| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5970149253731343, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011940298507462687, | |
| "eval_loss": 1.5449435710906982, | |
| "eval_runtime": 33.4954, | |
| "eval_samples_per_second": 4.21, | |
| "eval_steps_per_second": 0.537, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03582089552238806, | |
| "grad_norm": 7.289577484130859, | |
| "learning_rate": 3e-05, | |
| "loss": 6.1357, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05970149253731343, | |
| "eval_loss": 1.4649710655212402, | |
| "eval_runtime": 33.7856, | |
| "eval_samples_per_second": 4.173, | |
| "eval_steps_per_second": 0.533, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07164179104477612, | |
| "grad_norm": 7.276589393615723, | |
| "learning_rate": 6e-05, | |
| "loss": 5.8751, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.10746268656716418, | |
| "grad_norm": 4.452966213226318, | |
| "learning_rate": 9e-05, | |
| "loss": 5.6047, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11940298507462686, | |
| "eval_loss": 1.3938730955123901, | |
| "eval_runtime": 33.7912, | |
| "eval_samples_per_second": 4.173, | |
| "eval_steps_per_second": 0.533, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14328358208955225, | |
| "grad_norm": 4.445888042449951, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 5.5517, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1791044776119403, | |
| "grad_norm": 3.2838003635406494, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.5237, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1791044776119403, | |
| "eval_loss": 1.3736783266067505, | |
| "eval_runtime": 33.7833, | |
| "eval_samples_per_second": 4.174, | |
| "eval_steps_per_second": 0.533, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21492537313432836, | |
| "grad_norm": 3.3037467002868652, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 5.4188, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.23880597014925373, | |
| "eval_loss": 1.3579882383346558, | |
| "eval_runtime": 33.8243, | |
| "eval_samples_per_second": 4.169, | |
| "eval_steps_per_second": 0.532, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2507462686567164, | |
| "grad_norm": 3.0785763263702393, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 5.4397, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2865671641791045, | |
| "grad_norm": 3.0347342491149902, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 5.3316, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "eval_loss": 1.3502321243286133, | |
| "eval_runtime": 33.8052, | |
| "eval_samples_per_second": 4.171, | |
| "eval_steps_per_second": 0.532, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.32238805970149254, | |
| "grad_norm": 2.8705027103424072, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 5.4831, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3582089552238806, | |
| "grad_norm": 2.9315133094787598, | |
| "learning_rate": 5e-05, | |
| "loss": 5.4605, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3582089552238806, | |
| "eval_loss": 1.342836856842041, | |
| "eval_runtime": 33.8234, | |
| "eval_samples_per_second": 4.169, | |
| "eval_steps_per_second": 0.532, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3940298507462687, | |
| "grad_norm": 2.7453272342681885, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 5.4128, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.417910447761194, | |
| "eval_loss": 1.3384729623794556, | |
| "eval_runtime": 33.805, | |
| "eval_samples_per_second": 4.171, | |
| "eval_steps_per_second": 0.532, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4298507462686567, | |
| "grad_norm": 2.74045467376709, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 5.2587, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.46567164179104475, | |
| "grad_norm": 2.70888090133667, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 5.2953, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.47761194029850745, | |
| "eval_loss": 1.3347140550613403, | |
| "eval_runtime": 33.828, | |
| "eval_samples_per_second": 4.168, | |
| "eval_steps_per_second": 0.532, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5014925373134328, | |
| "grad_norm": 2.642303228378296, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 5.2156, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5373134328358209, | |
| "grad_norm": 2.631282091140747, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 5.3161, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5373134328358209, | |
| "eval_loss": 1.3332561254501343, | |
| "eval_runtime": 33.8375, | |
| "eval_samples_per_second": 4.167, | |
| "eval_steps_per_second": 0.532, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.573134328358209, | |
| "grad_norm": 2.71305251121521, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 5.3342, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "eval_loss": 1.3329530954360962, | |
| "eval_runtime": 33.8044, | |
| "eval_samples_per_second": 4.171, | |
| "eval_steps_per_second": 0.532, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.430998008987648e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |