ryanmarten commited on
Commit
ab29849
·
verified ·
1 Parent(s): 70a54d7

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 sha256:4dc68b9bfcab0339554fe8973b5c5b06c60f4687175c6d7513ba0c2de632e593
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d9cd478c32e7a8f8aee819821ec1f0edab4509e65f1ff0159c06a56c4167cf6
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7501e370f6f59c9c856d4c72727d687d4287c751aa9dfef59b31595b0d58ba54
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24c46748bfd555ac596c7516ab6f73a1fce76dff1273a6e8a662152a85ef02ab
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4edc3e17dfa6ae597278a0ea8f6fb7cd2c0a94491c724dc4f59986becb1acb52
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31b7c8fd2a80360f1ccda055425082b55c46ed6e6146ccfa5ce86a5765db9bfd
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:e1758ca9a8d0b5fd1041506efe5273ec63cb59621c5e2ddd799b12497e328d80
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b4ae860834e90c442a4a1c655feb05ff4b1f25d1e28c131c327185797a10fab
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -76,3 +76,79 @@
76
  {"current_steps": 76, "total_steps": 380, "loss": 0.6102, "lr": 7.758770483143634e-05, "epoch": 0.9878147847278635, "percentage": 20.0, "elapsed_time": "2:06:09", "remaining_time": "8:24:39"}
77
  {"current_steps": 77, "total_steps": 380, "loss": 0.6116, "lr": 7.74604496478822e-05, "epoch": 1.0024370430544274, "percentage": 20.26, "elapsed_time": "2:09:38", "remaining_time": "8:30:09"}
78
  {"current_steps": 78, "total_steps": 380, "loss": 0.5828, "lr": 7.733003351549829e-05, "epoch": 1.0154346060113728, "percentage": 20.53, "elapsed_time": "2:11:18", "remaining_time": "8:28:23"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  {"current_steps": 76, "total_steps": 380, "loss": 0.6102, "lr": 7.758770483143634e-05, "epoch": 0.9878147847278635, "percentage": 20.0, "elapsed_time": "2:06:09", "remaining_time": "8:24:39"}
77
  {"current_steps": 77, "total_steps": 380, "loss": 0.6116, "lr": 7.74604496478822e-05, "epoch": 1.0024370430544274, "percentage": 20.26, "elapsed_time": "2:09:38", "remaining_time": "8:30:09"}
78
  {"current_steps": 78, "total_steps": 380, "loss": 0.5828, "lr": 7.733003351549829e-05, "epoch": 1.0154346060113728, "percentage": 20.53, "elapsed_time": "2:11:18", "remaining_time": "8:28:23"}
79
+ {"current_steps": 79, "total_steps": 380, "loss": 0.584, "lr": 7.719646743892352e-05, "epoch": 1.0284321689683185, "percentage": 20.79, "elapsed_time": "2:12:58", "remaining_time": "8:26:37"}
80
+ {"current_steps": 80, "total_steps": 380, "loss": 0.5892, "lr": 7.705976268859207e-05, "epoch": 1.0414297319252641, "percentage": 21.05, "elapsed_time": "2:14:38", "remaining_time": "8:24:52"}
81
+ {"current_steps": 81, "total_steps": 380, "loss": 0.5809, "lr": 7.691993079978252e-05, "epoch": 1.0544272948822095, "percentage": 21.32, "elapsed_time": "2:16:17", "remaining_time": "8:23:06"}
82
+ {"current_steps": 82, "total_steps": 380, "loss": 0.5745, "lr": 7.677698357164431e-05, "epoch": 1.0674248578391552, "percentage": 21.58, "elapsed_time": "2:17:57", "remaining_time": "8:21:20"}
83
+ {"current_steps": 83, "total_steps": 380, "loss": 0.5768, "lr": 7.663093306620231e-05, "epoch": 1.0804224207961006, "percentage": 21.84, "elapsed_time": "2:19:36", "remaining_time": "8:19:35"}
84
+ {"current_steps": 84, "total_steps": 380, "loss": 0.5735, "lr": 7.648179160733883e-05, "epoch": 1.0934199837530463, "percentage": 22.11, "elapsed_time": "2:21:16", "remaining_time": "8:17:49"}
85
+ {"current_steps": 85, "total_steps": 380, "loss": 0.5774, "lr": 7.632957177975387e-05, "epoch": 1.106417546709992, "percentage": 22.37, "elapsed_time": "2:22:56", "remaining_time": "8:16:04"}
86
+ {"current_steps": 86, "total_steps": 380, "loss": 0.5806, "lr": 7.61742864279031e-05, "epoch": 1.1194151096669374, "percentage": 22.63, "elapsed_time": "2:24:35", "remaining_time": "8:14:19"}
87
+ {"current_steps": 87, "total_steps": 380, "loss": 0.5725, "lr": 7.601594865491414e-05, "epoch": 1.132412672623883, "percentage": 22.89, "elapsed_time": "2:26:16", "remaining_time": "8:12:35"}
88
+ {"current_steps": 88, "total_steps": 380, "loss": 0.5766, "lr": 7.585457182148081e-05, "epoch": 1.1454102355808287, "percentage": 23.16, "elapsed_time": "2:27:55", "remaining_time": "8:10:50"}
89
+ {"current_steps": 89, "total_steps": 380, "loss": 0.5781, "lr": 7.569016954473577e-05, "epoch": 1.158407798537774, "percentage": 23.42, "elapsed_time": "2:29:35", "remaining_time": "8:09:05"}
90
+ {"current_steps": 90, "total_steps": 380, "loss": 0.5826, "lr": 7.552275569710152e-05, "epoch": 1.1714053614947197, "percentage": 23.68, "elapsed_time": "2:31:14", "remaining_time": "8:07:21"}
91
+ {"current_steps": 91, "total_steps": 380, "loss": 0.581, "lr": 7.535234440511979e-05, "epoch": 1.1844029244516654, "percentage": 23.95, "elapsed_time": "2:32:54", "remaining_time": "8:05:36"}
92
+ {"current_steps": 92, "total_steps": 380, "loss": 0.5821, "lr": 7.517895004825956e-05, "epoch": 1.1974004874086108, "percentage": 24.21, "elapsed_time": "2:34:34", "remaining_time": "8:03:52"}
93
+ {"current_steps": 93, "total_steps": 380, "loss": 0.5761, "lr": 7.500258725770375e-05, "epoch": 1.2103980503655565, "percentage": 24.47, "elapsed_time": "2:36:13", "remaining_time": "8:02:07"}
94
+ {"current_steps": 94, "total_steps": 380, "loss": 0.5695, "lr": 7.48232709151145e-05, "epoch": 1.2233956133225021, "percentage": 24.74, "elapsed_time": "2:37:53", "remaining_time": "8:00:23"}
95
+ {"current_steps": 95, "total_steps": 380, "loss": 0.5805, "lr": 7.464101615137756e-05, "epoch": 1.2363931762794476, "percentage": 25.0, "elapsed_time": "2:39:32", "remaining_time": "7:58:38"}
96
+ {"current_steps": 96, "total_steps": 380, "loss": 0.5649, "lr": 7.445583834532546e-05, "epoch": 1.2493907392363932, "percentage": 25.26, "elapsed_time": "2:41:12", "remaining_time": "7:56:54"}
97
+ {"current_steps": 97, "total_steps": 380, "loss": 0.5758, "lr": 7.426775312243986e-05, "epoch": 1.2623883021933389, "percentage": 25.53, "elapsed_time": "2:42:52", "remaining_time": "7:55:10"}
98
+ {"current_steps": 98, "total_steps": 380, "loss": 0.574, "lr": 7.407677635353308e-05, "epoch": 1.2753858651502843, "percentage": 25.79, "elapsed_time": "2:44:31", "remaining_time": "7:53:26"}
99
+ {"current_steps": 99, "total_steps": 380, "loss": 0.5685, "lr": 7.388292415340888e-05, "epoch": 1.28838342810723, "percentage": 26.05, "elapsed_time": "2:46:11", "remaining_time": "7:51:42"}
100
+ {"current_steps": 100, "total_steps": 380, "loss": 0.5645, "lr": 7.368621287950264e-05, "epoch": 1.3013809910641756, "percentage": 26.32, "elapsed_time": "2:47:51", "remaining_time": "7:49:58"}
101
+ {"current_steps": 101, "total_steps": 380, "loss": 0.5602, "lr": 7.348665913050115e-05, "epoch": 1.314378554021121, "percentage": 26.58, "elapsed_time": "2:49:30", "remaining_time": "7:48:15"}
102
+ {"current_steps": 102, "total_steps": 380, "loss": 0.5676, "lr": 7.328427974494201e-05, "epoch": 1.3273761169780667, "percentage": 26.84, "elapsed_time": "2:51:10", "remaining_time": "7:46:32"}
103
+ {"current_steps": 103, "total_steps": 380, "loss": 0.5648, "lr": 7.307909179979274e-05, "epoch": 1.340373679935012, "percentage": 27.11, "elapsed_time": "2:52:50", "remaining_time": "7:44:49"}
104
+ {"current_steps": 104, "total_steps": 380, "loss": 0.5651, "lr": 7.28711126090098e-05, "epoch": 1.3533712428919578, "percentage": 27.37, "elapsed_time": "2:54:29", "remaining_time": "7:43:05"}
105
+ {"current_steps": 105, "total_steps": 380, "loss": 0.5572, "lr": 7.266035972207773e-05, "epoch": 1.3663688058489034, "percentage": 27.63, "elapsed_time": "2:56:09", "remaining_time": "7:41:22"}
106
+ {"current_steps": 106, "total_steps": 380, "loss": 0.5689, "lr": 7.24468509225281e-05, "epoch": 1.3793663688058488, "percentage": 27.89, "elapsed_time": "2:57:49", "remaining_time": "7:39:38"}
107
+ {"current_steps": 107, "total_steps": 380, "loss": 0.5685, "lr": 7.223060422643914e-05, "epoch": 1.3923639317627945, "percentage": 28.16, "elapsed_time": "2:59:28", "remaining_time": "7:37:55"}
108
+ {"current_steps": 108, "total_steps": 380, "loss": 0.5669, "lr": 7.201163788091536e-05, "epoch": 1.40536149471974, "percentage": 28.42, "elapsed_time": "3:01:08", "remaining_time": "7:36:12"}
109
+ {"current_steps": 109, "total_steps": 380, "loss": 0.5681, "lr": 7.178997036254799e-05, "epoch": 1.4183590576766856, "percentage": 28.68, "elapsed_time": "3:02:48", "remaining_time": "7:34:29"}
110
+ {"current_steps": 110, "total_steps": 380, "loss": 0.5661, "lr": 7.156562037585576e-05, "epoch": 1.4313566206336312, "percentage": 28.95, "elapsed_time": "3:04:27", "remaining_time": "7:32:46"}
111
+ {"current_steps": 111, "total_steps": 380, "loss": 0.5736, "lr": 7.133860685170665e-05, "epoch": 1.4443541835905767, "percentage": 29.21, "elapsed_time": "3:06:07", "remaining_time": "7:31:03"}
112
+ {"current_steps": 112, "total_steps": 380, "loss": 0.5641, "lr": 7.110894894572056e-05, "epoch": 1.4573517465475223, "percentage": 29.47, "elapsed_time": "3:07:47", "remaining_time": "7:29:20"}
113
+ {"current_steps": 113, "total_steps": 380, "loss": 0.5606, "lr": 7.087666603665284e-05, "epoch": 1.470349309504468, "percentage": 29.74, "elapsed_time": "3:09:27", "remaining_time": "7:27:38"}
114
+ {"current_steps": 114, "total_steps": 380, "loss": 0.5677, "lr": 7.064177772475912e-05, "epoch": 1.4833468724614134, "percentage": 30.0, "elapsed_time": "3:11:06", "remaining_time": "7:25:55"}
115
+ {"current_steps": 115, "total_steps": 380, "loss": 0.5653, "lr": 7.040430383014146e-05, "epoch": 1.496344435418359, "percentage": 30.26, "elapsed_time": "3:12:46", "remaining_time": "7:24:12"}
116
+ {"current_steps": 116, "total_steps": 380, "loss": 0.5644, "lr": 7.016426439107586e-05, "epoch": 1.5093419983753047, "percentage": 30.53, "elapsed_time": "3:14:25", "remaining_time": "7:22:30"}
117
+ {"current_steps": 117, "total_steps": 380, "loss": 0.5567, "lr": 6.992167966232143e-05, "epoch": 1.5223395613322501, "percentage": 30.79, "elapsed_time": "3:16:05", "remaining_time": "7:20:47"}
118
+ {"current_steps": 118, "total_steps": 380, "loss": 0.5749, "lr": 6.967657011341126e-05, "epoch": 1.5353371242891958, "percentage": 31.05, "elapsed_time": "3:17:45", "remaining_time": "7:19:04"}
119
+ {"current_steps": 119, "total_steps": 380, "loss": 0.561, "lr": 6.942895642692527e-05, "epoch": 1.5483346872461414, "percentage": 31.32, "elapsed_time": "3:19:24", "remaining_time": "7:17:22"}
120
+ {"current_steps": 120, "total_steps": 380, "loss": 0.565, "lr": 6.917885949674483e-05, "epoch": 1.5613322502030869, "percentage": 31.58, "elapsed_time": "3:21:05", "remaining_time": "7:15:41"}
121
+ {"current_steps": 121, "total_steps": 380, "loss": 0.5559, "lr": 6.892630042628988e-05, "epoch": 1.5743298131600325, "percentage": 31.84, "elapsed_time": "3:22:46", "remaining_time": "7:14:01"}
122
+ {"current_steps": 122, "total_steps": 380, "loss": 0.5627, "lr": 6.867130052673806e-05, "epoch": 1.5873273761169782, "percentage": 32.11, "elapsed_time": "3:24:27", "remaining_time": "7:12:21"}
123
+ {"current_steps": 123, "total_steps": 380, "loss": 0.561, "lr": 6.841388131522656e-05, "epoch": 1.6003249390739236, "percentage": 32.37, "elapsed_time": "3:26:07", "remaining_time": "7:10:40"}
124
+ {"current_steps": 124, "total_steps": 380, "loss": 0.5619, "lr": 6.815406451303647e-05, "epoch": 1.6133225020308692, "percentage": 32.63, "elapsed_time": "3:27:46", "remaining_time": "7:08:58"}
125
+ {"current_steps": 125, "total_steps": 380, "loss": 0.5637, "lr": 6.789187204375981e-05, "epoch": 1.626320064987815, "percentage": 32.89, "elapsed_time": "3:29:26", "remaining_time": "7:07:15"}
126
+ {"current_steps": 126, "total_steps": 380, "loss": 0.5605, "lr": 6.762732603144978e-05, "epoch": 1.6393176279447603, "percentage": 33.16, "elapsed_time": "3:31:06", "remaining_time": "7:05:33"}
127
+ {"current_steps": 127, "total_steps": 380, "loss": 0.5536, "lr": 6.736044879875373e-05, "epoch": 1.652315190901706, "percentage": 33.42, "elapsed_time": "3:32:45", "remaining_time": "7:03:50"}
128
+ {"current_steps": 128, "total_steps": 380, "loss": 0.5623, "lr": 6.709126286502965e-05, "epoch": 1.6653127538586516, "percentage": 33.68, "elapsed_time": "3:34:25", "remaining_time": "7:02:08"}
129
+ {"current_steps": 129, "total_steps": 380, "loss": 0.5569, "lr": 6.681979094444596e-05, "epoch": 1.678310316815597, "percentage": 33.95, "elapsed_time": "3:36:04", "remaining_time": "7:00:26"}
130
+ {"current_steps": 130, "total_steps": 380, "loss": 0.5575, "lr": 6.654605594406486e-05, "epoch": 1.6913078797725425, "percentage": 34.21, "elapsed_time": "3:37:44", "remaining_time": "6:58:44"}
131
+ {"current_steps": 131, "total_steps": 380, "loss": 0.5573, "lr": 6.627008096190938e-05, "epoch": 1.7043054427294884, "percentage": 34.47, "elapsed_time": "3:39:24", "remaining_time": "6:57:02"}
132
+ {"current_steps": 132, "total_steps": 380, "loss": 0.5598, "lr": 6.59918892850144e-05, "epoch": 1.7173030056864338, "percentage": 34.74, "elapsed_time": "3:41:03", "remaining_time": "6:55:20"}
133
+ {"current_steps": 133, "total_steps": 380, "loss": 0.5573, "lr": 6.571150438746157e-05, "epoch": 1.7303005686433792, "percentage": 35.0, "elapsed_time": "3:42:43", "remaining_time": "6:53:38"}
134
+ {"current_steps": 134, "total_steps": 380, "loss": 0.5525, "lr": 6.542894992839873e-05, "epoch": 1.743298131600325, "percentage": 35.26, "elapsed_time": "3:44:23", "remaining_time": "6:51:55"}
135
+ {"current_steps": 135, "total_steps": 380, "loss": 0.5569, "lr": 6.514424975004329e-05, "epoch": 1.7562956945572705, "percentage": 35.53, "elapsed_time": "3:46:03", "remaining_time": "6:50:14"}
136
+ {"current_steps": 136, "total_steps": 380, "loss": 0.5581, "lr": 6.48574278756706e-05, "epoch": 1.769293257514216, "percentage": 35.79, "elapsed_time": "3:47:42", "remaining_time": "6:48:32"}
137
+ {"current_steps": 137, "total_steps": 380, "loss": 0.5523, "lr": 6.456850850758673e-05, "epoch": 1.7822908204711616, "percentage": 36.05, "elapsed_time": "3:49:22", "remaining_time": "6:46:50"}
138
+ {"current_steps": 138, "total_steps": 380, "loss": 0.5513, "lr": 6.427751602508628e-05, "epoch": 1.7952883834281073, "percentage": 36.32, "elapsed_time": "3:51:02", "remaining_time": "6:45:08"}
139
+ {"current_steps": 139, "total_steps": 380, "loss": 0.5597, "lr": 6.398447498239527e-05, "epoch": 1.8082859463850527, "percentage": 36.58, "elapsed_time": "3:52:41", "remaining_time": "6:43:27"}
140
+ {"current_steps": 140, "total_steps": 380, "loss": 0.5582, "lr": 6.368941010659921e-05, "epoch": 1.8212835093419983, "percentage": 36.84, "elapsed_time": "3:54:21", "remaining_time": "6:41:45"}
141
+ {"current_steps": 141, "total_steps": 380, "loss": 0.5561, "lr": 6.339234629555655e-05, "epoch": 1.834281072298944, "percentage": 37.11, "elapsed_time": "3:56:01", "remaining_time": "6:40:03"}
142
+ {"current_steps": 142, "total_steps": 380, "loss": 0.5584, "lr": 6.309330861579786e-05, "epoch": 1.8472786352558894, "percentage": 37.37, "elapsed_time": "3:57:40", "remaining_time": "6:38:21"}
143
+ {"current_steps": 143, "total_steps": 380, "loss": 0.5536, "lr": 6.279232230041065e-05, "epoch": 1.860276198212835, "percentage": 37.63, "elapsed_time": "3:59:20", "remaining_time": "6:36:40"}
144
+ {"current_steps": 144, "total_steps": 380, "loss": 0.5511, "lr": 6.248941274691017e-05, "epoch": 1.8732737611697807, "percentage": 37.89, "elapsed_time": "4:01:00", "remaining_time": "6:34:58"}
145
+ {"current_steps": 145, "total_steps": 380, "loss": 0.5471, "lr": 6.218460551509636e-05, "epoch": 1.8862713241267262, "percentage": 38.16, "elapsed_time": "4:02:39", "remaining_time": "6:33:16"}
146
+ {"current_steps": 146, "total_steps": 380, "loss": 0.5553, "lr": 6.18779263248971e-05, "epoch": 1.8992688870836718, "percentage": 38.42, "elapsed_time": "4:04:19", "remaining_time": "6:31:35"}
147
+ {"current_steps": 147, "total_steps": 380, "loss": 0.5491, "lr": 6.156940105419785e-05, "epoch": 1.9122664500406175, "percentage": 38.68, "elapsed_time": "4:05:59", "remaining_time": "6:29:54"}
148
+ {"current_steps": 148, "total_steps": 380, "loss": 0.5512, "lr": 6.125905573665824e-05, "epoch": 1.925264012997563, "percentage": 38.95, "elapsed_time": "4:07:38", "remaining_time": "6:28:12"}
149
+ {"current_steps": 149, "total_steps": 380, "loss": 0.5537, "lr": 6.094691655951512e-05, "epoch": 1.9382615759545085, "percentage": 39.21, "elapsed_time": "4:09:18", "remaining_time": "6:26:31"}
150
+ {"current_steps": 150, "total_steps": 380, "loss": 0.5519, "lr": 6.063300986137297e-05, "epoch": 1.9512591389114542, "percentage": 39.47, "elapsed_time": "4:10:58", "remaining_time": "6:24:49"}
151
+ {"current_steps": 151, "total_steps": 380, "loss": 0.5519, "lr": 6.0317362129981375e-05, "epoch": 1.9642567018683996, "percentage": 39.74, "elapsed_time": "4:12:38", "remaining_time": "6:23:08"}
152
+ {"current_steps": 152, "total_steps": 380, "loss": 0.5555, "lr": 6.000000000000001e-05, "epoch": 1.9772542648253453, "percentage": 40.0, "elapsed_time": "4:14:17", "remaining_time": "6:21:26"}
153
+ {"current_steps": 153, "total_steps": 380, "loss": 0.5571, "lr": 5.968095025075114e-05, "epoch": 1.990251827782291, "percentage": 40.26, "elapsed_time": "4:15:56", "remaining_time": "6:19:44"}
154
+ {"current_steps": 154, "total_steps": 380, "loss": 0.5401, "lr": 5.936023980395997e-05, "epoch": 2.0048740861088548, "percentage": 40.53, "elapsed_time": "4:19:34", "remaining_time": "6:20:55"}