| { | |
| "best_metric": 0.0, | |
| "best_model_checkpoint": "hiera_model/checkpoint-283", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 283, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0353356890459364, | |
| "grad_norm": 4.513326644897461, | |
| "learning_rate": 5.882352941176471e-06, | |
| "loss": 7.6619, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0706713780918728, | |
| "grad_norm": 5.347131729125977, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 7.6612, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10600706713780919, | |
| "grad_norm": 7.650573253631592, | |
| "learning_rate": 1.7647058823529414e-05, | |
| "loss": 7.6148, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1413427561837456, | |
| "grad_norm": 6.892947196960449, | |
| "learning_rate": 2.3529411764705884e-05, | |
| "loss": 7.532, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.17667844522968199, | |
| "grad_norm": 7.388574600219727, | |
| "learning_rate": 2.9411764705882354e-05, | |
| "loss": 7.4152, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.21201413427561838, | |
| "grad_norm": 8.62385368347168, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 7.4114, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.24734982332155478, | |
| "grad_norm": 10.373017311096191, | |
| "learning_rate": 4.11764705882353e-05, | |
| "loss": 7.3113, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2826855123674912, | |
| "grad_norm": 6.3279500007629395, | |
| "learning_rate": 4.705882352941177e-05, | |
| "loss": 7.2527, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.31802120141342755, | |
| "grad_norm": 5.869943618774414, | |
| "learning_rate": 4.967277486910995e-05, | |
| "loss": 7.2645, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.35335689045936397, | |
| "grad_norm": 5.0281453132629395, | |
| "learning_rate": 4.9018324607329844e-05, | |
| "loss": 7.1714, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.38869257950530034, | |
| "grad_norm": 7.027573585510254, | |
| "learning_rate": 4.836387434554974e-05, | |
| "loss": 7.1634, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.42402826855123676, | |
| "grad_norm": 4.754793167114258, | |
| "learning_rate": 4.770942408376964e-05, | |
| "loss": 7.1112, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.45936395759717313, | |
| "grad_norm": 6.395844459533691, | |
| "learning_rate": 4.7054973821989526e-05, | |
| "loss": 7.0364, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.49469964664310956, | |
| "grad_norm": 5.85114049911499, | |
| "learning_rate": 4.6400523560209424e-05, | |
| "loss": 7.0286, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5300353356890459, | |
| "grad_norm": 5.452080249786377, | |
| "learning_rate": 4.574607329842932e-05, | |
| "loss": 7.1043, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5653710247349824, | |
| "grad_norm": 5.287403583526611, | |
| "learning_rate": 4.5091623036649215e-05, | |
| "loss": 6.9891, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6007067137809188, | |
| "grad_norm": 5.20114803314209, | |
| "learning_rate": 4.4437172774869113e-05, | |
| "loss": 6.9994, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6360424028268551, | |
| "grad_norm": 5.050561428070068, | |
| "learning_rate": 4.3782722513089005e-05, | |
| "loss": 6.9812, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.6713780918727915, | |
| "grad_norm": 4.857853412628174, | |
| "learning_rate": 4.3128272251308904e-05, | |
| "loss": 7.1296, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7067137809187279, | |
| "grad_norm": 4.78601598739624, | |
| "learning_rate": 4.24738219895288e-05, | |
| "loss": 7.0627, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7420494699646644, | |
| "grad_norm": 7.134556293487549, | |
| "learning_rate": 4.181937172774869e-05, | |
| "loss": 7.0056, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.7773851590106007, | |
| "grad_norm": 5.701265811920166, | |
| "learning_rate": 4.1164921465968586e-05, | |
| "loss": 6.9878, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.8127208480565371, | |
| "grad_norm": 5.249512672424316, | |
| "learning_rate": 4.0510471204188485e-05, | |
| "loss": 6.9481, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.8480565371024735, | |
| "grad_norm": 5.31380558013916, | |
| "learning_rate": 3.985602094240838e-05, | |
| "loss": 6.9556, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.8833922261484098, | |
| "grad_norm": 5.351413726806641, | |
| "learning_rate": 3.9201570680628275e-05, | |
| "loss": 6.9064, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.9187279151943463, | |
| "grad_norm": 5.594610214233398, | |
| "learning_rate": 3.8547120418848174e-05, | |
| "loss": 6.934, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.9540636042402827, | |
| "grad_norm": 8.065481185913086, | |
| "learning_rate": 3.7892670157068066e-05, | |
| "loss": 6.8646, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.9893992932862191, | |
| "grad_norm": 6.58479642868042, | |
| "learning_rate": 3.7238219895287964e-05, | |
| "loss": 6.9557, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 8.122916221618652, | |
| "eval_runtime": 9.1372, | |
| "eval_samples_per_second": 10.944, | |
| "eval_steps_per_second": 0.219, | |
| "step": 283 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 849, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 4.651092260493558e+17, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |