| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00421896424427803, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.437928488556059e-05, | |
| "eval_loss": 0.9703615307807922, | |
| "eval_runtime": 637.2947, | |
| "eval_samples_per_second": 7.83, | |
| "eval_steps_per_second": 3.915, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00042189642442780296, | |
| "grad_norm": 0.5675859451293945, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9916, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008437928488556059, | |
| "grad_norm": 0.6622980833053589, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9344, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008437928488556059, | |
| "eval_loss": 0.9052106142044067, | |
| "eval_runtime": 651.5862, | |
| "eval_samples_per_second": 7.658, | |
| "eval_steps_per_second": 3.829, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012656892732834089, | |
| "grad_norm": 0.48470181226730347, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7925, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0016875856977112118, | |
| "grad_norm": 0.4948732256889343, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.8193, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0016875856977112118, | |
| "eval_loss": 0.8120317459106445, | |
| "eval_runtime": 651.774, | |
| "eval_samples_per_second": 7.656, | |
| "eval_steps_per_second": 3.828, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002109482122139015, | |
| "grad_norm": 0.4612963795661926, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8603, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0025313785465668178, | |
| "grad_norm": 0.4521726369857788, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7412, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0025313785465668178, | |
| "eval_loss": 0.7803506255149841, | |
| "eval_runtime": 651.2285, | |
| "eval_samples_per_second": 7.662, | |
| "eval_steps_per_second": 3.831, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0029532749709946207, | |
| "grad_norm": 0.39906030893325806, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.7043, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0033751713954224237, | |
| "grad_norm": 0.4752287268638611, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.811, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0033751713954224237, | |
| "eval_loss": 0.7723866105079651, | |
| "eval_runtime": 651.4853, | |
| "eval_samples_per_second": 7.659, | |
| "eval_steps_per_second": 3.83, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0037970678198502267, | |
| "grad_norm": 0.4312344789505005, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8428, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00421896424427803, | |
| "grad_norm": 0.40048474073410034, | |
| "learning_rate": 0.0, | |
| "loss": 0.6917, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00421896424427803, | |
| "eval_loss": 0.7709933519363403, | |
| "eval_runtime": 651.1988, | |
| "eval_samples_per_second": 7.663, | |
| "eval_steps_per_second": 3.831, | |
| "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": 1.3131906161836032e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |