ryanmarten commited on
Commit
65ee0d8
·
verified ·
1 Parent(s): b11a6a9

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 sha256:9d29d52699cbb89772524dd30c095a28a6bf5e36cf30cbcf5f95ffb92a2a974c
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cbf1043ac3ad98eb1239a0ce8d9e35918c464fa8042f18c408b64d64ebadf2e
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:cac8a79f1cb898c9a0579c268a2e9be8aea2efd12de0471d02d242654303ec72
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23b07a83d7ff9935ecc48e79bc4f306cc092640dde6d69ca5f1c9ee94d11df2d
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:507fa679593ce08913c770bdc5bd3f80b6f85939ba1eedadfb45dd7f9ac9497e
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4754fc24f56ebb3c13b3d71f7fdf1bcf983fc4164ca897381027bc30a93564cc
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0252fff2a42f4681ef161edc04f222f5b70c10277a54cfee0a23ac1979a0da2f
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ac2a1128c10962e4f8aaf005fd132b055197408bcb6549d24fac55ad0f18a5d
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -86,3 +86,79 @@
86
  {"current_steps": 86, "total_steps": 380, "loss": 0.5923, "lr": 7.61742864279031e-05, "epoch": 1.1194151096669374, "percentage": 22.63, "elapsed_time": "2:27:54", "remaining_time": "8:25:37"}
87
  {"current_steps": 87, "total_steps": 380, "loss": 0.5803, "lr": 7.601594865491414e-05, "epoch": 1.132412672623883, "percentage": 22.89, "elapsed_time": "2:29:35", "remaining_time": "8:23:48"}
88
  {"current_steps": 88, "total_steps": 380, "loss": 0.5838, "lr": 7.585457182148081e-05, "epoch": 1.1454102355808287, "percentage": 23.16, "elapsed_time": "2:31:19", "remaining_time": "8:22:06"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
86
  {"current_steps": 86, "total_steps": 380, "loss": 0.5923, "lr": 7.61742864279031e-05, "epoch": 1.1194151096669374, "percentage": 22.63, "elapsed_time": "2:27:54", "remaining_time": "8:25:37"}
87
  {"current_steps": 87, "total_steps": 380, "loss": 0.5803, "lr": 7.601594865491414e-05, "epoch": 1.132412672623883, "percentage": 22.89, "elapsed_time": "2:29:35", "remaining_time": "8:23:48"}
88
  {"current_steps": 88, "total_steps": 380, "loss": 0.5838, "lr": 7.585457182148081e-05, "epoch": 1.1454102355808287, "percentage": 23.16, "elapsed_time": "2:31:19", "remaining_time": "8:22:06"}
89
+ {"current_steps": 89, "total_steps": 380, "loss": 0.5811, "lr": 7.569016954473577e-05, "epoch": 1.158407798537774, "percentage": 23.42, "elapsed_time": "2:32:59", "remaining_time": "8:20:14"}
90
+ {"current_steps": 90, "total_steps": 380, "loss": 0.5875, "lr": 7.552275569710152e-05, "epoch": 1.1714053614947197, "percentage": 23.68, "elapsed_time": "2:34:40", "remaining_time": "8:18:24"}
91
+ {"current_steps": 91, "total_steps": 380, "loss": 0.5811, "lr": 7.535234440511979e-05, "epoch": 1.1844029244516654, "percentage": 23.95, "elapsed_time": "2:36:21", "remaining_time": "8:16:33"}
92
+ {"current_steps": 92, "total_steps": 380, "loss": 0.5808, "lr": 7.517895004825956e-05, "epoch": 1.1974004874086108, "percentage": 24.21, "elapsed_time": "2:38:01", "remaining_time": "8:14:42"}
93
+ {"current_steps": 93, "total_steps": 380, "loss": 0.5768, "lr": 7.500258725770375e-05, "epoch": 1.2103980503655565, "percentage": 24.47, "elapsed_time": "2:39:42", "remaining_time": "8:12:53"}
94
+ {"current_steps": 94, "total_steps": 380, "loss": 0.5705, "lr": 7.48232709151145e-05, "epoch": 1.2233956133225021, "percentage": 24.74, "elapsed_time": "2:41:23", "remaining_time": "8:11:02"}
95
+ {"current_steps": 95, "total_steps": 380, "loss": 0.5818, "lr": 7.464101615137756e-05, "epoch": 1.2363931762794476, "percentage": 25.0, "elapsed_time": "2:43:05", "remaining_time": "8:09:15"}
96
+ {"current_steps": 96, "total_steps": 380, "loss": 0.5642, "lr": 7.445583834532546e-05, "epoch": 1.2493907392363932, "percentage": 25.26, "elapsed_time": "2:44:45", "remaining_time": "8:07:25"}
97
+ {"current_steps": 97, "total_steps": 380, "loss": 0.5779, "lr": 7.426775312243986e-05, "epoch": 1.2623883021933389, "percentage": 25.53, "elapsed_time": "2:46:26", "remaining_time": "8:05:36"}
98
+ {"current_steps": 98, "total_steps": 380, "loss": 0.5743, "lr": 7.407677635353308e-05, "epoch": 1.2753858651502843, "percentage": 25.79, "elapsed_time": "2:48:07", "remaining_time": "8:03:48"}
99
+ {"current_steps": 99, "total_steps": 380, "loss": 0.568, "lr": 7.388292415340888e-05, "epoch": 1.28838342810723, "percentage": 26.05, "elapsed_time": "2:49:49", "remaining_time": "8:02:01"}
100
+ {"current_steps": 100, "total_steps": 380, "loss": 0.5657, "lr": 7.368621287950264e-05, "epoch": 1.3013809910641756, "percentage": 26.32, "elapsed_time": "2:51:32", "remaining_time": "8:00:20"}
101
+ {"current_steps": 101, "total_steps": 380, "loss": 0.5608, "lr": 7.348665913050115e-05, "epoch": 1.314378554021121, "percentage": 26.58, "elapsed_time": "2:53:13", "remaining_time": "7:58:29"}
102
+ {"current_steps": 102, "total_steps": 380, "loss": 0.5676, "lr": 7.328427974494201e-05, "epoch": 1.3273761169780667, "percentage": 26.84, "elapsed_time": "2:54:55", "remaining_time": "7:56:45"}
103
+ {"current_steps": 103, "total_steps": 380, "loss": 0.5649, "lr": 7.307909179979274e-05, "epoch": 1.340373679935012, "percentage": 27.11, "elapsed_time": "2:56:36", "remaining_time": "7:54:58"}
104
+ {"current_steps": 104, "total_steps": 380, "loss": 0.5662, "lr": 7.28711126090098e-05, "epoch": 1.3533712428919578, "percentage": 27.37, "elapsed_time": "2:58:17", "remaining_time": "7:53:09"}
105
+ {"current_steps": 105, "total_steps": 380, "loss": 0.5576, "lr": 7.266035972207773e-05, "epoch": 1.3663688058489034, "percentage": 27.63, "elapsed_time": "3:00:00", "remaining_time": "7:51:26"}
106
+ {"current_steps": 106, "total_steps": 380, "loss": 0.5696, "lr": 7.24468509225281e-05, "epoch": 1.3793663688058488, "percentage": 27.89, "elapsed_time": "3:01:41", "remaining_time": "7:49:40"}
107
+ {"current_steps": 107, "total_steps": 380, "loss": 0.5681, "lr": 7.223060422643914e-05, "epoch": 1.3923639317627945, "percentage": 28.16, "elapsed_time": "3:03:22", "remaining_time": "7:47:51"}
108
+ {"current_steps": 108, "total_steps": 380, "loss": 0.568, "lr": 7.201163788091536e-05, "epoch": 1.40536149471974, "percentage": 28.42, "elapsed_time": "3:05:04", "remaining_time": "7:46:06"}
109
+ {"current_steps": 109, "total_steps": 380, "loss": 0.5681, "lr": 7.178997036254799e-05, "epoch": 1.4183590576766856, "percentage": 28.68, "elapsed_time": "3:06:46", "remaining_time": "7:44:21"}
110
+ {"current_steps": 110, "total_steps": 380, "loss": 0.5681, "lr": 7.156562037585576e-05, "epoch": 1.4313566206336312, "percentage": 28.95, "elapsed_time": "3:08:27", "remaining_time": "7:42:34"}
111
+ {"current_steps": 111, "total_steps": 380, "loss": 0.5766, "lr": 7.133860685170665e-05, "epoch": 1.4443541835905767, "percentage": 29.21, "elapsed_time": "3:10:07", "remaining_time": "7:40:46"}
112
+ {"current_steps": 112, "total_steps": 380, "loss": 0.5654, "lr": 7.110894894572056e-05, "epoch": 1.4573517465475223, "percentage": 29.47, "elapsed_time": "3:11:50", "remaining_time": "7:39:03"}
113
+ {"current_steps": 113, "total_steps": 380, "loss": 0.5613, "lr": 7.087666603665284e-05, "epoch": 1.470349309504468, "percentage": 29.74, "elapsed_time": "3:13:32", "remaining_time": "7:37:18"}
114
+ {"current_steps": 114, "total_steps": 380, "loss": 0.5695, "lr": 7.064177772475912e-05, "epoch": 1.4833468724614134, "percentage": 30.0, "elapsed_time": "3:15:17", "remaining_time": "7:35:40"}
115
+ {"current_steps": 115, "total_steps": 380, "loss": 0.5671, "lr": 7.040430383014146e-05, "epoch": 1.496344435418359, "percentage": 30.26, "elapsed_time": "3:16:58", "remaining_time": "7:33:55"}
116
+ {"current_steps": 116, "total_steps": 380, "loss": 0.565, "lr": 7.016426439107586e-05, "epoch": 1.5093419983753047, "percentage": 30.53, "elapsed_time": "3:18:40", "remaining_time": "7:32:09"}
117
+ {"current_steps": 117, "total_steps": 380, "loss": 0.5571, "lr": 6.992167966232143e-05, "epoch": 1.5223395613322501, "percentage": 30.79, "elapsed_time": "3:20:22", "remaining_time": "7:30:24"}
118
+ {"current_steps": 118, "total_steps": 380, "loss": 0.5764, "lr": 6.967657011341126e-05, "epoch": 1.5353371242891958, "percentage": 31.05, "elapsed_time": "3:22:03", "remaining_time": "7:28:37"}
119
+ {"current_steps": 119, "total_steps": 380, "loss": 0.5622, "lr": 6.942895642692527e-05, "epoch": 1.5483346872461414, "percentage": 31.32, "elapsed_time": "3:23:44", "remaining_time": "7:26:52"}
120
+ {"current_steps": 120, "total_steps": 380, "loss": 0.5668, "lr": 6.917885949674483e-05, "epoch": 1.5613322502030869, "percentage": 31.58, "elapsed_time": "3:25:26", "remaining_time": "7:25:07"}
121
+ {"current_steps": 121, "total_steps": 380, "loss": 0.5579, "lr": 6.892630042628988e-05, "epoch": 1.5743298131600325, "percentage": 31.84, "elapsed_time": "3:27:08", "remaining_time": "7:23:22"}
122
+ {"current_steps": 122, "total_steps": 380, "loss": 0.5651, "lr": 6.867130052673806e-05, "epoch": 1.5873273761169782, "percentage": 32.11, "elapsed_time": "3:28:50", "remaining_time": "7:21:38"}
123
+ {"current_steps": 123, "total_steps": 380, "loss": 0.5644, "lr": 6.841388131522656e-05, "epoch": 1.6003249390739236, "percentage": 32.37, "elapsed_time": "3:30:32", "remaining_time": "7:19:54"}
124
+ {"current_steps": 124, "total_steps": 380, "loss": 0.5652, "lr": 6.815406451303647e-05, "epoch": 1.6133225020308692, "percentage": 32.63, "elapsed_time": "3:32:13", "remaining_time": "7:18:09"}
125
+ {"current_steps": 125, "total_steps": 380, "loss": 0.5677, "lr": 6.789187204375981e-05, "epoch": 1.626320064987815, "percentage": 32.89, "elapsed_time": "3:33:55", "remaining_time": "7:16:23"}
126
+ {"current_steps": 126, "total_steps": 380, "loss": 0.563, "lr": 6.762732603144978e-05, "epoch": 1.6393176279447603, "percentage": 33.16, "elapsed_time": "3:35:36", "remaining_time": "7:14:37"}
127
+ {"current_steps": 127, "total_steps": 380, "loss": 0.5554, "lr": 6.736044879875373e-05, "epoch": 1.652315190901706, "percentage": 33.42, "elapsed_time": "3:37:17", "remaining_time": "7:12:51"}
128
+ {"current_steps": 128, "total_steps": 380, "loss": 0.564, "lr": 6.709126286502965e-05, "epoch": 1.6653127538586516, "percentage": 33.68, "elapsed_time": "3:39:00", "remaining_time": "7:11:09"}
129
+ {"current_steps": 129, "total_steps": 380, "loss": 0.559, "lr": 6.681979094444596e-05, "epoch": 1.678310316815597, "percentage": 33.95, "elapsed_time": "3:40:40", "remaining_time": "7:09:23"}
130
+ {"current_steps": 130, "total_steps": 380, "loss": 0.5586, "lr": 6.654605594406486e-05, "epoch": 1.6913078797725425, "percentage": 34.21, "elapsed_time": "3:42:22", "remaining_time": "7:07:37"}
131
+ {"current_steps": 131, "total_steps": 380, "loss": 0.5581, "lr": 6.627008096190938e-05, "epoch": 1.7043054427294884, "percentage": 34.47, "elapsed_time": "3:44:03", "remaining_time": "7:05:52"}
132
+ {"current_steps": 132, "total_steps": 380, "loss": 0.5601, "lr": 6.59918892850144e-05, "epoch": 1.7173030056864338, "percentage": 34.74, "elapsed_time": "3:45:44", "remaining_time": "7:04:07"}
133
+ {"current_steps": 133, "total_steps": 380, "loss": 0.5584, "lr": 6.571150438746157e-05, "epoch": 1.7303005686433792, "percentage": 35.0, "elapsed_time": "3:47:27", "remaining_time": "7:02:24"}
134
+ {"current_steps": 134, "total_steps": 380, "loss": 0.5524, "lr": 6.542894992839873e-05, "epoch": 1.743298131600325, "percentage": 35.26, "elapsed_time": "3:49:08", "remaining_time": "7:00:39"}
135
+ {"current_steps": 135, "total_steps": 380, "loss": 0.5551, "lr": 6.514424975004329e-05, "epoch": 1.7562956945572705, "percentage": 35.53, "elapsed_time": "3:50:52", "remaining_time": "6:58:59"}
136
+ {"current_steps": 136, "total_steps": 380, "loss": 0.5554, "lr": 6.48574278756706e-05, "epoch": 1.769293257514216, "percentage": 35.79, "elapsed_time": "3:52:33", "remaining_time": "6:57:13"}
137
+ {"current_steps": 137, "total_steps": 380, "loss": 0.5503, "lr": 6.456850850758673e-05, "epoch": 1.7822908204711616, "percentage": 36.05, "elapsed_time": "3:54:13", "remaining_time": "6:55:27"}
138
+ {"current_steps": 138, "total_steps": 380, "loss": 0.5508, "lr": 6.427751602508628e-05, "epoch": 1.7952883834281073, "percentage": 36.32, "elapsed_time": "3:55:55", "remaining_time": "6:53:43"}
139
+ {"current_steps": 139, "total_steps": 380, "loss": 0.5588, "lr": 6.398447498239527e-05, "epoch": 1.8082859463850527, "percentage": 36.58, "elapsed_time": "3:57:36", "remaining_time": "6:51:58"}
140
+ {"current_steps": 140, "total_steps": 380, "loss": 0.5572, "lr": 6.368941010659921e-05, "epoch": 1.8212835093419983, "percentage": 36.84, "elapsed_time": "3:59:17", "remaining_time": "6:50:13"}
141
+ {"current_steps": 141, "total_steps": 380, "loss": 0.5552, "lr": 6.339234629555655e-05, "epoch": 1.834281072298944, "percentage": 37.11, "elapsed_time": "4:00:59", "remaining_time": "6:48:29"}
142
+ {"current_steps": 142, "total_steps": 380, "loss": 0.5585, "lr": 6.309330861579786e-05, "epoch": 1.8472786352558894, "percentage": 37.37, "elapsed_time": "4:02:42", "remaining_time": "6:46:48"}
143
+ {"current_steps": 143, "total_steps": 380, "loss": 0.5529, "lr": 6.279232230041065e-05, "epoch": 1.860276198212835, "percentage": 37.63, "elapsed_time": "4:04:23", "remaining_time": "6:45:03"}
144
+ {"current_steps": 144, "total_steps": 380, "loss": 0.5505, "lr": 6.248941274691017e-05, "epoch": 1.8732737611697807, "percentage": 37.89, "elapsed_time": "4:06:05", "remaining_time": "6:43:18"}
145
+ {"current_steps": 145, "total_steps": 380, "loss": 0.5466, "lr": 6.218460551509636e-05, "epoch": 1.8862713241267262, "percentage": 38.16, "elapsed_time": "4:07:46", "remaining_time": "6:41:34"}
146
+ {"current_steps": 146, "total_steps": 380, "loss": 0.555, "lr": 6.18779263248971e-05, "epoch": 1.8992688870836718, "percentage": 38.42, "elapsed_time": "4:09:27", "remaining_time": "6:39:49"}
147
+ {"current_steps": 147, "total_steps": 380, "loss": 0.5491, "lr": 6.156940105419785e-05, "epoch": 1.9122664500406175, "percentage": 38.68, "elapsed_time": "4:11:10", "remaining_time": "6:38:07"}
148
+ {"current_steps": 148, "total_steps": 380, "loss": 0.5511, "lr": 6.125905573665824e-05, "epoch": 1.925264012997563, "percentage": 38.95, "elapsed_time": "4:12:51", "remaining_time": "6:36:22"}
149
+ {"current_steps": 149, "total_steps": 380, "loss": 0.5531, "lr": 6.094691655951512e-05, "epoch": 1.9382615759545085, "percentage": 39.21, "elapsed_time": "4:14:33", "remaining_time": "6:34:39"}
150
+ {"current_steps": 150, "total_steps": 380, "loss": 0.5519, "lr": 6.063300986137297e-05, "epoch": 1.9512591389114542, "percentage": 39.47, "elapsed_time": "4:16:14", "remaining_time": "6:32:54"}
151
+ {"current_steps": 151, "total_steps": 380, "loss": 0.5512, "lr": 6.0317362129981375e-05, "epoch": 1.9642567018683996, "percentage": 39.74, "elapsed_time": "4:17:57", "remaining_time": "6:31:11"}
152
+ {"current_steps": 152, "total_steps": 380, "loss": 0.5558, "lr": 6.000000000000001e-05, "epoch": 1.9772542648253453, "percentage": 40.0, "elapsed_time": "4:19:37", "remaining_time": "6:29:26"}
153
+ {"current_steps": 153, "total_steps": 380, "loss": 0.5582, "lr": 5.968095025075114e-05, "epoch": 1.990251827782291, "percentage": 40.26, "elapsed_time": "4:21:19", "remaining_time": "6:27:42"}
154
+ {"current_steps": 154, "total_steps": 380, "loss": 0.5421, "lr": 5.936023980395997e-05, "epoch": 2.0048740861088548, "percentage": 40.53, "elapsed_time": "4:24:48", "remaining_time": "6:28:36"}
155
+ {"current_steps": 155, "total_steps": 380, "loss": 0.5126, "lr": 5.903789572148295e-05, "epoch": 2.0178716490658, "percentage": 40.79, "elapsed_time": "4:26:32", "remaining_time": "6:26:54"}
156
+ {"current_steps": 156, "total_steps": 380, "loss": 0.5046, "lr": 5.871394520302432e-05, "epoch": 2.0308692120227456, "percentage": 41.05, "elapsed_time": "4:28:16", "remaining_time": "6:25:12"}
157
+ {"current_steps": 157, "total_steps": 380, "loss": 0.5045, "lr": 5.838841558384091e-05, "epoch": 2.0438667749796915, "percentage": 41.32, "elapsed_time": "4:29:58", "remaining_time": "6:23:27"}
158
+ {"current_steps": 158, "total_steps": 380, "loss": 0.5145, "lr": 5.806133433243558e-05, "epoch": 2.056864337936637, "percentage": 41.58, "elapsed_time": "4:31:42", "remaining_time": "6:21:46"}
159
+ {"current_steps": 159, "total_steps": 380, "loss": 0.5092, "lr": 5.7732729048239444e-05, "epoch": 2.0698619008935824, "percentage": 41.84, "elapsed_time": "4:33:26", "remaining_time": "6:20:03"}
160
+ {"current_steps": 160, "total_steps": 380, "loss": 0.5103, "lr": 5.740262745928293e-05, "epoch": 2.0828594638505282, "percentage": 42.11, "elapsed_time": "4:35:10", "remaining_time": "6:18:21"}
161
+ {"current_steps": 161, "total_steps": 380, "loss": 0.5104, "lr": 5.707105741985615e-05, "epoch": 2.0958570268074737, "percentage": 42.37, "elapsed_time": "4:36:53", "remaining_time": "6:16:38"}
162
+ {"current_steps": 162, "total_steps": 380, "loss": 0.5117, "lr": 5.673804690815845e-05, "epoch": 2.108854589764419, "percentage": 42.63, "elapsed_time": "4:38:37", "remaining_time": "6:14:56"}
163
+ {"current_steps": 163, "total_steps": 380, "loss": 0.5039, "lr": 5.6403624023937614e-05, "epoch": 2.121852152721365, "percentage": 42.89, "elapsed_time": "4:40:20", "remaining_time": "6:13:12"}
164
+ {"current_steps": 164, "total_steps": 380, "loss": 0.5043, "lr": 5.606781698611879e-05, "epoch": 2.1348497156783104, "percentage": 43.16, "elapsed_time": "4:42:04", "remaining_time": "6:11:30"}