| 62 |
{"current_steps": 62, "total_steps": 186, "loss": 0.4256, "lr": 6.761141075339546e-05, "epoch": 0.992, "percentage": 33.33, "elapsed_time": "3:45:49", "remaining_time": "7:31:38"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
{"current_steps": 60, "total_steps": 186, "loss": 0.4277, "lr": 6.868050422828812e-05, "epoch": 0.96, "percentage": 32.26, "elapsed_time": "3:38:34", "remaining_time": "7:38:59"}
|
| 61 |
{"current_steps": 61, "total_steps": 186, "loss": 0.4296, "lr": 6.815093849469446e-05, "epoch": 0.976, "percentage": 32.8, "elapsed_time": "3:42:11", "remaining_time": "7:35:19"}
|
| 62 |
{"current_steps": 62, "total_steps": 186, "loss": 0.4256, "lr": 6.761141075339546e-05, "epoch": 0.992, "percentage": 33.33, "elapsed_time": "3:45:49", "remaining_time": "7:31:38"}
|
| 63 |
+
{"current_steps": 63, "total_steps": 186, "loss": 0.7285, "lr": 6.706211193157875e-05, "epoch": 1.012, "percentage": 33.87, "elapsed_time": "3:50:55", "remaining_time": "7:30:50"}
|
| 64 |
+
{"current_steps": 64, "total_steps": 186, "loss": 0.4151, "lr": 6.650323641420585e-05, "epoch": 1.028, "percentage": 34.41, "elapsed_time": "3:54:32", "remaining_time": "7:27:06"}
|
| 65 |
+
{"current_steps": 65, "total_steps": 186, "loss": 0.4082, "lr": 6.593498197522348e-05, "epoch": 1.044, "percentage": 34.95, "elapsed_time": "3:58:10", "remaining_time": "7:23:22"}
|
| 66 |
+
{"current_steps": 66, "total_steps": 186, "loss": 0.4055, "lr": 6.535754970757567e-05, "epoch": 1.06, "percentage": 35.48, "elapsed_time": "4:01:47", "remaining_time": "7:19:38"}
|
| 67 |
+
{"current_steps": 67, "total_steps": 186, "loss": 0.4079, "lr": 6.477114395204142e-05, "epoch": 1.076, "percentage": 36.02, "elapsed_time": "4:05:25", "remaining_time": "7:15:54"}
|
| 68 |
+
{"current_steps": 68, "total_steps": 186, "loss": 0.4013, "lr": 6.417597222492268e-05, "epoch": 1.092, "percentage": 36.56, "elapsed_time": "4:09:02", "remaining_time": "7:12:10"}
|
| 69 |
+
{"current_steps": 69, "total_steps": 186, "loss": 0.4065, "lr": 6.35722451446091e-05, "epoch": 1.108, "percentage": 37.1, "elapsed_time": "4:12:40", "remaining_time": "7:08:26"}
|
| 70 |
+
{"current_steps": 70, "total_steps": 186, "loss": 0.3964, "lr": 6.296017635704455e-05, "epoch": 1.124, "percentage": 37.63, "elapsed_time": "4:16:17", "remaining_time": "7:04:43"}
|
| 71 |
+
{"current_steps": 71, "total_steps": 186, "loss": 0.4053, "lr": 6.233998246012253e-05, "epoch": 1.1400000000000001, "percentage": 38.17, "elapsed_time": "4:19:55", "remaining_time": "7:01:00"}
|
| 72 |
+
{"current_steps": 72, "total_steps": 186, "loss": 0.3926, "lr": 6.171188292703685e-05, "epoch": 1.156, "percentage": 38.71, "elapsed_time": "4:23:33", "remaining_time": "6:57:18"}
|
| 73 |
+
{"current_steps": 73, "total_steps": 186, "loss": 0.3957, "lr": 6.10761000286148e-05, "epoch": 1.172, "percentage": 39.25, "elapsed_time": "4:27:11", "remaining_time": "6:53:35"}
|
| 74 |
+
{"current_steps": 74, "total_steps": 186, "loss": 0.401, "lr": 6.043285875466032e-05, "epoch": 1.188, "percentage": 39.78, "elapsed_time": "4:30:48", "remaining_time": "6:49:52"}
|
| 75 |
+
{"current_steps": 75, "total_steps": 186, "loss": 0.4009, "lr": 5.978238673433502e-05, "epoch": 1.204, "percentage": 40.32, "elapsed_time": "4:34:26", "remaining_time": "6:46:09"}
|
| 76 |
+
{"current_steps": 76, "total_steps": 186, "loss": 0.3976, "lr": 5.912491415560507e-05, "epoch": 1.22, "percentage": 40.86, "elapsed_time": "4:38:03", "remaining_time": "6:42:27"}
|
| 77 |
+
{"current_steps": 77, "total_steps": 186, "loss": 0.3983, "lr": 5.8460673683782756e-05, "epoch": 1.236, "percentage": 41.4, "elapsed_time": "4:41:40", "remaining_time": "6:38:44"}
|
| 78 |
+
{"current_steps": 78, "total_steps": 186, "loss": 0.3989, "lr": 5.7789900379191186e-05, "epoch": 1.252, "percentage": 41.94, "elapsed_time": "4:45:18", "remaining_time": "6:35:01"}
|
| 79 |
+
{"current_steps": 79, "total_steps": 186, "loss": 0.3995, "lr": 5.7112831613981554e-05, "epoch": 1.268, "percentage": 42.47, "elapsed_time": "4:48:55", "remaining_time": "6:31:19"}
|
| 80 |
+
{"current_steps": 80, "total_steps": 186, "loss": 0.3968, "lr": 5.64297069881323e-05, "epoch": 1.284, "percentage": 43.01, "elapsed_time": "4:52:32", "remaining_time": "6:27:36"}
|
| 81 |
+
{"current_steps": 81, "total_steps": 186, "loss": 0.3963, "lr": 5.574076824465983e-05, "epoch": 1.3, "percentage": 43.55, "elapsed_time": "4:56:09", "remaining_time": "6:23:55"}
|
| 82 |
+
{"current_steps": 82, "total_steps": 186, "loss": 0.3985, "lr": 5.5046259184070894e-05, "epoch": 1.316, "percentage": 44.09, "elapsed_time": "4:59:47", "remaining_time": "6:20:13"}
|
| 83 |
+
{"current_steps": 83, "total_steps": 186, "loss": 0.3893, "lr": 5.4346425578086915e-05, "epoch": 1.332, "percentage": 44.62, "elapsed_time": "5:03:24", "remaining_time": "6:16:31"}
|
| 84 |
+
{"current_steps": 84, "total_steps": 186, "loss": 0.3927, "lr": 5.364151508267064e-05, "epoch": 1.3479999999999999, "percentage": 45.16, "elapsed_time": "5:07:02", "remaining_time": "6:12:49"}
|
| 85 |
+
{"current_steps": 85, "total_steps": 186, "loss": 0.3913, "lr": 5.293177715038608e-05, "epoch": 1.3639999999999999, "percentage": 45.7, "elapsed_time": "5:10:39", "remaining_time": "6:09:08"}
|
| 86 |
+
{"current_steps": 86, "total_steps": 186, "loss": 0.3893, "lr": 5.2217462942122664e-05, "epoch": 1.38, "percentage": 46.24, "elapsed_time": "5:14:16", "remaining_time": "6:05:26"}
|
| 87 |
+
{"current_steps": 87, "total_steps": 186, "loss": 0.3903, "lr": 5.1498825238214786e-05, "epoch": 1.396, "percentage": 46.77, "elapsed_time": "5:17:54", "remaining_time": "6:01:45"}
|
| 88 |
+
{"current_steps": 88, "total_steps": 186, "loss": 0.3974, "lr": 5.077611834898839e-05, "epoch": 1.412, "percentage": 47.31, "elapsed_time": "5:21:32", "remaining_time": "5:58:04"}
|
| 89 |
+
{"current_steps": 89, "total_steps": 186, "loss": 0.3912, "lr": 5.004959802476596e-05, "epoch": 1.428, "percentage": 47.85, "elapsed_time": "5:25:09", "remaining_time": "5:54:23"}
|
| 90 |
+
{"current_steps": 90, "total_steps": 186, "loss": 0.3898, "lr": 4.931952136536213e-05, "epoch": 1.444, "percentage": 48.39, "elapsed_time": "5:28:47", "remaining_time": "5:50:42"}
|
| 91 |
+
{"current_steps": 91, "total_steps": 186, "loss": 0.3902, "lr": 4.858614672910155e-05, "epoch": 1.46, "percentage": 48.92, "elapsed_time": "5:32:24", "remaining_time": "5:47:01"}
|
| 92 |
+
{"current_steps": 92, "total_steps": 186, "loss": 0.389, "lr": 4.784973364139144e-05, "epoch": 1.476, "percentage": 49.46, "elapsed_time": "5:36:02", "remaining_time": "5:43:20"}
|
| 93 |
+
{"current_steps": 93, "total_steps": 186, "loss": 0.3923, "lr": 4.711054270288125e-05, "epoch": 1.492, "percentage": 50.0, "elapsed_time": "5:39:39", "remaining_time": "5:39:39"}
|
| 94 |
+
{"current_steps": 94, "total_steps": 186, "loss": 0.3915, "lr": 4.6368835497241704e-05, "epoch": 1.508, "percentage": 50.54, "elapsed_time": "5:43:17", "remaining_time": "5:35:58"}
|
| 95 |
+
{"current_steps": 95, "total_steps": 186, "loss": 0.3868, "lr": 4.562487449859594e-05, "epoch": 1.524, "percentage": 51.08, "elapsed_time": "5:46:54", "remaining_time": "5:32:18"}
|
| 96 |
+
{"current_steps": 96, "total_steps": 186, "loss": 0.3901, "lr": 4.4878922978635686e-05, "epoch": 1.54, "percentage": 51.61, "elapsed_time": "5:50:32", "remaining_time": "5:28:37"}
|
| 97 |
+
{"current_steps": 97, "total_steps": 186, "loss": 0.3918, "lr": 4.4131244913455064e-05, "epoch": 1.556, "percentage": 52.15, "elapsed_time": "5:54:10", "remaining_time": "5:24:57"}
|
| 98 |
+
{"current_steps": 98, "total_steps": 186, "loss": 0.3857, "lr": 4.3382104890135164e-05, "epoch": 1.572, "percentage": 52.69, "elapsed_time": "5:57:47", "remaining_time": "5:21:17"}
|
| 99 |
+
{"current_steps": 99, "total_steps": 186, "loss": 0.3872, "lr": 4.263176801311243e-05, "epoch": 1.588, "percentage": 53.23, "elapsed_time": "6:01:25", "remaining_time": "5:17:36"}
|
| 100 |
+
{"current_steps": 100, "total_steps": 186, "loss": 0.386, "lr": 4.1880499810363906e-05, "epoch": 1.604, "percentage": 53.76, "elapsed_time": "6:05:02", "remaining_time": "5:13:56"}
|
| 101 |
+
{"current_steps": 101, "total_steps": 186, "loss": 0.3858, "lr": 4.112856613944265e-05, "epoch": 1.62, "percentage": 54.3, "elapsed_time": "6:08:40", "remaining_time": "5:10:16"}
|
| 102 |
+
{"current_steps": 102, "total_steps": 186, "loss": 0.3867, "lr": 4.03762330933965e-05, "epoch": 1.6360000000000001, "percentage": 54.84, "elapsed_time": "6:12:17", "remaining_time": "5:06:35"}
|
| 103 |
+
{"current_steps": 103, "total_steps": 186, "loss": 0.3818, "lr": 3.962376690660352e-05, "epoch": 1.6520000000000001, "percentage": 55.38, "elapsed_time": "6:15:55", "remaining_time": "5:02:55"}
|
| 104 |
+
{"current_steps": 104, "total_steps": 186, "loss": 0.3856, "lr": 3.8871433860557365e-05, "epoch": 1.6680000000000001, "percentage": 55.91, "elapsed_time": "6:19:32", "remaining_time": "4:59:15"}
|
| 105 |
+
{"current_steps": 105, "total_steps": 186, "loss": 0.389, "lr": 3.811950018963611e-05, "epoch": 1.6840000000000002, "percentage": 56.45, "elapsed_time": "6:23:10", "remaining_time": "4:55:35"}
|
| 106 |
+
{"current_steps": 106, "total_steps": 186, "loss": 0.3876, "lr": 3.736823198688758e-05, "epoch": 1.7, "percentage": 56.99, "elapsed_time": "6:26:48", "remaining_time": "4:51:55"}
|
| 107 |
+
{"current_steps": 107, "total_steps": 186, "loss": 0.3849, "lr": 3.6617895109864836e-05, "epoch": 1.716, "percentage": 57.53, "elapsed_time": "6:30:26", "remaining_time": "4:48:15"}
|
| 108 |
+
{"current_steps": 108, "total_steps": 186, "loss": 0.3881, "lr": 3.586875508654495e-05, "epoch": 1.732, "percentage": 58.06, "elapsed_time": "6:34:03", "remaining_time": "4:44:36"}
|
| 109 |
+
{"current_steps": 109, "total_steps": 186, "loss": 0.3882, "lr": 3.512107702136432e-05, "epoch": 1.748, "percentage": 58.6, "elapsed_time": "6:37:41", "remaining_time": "4:40:56"}
|
| 110 |
+
{"current_steps": 110, "total_steps": 186, "loss": 0.3796, "lr": 3.437512550140408e-05, "epoch": 1.764, "percentage": 59.14, "elapsed_time": "6:41:19", "remaining_time": "4:37:16"}
|
| 111 |
+
{"current_steps": 111, "total_steps": 186, "loss": 0.3807, "lr": 3.363116450275831e-05, "epoch": 1.78, "percentage": 59.68, "elapsed_time": "6:44:57", "remaining_time": "4:33:36"}
|
| 112 |
+
{"current_steps": 112, "total_steps": 186, "loss": 0.3898, "lr": 3.2889457297118754e-05, "epoch": 1.796, "percentage": 60.22, "elapsed_time": "6:48:35", "remaining_time": "4:29:57"}
|
| 113 |
+
{"current_steps": 113, "total_steps": 186, "loss": 0.3829, "lr": 3.2150266358608566e-05, "epoch": 1.812, "percentage": 60.75, "elapsed_time": "6:52:13", "remaining_time": "4:26:18"}
|
| 114 |
+
{"current_steps": 114, "total_steps": 186, "loss": 0.3831, "lr": 3.1413853270898456e-05, "epoch": 1.8279999999999998, "percentage": 61.29, "elapsed_time": "6:55:50", "remaining_time": "4:22:38"}
|
| 115 |
+
{"current_steps": 115, "total_steps": 186, "loss": 0.3797, "lr": 3.0680478634637876e-05, "epoch": 1.8439999999999999, "percentage": 61.83, "elapsed_time": "6:59:27", "remaining_time": "4:18:58"}
|
| 116 |
+
{"current_steps": 116, "total_steps": 186, "loss": 0.3784, "lr": 2.9950401975234053e-05, "epoch": 1.8599999999999999, "percentage": 62.37, "elapsed_time": "7:03:05", "remaining_time": "4:15:18"}
|
| 117 |
+
{"current_steps": 117, "total_steps": 186, "loss": 0.38, "lr": 2.922388165101164e-05, "epoch": 1.876, "percentage": 62.9, "elapsed_time": "7:06:43", "remaining_time": "4:11:39"}
|
| 118 |
+
{"current_steps": 118, "total_steps": 186, "loss": 0.383, "lr": 2.8501174761785227e-05, "epoch": 1.892, "percentage": 63.44, "elapsed_time": "7:10:20", "remaining_time": "4:07:59"}
|
| 119 |
+
{"current_steps": 119, "total_steps": 186, "loss": 0.3803, "lr": 2.7782537057877353e-05, "epoch": 1.908, "percentage": 63.98, "elapsed_time": "7:13:58", "remaining_time": "4:04:20"}
|
| 120 |
+
{"current_steps": 120, "total_steps": 186, "loss": 0.3828, "lr": 2.7068222849613924e-05, "epoch": 1.924, "percentage": 64.52, "elapsed_time": "7:17:35", "remaining_time": "4:00:40"}
|
| 121 |
+
{"current_steps": 121, "total_steps": 186, "loss": 0.3807, "lr": 2.635848491732936e-05, "epoch": 1.94, "percentage": 65.05, "elapsed_time": "7:21:13", "remaining_time": "3:57:01"}
|
| 122 |
+
{"current_steps": 122, "total_steps": 186, "loss": 0.3762, "lr": 2.56535744219131e-05, "epoch": 1.956, "percentage": 65.59, "elapsed_time": "7:24:51", "remaining_time": "3:53:21"}
|
| 123 |
+
{"current_steps": 123, "total_steps": 186, "loss": 0.3779, "lr": 2.4953740815929112e-05, "epoch": 1.972, "percentage": 66.13, "elapsed_time": "7:28:32", "remaining_time": "3:49:44"}
|
| 124 |
+
{"current_steps": 124, "total_steps": 186, "loss": 0.3772, "lr": 2.4259231755340185e-05, "epoch": 1.988, "percentage": 66.67, "elapsed_time": "7:32:13", "remaining_time": "3:46:06"}
|
| 125 |
+
{"current_steps": 125, "total_steps": 186, "loss": 0.6469, "lr": 2.3570293011867705e-05, "epoch": 2.008, "percentage": 67.2, "elapsed_time": "7:37:24", "remaining_time": "3:43:12"}
|