| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1422475106685633, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002844950213371266, | |
| "eval_loss": 10.37409496307373, | |
| "eval_runtime": 0.8696, | |
| "eval_samples_per_second": 170.187, | |
| "eval_steps_per_second": 85.094, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01422475106685633, | |
| "grad_norm": 0.023065494373440742, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3786, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02844950213371266, | |
| "grad_norm": 0.0242258682847023, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3796, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02844950213371266, | |
| "eval_loss": 10.374069213867188, | |
| "eval_runtime": 0.8623, | |
| "eval_samples_per_second": 171.641, | |
| "eval_steps_per_second": 85.82, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04267425320056899, | |
| "grad_norm": 0.022381599992513657, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3751, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05689900426742532, | |
| "grad_norm": 0.02105828933417797, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3762, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05689900426742532, | |
| "eval_loss": 10.373991966247559, | |
| "eval_runtime": 0.8862, | |
| "eval_samples_per_second": 167.007, | |
| "eval_steps_per_second": 83.503, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07112375533428165, | |
| "grad_norm": 0.024705884978175163, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3769, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08534850640113797, | |
| "grad_norm": 0.024922257289290428, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3789, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08534850640113797, | |
| "eval_loss": 10.373941421508789, | |
| "eval_runtime": 0.8889, | |
| "eval_samples_per_second": 166.498, | |
| "eval_steps_per_second": 83.249, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09957325746799431, | |
| "grad_norm": 0.021093839779496193, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3783, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11379800853485064, | |
| "grad_norm": 0.026645995676517487, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3738, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11379800853485064, | |
| "eval_loss": 10.373921394348145, | |
| "eval_runtime": 0.8687, | |
| "eval_samples_per_second": 170.376, | |
| "eval_steps_per_second": 85.188, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12802275960170698, | |
| "grad_norm": 0.028516408056020737, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3772, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1422475106685633, | |
| "grad_norm": 0.023940356448292732, | |
| "learning_rate": 0.0, | |
| "loss": 10.3792, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1422475106685633, | |
| "eval_loss": 10.373919486999512, | |
| "eval_runtime": 0.8942, | |
| "eval_samples_per_second": 165.508, | |
| "eval_steps_per_second": 82.754, | |
| "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": 1082963558400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |