| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.11210369591872482, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011210369591872482, | |
| "eval_loss": NaN, | |
| "eval_runtime": 363.8331, | |
| "eval_samples_per_second": 8.259, | |
| "eval_steps_per_second": 4.131, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0033631108775617445, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2499999999999998e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006726221755123489, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4999999999999996e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010089332632685234, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.75e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010089332632685234, | |
| "eval_loss": NaN, | |
| "eval_runtime": 363.3391, | |
| "eval_samples_per_second": 8.271, | |
| "eval_steps_per_second": 4.137, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013452443510246978, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.016815554387808723, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001125, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.020178665265370467, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000135, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.020178665265370467, | |
| "eval_loss": NaN, | |
| "eval_runtime": 363.475, | |
| "eval_samples_per_second": 8.267, | |
| "eval_steps_per_second": 4.135, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02354177614293221, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014994217771805422, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.026904887020493956, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014907662554463532, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0302679978980557, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001471841427340235, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0302679978980557, | |
| "eval_loss": NaN, | |
| "eval_runtime": 363.5241, | |
| "eval_samples_per_second": 8.266, | |
| "eval_steps_per_second": 4.135, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.033631108775617445, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001442909649383465, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03699421965317919, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001404372005304598, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.040357330530740934, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013567627457812106, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.040357330530740934, | |
| "eval_loss": NaN, | |
| "eval_runtime": 363.2495, | |
| "eval_samples_per_second": 8.273, | |
| "eval_steps_per_second": 4.138, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04372044140830268, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001300741882076764, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04708355228586442, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012370860362476374, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05044666316342617, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011666776747647015, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05044666316342617, | |
| "eval_loss": NaN, | |
| "eval_runtime": 363.3478, | |
| "eval_samples_per_second": 8.27, | |
| "eval_steps_per_second": 4.137, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05380977404098791, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010904928748046599, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05717288491854966, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010095877928081196, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0605359957961114, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.25084022891929e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0605359957961114, | |
| "eval_loss": NaN, | |
| "eval_runtime": 363.2733, | |
| "eval_samples_per_second": 8.272, | |
| "eval_steps_per_second": 4.137, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.06389910667367314, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.381530480933783e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.06726221755123489, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.5e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07062532842879664, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.618469519066217e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.07062532842879664, | |
| "eval_loss": NaN, | |
| "eval_runtime": 363.3706, | |
| "eval_samples_per_second": 8.27, | |
| "eval_steps_per_second": 4.136, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.07398843930635839, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.7491597710807114e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.07735155018392012, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.904122071918801e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.08071466106148187, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.095071251953399e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.08071466106148187, | |
| "eval_loss": NaN, | |
| "eval_runtime": 363.4291, | |
| "eval_samples_per_second": 8.268, | |
| "eval_steps_per_second": 4.136, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.08407777193904362, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.333223252352985e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.08744088281660536, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6291396375236232e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.0908039936941671, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.99258117923236e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.0908039936941671, | |
| "eval_loss": NaN, | |
| "eval_runtime": 363.4534, | |
| "eval_samples_per_second": 8.268, | |
| "eval_steps_per_second": 4.135, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.09416710457172885, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4323725421878949e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.0975302154492906, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.56279946954021e-06, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.10089332632685234, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.709035061653494e-06, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.10089332632685234, | |
| "eval_loss": NaN, | |
| "eval_runtime": 363.4698, | |
| "eval_samples_per_second": 8.268, | |
| "eval_steps_per_second": 4.135, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.10425643720441408, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.815857265976462e-06, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.10761954808197582, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.233744553646754e-07, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.11098265895953757, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.7822281945782424e-08, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.11098265895953757, | |
| "eval_loss": NaN, | |
| "eval_runtime": 363.4949, | |
| "eval_samples_per_second": 8.267, | |
| "eval_steps_per_second": 4.135, | |
| "step": 99 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.52759145644032e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |