| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9142857142857143, | |
| "eval_steps": 500, | |
| "global_step": 8, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11428571428571428, | |
| "grad_norm": 0.8518504500389099, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 1.1291, | |
| "num_input_tokens_seen": 2097152, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "grad_norm": 0.809882402420044, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 1.1246, | |
| "num_input_tokens_seen": 4194304, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.34285714285714286, | |
| "grad_norm": 1.4114207029342651, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 1.0721, | |
| "num_input_tokens_seen": 6291456, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 0.834094762802124, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.0703, | |
| "num_input_tokens_seen": 8388608, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.4744163453578949, | |
| "learning_rate": 1.5432914190872757e-05, | |
| "loss": 1.0601, | |
| "num_input_tokens_seen": 10485760, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.6857142857142857, | |
| "grad_norm": 0.34609249234199524, | |
| "learning_rate": 7.3223304703363135e-06, | |
| "loss": 1.0241, | |
| "num_input_tokens_seen": 12582912, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.2354990392923355, | |
| "learning_rate": 1.9030116872178316e-06, | |
| "loss": 1.0462, | |
| "num_input_tokens_seen": 14680064, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "grad_norm": 0.2111067920923233, | |
| "learning_rate": 0.0, | |
| "loss": 1.0376, | |
| "num_input_tokens_seen": 16777216, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "num_input_tokens_seen": 16777216, | |
| "step": 8, | |
| "total_flos": 7.554704537152389e+17, | |
| "train_loss": 1.0705121010541916, | |
| "train_runtime": 883.4072, | |
| "train_samples_per_second": 5.018, | |
| "train_steps_per_second": 0.009 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 8, | |
| "num_input_tokens_seen": 16777216, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.554704537152389e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |