neginr commited on
Commit
3adfa21
·
verified ·
1 Parent(s): aa681a7

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 sha256:411aac6604bf47f27d74f0904234df5caf42ff88267fe5b6de1627a500fcd735
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:867c09ca7488e0b53538e07ece7910f9cddc709326924ee3b0c789cd87c95a68
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7834dddeb1bee1c326f94023ba3b2208a1c391afb0e409ebeb768a7fe1bf7f20
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:669af510ccf69863b7ec7644cdc314b812cd337e7e206544b178543efa45b86e
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d74459e525fd3334ec6a17d9b173650272d72928c6fd88563a834adc01568a8
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e76ce8056b9c5bf2e510baaf8052a73dd11c6a107437b7fb84cc1bae53526a99
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:f5cc42bf111e8200f2f3d07caeb17b357369ba2f6ed8f8874f6093c5eb87c929
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1110f99ec37c558504d1be8a822f8f10edde50601c68700dd7c0586642810245
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -84,3 +84,53 @@
84
  {"current_steps": 84, "total_steps": 364, "loss": 0.5787, "lr": 1.8997744869421248e-05, "epoch": 1.605095541401274, "percentage": 23.08, "elapsed_time": "0:08:57", "remaining_time": "0:29:51"}
85
  {"current_steps": 85, "total_steps": 364, "loss": 0.6337, "lr": 1.8955408240595396e-05, "epoch": 1.6242038216560508, "percentage": 23.35, "elapsed_time": "0:09:03", "remaining_time": "0:29:45"}
86
  {"current_steps": 86, "total_steps": 364, "loss": 0.5819, "lr": 1.891224502911428e-05, "epoch": 1.643312101910828, "percentage": 23.63, "elapsed_time": "0:09:07", "remaining_time": "0:29:31"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
84
  {"current_steps": 84, "total_steps": 364, "loss": 0.5787, "lr": 1.8997744869421248e-05, "epoch": 1.605095541401274, "percentage": 23.08, "elapsed_time": "0:08:57", "remaining_time": "0:29:51"}
85
  {"current_steps": 85, "total_steps": 364, "loss": 0.6337, "lr": 1.8955408240595396e-05, "epoch": 1.6242038216560508, "percentage": 23.35, "elapsed_time": "0:09:03", "remaining_time": "0:29:45"}
86
  {"current_steps": 86, "total_steps": 364, "loss": 0.5819, "lr": 1.891224502911428e-05, "epoch": 1.643312101910828, "percentage": 23.63, "elapsed_time": "0:09:07", "remaining_time": "0:29:31"}
87
+ {"current_steps": 87, "total_steps": 364, "loss": 0.564, "lr": 1.886825921893497e-05, "epoch": 1.662420382165605, "percentage": 23.9, "elapsed_time": "0:09:11", "remaining_time": "0:29:16"}
88
+ {"current_steps": 88, "total_steps": 364, "loss": 0.5912, "lr": 1.8823454869940243e-05, "epoch": 1.6815286624203822, "percentage": 24.18, "elapsed_time": "0:09:17", "remaining_time": "0:29:07"}
89
+ {"current_steps": 89, "total_steps": 364, "loss": 0.5729, "lr": 1.8777836117563894e-05, "epoch": 1.700636942675159, "percentage": 24.45, "elapsed_time": "0:09:21", "remaining_time": "0:28:55"}
90
+ {"current_steps": 90, "total_steps": 364, "loss": 0.6001, "lr": 1.873140717240899e-05, "epoch": 1.7197452229299364, "percentage": 24.73, "elapsed_time": "0:09:30", "remaining_time": "0:28:56"}
91
+ {"current_steps": 91, "total_steps": 364, "loss": 0.6095, "lr": 1.8684172319859258e-05, "epoch": 1.7388535031847132, "percentage": 25.0, "elapsed_time": "0:09:36", "remaining_time": "0:28:48"}
92
+ {"current_steps": 92, "total_steps": 364, "loss": 0.6119, "lr": 1.863613591968355e-05, "epoch": 1.7579617834394905, "percentage": 25.27, "elapsed_time": "0:09:39", "remaining_time": "0:28:34"}
93
+ {"current_steps": 93, "total_steps": 364, "loss": 0.5596, "lr": 1.858730240563342e-05, "epoch": 1.7770700636942676, "percentage": 25.55, "elapsed_time": "0:09:47", "remaining_time": "0:28:31"}
94
+ {"current_steps": 94, "total_steps": 364, "loss": 0.6112, "lr": 1.8537676285033886e-05, "epoch": 1.7961783439490446, "percentage": 25.82, "elapsed_time": "0:09:52", "remaining_time": "0:28:23"}
95
+ {"current_steps": 95, "total_steps": 364, "loss": 0.5481, "lr": 1.848726213836744e-05, "epoch": 1.8152866242038217, "percentage": 26.1, "elapsed_time": "0:10:00", "remaining_time": "0:28:21"}
96
+ {"current_steps": 96, "total_steps": 364, "loss": 0.574, "lr": 1.8436064618851225e-05, "epoch": 1.8343949044585988, "percentage": 26.37, "elapsed_time": "0:10:04", "remaining_time": "0:28:07"}
97
+ {"current_steps": 97, "total_steps": 364, "loss": 0.5501, "lr": 1.838408845200758e-05, "epoch": 1.8535031847133758, "percentage": 26.65, "elapsed_time": "0:10:10", "remaining_time": "0:28:01"}
98
+ {"current_steps": 98, "total_steps": 364, "loss": 0.5783, "lr": 1.8331338435227838e-05, "epoch": 1.872611464968153, "percentage": 26.92, "elapsed_time": "0:10:15", "remaining_time": "0:27:49"}
99
+ {"current_steps": 99, "total_steps": 364, "loss": 0.6018, "lr": 1.8277819437329577e-05, "epoch": 1.89171974522293, "percentage": 27.2, "elapsed_time": "0:10:20", "remaining_time": "0:27:41"}
100
+ {"current_steps": 100, "total_steps": 364, "loss": 0.5573, "lr": 1.8223536398107177e-05, "epoch": 1.910828025477707, "percentage": 27.47, "elapsed_time": "0:10:26", "remaining_time": "0:27:33"}
101
+ {"current_steps": 101, "total_steps": 364, "loss": 0.5748, "lr": 1.8168494327875918e-05, "epoch": 1.929936305732484, "percentage": 27.75, "elapsed_time": "0:10:34", "remaining_time": "0:27:32"}
102
+ {"current_steps": 102, "total_steps": 364, "loss": 0.5961, "lr": 1.8112698307009506e-05, "epoch": 1.9490445859872612, "percentage": 28.02, "elapsed_time": "0:10:38", "remaining_time": "0:27:20"}
103
+ {"current_steps": 103, "total_steps": 364, "loss": 0.6006, "lr": 1.8056153485471167e-05, "epoch": 1.9681528662420382, "percentage": 28.3, "elapsed_time": "0:10:43", "remaining_time": "0:27:11"}
104
+ {"current_steps": 104, "total_steps": 364, "loss": 0.5827, "lr": 1.799886508233829e-05, "epoch": 1.9872611464968153, "percentage": 28.57, "elapsed_time": "0:10:47", "remaining_time": "0:26:59"}
105
+ {"current_steps": 105, "total_steps": 364, "loss": 0.4899, "lr": 1.7940838385320732e-05, "epoch": 2.0063694267515926, "percentage": 28.85, "elapsed_time": "0:12:37", "remaining_time": "0:31:08"}
106
+ {"current_steps": 106, "total_steps": 364, "loss": 0.3823, "lr": 1.788207875027274e-05, "epoch": 2.0254777070063694, "percentage": 29.12, "elapsed_time": "0:12:42", "remaining_time": "0:30:55"}
107
+ {"current_steps": 107, "total_steps": 364, "loss": 0.3707, "lr": 1.7822591600698632e-05, "epoch": 2.0445859872611467, "percentage": 29.4, "elapsed_time": "0:12:46", "remaining_time": "0:30:42"}
108
+ {"current_steps": 108, "total_steps": 364, "loss": 0.3515, "lr": 1.776238242725217e-05, "epoch": 2.0636942675159236, "percentage": 29.67, "elapsed_time": "0:12:50", "remaining_time": "0:30:26"}
109
+ {"current_steps": 109, "total_steps": 364, "loss": 0.3351, "lr": 1.7701456787229805e-05, "epoch": 2.082802547770701, "percentage": 29.95, "elapsed_time": "0:12:54", "remaining_time": "0:30:12"}
110
+ {"current_steps": 110, "total_steps": 364, "loss": 0.3682, "lr": 1.7639820304057745e-05, "epoch": 2.1019108280254777, "percentage": 30.22, "elapsed_time": "0:13:01", "remaining_time": "0:30:03"}
111
+ {"current_steps": 111, "total_steps": 364, "loss": 0.347, "lr": 1.7577478666772886e-05, "epoch": 2.121019108280255, "percentage": 30.49, "elapsed_time": "0:13:06", "remaining_time": "0:29:53"}
112
+ {"current_steps": 112, "total_steps": 364, "loss": 0.306, "lr": 1.751443762949772e-05, "epoch": 2.140127388535032, "percentage": 30.77, "elapsed_time": "0:13:10", "remaining_time": "0:29:38"}
113
+ {"current_steps": 113, "total_steps": 364, "loss": 0.3544, "lr": 1.7450703010909263e-05, "epoch": 2.159235668789809, "percentage": 31.04, "elapsed_time": "0:13:17", "remaining_time": "0:29:31"}
114
+ {"current_steps": 114, "total_steps": 364, "loss": 0.3186, "lr": 1.738628069370195e-05, "epoch": 2.178343949044586, "percentage": 31.32, "elapsed_time": "0:13:22", "remaining_time": "0:29:20"}
115
+ {"current_steps": 115, "total_steps": 364, "loss": 0.3264, "lr": 1.732117662404469e-05, "epoch": 2.1974522292993632, "percentage": 31.59, "elapsed_time": "0:13:27", "remaining_time": "0:29:08"}
116
+ {"current_steps": 116, "total_steps": 364, "loss": 0.3757, "lr": 1.7255396811032014e-05, "epoch": 2.21656050955414, "percentage": 31.87, "elapsed_time": "0:13:35", "remaining_time": "0:29:03"}
117
+ {"current_steps": 117, "total_steps": 364, "loss": 0.3388, "lr": 1.718894732612947e-05, "epoch": 2.2356687898089174, "percentage": 32.14, "elapsed_time": "0:13:39", "remaining_time": "0:28:49"}
118
+ {"current_steps": 118, "total_steps": 364, "loss": 0.3461, "lr": 1.712183430261319e-05, "epoch": 2.254777070063694, "percentage": 32.42, "elapsed_time": "0:13:44", "remaining_time": "0:28:38"}
119
+ {"current_steps": 119, "total_steps": 364, "loss": 0.343, "lr": 1.7054063935003813e-05, "epoch": 2.2738853503184715, "percentage": 32.69, "elapsed_time": "0:13:48", "remaining_time": "0:28:26"}
120
+ {"current_steps": 120, "total_steps": 364, "loss": 0.3578, "lr": 1.698564247849473e-05, "epoch": 2.2929936305732483, "percentage": 32.97, "elapsed_time": "0:13:53", "remaining_time": "0:28:13"}
121
+ {"current_steps": 121, "total_steps": 364, "loss": 0.3338, "lr": 1.691657624837472e-05, "epoch": 2.3121019108280256, "percentage": 33.24, "elapsed_time": "0:13:59", "remaining_time": "0:28:05"}
122
+ {"current_steps": 122, "total_steps": 364, "loss": 0.3513, "lr": 1.684687161944506e-05, "epoch": 2.3312101910828025, "percentage": 33.52, "elapsed_time": "0:14:03", "remaining_time": "0:27:53"}
123
+ {"current_steps": 123, "total_steps": 364, "loss": 0.3774, "lr": 1.677653502543113e-05, "epoch": 2.3503184713375798, "percentage": 33.79, "elapsed_time": "0:14:11", "remaining_time": "0:27:47"}
124
+ {"current_steps": 124, "total_steps": 364, "loss": 0.366, "lr": 1.6705572958388576e-05, "epoch": 2.3694267515923566, "percentage": 34.07, "elapsed_time": "0:14:16", "remaining_time": "0:27:38"}
125
+ {"current_steps": 125, "total_steps": 364, "loss": 0.3268, "lr": 1.6633991968104095e-05, "epoch": 2.388535031847134, "percentage": 34.34, "elapsed_time": "0:14:22", "remaining_time": "0:27:29"}
126
+ {"current_steps": 126, "total_steps": 364, "loss": 0.3329, "lr": 1.6561798661490904e-05, "epoch": 2.4076433121019107, "percentage": 34.62, "elapsed_time": "0:14:31", "remaining_time": "0:27:26"}
127
+ {"current_steps": 127, "total_steps": 364, "loss": 0.367, "lr": 1.6488999701978905e-05, "epoch": 2.426751592356688, "percentage": 34.89, "elapsed_time": "0:14:38", "remaining_time": "0:27:18"}
128
+ {"current_steps": 128, "total_steps": 364, "loss": 0.2974, "lr": 1.6415601808899658e-05, "epoch": 2.445859872611465, "percentage": 35.16, "elapsed_time": "0:14:45", "remaining_time": "0:27:12"}
129
+ {"current_steps": 129, "total_steps": 364, "loss": 0.3347, "lr": 1.63416117568662e-05, "epoch": 2.464968152866242, "percentage": 35.44, "elapsed_time": "0:14:49", "remaining_time": "0:27:00"}
130
+ {"current_steps": 130, "total_steps": 364, "loss": 0.336, "lr": 1.6267036375147728e-05, "epoch": 2.484076433121019, "percentage": 35.71, "elapsed_time": "0:14:55", "remaining_time": "0:26:51"}
131
+ {"current_steps": 131, "total_steps": 364, "loss": 0.3083, "lr": 1.619188254703927e-05, "epoch": 2.5031847133757963, "percentage": 35.99, "elapsed_time": "0:15:01", "remaining_time": "0:26:43"}
132
+ {"current_steps": 132, "total_steps": 364, "loss": 0.3366, "lr": 1.6116157209226356e-05, "epoch": 2.522292993630573, "percentage": 36.26, "elapsed_time": "0:15:05", "remaining_time": "0:26:31"}
133
+ {"current_steps": 133, "total_steps": 364, "loss": 0.3719, "lr": 1.6039867351144778e-05, "epoch": 2.5414012738853504, "percentage": 36.54, "elapsed_time": "0:15:12", "remaining_time": "0:26:24"}
134
+ {"current_steps": 134, "total_steps": 364, "loss": 0.3283, "lr": 1.5963020014335437e-05, "epoch": 2.5605095541401273, "percentage": 36.81, "elapsed_time": "0:15:15", "remaining_time": "0:26:11"}
135
+ {"current_steps": 135, "total_steps": 364, "loss": 0.3597, "lr": 1.588562229179443e-05, "epoch": 2.5796178343949046, "percentage": 37.09, "elapsed_time": "0:15:20", "remaining_time": "0:26:00"}
136
+ {"current_steps": 136, "total_steps": 364, "loss": 0.361, "lr": 1.5807681327318372e-05, "epoch": 2.5987261146496814, "percentage": 37.36, "elapsed_time": "0:15:24", "remaining_time": "0:25:49"}