| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04547521600727603, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009095043201455207, | |
| "eval_loss": 3.3733649253845215, | |
| "eval_runtime": 17.8696, | |
| "eval_samples_per_second": 25.91, | |
| "eval_steps_per_second": 12.983, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004547521600727604, | |
| "grad_norm": 1.3267475366592407, | |
| "learning_rate": 5e-05, | |
| "loss": 3.4053, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009095043201455207, | |
| "grad_norm": 1.4344451427459717, | |
| "learning_rate": 0.0001, | |
| "loss": 3.0979, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009095043201455207, | |
| "eval_loss": 3.200488805770874, | |
| "eval_runtime": 17.662, | |
| "eval_samples_per_second": 26.214, | |
| "eval_steps_per_second": 13.136, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013642564802182811, | |
| "grad_norm": 1.9536134004592896, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.9333, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.018190086402910415, | |
| "grad_norm": 1.8259481191635132, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.0527, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.018190086402910415, | |
| "eval_loss": 2.230600118637085, | |
| "eval_runtime": 17.7704, | |
| "eval_samples_per_second": 26.055, | |
| "eval_steps_per_second": 13.055, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.022737608003638016, | |
| "grad_norm": 1.6889228820800781, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6847, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.027285129604365622, | |
| "grad_norm": 1.6155500411987305, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9678, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.027285129604365622, | |
| "eval_loss": 1.909964919090271, | |
| "eval_runtime": 17.9512, | |
| "eval_samples_per_second": 25.792, | |
| "eval_steps_per_second": 12.924, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.031832651205093224, | |
| "grad_norm": 2.7540478706359863, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.1482, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03638017280582083, | |
| "grad_norm": 1.552095651626587, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.7002, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03638017280582083, | |
| "eval_loss": 1.860257625579834, | |
| "eval_runtime": 18.0583, | |
| "eval_samples_per_second": 25.639, | |
| "eval_steps_per_second": 12.847, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.040927694406548434, | |
| "grad_norm": 1.3981469869613647, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.5404, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04547521600727603, | |
| "grad_norm": 2.001523494720459, | |
| "learning_rate": 0.0, | |
| "loss": 1.7515, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04547521600727603, | |
| "eval_loss": 1.853514552116394, | |
| "eval_runtime": 17.853, | |
| "eval_samples_per_second": 25.934, | |
| "eval_steps_per_second": 12.995, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4100243324928000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |