| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0004216198211910338, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.432396423820677e-06, | |
| "eval_loss": 0.8909456729888916, | |
| "eval_runtime": 4480.4241, | |
| "eval_samples_per_second": 11.145, | |
| "eval_steps_per_second": 5.572, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.216198211910338e-05, | |
| "grad_norm": 4.769817352294922, | |
| "learning_rate": 5e-05, | |
| "loss": 3.4832, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 8.432396423820676e-05, | |
| "grad_norm": 4.518204212188721, | |
| "learning_rate": 0.0001, | |
| "loss": 3.555, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 8.432396423820676e-05, | |
| "eval_loss": 0.8294536471366882, | |
| "eval_runtime": 4497.7777, | |
| "eval_samples_per_second": 11.102, | |
| "eval_steps_per_second": 5.551, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00012648594635731016, | |
| "grad_norm": 6.111549377441406, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.3884, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00016864792847641352, | |
| "grad_norm": 12.450406074523926, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.8286, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00016864792847641352, | |
| "eval_loss": 0.7843873500823975, | |
| "eval_runtime": 4513.5211, | |
| "eval_samples_per_second": 11.063, | |
| "eval_steps_per_second": 5.532, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0002108099105955169, | |
| "grad_norm": 4.027885437011719, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.1528, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0002529718927146203, | |
| "grad_norm": 6.886721611022949, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5525, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0002529718927146203, | |
| "eval_loss": 0.7667730450630188, | |
| "eval_runtime": 4495.5246, | |
| "eval_samples_per_second": 11.107, | |
| "eval_steps_per_second": 5.554, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0002951338748337237, | |
| "grad_norm": 6.5152153968811035, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.1792, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.00033729585695282705, | |
| "grad_norm": 15.089554786682129, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.8384, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00033729585695282705, | |
| "eval_loss": 0.7566215395927429, | |
| "eval_runtime": 4498.0748, | |
| "eval_samples_per_second": 11.101, | |
| "eval_steps_per_second": 5.551, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00037945783907193046, | |
| "grad_norm": 4.627601146697998, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.4376, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0004216198211910338, | |
| "grad_norm": 3.869359254837036, | |
| "learning_rate": 0.0, | |
| "loss": 3.0871, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0004216198211910338, | |
| "eval_loss": 0.755088746547699, | |
| "eval_runtime": 4485.5267, | |
| "eval_samples_per_second": 11.132, | |
| "eval_steps_per_second": 5.566, | |
| "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": 1.337000196046848e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |