Training in progress, step 10000

experiment_log.txt

@@ -3686,4 +3686,193 @@ A custom logits processor of type <class 'transformers.generation.logits_process
 
 
 
-
 95%|█████████▌| 9501/10000 [19:56:33<16:24:21, 118.36s/it]
 95%|█████████▌| 9502/10000 [19:56:40<11:44:28, 84.88s/it] 
 95%|█████████▌| 9503/10000 [19:56:47<8:28:55, 61.44s/it] 
 95%|█████████▌| 9504/10000 [19:56:54<6:12:27, 45.06s/it]
 95%|█████████▌| 9505/10000 [19:57:01<4:37:06, 33.59s/it]
 95%|█████████▌| 9506/10000 [19:57:08<3:30:38, 25.58s/it]
+
 95%|█████████▌| 9501/10000 [19:56:33<16:24:21, 118.36s/it]
 95%|█████████▌| 9502/10000 [19:56:40<11:44:28, 84.88s/it] 
 95%|█████████▌| 9503/10000 [19:56:47<8:28:55, 61.44s/it] 
 95%|█████████▌| 9504/10000 [19:56:54<6:12:27, 45.06s/it]
 95%|█████████▌| 9505/10000 [19:57:01<4:37:06, 33.59s/it]
 95%|█████████▌| 9506/10000 [19:57:08<3:30:38, 25.58s/it]
 95%|█████████▌| 9507/10000 [19:57:14<2:44:15, 19.99s/it]
 95%|█████████▌| 9508/10000 [19:57:21<2:11:31, 16.04s/it]
 95%|█████████▌| 9509/10000 [19:57:28<1:48:39, 13.28s/it]
 95%|█████████▌| 9510/10000 [19:57:35<1:32:43, 11.35s/it]
 95%|█████████▌| 9511/10000 [19:57:42<1:21:30, 10.00s/it]
 95%|█████████▌| 9512/10000 [19:57:49<1:13:25,  9.03s/it]
 95%|█████████▌| 9513/10000 [19:57:55<1:07:42,  8.34s/it]
 95%|█████████▌| 9514/10000 [19:58:02<1:03:40,  7.86s/it]
 95%|█████████▌| 9515/10000 [19:58:09<1:00:52,  7.53s/it]
 95%|█████████▌| 9516/10000 [19:58:16<58:58,  7.31s/it]  
 95%|█████████▌| 9517/10000 [19:58:22<57:36,  7.16s/it]
 95%|█████████▌| 9518/10000 [19:58:29<56:34,  7.04s/it]
 95%|█████████▌| 9519/10000 [19:58:36<55:46,  6.96s/it]
 95%|█████████▌| 9520/10000 [19:58:43<55:07,  6.89s/it]
 95%|█████████▌| 9521/10000 [19:58:49<54:46,  6.86s/it]
 95%|█████████▌| 9522/10000 [19:58:56<54:23,  6.83s/it]
 95%|█████████▌| 9523/10000 [19:59:03<53:59,  6.79s/it]
 95%|█████████▌| 9524/10000 [19:59:10<53:50,  6.79s/it]
 95%|█████████▌| 9525/10000 [19:59:16<53:38,  6.78s/it]
 95%|█████████▌| 9526/10000 [19:59:23<53:25,  6.76s/it]
 95%|█████████▌| 9527/10000 [19:59:30<53:15,  6.76s/it]
 95%|█████████▌| 9528/10000 [19:59:37<53:17,  6.77s/it]
 95%|█████████▌| 9529/10000 [19:59:44<53:08,  6.77s/it]
 95%|█████████▌| 9530/10000 [19:59:50<53:11,  6.79s/it]
 95%|█████████▌| 9531/10000 [19:59:57<52:59,  6.78s/it]
 95%|█████████▌| 9532/10000 [20:00:04<52:56,  6.79s/it]
 95%|█████████▌| 9533/10000 [20:00:11<52:48,  6.79s/it]
 95%|█████████▌| 9534/10000 [20:00:17<52:38,  6.78s/it]
 95%|█████████▌| 9535/10000 [20:00:24<52:30,  6.77s/it]
 95%|█████████▌| 9536/10000 [20:00:31<52:26,  6.78s/it]
 95%|█████████▌| 9537/10000 [20:00:38<52:16,  6.78s/it]
 95%|█████████▌| 9538/10000 [20:00:45<52:07,  6.77s/it]
 95%|█████████▌| 9539/10000 [20:00:51<52:02,  6.77s/it]
 95%|█████████▌| 9540/10000 [20:00:58<52:08,  6.80s/it]
 95%|█████████▌| 9541/10000 [20:01:05<51:51,  6.78s/it]
 95%|█████████▌| 9542/10000 [20:01:12<51:39,  6.77s/it]
 95%|█████████▌| 9543/10000 [20:01:18<51:28,  6.76s/it]
 95%|█████████▌| 9544/10000 [20:01:25<51:22,  6.76s/it]
 95%|█████████▌| 9545/10000 [20:01:32<51:15,  6.76s/it]
 95%|█████████▌| 9546/10000 [20:01:39<51:08,  6.76s/it]
 95%|█████████▌| 9547/10000 [20:01:45<50:58,  6.75s/it]
 95%|█████████▌| 9548/10000 [20:01:52<50:52,  6.75s/it]
 95%|█████████▌| 9549/10000 [20:01:59<50:41,  6.74s/it]
 96%|█████████▌| 9550/10000 [20:02:06<50:38,  6.75s/it]
 96%|█████████▌| 9551/10000 [20:02:12<50:26,  6.74s/it]
 96%|█████████▌| 9552/10000 [20:02:19<50:21,  6.74s/it]
 96%|█████████▌| 9553/10000 [20:02:26<50:14,  6.74s/it]
 96%|█████████▌| 9554/10000 [20:02:33<50:12,  6.75s/it]
 96%|█████████▌| 9555/10000 [20:02:40<50:20,  6.79s/it]
 96%|█████████▌| 9556/10000 [20:02:46<50:16,  6.79s/it]
 96%|█████████▌| 9557/10000 [20:02:53<50:03,  6.78s/it]
 96%|█████████▌| 9558/10000 [20:03:00<50:00,  6.79s/it]
 96%|█████████▌| 9559/10000 [20:03:07<49:58,  6.80s/it]
 96%|█████████▌| 9560/10000 [20:03:14<50:10,  6.84s/it]
 96%|█████████▌| 9561/10000 [20:03:20<49:40,  6.79s/it]
 96%|█████████▌| 9562/10000 [20:03:27<49:27,  6.78s/it]
 96%|█████████▌| 9563/10000 [20:03:34<49:16,  6.77s/it]
 96%|█████████▌| 9564/10000 [20:03:41<49:09,  6.77s/it]
 96%|█████████▌| 9565/10000 [20:03:47<49:14,  6.79s/it]
 96%|█████████▌| 9566/10000 [20:03:54<49:05,  6.79s/it]
 96%|█████████▌| 9567/10000 [20:04:01<48:55,  6.78s/it]
 96%|█████████▌| 9568/10000 [20:04:08<48:54,  6.79s/it]
 96%|█████████▌| 9569/10000 [20:04:15<48:41,  6.78s/it]
 96%|█████████▌| 9570/10000 [20:04:21<48:37,  6.79s/it]
 96%|█████████▌| 9571/10000 [20:04:28<48:25,  6.77s/it]
 96%|█████████▌| 9572/10000 [20:04:35<48:12,  6.76s/it]
 96%|█████████▌| 9573/10000 [20:04:42<48:03,  6.75s/it]
 96%|█████████▌| 9574/10000 [20:04:48<47:49,  6.74s/it]
 96%|█████████▌| 9575/10000 [20:04:55<47:55,  6.77s/it]
 96%|█████████▌| 9576/10000 [20:05:02<47:53,  6.78s/it]
 96%|█████████▌| 9577/10000 [20:05:09<47:40,  6.76s/it]
 96%|█████████▌| 9578/10000 [20:05:15<47:36,  6.77s/it]
 96%|█████████▌| 9579/10000 [20:05:22<47:26,  6.76s/it]
 96%|█████████▌| 9580/10000 [20:05:29<47:21,  6.77s/it]
 96%|█████████▌| 9581/10000 [20:05:36<47:08,  6.75s/it]
 96%|█████████▌| 9582/10000 [20:05:42<46:55,  6.74s/it]
 96%|█████████▌| 9583/10000 [20:05:49<46:45,  6.73s/it]
 96%|█████████▌| 9584/10000 [20:05:56<46:48,  6.75s/it]
 96%|█████████▌| 9585/10000 [20:06:03<46:52,  6.78s/it]
 96%|█████████▌| 9586/10000 [20:06:09<46:50,  6.79s/it]
 96%|█████████▌| 9587/10000 [20:06:16<46:40,  6.78s/it]
 96%|█████████▌| 9588/10000 [20:06:23<46:36,  6.79s/it]
 96%|█████████▌| 9589/10000 [20:06:30<46:28,  6.78s/it]
 96%|█████████▌| 9590/10000 [20:06:37<46:21,  6.78s/it]
 96%|█████████▌| 9591/10000 [20:06:43<46:21,  6.80s/it]
 96%|█████████▌| 9592/10000 [20:06:50<46:12,  6.80s/it]
 96%|█████████▌| 9593/10000 [20:06:57<45:56,  6.77s/it]
 96%|█████████▌| 9594/10000 [20:07:04<45:48,  6.77s/it]
 96%|█████████▌| 9595/10000 [20:07:10<45:43,  6.77s/it]
 96%|█████████▌| 9596/10000 [20:07:17<45:36,  6.77s/it]
 96%|█████████▌| 9597/10000 [20:07:24<45:36,  6.79s/it]
 96%|█████████▌| 9598/10000 [20:07:31<45:33,  6.80s/it]
 96%|█████████▌| 9599/10000 [20:07:38<45:19,  6.78s/it]
 96%|█████████▌| 9600/10000 [20:07:44<45:11,  6.78s/it]
                                                       
 96%|█████████▌| 9600/10000 [20:07:44<45:11,  6.78s/it]
 96%|█████████▌| 9601/10000 [20:07:51<45:14,  6.80s/it]
 96%|█████████▌| 9602/10000 [20:07:58<45:23,  6.84s/it]
 96%|█████████▌| 9603/10000 [20:08:05<45:30,  6.88s/it]
 96%|█████████▌| 9604/10000 [20:08:12<45:16,  6.86s/it]
 96%|█████████▌| 9605/10000 [20:08:19<45:05,  6.85s/it]
 96%|█████████▌| 9606/10000 [20:08:26<45:14,  6.89s/it]
 96%|█████████▌| 9607/10000 [20:08:33<44:49,  6.84s/it]
 96%|█████████▌| 9608/10000 [20:08:39<44:36,  6.83s/it]
 96%|█████████▌| 9609/10000 [20:08:46<44:22,  6.81s/it]
 96%|█████████▌| 9610/10000 [20:08:53<44:10,  6.80s/it]
 96%|█████████▌| 9611/10000 [20:09:00<44:00,  6.79s/it]
 96%|█████████▌| 9612/10000 [20:09:06<43:51,  6.78s/it]
 96%|█████████▌| 9613/10000 [20:09:13<43:42,  6.78s/it]
 96%|█████████▌| 9614/10000 [20:09:20<43:39,  6.79s/it]
 96%|█████████▌| 9615/10000 [20:09:27<43:32,  6.79s/it]
 96%|█████████▌| 9616/10000 [20:09:34<43:26,  6.79s/it]
 96%|█████████▌| 9617/10000 [20:09:40<43:16,  6.78s/it]
 96%|█████████▌| 9618/10000 [20:09:47<43:05,  6.77s/it]
 96%|█████████▌| 9619/10000 [20:09:54<43:04,  6.78s/it]
 96%|█████████▌| 9620/10000 [20:10:01<43:07,  6.81s/it]
 96%|█████████▌| 9621/10000 [20:10:07<42:53,  6.79s/it]
 96%|███��█████▌| 9622/10000 [20:10:14<42:50,  6.80s/it]
 96%|█████████▌| 9623/10000 [20:10:21<42:39,  6.79s/it]
 96%|█████████▌| 9624/10000 [20:10:28<42:39,  6.81s/it]
 96%|█████████▋| 9625/10000 [20:10:35<42:24,  6.78s/it]
 96%|█████████▋| 9626/10000 [20:10:41<42:12,  6.77s/it]
 96%|█████████▋| 9627/10000 [20:10:48<41:59,  6.76s/it]
 96%|█████████▋| 9628/10000 [20:10:55<41:47,  6.74s/it]
 96%|█████████▋| 9629/10000 [20:11:02<41:39,  6.74s/it]
 96%|█████████▋| 9630/10000 [20:11:08<41:35,  6.75s/it]
 96%|█████████▋| 9631/10000 [20:11:15<41:26,  6.74s/it]
 96%|█████████▋| 9632/10000 [20:11:22<41:27,  6.76s/it]
 96%|█████████▋| 9633/10000 [20:11:29<41:16,  6.75s/it]
 96%|█████████▋| 9634/10000 [20:11:35<41:21,  6.78s/it]
 96%|█████████▋| 9635/10000 [20:11:42<41:09,  6.77s/it]
 96%|█████████▋| 9636/10000 [20:11:49<41:03,  6.77s/it]
 96%|█████████▋| 9637/10000 [20:11:56<40:55,  6.76s/it]
 96%|█████████▋| 9638/10000 [20:12:03<40:55,  6.78s/it]
 96%|█████████▋| 9639/10000 [20:12:09<40:47,  6.78s/it]
 96%|█████████▋| 9640/10000 [20:12:16<40:44,  6.79s/it]
 96%|█████████▋| 9641/10000 [20:12:23<40:36,  6.79s/it]
 96%|█████████▋| 9642/10000 [20:12:30<40:27,  6.78s/it]
 96%|█████████▋| 9643/10000 [20:12:36<40:20,  6.78s/it]
 96%|█████████▋| 9644/10000 [20:12:43<40:11,  6.77s/it]
 96%|█████████▋| 9645/10000 [20:12:50<39:56,  6.75s/it]
 96%|█████████▋| 9646/10000 [20:12:57<39:53,  6.76s/it]
 96%|█████████▋| 9647/10000 [20:13:03<39:47,  6.76s/it]
 96%|█████████▋| 9648/10000 [20:13:10<39:42,  6.77s/it]
 96%|█████████▋| 9649/10000 [20:13:17<39:38,  6.77s/it]
 96%|█████████▋| 9650/10000 [20:13:24<39:35,  6.79s/it]
 97%|█████████▋| 9651/10000 [20:13:31<39:26,  6.78s/it]
 97%|█████████▋| 9652/10000 [20:13:37<39:13,  6.76s/it]
 97%|█████████▋| 9653/10000 [20:13:44<39:10,  6.77s/it]
 97%|█████████▋| 9654/10000 [20:13:51<39:06,  6.78s/it]
 97%|█████████▋| 9655/10000 [20:13:58<38:53,  6.76s/it]
 97%|█████████▋| 9656/10000 [20:14:04<38:44,  6.76s/it]
 97%|█████████▋| 9657/10000 [20:14:11<38:35,  6.75s/it]
 97%|█████████▋| 9658/10000 [20:14:18<38:36,  6.77s/it]
 97%|█████████▋| 9659/10000 [20:14:25<38:31,  6.78s/it]
 97%|█████████▋| 9660/10000 [20:14:32<38:27,  6.79s/it]
 97%|█████████▋| 9661/10000 [20:14:38<38:23,  6.79s/it]
 97%|█████████▋| 9662/10000 [20:14:45<38:12,  6.78s/it]
 97%|█████████▋| 9663/10000 [20:14:52<38:04,  6.78s/it]
 97%|█████████▋| 9664/10000 [20:14:59<37:57,  6.78s/it]
 97%|█████████▋| 9665/10000 [20:15:05<37:48,  6.77s/it]
 97%|█████████▋| 9666/10000 [20:15:12<37:45,  6.78s/it]
 97%|█████████▋| 9667/10000 [20:15:19<37:34,  6.77s/it]
 97%|█████████▋| 9668/10000 [20:15:26<37:26,  6.77s/it]
 97%|█████████▋| 9669/10000 [20:15:32<37:17,  6.76s/it]
 97%|█████████▋| 9670/10000 [20:15:39<37:10,  6.76s/it]
 97%|█████████▋| 9671/10000 [20:15:46<36:59,  6.75s/it]
 97%|█████████▋| 9672/10000 [20:15:53<36:59,  6.77s/it]
 97%|█████████▋| 9673/10000 [20:15:59<36:52,  6.77s/it]
 97%|█████████▋| 9674/10000 [20:16:06<36:53,  6.79s/it]
 97%|█████████▋| 9675/10000 [20:16:13<36:44,  6.78s/it]
 97%|█████████▋| 9676/10000 [20:16:20<36:40,  6.79s/it]
 97%|█████████▋| 9677/10000 [20:16:27<36:32,  6.79s/it]
 97%|█████████▋| 9678/10000 [20:16:33<36:23,  6.78s/it]
 97%|█████████▋| 9679/10000 [20:16:40<36:19,  6.79s/it]
 97%|█████████▋| 9680/10000 [20:16:47<36:12,  6.79s/it]
 97%|█████████▋| 9681/10000 [20:16:54<36:02,  6.78s/it]
 97%|█████████▋| 9682/10000 [20:17:01<35:57,  6.78s/it]
 97%|█████████▋| 9683/10000 [20:17:07<35:51,  6.79s/it]
 97%|█████████▋| 9684/10000 [20:17:14<35:40,  6.77s/it]
 97%|█████████▋| 9685/10000 [20:17:21<35:35,  6.78s/it]
 97%|█████████▋| 9686/10000 [20:17:28<35:36,  6.80s/it]
 97%|█████████▋| 9687/10000 [20:17:35<35:23,  6.78s/it]
 97%|█████████▋| 9688/10000 [20:17:41<35:18,  6.79s/it]
 97%|█████████▋| 9689/10000 [20:17:48<35:04,  6.77s/it]
 97%|█████████▋| 9690/10000 [20:17:55<35:02,  6.78s/it]
 97%|█████████▋| 9691/10000 [20:18:02<34:53,  6.78s/it]
 97%|█████████▋| 9692/10000 [20:18:08<34:49,  6.78s/it]
 97%|█████████▋| 9693/10000 [20:18:15<34:41,  6.78s/it]
 97%|█████████▋| 9694/10000 [20:18:22<34:32,  6.77s/it]
 97%|█████████▋| 9695/10000 [20:18:29<34:22,  6.76s/it]
 97%|█████████▋| 9696/10000 [20:18:36<34:19,  6.77s/it]
 97%|█████████▋| 9697/10000 [20:18:42<34:05,  6.75s/it]
 97%|█████████▋| 9698/10000 [20:18:49<34:04,  6.77s/it]
 97%|█████████▋| 9699/10000 [20:18:56<33:59,  6.78s/it]
 97%|█████████▋| 9700/10000 [20:19:03<33:55,  6.79s/it]
                                                       
 97%|█████████▋| 9700/10000 [20:19:03<33:55,  6.79s/it]
 97%|█████████▋| 9701/10000 [20:19:09<33:48,  6.78s/it]
 97%|█████████▋| 9702/10000 [20:19:16<33:36,  6.77s/it]
 97%|█████████▋| 9703/10000 [20:19:23<33:32,  6.77s/it]
 97%|█████████▋| 9704/10000 [20:19:30<33:25,  6.78s/it]
 97%|█████████▋| 9705/10000 [20:19:36<33:15,  6.77s/it]
 97%|█████████▋| 9706/10000 [20:19:43<33:10,  6.77s/it]
 97%|█████████▋| 9707/10000 [20:19:50<32:57,  6.75s/it]
 97%|█████████▋| 9708/10000 [20:19:57<32:52,  6.75s/it]
 97%|█████████▋| 9709/10000 [20:20:03<32:46,  6.76s/it]
 97%|█████████▋| 9710/10000 [20:20:10<32:39,  6.76s/it]
 97%|█████████▋| 9711/10000 [20:20:17<32:49,  6.81s/it]
 97%|█████████▋| 9712/10000 [20:20:24<32:37,  6.80s/it]
 97%|█████████▋| 9713/10000 [20:20:31<32:29,  6.79s/it]
 97%|█████████▋| 9714/10000 [20:20:37<32:16,  6.77s/it]
 97%|█████████▋| 9715/10000 [20:20:44<32:04,  6.75s/it]
 97%|█████████▋| 9716/10000 [20:20:51<31:57,  6.75s/it]
 97%|█████████▋| 9717/10000 [20:20:58<31:49,  6.75s/it]
 97%|█████████▋| 9718/10000 [20:21:04<31:51,  6.78s/it]
 97%|█████████▋| 9719/10000 [20:21:11<31:47,  6.79s/it]
 97%|█████████▋| 9720/10000 [20:21:18<31:45,  6.80s/it]
 97%|█████████▋| 9721/10000 [20:21:25<31:32,  6.78s/it]
 97%|█████████▋| 9722/10000 [20:21:32<31:22,  6.77s/it]
 97%|█████████▋| 9723/10000 [20:21:38<31:19,  6.78s/it]
 97%|█████████▋| 9724/10000 [20:21:45<31:08,  6.77s/it]
 97%|█████████▋| 9725/10000 [20:21:52<30:57,  6.76s/it]
 97%|█████████▋| 9726/10000 [20:21:59<30:54,  6.77s/it]
 97%|█████████▋| 9727/10000 [20:22:05<30:44,  6.75s/it]
 97%|█████████▋| 9728/10000 [20:22:12<30:39,  6.76s/it]
 97%|█████████▋| 9729/10000 [20:22:19<30:28,  6.75s/it]
 97%|█████████▋| 9730/10000 [20:22:26<30:22,  6.75s/it]
 97%|█████████▋| 9731/10000 [20:22:32<30:13,  6.74s/it]
 97%|█████████▋| 9732/10000 [20:22:39<30:08,  6.75s/it]
 97%|█████████▋| 9733/10000 [20:22:46<30:03,  6.76s/it]
 97%|█████████▋| 9734/10000 [20:22:53<29:56,  6.75s/it]
 97%|█████████▋| 9735/10000 [20:22:59<29:49,  6.75s/it]
 97%|█████████▋| 9736/10000 [20:23:06<29:44,  6.76s/it]
 97%|█████████▋| 9737/10000 [20:23:13<29:40,  6.77s/it]
 97%|█████████▋| 9738/10000 [20:23:20<29:34,  6.77s/it]
 97%|█████████▋| 9739/10000 [20:23:26<29:25,  6.77s/it]
 97%|█████████▋| 9740/10000 [20:23:33<29:16,  6.75s/it]
 97%|█████████▋| 9741/10000 [20:23:40<29:08,  6.75s/it]
 97%|█████████▋| 9742/10000 [20:23:47<28:59,  6.74s/it]
 97%|█████████▋| 9743/10000 [20:23:53<28:56,  6.76s/it]
 97%|█████████▋| 9744/10000 [20:24:00<28:52,  6.77s/it]
 97%|█████████▋| 9745/10000 [20:24:07<28:45,  6.77s/it]
 97%|█████████▋| 9746/10000 [20:24:14<28:37,  6.76s/it]
 97%|█████████▋| 9747/10000 [20:24:21<28:30,  6.76s/it]
 97%|█████████▋| 9748/10000 [20:24:27<28:21,  6.75s/it]
 97%|█████████▋| 9749/10000 [20:24:34<28:12,  6.74s/it]
 98%|█████████▊| 9750/10000 [20:24:41<28:04,  6.74s/it]
 98%|█████████▊| 9751/10000 [20:24:47<27:59,  6.75s/it]
 98%|█████████▊| 9752/10000 [20:24:54<28:00,  6.78s/it]
 98%|█████████▊| 9753/10000 [20:25:01<27:51,  6.77s/it]
 98%|█████████▊| 9754/10000 [20:25:08<27:43,  6.76s/it]
 98%|███���█████▊| 9755/10000 [20:25:15<27:34,  6.75s/it]
 98%|█████████▊| 9756/10000 [20:25:21<27:27,  6.75s/it]
 98%|█████████▊| 9757/10000 [20:25:28<27:14,  6.73s/it]
 98%|█████████▊| 9758/10000 [20:25:35<27:11,  6.74s/it]
 98%|█████████▊| 9759/10000 [20:25:42<27:06,  6.75s/it]
 98%|█████████▊| 9760/10000 [20:25:48<26:59,  6.75s/it]
 98%|█████████▊| 9761/10000 [20:25:55<26:51,  6.74s/it]
 98%|█████████▊| 9762/10000 [20:26:02<26:45,  6.75s/it]
 98%|█████████▊| 9763/10000 [20:26:09<26:40,  6.75s/it]
 98%|█████████▊| 9764/10000 [20:26:15<26:28,  6.73s/it]
 98%|█████████▊| 9765/10000 [20:26:22<26:20,  6.72s/it]
 98%|█████████▊| 9766/10000 [20:26:29<26:12,  6.72s/it]
 98%|█████████▊| 9767/10000 [20:26:35<26:02,  6.71s/it]
 98%|█████████▊| 9768/10000 [20:26:42<25:55,  6.70s/it]
 98%|█████████▊| 9769/10000 [20:26:49<25:51,  6.72s/it]
 98%|█████████▊| 9770/10000 [20:26:55<25:46,  6.73s/it]
 98%|█████████▊| 9771/10000 [20:27:02<25:40,  6.73s/it]
 98%|█████████▊| 9772/10000 [20:27:09<25:33,  6.73s/it]
 98%|█████████▊| 9773/10000 [20:27:16<25:30,  6.74s/it]
 98%|█████████▊| 9774/10000 [20:27:22<25:19,  6.72s/it]
 98%|█████████▊| 9775/10000 [20:27:29<25:09,  6.71s/it]
 98%|█████████▊| 9776/10000 [20:27:36<25:05,  6.72s/it]
 98%|█████████▊| 9777/10000 [20:27:43<25:03,  6.74s/it]
 98%|█████████▊| 9778/10000 [20:27:49<24:57,  6.75s/it]
 98%|█████████▊| 9779/10000 [20:27:56<24:51,  6.75s/it]
 98%|█████████▊| 9780/10000 [20:28:03<24:46,  6.76s/it]
 98%|█████████▊| 9781/10000 [20:28:10<24:41,  6.77s/it]
 98%|█████████▊| 9782/10000 [20:28:16<24:31,  6.75s/it]
 98%|█████████▊| 9783/10000 [20:28:23<24:24,  6.75s/it]
 98%|█████████▊| 9784/10000 [20:28:30<24:17,  6.75s/it]
 98%|█████████▊| 9785/10000 [20:28:37<24:13,  6.76s/it]
 98%|█████████▊| 9786/10000 [20:28:43<24:06,  6.76s/it]
 98%|█████████▊| 9787/10000 [20:28:50<24:02,  6.77s/it]
 98%|█████████▊| 9788/10000 [20:28:57<23:57,  6.78s/it]
 98%|█████████▊| 9789/10000 [20:29:04<23:51,  6.78s/it]
 98%|█████████▊| 9790/10000 [20:29:11<23:42,  6.77s/it]
 98%|█████████▊| 9791/10000 [20:29:17<23:36,  6.78s/it]
 98%|█████████▊| 9792/10000 [20:29:24<23:28,  6.77s/it]
 98%|█████████▊| 9793/10000 [20:29:31<23:25,  6.79s/it]
 98%|█████████▊| 9794/10000 [20:29:38<23:19,  6.79s/it]
 98%|█████████▊| 9795/10000 [20:29:45<23:13,  6.80s/it]
 98%|█████████▊| 9796/10000 [20:29:51<23:02,  6.78s/it]
 98%|█████████▊| 9797/10000 [20:29:58<22:54,  6.77s/it]
 98%|█████████▊| 9798/10000 [20:30:05<22:49,  6.78s/it]
 98%|█████████▊| 9799/10000 [20:30:12<22:40,  6.77s/it]
 98%|█████████▊| 9800/10000 [20:30:18<22:31,  6.76s/it]
                                                       
 98%|█████████▊| 9800/10000 [20:30:18<22:31,  6.76s/it]
 98%|█████████▊| 9801/10000 [20:30:25<22:27,  6.77s/it]
 98%|█████████▊| 9802/10000 [20:30:32<22:18,  6.76s/it]
 98%|█████████▊| 9803/10000 [20:30:39<22:15,  6.78s/it]
 98%|█████████▊| 9804/10000 [20:30:45<22:04,  6.76s/it]
 98%|█████████▊| 9805/10000 [20:30:52<21:56,  6.75s/it]
 98%|█████████▊| 9806/10000 [20:30:59<21:51,  6.76s/it]
 98%|█████████▊| 9807/10000 [20:31:06<21:45,  6.76s/it]
 98%|█████████▊| 9808/10000 [20:31:12<21:39,  6.77s/it]
 98%|█████████▊| 9809/10000 [20:31:19<21:33,  6.77s/it]
 98%|█████████▊| 9810/10000 [20:31:26<21:24,  6.76s/it]
 98%|█████████▊| 9811/10000 [20:31:33<21:17,  6.76s/it]
 98%|█████████▊| 9812/10000 [20:31:39<21:09,  6.75s/it]
 98%|█████████▊| 9813/10000 [20:31:46<21:03,  6.76s/it]
 98%|█████████▊| 9814/10000 [20:31:53<20:58,  6.77s/it]
 98%|█████████▊| 9815/10000 [20:32:00<20:53,  6.77s/it]
 98%|█████████▊| 9816/10000 [20:32:07<20:46,  6.78s/it]
 98%|█████████▊| 9817/10000 [20:32:13<20:39,  6.78s/it]
 98%|█████████▊| 9818/10000 [20:32:20<20:33,  6.78s/it]
 98%|█████████▊| 9819/10000 [20:32:27<20:25,  6.77s/it]
 98%|█████████▊| 9820/10000 [20:32:34<20:18,  6.77s/it]
 98%|█████████▊| 9821/10000 [20:32:40<20:13,  6.78s/it]
 98%|█████████▊| 9822/10000 [20:32:47<20:06,  6.78s/it]
 98%|█████████▊| 9823/10000 [20:32:54<20:00,  6.78s/it]
 98%|█████████▊| 9824/10000 [20:33:01<19:55,  6.79s/it]
 98%|█████████▊| 9825/10000 [20:33:08<19:46,  6.78s/it]
 98%|█████████▊| 9826/10000 [20:33:14<19:38,  6.77s/it]
 98%|█████████▊| 9827/10000 [20:33:21<19:33,  6.78s/it]
 98%|█████████▊| 9828/10000 [20:33:28<19:26,  6.78s/it]
 98%|█████████▊| 9829/10000 [20:33:35<19:16,  6.77s/it]
 98%|█████████▊| 9830/10000 [20:33:41<19:10,  6.77s/it]
 98%|█████████▊| 9831/10000 [20:33:48<19:02,  6.76s/it]
 98%|█████████▊| 9832/10000 [20:33:55<18:54,  6.76s/it]
 98%|█████████▊| 9833/10000 [20:34:02<18:48,  6.76s/it]
 98%|█████████▊| 9834/10000 [20:34:08<18:43,  6.77s/it]
 98%|█████████▊| 9835/10000 [20:34:15<18:35,  6.76s/it]
 98%|█████████▊| 9836/10000 [20:34:22<18:29,  6.76s/it]
 98%|█████████▊| 9837/10000 [20:34:29<18:24,  6.78s/it]
 98%|█████████▊| 9838/10000 [20:34:36<18:18,  6.78s/it]
 98%|█████████▊| 9839/10000 [20:34:42<18:08,  6.76s/it]
 98%|█████████▊| 9840/10000 [20:34:49<18:02,  6.77s/it]
 98%|█████████▊| 9841/10000 [20:34:56<17:57,  6.77s/it]
 98%|█████████▊| 9842/10000 [20:35:03<17:53,  6.79s/it]
 98%|█████████▊| 9843/10000 [20:35:09<17:45,  6.79s/it]
 98%|█████████▊| 9844/10000 [20:35:16<17:37,  6.78s/it]
 98%|█████████▊| 9845/10000 [20:35:23<17:29,  6.77s/it]
 98%|█████████▊| 9846/10000 [20:35:30<17:24,  6.78s/it]
 98%|█████████▊| 9847/10000 [20:35:37<17:14,  6.76s/it]
 98%|█████████▊| 9848/10000 [20:35:43<17:05,  6.75s/it]
 98%|█████████▊| 9849/10000 [20:35:50<16:58,  6.74s/it]
 98%|█████████▊| 9850/10000 [20:35:57<16:52,  6.75s/it]
 99%|█████████▊| 9851/10000 [20:36:03<16:45,  6.75s/it]
 99%|█████████▊| 9852/10000 [20:36:10<16:38,  6.75s/it]
 99%|█████████▊| 9853/10000 [20:36:17<16:33,  6.76s/it]
 99%|█████████▊| 9854/10000 [20:36:24<16:26,  6.76s/it]
 99%|█████████▊| 9855/10000 [20:36:31<16:21,  6.77s/it]
 99%|█████████▊| 9856/10000 [20:36:37<16:13,  6.76s/it]
 99%|█████████▊| 9857/10000 [20:36:44<16:07,  6.76s/it]
 99%|█████████▊| 9858/10000 [20:36:51<15:59,  6.76s/it]
 99%|█████████▊| 9859/10000 [20:36:58<15:50,  6.74s/it]
 99%|█████████▊| 9860/10000 [20:37:04<15:45,  6.75s/it]
 99%|█████████▊| 9861/10000 [20:37:11<15:39,  6.76s/it]
 99%|█████████▊| 9862/10000 [20:37:18<15:31,  6.75s/it]
 99%|█████████▊| 9863/10000 [20:37:25<15:25,  6.76s/it]
 99%|█████████▊| 9864/10000 [20:37:31<15:17,  6.75s/it]
 99%|█████████▊| 9865/10000 [20:37:38<15:09,  6.74s/it]
 99%|█████████▊| 9866/10000 [20:37:45<15:05,  6.76s/it]
 99%|█████████▊| 9867/10000 [20:37:52<15:01,  6.77s/it]
 99%|█████████▊| 9868/10000 [20:37:58<14:52,  6.76s/it]
 99%|█████████▊| 9869/10000 [20:38:05<14:45,  6.76s/it]
 99%|█████████▊| 9870/10000 [20:38:12<14:41,  6.78s/it]
 99%|█████████▊| 9871/10000 [20:38:19<14:34,  6.78s/it]
 99%|█████████▊| 9872/10000 [20:38:25<14:27,  6.78s/it]
 99%|█████████▊| 9873/10000 [20:38:32<14:20,  6.78s/it]
 99%|█████████▊| 9874/10000 [20:38:39<14:13,  6.78s/it]
 99%|█████████▉| 9875/10000 [20:38:46<14:08,  6.79s/it]
 99%|█████████▉| 9876/10000 [20:38:53<14:02,  6.79s/it]
 99%|█████████▉| 9877/10000 [20:38:59<13:56,  6.80s/it]
 99%|█████████▉| 9878/10000 [20:39:06<13:49,  6.80s/it]
 99%|█████████▉| 9879/10000 [20:39:13<13:40,  6.78s/it]
 99%|█████████▉| 9880/10000 [20:39:20<13:33,  6.78s/it]
 99%|█████████▉| 9881/10000 [20:39:27<13:25,  6.77s/it]
 99%|█████████▉| 9882/10000 [20:39:33<13:21,  6.79s/it]
 99%|█████████▉| 9883/10000 [20:39:40<13:14,  6.79s/it]
 99%|█████████▉| 9884/10000 [20:39:47<13:08,  6.79s/it]
 99%|█████████▉| 9885/10000 [20:39:54<12:58,  6.77s/it]
 99%|█████████▉| 9886/10000 [20:40:00<12:52,  6.77s/it]
 99%|█████████▉| 9887/10000 [20:40:07<12:46,  6.78s/it]
 99%|█████████▉| 9888/10000 [20:40:14<12:39,  6.78s/it]
 99%|█████████▉| 9889/10000 [20:40:21<12:31,  6.77s/it]
 99%|█████████▉| 9890/10000 [20:40:28<12:23,  6.76s/it]
 99%|█████████▉| 9891/10000 [20:40:34<12:17,  6.77s/it]
 99%|█████████▉| 9892/10000 [20:40:41<12:12,  6.78s/it]
 99%|█████████▉| 9893/10000 [20:40:48<12:05,  6.78s/it]
 99%|█████████▉| 9894/10000 [20:40:55<12:00,  6.80s/it]
 99%|█████████▉| 9895/10000 [20:41:02<11:53,  6.80s/it]
 99%|█████████▉| 9896/10000 [20:41:08<11:46,  6.80s/it]
 99%|█████████▉| 9897/10000 [20:41:15<11:41,  6.81s/it]
 99%|█████████▉| 9898/10000 [20:41:22<11:34,  6.80s/it]
 99%|█████████▉| 9899/10000 [20:41:29<11:27,  6.81s/it]
 99%|█████████▉| 9900/10000 [20:41:36<11:20,  6.80s/it]
                                                       
 99%|█████████▉| 9900/10000 [20:41:36<11:20,  6.80s/it]
 99%|█████████▉| 9901/10000 [20:41:42<11:11,  6.79s/it]
 99%|█████████▉| 9902/10000 [20:41:49<11:05,  6.80s/it]
 99%|█████████▉| 9903/10000 [20:41:56<10:58,  6.79s/it]
 99%|█████████▉| 9904/10000 [20:42:03<10:52,  6.80s/it]
 99%|█████████▉| 9905/10000 [20:42:09<10:44,  6.78s/it]
 99%|█████████▉| 9906/10000 [20:42:16<10:36,  6.77s/it]
 99%|█████████▉| 9907/10000 [20:42:23<10:29,  6.76s/it]
 99%|█████████▉| 9908/10000 [20:42:30<10:22,  6.77s/it]
 99%|█████████▉| 9909/10000 [20:42:37<10:16,  6.77s/it]
 99%|█████████▉| 9910/10000 [20:42:43<10:08,  6.76s/it]
 99%|█████████▉| 9911/10000 [20:42:50<10:01,  6.76s/it]
 99%|█████████▉| 9912/10000 [20:42:57<09:56,  6.78s/it]
 99%|█████████▉| 9913/10000 [20:43:04<09:50,  6.78s/it]
 99%|█████████▉| 9914/10000 [20:43:10<09:44,  6.79s/it]
 99%|█████████▉| 9915/10000 [20:43:17<09:38,  6.80s/it]
 99%|█████████▉| 9916/10000 [20:43:24<09:31,  6.80s/it]
 99%|█████████▉| 9917/10000 [20:43:31<09:24,  6.80s/it]
 99%|█████████▉| 9918/10000 [20:43:38<09:15,  6.77s/it]
 99%|█████████▉| 9919/10000 [20:43:44<09:07,  6.76s/it]
 99%|█████████▉| 9920/10000 [20:43:51<09:02,  6.78s/it]
 99%|█████████▉| 9921/10000 [20:43:58<08:55,  6.78s/it]
 99%|█████████▉| 9922/10000 [20:44:05<08:49,  6.78s/it]
 99%|█████████▉| 9923/10000 [20:44:11<08:42,  6.78s/it]
 99%|█████████▉| 9924/10000 [20:44:18<08:34,  6.77s/it]
 99%|█████████▉| 9925/10000 [20:44:25<08:27,  6.77s/it]
 99%|█████████▉| 9926/10000 [20:44:32<08:21,  6.78s/it]
 99%|█████████▉| 9927/10000 [20:44:39<08:14,  6.78s/it]
 99%|█████████▉| 9928/10000 [20:44:45<08:08,  6.79s/it]
 99%|█████████▉| 9929/10000 [20:44:52<08:01,  6.79s/it]
 99%|█████████▉| 9930/10000 [20:44:59<07:54,  6.78s/it]
 99%|█████████▉| 9931/10000 [20:45:06<07:47,  6.77s/it]
 99%|█████████▉| 9932/10000 [20:45:12<07:41,  6.78s/it]
 99%|█████████▉| 9933/10000 [20:45:19<07:35,  6.79s/it]
 99%|█████████▉| 9934/10000 [20:45:26<07:28,  6.79s/it]
 99%|█████████▉| 9935/10000 [20:45:33<07:19,  6.76s/it]
 99%|█████████▉| 9936/10000 [20:45:40<07:13,  6.77s/it]
 99%|█████████▉| 9937/10000 [20:45:46<07:07,  6.78s/it]
 99%|█████████▉| 9938/10000 [20:45:53<06:59,  6.77s/it]
 99%|█████████▉| 9939/10000 [20:46:00<06:52,  6.76s/it]
 99%|█████████▉| 9940/10000 [20:46:07<06:45,  6.76s/it]
 99%|█████████▉| 9941/10000 [20:46:13<06:39,  6.77s/it]
 99%|█████████▉| 9942/10000 [20:46:20<06:31,  6.76s/it]
 99%|█████████▉| 9943/10000 [20:46:27<06:25,  6.77s/it]
 99%|█████████▉| 9944/10000 [20:46:34<06:19,  6.77s/it]
 99%|█████████▉| 9945/10000 [20:46:40<06:12,  6.77s/it]
 99%|█████████▉| 9946/10000 [20:46:47<06:05,  6.78s/it]
 99%|█████████▉| 9947/10000 [20:46:54<05:59,  6.78s/it]
 99%|█████████▉| 9948/10000 [20:47:01<05:52,  6.78s/it]
 99%|█████████▉| 9949/10000 [20:47:08<05:45,  6.78s/it]
                                                        
+{'loss': '0.0004261', 'grad_norm': '0.02463', 'learning_rate': '3.344e-06', 'epoch': '12.44'}
+{'loss': '0.0004271', 'grad_norm': '0.02427', 'learning_rate': '2.233e-06', 'epoch': '12.56'}
+{'loss': '0.0003907', 'grad_norm': '0.03133', 'learning_rate': '1.122e-06', 'epoch': '12.69'}
+{'loss': '0.0003829', 'grad_norm': '0.03741', 'learning_rate': '1.111e-08', 'epoch': '12.82'}
+
+
  0%|          | 0/176 [00:00<?, ?it/s]
+
  1%|          | 2/176 [00:02<02:59,  1.03s/it]
+
  2%|▏         | 3/176 [00:04<04:11,  1.45s/it]
+
  2%|▏         | 4/176 [00:06<04:54,  1.71s/it]
+
  3%|▎         | 5/176 [00:08<05:14,  1.84s/it]
+
  3%|▎         | 6/176 [00:10<05:27,  1.92s/it]
+
  4%|▍         | 7/176 [00:12<05:37,  2.00s/it]
+
  5%|▍         | 8/176 [00:14<05:37,  2.01s/it]
+
  5%|▌         | 9/176 [00:16<05:39,  2.03s/it]
+
  6%|▌         | 10/176 [00:18<05:40,  2.05s/it]
+
  6%|▋         | 11/176 [00:20<05:39,  2.05s/it]
+
  7%|▋         | 12/176 [00:22<05:36,  2.05s/it]
+
  7%|▋         | 13/176 [00:24<05:34,  2.05s/it]
+
  8%|▊         | 14/176 [00:26<05:29,  2.03s/it]
+
  9%|▊         | 15/176 [00:29<05:29,  2.04s/it]
+
  9%|▉         | 16/176 [00:31<05:27,  2.04s/it]
+
 10%|▉         | 17/176 [00:33<05:26,  2.05s/it]
+
 10%|█         | 18/176 [00:35<05:28,  2.08s/it]
+
 11%|█         | 19/176 [00:37<05:29,  2.10s/it]
+
 11%|█▏        | 20/176 [00:39<05:23,  2.08s/it]
+
 12%|█▏        | 21/176 [00:41<05:23,  2.09s/it]
+
 12%|█▎        | 22/176 [00:43<05:24,  2.10s/it]
+
 13%|█▎        | 23/176 [00:45<05:19,  2.09s/it]
+
 14%|█▎        | 24/176 [00:47<05:16,  2.08s/it]
+
 14%|█▍        | 25/176 [00:49<05:15,  2.09s/it]
+
 15%|█▍        | 26/176 [00:52<05:15,  2.10s/it]
+
 15%|█▌        | 27/176 [00:54<05:12,  2.10s/it]
+
 16%|█▌        | 28/176 [00:56<05:10,  2.10s/it]
+
 16%|█▋        | 29/176 [00:58<05:08,  2.10s/it]
+
 17%|█▋        | 30/176 [01:00<05:07,  2.11s/it]
+
 18%|█▊        | 31/176 [01:02<05:04,  2.10s/it]
+
 18%|█▊        | 32/176 [01:04<05:01,  2.09s/it]
+
 19%|█▉        | 33/176 [01:06<04:56,  2.07s/it]
+
 19%|█▉        | 34/176 [01:08<04:55,  2.08s/it]
+
 20%|█▉        | 35/176 [01:10<04:52,  2.08s/it]
+
 20%|██        | 36/176 [01:12<04:53,  2.10s/it]
+
 21%|██        | 37/176 [01:15<04:54,  2.12s/it]
+
 22%|██▏       | 38/176 [01:17<04:51,  2.11s/it]
+
 22%|██▏       | 39/176 [01:19<04:51,  2.13s/it]
+
 23%|██▎       | 40/176 [01:21<04:46,  2.11s/it]
+
 23%|██▎       | 41/176 [01:23<04:43,  2.10s/it]
+
 24%|██▍       | 42/176 [01:25<04:43,  2.12s/it]
+
 24%|██▍       | 43/176 [01:27<04:41,  2.12s/it]
+
 25%|██▌       | 44/176 [01:29<04:38,  2.11s/it]
+
 26%|██▌       | 45/176 [01:31<04:32,  2.08s/it]
+
 26%|██▌       | 46/176 [01:33<04:29,  2.08s/it]
+
 27%|██▋       | 47/176 [01:36<04:25,  2.06s/it]
+
 27%|██▋       | 48/176 [01:38<04:26,  2.08s/it]
+
 28%|██▊       | 49/176 [01:40<04:26,  2.10s/it]
+
 28%|██▊       | 50/176 [01:42<04:19,  2.06s/it]
+
 29%|██▉       | 51/176 [01:44<04:14,  2.04s/it]
+
 30%|██▉       | 52/176 [01:46<04:15,  2.06s/it]
+
 30%|███       | 53/176 [01:48<04:15,  2.08s/it]
+
 31%|███       | 54/176 [01:50<04:13,  2.08s/it]
+
 31%|███▏      | 55/176 [01:52<04:13,  2.10s/it]
+
 32%|███▏      | 56/176 [01:54<04:15,  2.13s/it]
+
 32%|███▏      | 57/176 [01:57<04:13,  2.13s/it]
+
 33%|███▎      | 58/176 [01:59<04:09,  2.12s/it]
+
 34%|███▎      | 59/176 [02:01<04:06,  2.11s/it]
+
 34%|███▍      | 60/176 [02:03<04:03,  2.10s/it]
+
 35%|███▍      | 61/176 [02:05<04:02,  2.11s/it]
+
 35%|███▌      | 62/176 [02:07<04:00,  2.11s/it]
+
 36%|███▌      | 63/176 [02:09<03:59,  2.12s/it]
+
 36%|███▋      | 64/176 [02:11<03:55,  2.10s/it]
+
 37%|███▋      | 65/176 [02:13<03:54,  2.11s/it]
+
 38%|███▊      | 66/176 [02:15<03:49,  2.08s/it]
+
 38%|███▊      | 67/176 [02:18<03:48,  2.10s/it]
+
 39%|███▊      | 68/176 [02:20<03:44,  2.08s/it]
+
 39%|███▉      | 69/176 [02:22<03:42,  2.08s/it]
+
 40%|███▉      | 70/176 [02:24<03:39,  2.07s/it]
+
 40%|████      | 71/176 [02:26<03:39,  2.09s/it]
+
 41%|████      | 72/176 [02:28<03:36,  2.09s/it]
+
 41%|████▏     | 73/176 [02:30<03:36,  2.10s/it]
+
 42%|████▏     | 74/176 [02:32<03:32,  2.08s/it]
+
 43%|████▎     | 75/176 [02:34<03:29,  2.07s/it]
+
 43%|████▎     | 76/176 [02:36<03:28,  2.08s/it]
+
 44%|████▍     | 77/176 [02:38<03:25,  2.08s/it]
+
 44%|████▍     | 78/176 [02:40<03:22,  2.07s/it]
+
 45%|████▍     | 79/176 [02:42<03:21,  2.08s/it]
+
 45%|████▌     | 80/176 [02:45<03:20,  2.08s/it]
+
 46%|████▌     | 81/176 [02:47<03:17,  2.08s/it]
+
 47%|████▋     | 82/176 [02:49<03:14,  2.07s/it]
+
 47%|████▋     | 83/176 [02:51<03:14,  2.10s/it]
+
 48%|████▊     | 84/176 [02:53<03:12,  2.09s/it]
+
 48%|████▊     | 85/176 [02:55<03:09,  2.08s/it]
+
 49%|████▉     | 86/176 [02:57<03:05,  2.06s/it]
+
 49%|████▉     | 87/176 [02:59<03:04,  2.07s/it]
+
 50%|█████     | 88/176 [03:01<03:03,  2.08s/it]
+
 51%|█████     | 89/176 [03:03<03:01,  2.08s/it]
+
 51%|█████     | 90/176 [03:05<03:00,  2.10s/it]
+
 52%|█████▏    | 91/176 [03:07<02:56,  2.08s/it]
+
 52%|█████▏    | 92/176 [03:09<02:53,  2.07s/it]
+
 53%|█████▎    | 93/176 [03:12<02:52,  2.07s/it]
+
 53%|█████▎    | 94/176 [03:14<02:50,  2.08s/it]
+
 54%|█████▍    | 95/176 [03:16<02:49,  2.10s/it]
+
 55%|█████▍    | 96/176 [03:18<02:47,  2.09s/it]
+
 55%|█████▌    | 97/176 [03:20<02:47,  2.12s/it]
+
 56%|█████▌    | 98/176 [03:22<02:44,  2.11s/it]
+
 56%|█████▋    | 99/176 [03:24<02:43,  2.12s/it]
+
 57%|█████▋    | 100/176 [03:26<02:39,  2.11s/it]
+
 57%|█████▋    | 101/176 [03:29<02:39,  2.13s/it]
+
 58%|█████▊    | 102/176 [03:31<02:36,  2.12s/it]
+
 59%|█████▊    | 103/176 [03:33<02:33,  2.10s/it]
+
 59%|█████▉    | 104/176 [03:35<02:30,  2.09s/it]
+
 60%|█████▉    | 105/176 [03:37<02:29,  2.10s/it]
+
 60%|██████    | 106/176 [03:39<02:28,  2.12s/it]
+
 61%|██████    | 107/176 [03:41<02:25,  2.10s/it]
+
 61%|██████▏   | 108/176 [03:43<02:21,  2.09s/it]
+
 62%|██████▏   | 109/176 [03:45<02:19,  2.08s/it]
+
 62%|██████▎   | 110/176 [03:47<02:16,  2.07s/it]
+
 63%|██████▎   | 111/176 [03:49<02:14,  2.07s/it]
+
 64%|██████▎   | 112/176 [03:51<02:12,  2.06s/it]
+
 64%|██████▍   | 113/176 [03:53<02:09,  2.06s/it]
+
 65%|██████▍   | 114/176 [03:56<02:08,  2.07s/it]
+
 65%|██████▌   | 115/176 [03:58<02:05,  2.06s/it]
+
 66%|██████▌   | 116/176 [04:00<02:03,  2.06s/it]
+
 66%|██████▋   | 117/176 [04:02<02:02,  2.07s/it]
+
 67%|██████▋   | 118/176 [04:04<02:00,  2.07s/it]
+
 68%|██████▊   | 119/176 [04:06<01:58,  2.08s/it]
+
 68%|██████▊   | 120/176 [04:08<01:57,  2.10s/it]
+
 69%|██████▉   | 121/176 [04:10<01:54,  2.09s/it]
+
 69%|██████▉   | 122/176 [04:12<01:53,  2.10s/it]
+
 70%|██████▉   | 123/176 [04:14<01:50,  2.09s/it]
+
 70%|███████   | 124/176 [04:17<01:51,  2.14s/it]
+
 71%|███████   | 125/176 [04:19<01:47,  2.12s/it]
+
 72%|███████▏  | 126/176 [04:21<01:45,  2.10s/it]
+
 72%|███████▏  | 127/176 [04:23<01:42,  2.10s/it]
+
 73%|███████▎  | 128/176 [04:25<01:41,  2.11s/it]
+
 73%|███████▎  | 129/176 [04:27<01:38,  2.09s/it]
+
 74%|███████▍  | 130/176 [04:29<01:35,  2.08s/it]
+
 74%|███████▍  | 131/176 [04:31<01:32,  2.06s/it]
+
 75%|███████▌  | 132/176 [04:33<01:31,  2.07s/it]
+
 76%|███████▌  | 133/176 [04:35<01:29,  2.08s/it]
+
 76%|███████▌  | 134/176 [04:37<01:27,  2.08s/it]
+
 77%|███████▋  | 135/176 [04:39<01:26,  2.10s/it]
+
 77%|███████▋  | 136/176 [04:42<01:23,  2.09s/it]
+
 78%|███████▊  | 137/176 [04:44<01:20,  2.07s/it]
+
 78%|███████▊  | 138/176 [04:46<01:19,  2.09s/it]
+
 79%|███████▉  | 139/176 [04:48<01:17,  2.08s/it]
+
 80%|███████▉  | 140/176 [04:50<01:14,  2.08s/it]
+
 80%|████████  | 141/176 [04:52<01:12,  2.08s/it]
+
 81%|████████  | 142/176 [04:54<01:10,  2.08s/it]
+
 81%|████████▏ | 143/176 [04:56<01:07,  2.05s/it]
+
 82%|████████▏ | 144/176 [04:58<01:05,  2.05s/it]
+
 82%|████████▏ | 145/176 [05:00<01:04,  2.07s/it]
+
 83%|████████▎ | 146/176 [05:02<01:02,  2.08s/it]
+
 84%|████████▎ | 147/176 [05:04<01:00,  2.08s/it]
+
 84%|████████▍ | 148/176 [05:06<00:58,  2.08s/it]
+
 85%|████████▍ | 149/176 [05:09<00:56,  2.11s/it]
+
 85%|████████▌ | 150/176 [05:11<00:54,  2.09s/it]
+
 86%|████████▌ | 151/176 [05:13<00:52,  2.09s/it]
+
 86%|████████▋ | 152/176 [05:15<00:50,  2.08s/it]
+
 87%|████████▋ | 153/176 [05:17<00:48,  2.09s/it]
+
 88%|████████▊ | 154/176 [05:19<00:45,  2.08s/it]
+
 88%|████████▊ | 155/176 [05:21<00:43,  2.09s/it]
+
 89%|████████▊ | 156/176 [05:23<00:41,  2.07s/it]
+
 89%|████████▉ | 157/176 [05:25<00:38,  2.05s/it]
+
 90%|████████▉ | 158/176 [05:27<00:37,  2.07s/it]
+
 90%|█████████ | 159/176 [05:29<00:35,  2.08s/it]
+
 91%|█████████ | 160/176 [05:31<00:33,  2.09s/it]
+
 91%|█████████▏| 161/176 [05:33<00:31,  2.09s/it]
+
 92%|█████████▏| 162/176 [05:36<00:29,  2.08s/it]
+
 93%|█████████▎| 163/176 [05:38<00:27,  2.08s/it]
+
 93%|█████████▎| 164/176 [05:40<00:24,  2.07s/it]
+
 94%|█████████▍| 165/176 [05:42<00:22,  2.09s/it]
+
 94%|█████████▍| 166/176 [05:44<00:21,  2.13s/it]
+
 95%|█████████▍| 167/176 [05:46<00:19,  2.13s/it]
+
 95%|█████████▌| 168/176 [05:48<00:16,  2.12s/it]
+
 96%|█████████▌| 169/176 [05:50<00:14,  2.09s/it]
+
 97%|█████████▋| 170/176 [05:52<00:12,  2.11s/it]
+
 97%|█████████▋| 171/176 [05:55<00:10,  2.11s/it]
+
 98%|█████████▊| 172/176 [05:57<00:08,  2.09s/it]
+
 98%|█████████▊| 173/176 [05:59<00:06,  2.10s/it]
+
 99%|█████████▉| 174/176 [06:01<00:04,  2.08s/it]
+
 99%|█████████▉| 175/176 [06:01<00:01,  1.67s/it]
+
                                                        
+
                                                 
+
+
                                                 {'eval_loss': '0.02808', 'eval_wer': '21.22', 'eval_wer_ortho': '22.56', 'eval_cer': '8.515', 'eval_runtime': '372', 'eval_samples_per_second': '7.529', 'eval_steps_per_second': '0.473', 'epoch': '12.82'}
+
+
+
+There were missing keys in the checkpoint model loaded: ['proj_out.weight'].
+
                                                        

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b70ff84abc1c88e88301556d38076f26e9febdbf7d1c9630dc5af5d17f22dfb
+oid sha256:bd234ffb57bf119f343597ccad651e3077b34db27564b2c3c561f6cef67fa60f
 size 290403936

runs/Feb03_19-00-05_74464e924814/events.out.tfevents.1770145205.74464e924814.17628.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd71a84a92318f3fd6471ce22e8e9b3da56b38688c849408b6f5f608bb3ecc29
-size 33103
+oid sha256:3990e0cdfb740709bce39512e8ff52d94e5df9939a097d958f6389f7ea868c13
+size 34930