| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1e-06, | |
| "loss": 3.3352, | |
| "perplexity": 28.083999462050915, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_accuracy": 0.23046520883543017, | |
| "eval_loss": 3.173828125, | |
| "eval_perplexity": 23.898797049169467, | |
| "eval_runtime": 8.0774, | |
| "eval_samples_per_second": 45.064, | |
| "eval_steps_per_second": 5.695, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1e-06, | |
| "loss": 3.3091, | |
| "perplexity": 27.360489946627773, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_accuracy": 0.23046520883543017, | |
| "eval_loss": 3.173828125, | |
| "eval_perplexity": 23.898797049169467, | |
| "eval_runtime": 7.9509, | |
| "eval_samples_per_second": 45.781, | |
| "eval_steps_per_second": 5.785, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1e-06, | |
| "loss": 3.3347, | |
| "perplexity": 28.06996097223482, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.23046520883543017, | |
| "eval_loss": 3.173828125, | |
| "eval_perplexity": 23.898797049169467, | |
| "eval_runtime": 7.9602, | |
| "eval_samples_per_second": 45.728, | |
| "eval_steps_per_second": 5.779, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1e-06, | |
| "loss": 3.1445, | |
| "perplexity": 23.20806853752346, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_accuracy": 0.23053154089371394, | |
| "eval_loss": 3.173828125, | |
| "eval_perplexity": 23.898797049169467, | |
| "eval_runtime": 7.9267, | |
| "eval_samples_per_second": 45.921, | |
| "eval_steps_per_second": 5.803, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1e-06, | |
| "loss": 2.8918, | |
| "perplexity": 18.025726725492028, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.23053154089371394, | |
| "eval_loss": 3.173828125, | |
| "eval_perplexity": 23.898797049169467, | |
| "eval_runtime": 7.9947, | |
| "eval_samples_per_second": 45.53, | |
| "eval_steps_per_second": 5.754, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1e-06, | |
| "loss": 3.2068, | |
| "perplexity": 24.699919882371823, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.23053154089371394, | |
| "eval_loss": 3.173828125, | |
| "eval_perplexity": 23.898797049169467, | |
| "eval_runtime": 7.9696, | |
| "eval_samples_per_second": 45.674, | |
| "eval_steps_per_second": 5.772, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1e-06, | |
| "loss": 3.6245, | |
| "perplexity": 37.50596548782992, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_accuracy": 0.23047073650695382, | |
| "eval_loss": 3.171875, | |
| "eval_perplexity": 23.852165264858517, | |
| "eval_runtime": 7.9787, | |
| "eval_samples_per_second": 45.622, | |
| "eval_steps_per_second": 5.765, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1e-06, | |
| "loss": 3.2256, | |
| "perplexity": 25.168670828860865, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.230514957879143, | |
| "eval_loss": 3.171875, | |
| "eval_perplexity": 23.852165264858517, | |
| "eval_runtime": 7.9349, | |
| "eval_samples_per_second": 45.873, | |
| "eval_steps_per_second": 5.797, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1e-06, | |
| "loss": 2.9991, | |
| "perplexity": 20.067468072159407, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.23050943020761935, | |
| "eval_loss": 3.169921875, | |
| "eval_perplexity": 23.80562446936611, | |
| "eval_runtime": 7.9581, | |
| "eval_samples_per_second": 45.74, | |
| "eval_steps_per_second": 5.78, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1e-06, | |
| "loss": 3.3257, | |
| "perplexity": 27.818464754063648, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.23057023459437948, | |
| "eval_loss": 3.16796875, | |
| "eval_perplexity": 23.75917448515314, | |
| "eval_runtime": 8.0497, | |
| "eval_samples_per_second": 45.219, | |
| "eval_steps_per_second": 5.715, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1e-06, | |
| "loss": 3.1199, | |
| "perplexity": 22.6441151184392, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_accuracy": 0.23057023459437948, | |
| "eval_loss": 3.166015625, | |
| "eval_perplexity": 23.71281513502692, | |
| "eval_runtime": 7.9865, | |
| "eval_samples_per_second": 45.577, | |
| "eval_steps_per_second": 5.76, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1e-06, | |
| "loss": 3.3735, | |
| "perplexity": 29.180480216449844, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.23062551130961595, | |
| "eval_loss": 3.166015625, | |
| "eval_perplexity": 23.71281513502692, | |
| "eval_runtime": 7.9024, | |
| "eval_samples_per_second": 46.062, | |
| "eval_steps_per_second": 5.821, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1e-06, | |
| "loss": 3.0051, | |
| "perplexity": 20.188234818531463, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.2306531496672342, | |
| "eval_loss": 3.1640625, | |
| "eval_perplexity": 23.666546242140512, | |
| "eval_runtime": 7.9745, | |
| "eval_samples_per_second": 45.646, | |
| "eval_steps_per_second": 5.768, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1e-06, | |
| "loss": 3.2695, | |
| "perplexity": 26.298186961963587, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_accuracy": 0.23081345214141996, | |
| "eval_loss": 3.162109375, | |
| "eval_perplexity": 23.620367629992042, | |
| "eval_runtime": 8.0031, | |
| "eval_samples_per_second": 45.483, | |
| "eval_steps_per_second": 5.748, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1e-06, | |
| "loss": 3.2004, | |
| "perplexity": 24.54234517205232, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.23086872885665644, | |
| "eval_loss": 3.16015625, | |
| "eval_perplexity": 23.574279122424027, | |
| "eval_runtime": 7.96, | |
| "eval_samples_per_second": 45.729, | |
| "eval_steps_per_second": 5.779, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1e-06, | |
| "loss": 3.2075, | |
| "perplexity": 24.71721587918212, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.2308300351559909, | |
| "eval_loss": 3.158203125, | |
| "eval_perplexity": 23.52828054362271, | |
| "eval_runtime": 7.9635, | |
| "eval_samples_per_second": 45.708, | |
| "eval_steps_per_second": 5.776, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1e-06, | |
| "loss": 3.321, | |
| "perplexity": 27.688024743861764, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_accuracy": 0.2308300351559909, | |
| "eval_loss": 3.15625, | |
| "eval_perplexity": 23.482371718117374, | |
| "eval_runtime": 7.9658, | |
| "eval_samples_per_second": 45.695, | |
| "eval_steps_per_second": 5.775, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1e-06, | |
| "loss": 3.4026, | |
| "perplexity": 30.04210807401033, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.23086872885665644, | |
| "eval_loss": 3.154296875, | |
| "eval_perplexity": 23.4365524707797, | |
| "eval_runtime": 7.934, | |
| "eval_samples_per_second": 45.878, | |
| "eval_steps_per_second": 5.798, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1e-06, | |
| "loss": 3.0383, | |
| "perplexity": 20.869734512558935, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.23087425652818008, | |
| "eval_loss": 3.15234375, | |
| "eval_perplexity": 23.390822626823073, | |
| "eval_runtime": 7.6988, | |
| "eval_samples_per_second": 47.28, | |
| "eval_steps_per_second": 5.975, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1e-06, | |
| "loss": 3.166, | |
| "perplexity": 23.71244462518505, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_accuracy": 0.23091847790036926, | |
| "eval_loss": 3.150390625, | |
| "eval_perplexity": 23.345182011801924, | |
| "eval_runtime": 7.9469, | |
| "eval_samples_per_second": 45.804, | |
| "eval_steps_per_second": 5.788, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1e-06, | |
| "loss": 3.144, | |
| "perplexity": 23.196467403779828, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_accuracy": 0.2309626992725584, | |
| "eval_loss": 3.1484375, | |
| "eval_perplexity": 23.299630451611073, | |
| "eval_runtime": 7.957, | |
| "eval_samples_per_second": 45.746, | |
| "eval_steps_per_second": 5.781, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1e-06, | |
| "loss": 3.1624, | |
| "perplexity": 23.627233296953413, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_accuracy": 0.23100139297322395, | |
| "eval_loss": 3.1484375, | |
| "eval_perplexity": 23.299630451611073, | |
| "eval_runtime": 8.0068, | |
| "eval_samples_per_second": 45.461, | |
| "eval_steps_per_second": 5.745, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1e-06, | |
| "loss": 3.0332, | |
| "perplexity": 20.763569816631378, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_accuracy": 0.23103455900236583, | |
| "eval_loss": 3.146484375, | |
| "eval_perplexity": 23.25416777248505, | |
| "eval_runtime": 7.9578, | |
| "eval_samples_per_second": 45.741, | |
| "eval_steps_per_second": 5.78, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1e-06, | |
| "loss": 3.3745, | |
| "perplexity": 29.209675291771028, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.23106772503150771, | |
| "eval_loss": 3.14453125, | |
| "eval_perplexity": 23.20879380099744, | |
| "eval_runtime": 7.9682, | |
| "eval_samples_per_second": 45.682, | |
| "eval_steps_per_second": 5.773, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1e-06, | |
| "loss": 3.0823, | |
| "perplexity": 21.808504316830465, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_accuracy": 0.23117827846198066, | |
| "eval_loss": 3.142578125, | |
| "eval_perplexity": 23.16350836406023, | |
| "eval_runtime": 7.916, | |
| "eval_samples_per_second": 45.983, | |
| "eval_steps_per_second": 5.811, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1e-06, | |
| "loss": 3.6021, | |
| "perplexity": 36.67517149163571, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_accuracy": 0.2312280275056935, | |
| "eval_loss": 3.140625, | |
| "eval_perplexity": 23.118311288923124, | |
| "eval_runtime": 7.9551, | |
| "eval_samples_per_second": 45.757, | |
| "eval_steps_per_second": 5.782, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1e-06, | |
| "loss": 3.1125, | |
| "perplexity": 22.477167135936607, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_accuracy": 0.23127777654940632, | |
| "eval_loss": 3.138671875, | |
| "eval_perplexity": 23.073202403172917, | |
| "eval_runtime": 7.9108, | |
| "eval_samples_per_second": 46.013, | |
| "eval_steps_per_second": 5.815, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1e-06, | |
| "loss": 3.1406, | |
| "perplexity": 23.117733338365316, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_accuracy": 0.23136621929378468, | |
| "eval_loss": 3.138671875, | |
| "eval_perplexity": 23.073202403172917, | |
| "eval_runtime": 7.9649, | |
| "eval_samples_per_second": 45.7, | |
| "eval_steps_per_second": 5.775, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1e-06, | |
| "loss": 3.1736, | |
| "perplexity": 23.893345757904175, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_accuracy": 0.2314049129944502, | |
| "eval_loss": 3.13671875, | |
| "eval_perplexity": 23.028181534732802, | |
| "eval_runtime": 7.9854, | |
| "eval_samples_per_second": 45.583, | |
| "eval_steps_per_second": 5.76, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1e-06, | |
| "loss": 3.1104, | |
| "perplexity": 22.43001461242937, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.23154863245406504, | |
| "eval_loss": 3.134765625, | |
| "eval_perplexity": 22.98324851186175, | |
| "eval_runtime": 7.9536, | |
| "eval_samples_per_second": 45.765, | |
| "eval_steps_per_second": 5.784, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1e-06, | |
| "loss": 3.1301, | |
| "perplexity": 22.876267054768768, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_accuracy": 0.23159285382625422, | |
| "eval_loss": 3.1328125, | |
| "eval_perplexity": 22.938403163153815, | |
| "eval_runtime": 7.904, | |
| "eval_samples_per_second": 46.053, | |
| "eval_steps_per_second": 5.82, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1e-06, | |
| "loss": 3.3376, | |
| "perplexity": 28.151482007422672, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_accuracy": 0.23154863245406504, | |
| "eval_loss": 3.130859375, | |
| "eval_perplexity": 22.893645317537526, | |
| "eval_runtime": 7.6495, | |
| "eval_samples_per_second": 47.585, | |
| "eval_steps_per_second": 6.013, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1e-06, | |
| "loss": 3.218, | |
| "perplexity": 24.978113963861347, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_accuracy": 0.23159285382625422, | |
| "eval_loss": 3.130859375, | |
| "eval_perplexity": 22.893645317537526, | |
| "eval_runtime": 7.9297, | |
| "eval_samples_per_second": 45.904, | |
| "eval_steps_per_second": 5.801, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1e-06, | |
| "loss": 3.0786, | |
| "perplexity": 21.727961946129383, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_accuracy": 0.2316481305414907, | |
| "eval_loss": 3.12890625, | |
| "eval_perplexity": 22.84897480427519, | |
| "eval_runtime": 7.9813, | |
| "eval_samples_per_second": 45.607, | |
| "eval_steps_per_second": 5.763, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1e-06, | |
| "loss": 3.0125, | |
| "perplexity": 20.33818187604361, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_accuracy": 0.23167024122758528, | |
| "eval_loss": 3.126953125, | |
| "eval_perplexity": 22.80439145296227, | |
| "eval_runtime": 7.9533, | |
| "eval_samples_per_second": 45.767, | |
| "eval_steps_per_second": 5.784, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1e-06, | |
| "loss": 3.2634, | |
| "perplexity": 26.138256305914563, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_accuracy": 0.2317199902712981, | |
| "eval_loss": 3.126953125, | |
| "eval_perplexity": 22.80439145296227, | |
| "eval_runtime": 6.9427, | |
| "eval_samples_per_second": 52.429, | |
| "eval_steps_per_second": 6.626, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1e-06, | |
| "loss": 2.9888, | |
| "perplexity": 19.861833984540883, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_accuracy": 0.23177526698653458, | |
| "eval_loss": 3.125, | |
| "eval_perplexity": 22.75989509352673, | |
| "eval_runtime": 7.9347, | |
| "eval_samples_per_second": 45.875, | |
| "eval_steps_per_second": 5.797, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1e-06, | |
| "loss": 3.1624, | |
| "perplexity": 23.627233296953413, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_accuracy": 0.23179737767262917, | |
| "eval_loss": 3.123046875, | |
| "eval_perplexity": 22.715485556228362, | |
| "eval_runtime": 7.9127, | |
| "eval_samples_per_second": 46.002, | |
| "eval_steps_per_second": 5.813, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1e-06, | |
| "loss": 2.9807, | |
| "perplexity": 19.7016029410545, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_accuracy": 0.2318581820593893, | |
| "eval_loss": 3.12109375, | |
| "eval_perplexity": 22.67116267165818, | |
| "eval_runtime": 7.9324, | |
| "eval_samples_per_second": 45.888, | |
| "eval_steps_per_second": 5.799, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1e-06, | |
| "loss": 3.446, | |
| "perplexity": 31.374642406982968, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_accuracy": 0.2319300417891967, | |
| "eval_loss": 3.12109375, | |
| "eval_perplexity": 22.67116267165818, | |
| "eval_runtime": 7.9334, | |
| "eval_samples_per_second": 45.882, | |
| "eval_steps_per_second": 5.798, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1e-06, | |
| "loss": 3.1338, | |
| "perplexity": 22.96106602422343, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_accuracy": 0.23195768014681495, | |
| "eval_loss": 3.119140625, | |
| "eval_perplexity": 22.626926270737744, | |
| "eval_runtime": 7.926, | |
| "eval_samples_per_second": 45.925, | |
| "eval_steps_per_second": 5.804, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 1e-06, | |
| "loss": 3.1841, | |
| "perplexity": 24.145547631095972, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_accuracy": 0.23199084617595683, | |
| "eval_loss": 3.119140625, | |
| "eval_perplexity": 22.626926270737744, | |
| "eval_runtime": 7.9503, | |
| "eval_samples_per_second": 45.785, | |
| "eval_steps_per_second": 5.786, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1e-06, | |
| "loss": 3.1079, | |
| "perplexity": 22.374009611318957, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_accuracy": 0.232035067548146, | |
| "eval_loss": 3.1171875, | |
| "eval_perplexity": 22.582776184718522, | |
| "eval_runtime": 7.7126, | |
| "eval_samples_per_second": 47.195, | |
| "eval_steps_per_second": 5.964, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1e-06, | |
| "loss": 3.0918, | |
| "perplexity": 22.016672340357456, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_accuracy": 0.23214562097861896, | |
| "eval_loss": 3.115234375, | |
| "eval_perplexity": 22.538712245181248, | |
| "eval_runtime": 7.9205, | |
| "eval_samples_per_second": 45.956, | |
| "eval_steps_per_second": 5.808, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1e-06, | |
| "loss": 3.0302, | |
| "perplexity": 20.701372449879624, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_accuracy": 0.23220089769385543, | |
| "eval_loss": 3.115234375, | |
| "eval_perplexity": 22.538712245181248, | |
| "eval_runtime": 7.9218, | |
| "eval_samples_per_second": 45.949, | |
| "eval_steps_per_second": 5.807, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1e-06, | |
| "loss": 3.1123, | |
| "perplexity": 22.472672152022792, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_accuracy": 0.23228381276671015, | |
| "eval_loss": 3.11328125, | |
| "eval_perplexity": 22.494734284035275, | |
| "eval_runtime": 7.9089, | |
| "eval_samples_per_second": 46.024, | |
| "eval_steps_per_second": 5.816, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1e-06, | |
| "loss": 2.9985, | |
| "perplexity": 20.055431202738045, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_accuracy": 0.23235567249651756, | |
| "eval_loss": 3.111328125, | |
| "eval_perplexity": 22.450842133517945, | |
| "eval_runtime": 7.9743, | |
| "eval_samples_per_second": 45.646, | |
| "eval_steps_per_second": 5.769, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1e-06, | |
| "loss": 3.3816, | |
| "perplexity": 29.417801961716197, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_accuracy": 0.23235567249651756, | |
| "eval_loss": 3.111328125, | |
| "eval_perplexity": 22.450842133517945, | |
| "eval_runtime": 7.9744, | |
| "eval_samples_per_second": 45.646, | |
| "eval_steps_per_second": 5.768, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1e-06, | |
| "loss": 3.0813, | |
| "perplexity": 21.786706713131952, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_accuracy": 0.23242753222632498, | |
| "eval_loss": 3.109375, | |
| "eval_perplexity": 22.40703562619394, | |
| "eval_runtime": 8.0068, | |
| "eval_samples_per_second": 45.461, | |
| "eval_steps_per_second": 5.745, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1e-06, | |
| "loss": 3.2024, | |
| "perplexity": 24.591478979826256, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_accuracy": 0.2324662259269905, | |
| "eval_loss": 3.109375, | |
| "eval_perplexity": 22.40703562619394, | |
| "eval_runtime": 7.9621, | |
| "eval_samples_per_second": 45.717, | |
| "eval_steps_per_second": 5.777, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1e-06, | |
| "loss": 3.0178, | |
| "perplexity": 20.446260395068368, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_accuracy": 0.23248280894156145, | |
| "eval_loss": 3.107421875, | |
| "eval_perplexity": 22.36331459495464, | |
| "eval_runtime": 7.9553, | |
| "eval_samples_per_second": 45.756, | |
| "eval_steps_per_second": 5.782, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1e-06, | |
| "loss": 3.1646, | |
| "perplexity": 23.67927043006483, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_accuracy": 0.23263758374422358, | |
| "eval_loss": 3.107421875, | |
| "eval_perplexity": 22.36331459495464, | |
| "eval_runtime": 7.9632, | |
| "eval_samples_per_second": 45.71, | |
| "eval_steps_per_second": 5.777, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1e-06, | |
| "loss": 3.0046, | |
| "perplexity": 20.17814322423101, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_accuracy": 0.23268180511641276, | |
| "eval_loss": 3.10546875, | |
| "eval_perplexity": 22.319678873017494, | |
| "eval_runtime": 7.9716, | |
| "eval_samples_per_second": 45.662, | |
| "eval_steps_per_second": 5.77, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1e-06, | |
| "loss": 3.0266, | |
| "perplexity": 20.626981493124443, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_accuracy": 0.23273708183164923, | |
| "eval_loss": 3.10546875, | |
| "eval_perplexity": 22.319678873017494, | |
| "eval_runtime": 7.9222, | |
| "eval_samples_per_second": 45.947, | |
| "eval_steps_per_second": 5.806, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1e-06, | |
| "loss": 3.3857, | |
| "perplexity": 29.538662544648755, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_accuracy": 0.23274813717469653, | |
| "eval_loss": 3.103515625, | |
| "eval_perplexity": 22.27612829392538, | |
| "eval_runtime": 8.0121, | |
| "eval_samples_per_second": 45.431, | |
| "eval_steps_per_second": 5.741, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1e-06, | |
| "loss": 3.064, | |
| "perplexity": 21.413038238853925, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_accuracy": 0.23277577553231477, | |
| "eval_loss": 3.103515625, | |
| "eval_perplexity": 22.27612829392538, | |
| "eval_runtime": 7.9323, | |
| "eval_samples_per_second": 45.888, | |
| "eval_steps_per_second": 5.799, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1e-06, | |
| "loss": 3.176, | |
| "perplexity": 23.950758655642247, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_accuracy": 0.2328144692329803, | |
| "eval_loss": 3.1015625, | |
| "eval_perplexity": 22.232662691545976, | |
| "eval_runtime": 7.9184, | |
| "eval_samples_per_second": 45.969, | |
| "eval_steps_per_second": 5.809, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1e-06, | |
| "loss": 3.1851, | |
| "perplexity": 24.169705255526146, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_accuracy": 0.23286974594821677, | |
| "eval_loss": 3.1015625, | |
| "eval_perplexity": 22.232662691545976, | |
| "eval_runtime": 7.9669, | |
| "eval_samples_per_second": 45.689, | |
| "eval_steps_per_second": 5.774, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1e-06, | |
| "loss": 3.0811, | |
| "perplexity": 21.782349807494416, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_accuracy": 0.232897384305835, | |
| "eval_loss": 3.099609375, | |
| "eval_perplexity": 22.189281900071105, | |
| "eval_runtime": 7.9339, | |
| "eval_samples_per_second": 45.879, | |
| "eval_steps_per_second": 5.798, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1e-06, | |
| "loss": 3.0205, | |
| "perplexity": 20.501539891873456, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.23296924403564243, | |
| "eval_loss": 3.099609375, | |
| "eval_perplexity": 22.189281900071105, | |
| "eval_runtime": 7.9929, | |
| "eval_samples_per_second": 45.54, | |
| "eval_steps_per_second": 5.755, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1e-06, | |
| "loss": 3.26, | |
| "perplexity": 26.049537142518336, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_accuracy": 0.23296371636411878, | |
| "eval_loss": 3.09765625, | |
| "eval_perplexity": 22.145985754016134, | |
| "eval_runtime": 7.9124, | |
| "eval_samples_per_second": 46.004, | |
| "eval_steps_per_second": 5.814, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1e-06, | |
| "loss": 3.2922, | |
| "perplexity": 26.90198296333493, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_accuracy": 0.23305768678002078, | |
| "eval_loss": 3.09765625, | |
| "eval_perplexity": 22.145985754016134, | |
| "eval_runtime": 7.9262, | |
| "eval_samples_per_second": 45.923, | |
| "eval_steps_per_second": 5.804, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1e-06, | |
| "loss": 3.5349, | |
| "perplexity": 34.29158538422678, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_accuracy": 0.2331295465098282, | |
| "eval_loss": 3.095703125, | |
| "eval_perplexity": 22.10277408821932, | |
| "eval_runtime": 7.9843, | |
| "eval_samples_per_second": 45.589, | |
| "eval_steps_per_second": 5.761, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1e-06, | |
| "loss": 3.3525, | |
| "perplexity": 28.57407962319162, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_accuracy": 0.23312401883830455, | |
| "eval_loss": 3.095703125, | |
| "eval_perplexity": 22.10277408821932, | |
| "eval_runtime": 7.9231, | |
| "eval_samples_per_second": 45.942, | |
| "eval_steps_per_second": 5.806, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1e-06, | |
| "loss": 3.135, | |
| "perplexity": 22.988635842034803, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_accuracy": 0.23312401883830455, | |
| "eval_loss": 3.09375, | |
| "eval_perplexity": 22.059646737841184, | |
| "eval_runtime": 7.9384, | |
| "eval_samples_per_second": 45.853, | |
| "eval_steps_per_second": 5.795, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1e-06, | |
| "loss": 3.1707, | |
| "perplexity": 23.824155429673073, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_accuracy": 0.23318482322506467, | |
| "eval_loss": 3.09375, | |
| "eval_perplexity": 22.059646737841184, | |
| "eval_runtime": 7.9764, | |
| "eval_samples_per_second": 45.635, | |
| "eval_steps_per_second": 5.767, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1e-06, | |
| "loss": 3.0127, | |
| "perplexity": 20.342249919209575, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_accuracy": 0.23324009994030115, | |
| "eval_loss": 3.091796875, | |
| "eval_perplexity": 22.016603538363892, | |
| "eval_runtime": 7.9476, | |
| "eval_samples_per_second": 45.8, | |
| "eval_steps_per_second": 5.788, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1e-06, | |
| "loss": 3.0952, | |
| "perplexity": 22.091656427027353, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_accuracy": 0.23322904459725385, | |
| "eval_loss": 3.091796875, | |
| "eval_perplexity": 22.016603538363892, | |
| "eval_runtime": 8.0177, | |
| "eval_samples_per_second": 45.4, | |
| "eval_steps_per_second": 5.737, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1e-06, | |
| "loss": 3.1023, | |
| "perplexity": 22.24906532800973, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_accuracy": 0.23338934707143963, | |
| "eval_loss": 3.08984375, | |
| "eval_perplexity": 21.973644325590612, | |
| "eval_runtime": 7.7593, | |
| "eval_samples_per_second": 46.911, | |
| "eval_steps_per_second": 5.928, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1e-06, | |
| "loss": 3.3821, | |
| "perplexity": 29.43251454053524, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_accuracy": 0.23339487474296328, | |
| "eval_loss": 3.08984375, | |
| "eval_perplexity": 21.973644325590612, | |
| "eval_runtime": 7.9307, | |
| "eval_samples_per_second": 45.898, | |
| "eval_steps_per_second": 5.8, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1e-06, | |
| "loss": 3.1118, | |
| "perplexity": 22.461438624562685, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_accuracy": 0.23339487474296328, | |
| "eval_loss": 3.087890625, | |
| "eval_perplexity": 21.930768935644906, | |
| "eval_runtime": 8.0017, | |
| "eval_samples_per_second": 45.49, | |
| "eval_steps_per_second": 5.749, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1e-06, | |
| "loss": 3.1143, | |
| "perplexity": 22.5176624716497, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.2334667344727707, | |
| "eval_loss": 3.087890625, | |
| "eval_perplexity": 21.930768935644906, | |
| "eval_runtime": 7.9822, | |
| "eval_samples_per_second": 45.602, | |
| "eval_steps_per_second": 5.763, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1e-06, | |
| "loss": 3.1118, | |
| "perplexity": 22.461438624562685, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_accuracy": 0.23352201118800717, | |
| "eval_loss": 3.087890625, | |
| "eval_perplexity": 21.930768935644906, | |
| "eval_runtime": 6.928, | |
| "eval_samples_per_second": 52.54, | |
| "eval_steps_per_second": 6.64, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1e-06, | |
| "loss": 3.0596, | |
| "perplexity": 21.319027845139193, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.2335828155747673, | |
| "eval_loss": 3.0859375, | |
| "eval_perplexity": 21.887977204970085, | |
| "eval_runtime": 7.9803, | |
| "eval_samples_per_second": 45.612, | |
| "eval_steps_per_second": 5.764, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1e-06, | |
| "loss": 3.1033, | |
| "perplexity": 22.271325521579506, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.23359387091781458, | |
| "eval_loss": 3.0859375, | |
| "eval_perplexity": 21.887977204970085, | |
| "eval_runtime": 7.9699, | |
| "eval_samples_per_second": 45.672, | |
| "eval_steps_per_second": 5.772, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 75, | |
| "total_flos": 352569360384.0, | |
| "train_loss": 3.1779069010416667, | |
| "train_runtime": 632.8224, | |
| "train_samples_per_second": 0.947, | |
| "train_steps_per_second": 0.119 | |
| } | |
| ], | |
| "max_steps": 75, | |
| "num_train_epochs": 1, | |
| "total_flos": 352569360384.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |