| { |
| "best_metric": 1.5678154230117798, |
| "best_model_checkpoint": "miner_id_24/checkpoint-400", |
| "epoch": 0.02466281310211946, |
| "eval_steps": 50, |
| "global_step": 400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 6.165703275529865e-05, |
| "eval_loss": 2.288787603378296, |
| "eval_runtime": 1041.9153, |
| "eval_samples_per_second": 13.109, |
| "eval_steps_per_second": 6.554, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0024662813102119463, |
| "grad_norm": 1.1392245292663574, |
| "learning_rate": 5e-05, |
| "loss": 1.8648, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0030828516377649326, |
| "eval_loss": 1.6245982646942139, |
| "eval_runtime": 1041.7956, |
| "eval_samples_per_second": 13.11, |
| "eval_steps_per_second": 6.555, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.0049325626204238925, |
| "grad_norm": 1.1976816654205322, |
| "learning_rate": 0.0001, |
| "loss": 1.6089, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.006165703275529865, |
| "eval_loss": 1.608966588973999, |
| "eval_runtime": 1041.4182, |
| "eval_samples_per_second": 13.115, |
| "eval_steps_per_second": 6.557, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.007398843930635838, |
| "grad_norm": 0.9106088876724243, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 1.5941, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.009248554913294798, |
| "eval_loss": 1.6026890277862549, |
| "eval_runtime": 1041.2784, |
| "eval_samples_per_second": 13.117, |
| "eval_steps_per_second": 6.558, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.009865125240847785, |
| "grad_norm": 1.0939823389053345, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 1.6436, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.01233140655105973, |
| "grad_norm": 1.1950139999389648, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 1.5907, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.01233140655105973, |
| "eval_loss": 1.5895808935165405, |
| "eval_runtime": 1041.3859, |
| "eval_samples_per_second": 13.115, |
| "eval_steps_per_second": 6.558, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.014797687861271676, |
| "grad_norm": 0.8904630541801453, |
| "learning_rate": 5e-05, |
| "loss": 1.587, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.015414258188824663, |
| "eval_loss": 1.5806567668914795, |
| "eval_runtime": 1041.1372, |
| "eval_samples_per_second": 13.118, |
| "eval_steps_per_second": 6.559, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.017263969171483623, |
| "grad_norm": 0.8200499415397644, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 1.6022, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.018497109826589597, |
| "eval_loss": 1.5710722208023071, |
| "eval_runtime": 1041.1766, |
| "eval_samples_per_second": 13.118, |
| "eval_steps_per_second": 6.559, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.01973025048169557, |
| "grad_norm": 0.7950920462608337, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 1.606, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.02157996146435453, |
| "eval_loss": 1.5714285373687744, |
| "eval_runtime": 1042.0279, |
| "eval_samples_per_second": 13.107, |
| "eval_steps_per_second": 6.554, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.022196531791907514, |
| "grad_norm": 0.8112738728523254, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 1.6334, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.02466281310211946, |
| "grad_norm": 1.1077427864074707, |
| "learning_rate": 0.0, |
| "loss": 1.6116, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.02466281310211946, |
| "eval_loss": 1.5678154230117798, |
| "eval_runtime": 1040.5356, |
| "eval_samples_per_second": 13.126, |
| "eval_steps_per_second": 6.563, |
| "step": 400 |
| } |
| ], |
| "logging_steps": 40, |
| "max_steps": 400, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.635628799188009e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
