| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0507227998985544, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001014455997971088, | |
| "eval_loss": 1.4664257764816284, | |
| "eval_runtime": 67.9343, | |
| "eval_samples_per_second": 6.109, | |
| "eval_steps_per_second": 3.062, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00507227998985544, | |
| "grad_norm": 10.344429969787598, | |
| "learning_rate": 5e-05, | |
| "loss": 5.4314, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01014455997971088, | |
| "grad_norm": 7.157459735870361, | |
| "learning_rate": 0.0001, | |
| "loss": 6.0997, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01014455997971088, | |
| "eval_loss": 1.2896093130111694, | |
| "eval_runtime": 72.9596, | |
| "eval_samples_per_second": 5.688, | |
| "eval_steps_per_second": 2.851, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01521683996956632, | |
| "grad_norm": 10.42927074432373, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.0509, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02028911995942176, | |
| "grad_norm": 10.226600646972656, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 5.1741, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02028911995942176, | |
| "eval_loss": 1.1783760786056519, | |
| "eval_runtime": 73.8495, | |
| "eval_samples_per_second": 5.62, | |
| "eval_steps_per_second": 2.817, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0253613999492772, | |
| "grad_norm": 7.611446857452393, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.3569, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03043367993913264, | |
| "grad_norm": 7.597216606140137, | |
| "learning_rate": 5e-05, | |
| "loss": 4.9156, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03043367993913264, | |
| "eval_loss": 1.136177897453308, | |
| "eval_runtime": 73.88, | |
| "eval_samples_per_second": 5.617, | |
| "eval_steps_per_second": 2.815, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03550595992898808, | |
| "grad_norm": 8.975362777709961, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 4.4263, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04057823991884352, | |
| "grad_norm": 6.083137512207031, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 4.3746, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04057823991884352, | |
| "eval_loss": 1.1202702522277832, | |
| "eval_runtime": 73.8313, | |
| "eval_samples_per_second": 5.621, | |
| "eval_steps_per_second": 2.817, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04565051990869896, | |
| "grad_norm": 7.438549995422363, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 4.2389, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0507227998985544, | |
| "grad_norm": 6.926421165466309, | |
| "learning_rate": 0.0, | |
| "loss": 4.2256, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0507227998985544, | |
| "eval_loss": 1.1173491477966309, | |
| "eval_runtime": 73.9264, | |
| "eval_samples_per_second": 5.614, | |
| "eval_steps_per_second": 2.814, | |
| "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": 1.7351430880886784e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |