neginr commited on
Commit
0050d4f
·
verified ·
1 Parent(s): a01f03d

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 sha256:6daad9e3fcbc2a922d4452b027e0e29a2762cae95ced4e90bb066bc222e85731
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:becfe500848c87be55030cde636635c45e3d75a11954c34e4abf07e4be3a11d0
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8dcd4bf98f605b65e08d571683b49e3e541142117a2f403b88d52b10ae3d40d6
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed70e0ee295229171ca30453388758ac4e3ba55f47c8646e344500c3b10849cc
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ae71d10a257a2fe948689384f7ea2e41047332795ff539d04c5d39248106224
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b59275f7678a7d8d2b5f34a2afbf8a889cee7c69b92e713df4c858cb2c298f9e
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ac079e6f776bec3b7bea2038e04b1c6576e41a3f74d24e7a86650a7211209de
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54a2d4d3b913f3f0b34dd76d4296219c2e9ee9559a4ae8dbea62f204f2b03808
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -85,3 +85,54 @@
85
  {"current_steps": 85, "total_steps": 364, "loss": 0.5773, "lr": 1.8955408240595396e-05, "epoch": 1.6242038216560508, "percentage": 23.35, "elapsed_time": "0:08:59", "remaining_time": "0:29:32"}
86
  {"current_steps": 86, "total_steps": 364, "loss": 0.6068, "lr": 1.891224502911428e-05, "epoch": 1.643312101910828, "percentage": 23.63, "elapsed_time": "0:09:04", "remaining_time": "0:29:21"}
87
  {"current_steps": 87, "total_steps": 364, "loss": 0.5602, "lr": 1.886825921893497e-05, "epoch": 1.662420382165605, "percentage": 23.9, "elapsed_time": "0:09:09", "remaining_time": "0:29:09"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
85
  {"current_steps": 85, "total_steps": 364, "loss": 0.5773, "lr": 1.8955408240595396e-05, "epoch": 1.6242038216560508, "percentage": 23.35, "elapsed_time": "0:08:59", "remaining_time": "0:29:32"}
86
  {"current_steps": 86, "total_steps": 364, "loss": 0.6068, "lr": 1.891224502911428e-05, "epoch": 1.643312101910828, "percentage": 23.63, "elapsed_time": "0:09:04", "remaining_time": "0:29:21"}
87
  {"current_steps": 87, "total_steps": 364, "loss": 0.5602, "lr": 1.886825921893497e-05, "epoch": 1.662420382165605, "percentage": 23.9, "elapsed_time": "0:09:09", "remaining_time": "0:29:09"}
88
+ {"current_steps": 88, "total_steps": 364, "loss": 0.582, "lr": 1.8823454869940243e-05, "epoch": 1.6815286624203822, "percentage": 24.18, "elapsed_time": "0:09:16", "remaining_time": "0:29:06"}
89
+ {"current_steps": 89, "total_steps": 364, "loss": 0.578, "lr": 1.8777836117563894e-05, "epoch": 1.700636942675159, "percentage": 24.45, "elapsed_time": "0:09:21", "remaining_time": "0:28:56"}
90
+ {"current_steps": 90, "total_steps": 364, "loss": 0.6215, "lr": 1.873140717240899e-05, "epoch": 1.7197452229299364, "percentage": 24.73, "elapsed_time": "0:09:29", "remaining_time": "0:28:53"}
91
+ {"current_steps": 91, "total_steps": 364, "loss": 0.6236, "lr": 1.8684172319859258e-05, "epoch": 1.7388535031847132, "percentage": 25.0, "elapsed_time": "0:09:35", "remaining_time": "0:28:45"}
92
+ {"current_steps": 92, "total_steps": 364, "loss": 0.5538, "lr": 1.863613591968355e-05, "epoch": 1.7579617834394905, "percentage": 25.27, "elapsed_time": "0:09:38", "remaining_time": "0:28:31"}
93
+ {"current_steps": 93, "total_steps": 364, "loss": 0.5492, "lr": 1.858730240563342e-05, "epoch": 1.7770700636942676, "percentage": 25.55, "elapsed_time": "0:09:45", "remaining_time": "0:28:27"}
94
+ {"current_steps": 94, "total_steps": 364, "loss": 0.6016, "lr": 1.8537676285033886e-05, "epoch": 1.7961783439490446, "percentage": 25.82, "elapsed_time": "0:09:50", "remaining_time": "0:28:14"}
95
+ {"current_steps": 95, "total_steps": 364, "loss": 0.5578, "lr": 1.848726213836744e-05, "epoch": 1.8152866242038217, "percentage": 26.1, "elapsed_time": "0:09:53", "remaining_time": "0:28:01"}
96
+ {"current_steps": 96, "total_steps": 364, "loss": 0.5573, "lr": 1.8436064618851225e-05, "epoch": 1.8343949044585988, "percentage": 26.37, "elapsed_time": "0:09:57", "remaining_time": "0:27:48"}
97
+ {"current_steps": 97, "total_steps": 364, "loss": 0.5524, "lr": 1.838408845200758e-05, "epoch": 1.8535031847133758, "percentage": 26.65, "elapsed_time": "0:10:02", "remaining_time": "0:27:38"}
98
+ {"current_steps": 98, "total_steps": 364, "loss": 0.5807, "lr": 1.8331338435227838e-05, "epoch": 1.872611464968153, "percentage": 26.92, "elapsed_time": "0:10:06", "remaining_time": "0:27:27"}
99
+ {"current_steps": 99, "total_steps": 364, "loss": 0.5997, "lr": 1.8277819437329577e-05, "epoch": 1.89171974522293, "percentage": 27.2, "elapsed_time": "0:10:12", "remaining_time": "0:27:19"}
100
+ {"current_steps": 100, "total_steps": 364, "loss": 0.5822, "lr": 1.8223536398107177e-05, "epoch": 1.910828025477707, "percentage": 27.47, "elapsed_time": "0:10:16", "remaining_time": "0:27:07"}
101
+ {"current_steps": 101, "total_steps": 364, "loss": 0.6029, "lr": 1.8168494327875918e-05, "epoch": 1.929936305732484, "percentage": 27.75, "elapsed_time": "0:10:23", "remaining_time": "0:27:02"}
102
+ {"current_steps": 102, "total_steps": 364, "loss": 0.5896, "lr": 1.8112698307009506e-05, "epoch": 1.9490445859872612, "percentage": 28.02, "elapsed_time": "0:10:27", "remaining_time": "0:26:52"}
103
+ {"current_steps": 103, "total_steps": 364, "loss": 0.5807, "lr": 1.8056153485471167e-05, "epoch": 1.9681528662420382, "percentage": 28.3, "elapsed_time": "0:10:32", "remaining_time": "0:26:42"}
104
+ {"current_steps": 104, "total_steps": 364, "loss": 0.5835, "lr": 1.799886508233829e-05, "epoch": 1.9872611464968153, "percentage": 28.57, "elapsed_time": "0:10:36", "remaining_time": "0:26:31"}
105
+ {"current_steps": 105, "total_steps": 364, "loss": 0.4879, "lr": 1.7940838385320732e-05, "epoch": 2.0063694267515926, "percentage": 28.85, "elapsed_time": "0:12:25", "remaining_time": "0:30:39"}
106
+ {"current_steps": 106, "total_steps": 364, "loss": 0.3399, "lr": 1.788207875027274e-05, "epoch": 2.0254777070063694, "percentage": 29.12, "elapsed_time": "0:12:33", "remaining_time": "0:30:35"}
107
+ {"current_steps": 107, "total_steps": 364, "loss": 0.3263, "lr": 1.7822591600698632e-05, "epoch": 2.0445859872611467, "percentage": 29.4, "elapsed_time": "0:12:38", "remaining_time": "0:30:22"}
108
+ {"current_steps": 108, "total_steps": 364, "loss": 0.3745, "lr": 1.776238242725217e-05, "epoch": 2.0636942675159236, "percentage": 29.67, "elapsed_time": "0:12:43", "remaining_time": "0:30:10"}
109
+ {"current_steps": 109, "total_steps": 364, "loss": 0.3178, "lr": 1.7701456787229805e-05, "epoch": 2.082802547770701, "percentage": 29.95, "elapsed_time": "0:12:48", "remaining_time": "0:29:57"}
110
+ {"current_steps": 110, "total_steps": 364, "loss": 0.3473, "lr": 1.7639820304057745e-05, "epoch": 2.1019108280254777, "percentage": 30.22, "elapsed_time": "0:12:54", "remaining_time": "0:29:48"}
111
+ {"current_steps": 111, "total_steps": 364, "loss": 0.3422, "lr": 1.7577478666772886e-05, "epoch": 2.121019108280255, "percentage": 30.49, "elapsed_time": "0:12:58", "remaining_time": "0:29:33"}
112
+ {"current_steps": 112, "total_steps": 364, "loss": 0.3631, "lr": 1.751443762949772e-05, "epoch": 2.140127388535032, "percentage": 30.77, "elapsed_time": "0:13:02", "remaining_time": "0:29:21"}
113
+ {"current_steps": 113, "total_steps": 364, "loss": 0.3147, "lr": 1.7450703010909263e-05, "epoch": 2.159235668789809, "percentage": 31.04, "elapsed_time": "0:13:08", "remaining_time": "0:29:11"}
114
+ {"current_steps": 114, "total_steps": 364, "loss": 0.3676, "lr": 1.738628069370195e-05, "epoch": 2.178343949044586, "percentage": 31.32, "elapsed_time": "0:13:12", "remaining_time": "0:28:58"}
115
+ {"current_steps": 115, "total_steps": 364, "loss": 0.3665, "lr": 1.732117662404469e-05, "epoch": 2.1974522292993632, "percentage": 31.59, "elapsed_time": "0:13:17", "remaining_time": "0:28:46"}
116
+ {"current_steps": 116, "total_steps": 364, "loss": 0.3573, "lr": 1.7255396811032014e-05, "epoch": 2.21656050955414, "percentage": 31.87, "elapsed_time": "0:13:21", "remaining_time": "0:28:33"}
117
+ {"current_steps": 117, "total_steps": 364, "loss": 0.322, "lr": 1.718894732612947e-05, "epoch": 2.2356687898089174, "percentage": 32.14, "elapsed_time": "0:13:25", "remaining_time": "0:28:19"}
118
+ {"current_steps": 118, "total_steps": 364, "loss": 0.3427, "lr": 1.712183430261319e-05, "epoch": 2.254777070063694, "percentage": 32.42, "elapsed_time": "0:13:31", "remaining_time": "0:28:11"}
119
+ {"current_steps": 119, "total_steps": 364, "loss": 0.3678, "lr": 1.7054063935003813e-05, "epoch": 2.2738853503184715, "percentage": 32.69, "elapsed_time": "0:13:38", "remaining_time": "0:28:04"}
120
+ {"current_steps": 120, "total_steps": 364, "loss": 0.3314, "lr": 1.698564247849473e-05, "epoch": 2.2929936305732483, "percentage": 32.97, "elapsed_time": "0:13:41", "remaining_time": "0:27:51"}
121
+ {"current_steps": 121, "total_steps": 364, "loss": 0.3298, "lr": 1.691657624837472e-05, "epoch": 2.3121019108280256, "percentage": 33.24, "elapsed_time": "0:13:46", "remaining_time": "0:27:39"}
122
+ {"current_steps": 122, "total_steps": 364, "loss": 0.3599, "lr": 1.684687161944506e-05, "epoch": 2.3312101910828025, "percentage": 33.52, "elapsed_time": "0:13:52", "remaining_time": "0:27:31"}
123
+ {"current_steps": 123, "total_steps": 364, "loss": 0.359, "lr": 1.677653502543113e-05, "epoch": 2.3503184713375798, "percentage": 33.79, "elapsed_time": "0:13:56", "remaining_time": "0:27:19"}
124
+ {"current_steps": 124, "total_steps": 364, "loss": 0.3477, "lr": 1.6705572958388576e-05, "epoch": 2.3694267515923566, "percentage": 34.07, "elapsed_time": "0:14:00", "remaining_time": "0:27:06"}
125
+ {"current_steps": 125, "total_steps": 364, "loss": 0.3131, "lr": 1.6633991968104095e-05, "epoch": 2.388535031847134, "percentage": 34.34, "elapsed_time": "0:14:03", "remaining_time": "0:26:53"}
126
+ {"current_steps": 126, "total_steps": 364, "loss": 0.3548, "lr": 1.6561798661490904e-05, "epoch": 2.4076433121019107, "percentage": 34.62, "elapsed_time": "0:14:12", "remaining_time": "0:26:50"}
127
+ {"current_steps": 127, "total_steps": 364, "loss": 0.3491, "lr": 1.6488999701978905e-05, "epoch": 2.426751592356688, "percentage": 34.89, "elapsed_time": "0:14:17", "remaining_time": "0:26:39"}
128
+ {"current_steps": 128, "total_steps": 364, "loss": 0.3177, "lr": 1.6415601808899658e-05, "epoch": 2.445859872611465, "percentage": 35.16, "elapsed_time": "0:14:26", "remaining_time": "0:26:36"}
129
+ {"current_steps": 129, "total_steps": 364, "loss": 0.3594, "lr": 1.63416117568662e-05, "epoch": 2.464968152866242, "percentage": 35.44, "elapsed_time": "0:14:30", "remaining_time": "0:26:25"}
130
+ {"current_steps": 130, "total_steps": 364, "loss": 0.3424, "lr": 1.6267036375147728e-05, "epoch": 2.484076433121019, "percentage": 35.71, "elapsed_time": "0:14:36", "remaining_time": "0:26:17"}
131
+ {"current_steps": 131, "total_steps": 364, "loss": 0.3567, "lr": 1.619188254703927e-05, "epoch": 2.5031847133757963, "percentage": 35.99, "elapsed_time": "0:14:40", "remaining_time": "0:26:05"}
132
+ {"current_steps": 132, "total_steps": 364, "loss": 0.3231, "lr": 1.6116157209226356e-05, "epoch": 2.522292993630573, "percentage": 36.26, "elapsed_time": "0:14:45", "remaining_time": "0:25:56"}
133
+ {"current_steps": 133, "total_steps": 364, "loss": 0.362, "lr": 1.6039867351144778e-05, "epoch": 2.5414012738853504, "percentage": 36.54, "elapsed_time": "0:14:51", "remaining_time": "0:25:48"}
134
+ {"current_steps": 134, "total_steps": 364, "loss": 0.3236, "lr": 1.5963020014335437e-05, "epoch": 2.5605095541401273, "percentage": 36.81, "elapsed_time": "0:14:55", "remaining_time": "0:25:37"}
135
+ {"current_steps": 135, "total_steps": 364, "loss": 0.3675, "lr": 1.588562229179443e-05, "epoch": 2.5796178343949046, "percentage": 37.09, "elapsed_time": "0:14:59", "remaining_time": "0:25:26"}
136
+ {"current_steps": 136, "total_steps": 364, "loss": 0.3488, "lr": 1.5807681327318372e-05, "epoch": 2.5987261146496814, "percentage": 37.36, "elapsed_time": "0:15:04", "remaining_time": "0:25:16"}
137
+ {"current_steps": 137, "total_steps": 364, "loss": 0.3616, "lr": 1.5729204314845002e-05, "epoch": 2.6178343949044587, "percentage": 37.64, "elapsed_time": "0:15:11", "remaining_time": "0:25:09"}
138
+ {"current_steps": 138, "total_steps": 364, "loss": 0.3413, "lr": 1.56501984977892e-05, "epoch": 2.6369426751592355, "percentage": 37.91, "elapsed_time": "0:15:14", "remaining_time": "0:24:58"}