| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.19890601690701143, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000994530084535057, | |
| "eval_loss": 0.19087886810302734, | |
| "eval_runtime": 18.3599, | |
| "eval_samples_per_second": 23.094, | |
| "eval_steps_per_second": 11.547, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009945300845350571, | |
| "grad_norm": 0.09784416109323502, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 0.4594, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.019890601690701143, | |
| "grad_norm": 0.007063413504511118, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 0.002, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.029835902536051714, | |
| "grad_norm": 0.038785140961408615, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 0.0113, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.039781203381402286, | |
| "grad_norm": 0.006827597506344318, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 0.0057, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04972650422675286, | |
| "grad_norm": 0.000748810765799135, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 0.0071, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04972650422675286, | |
| "eval_loss": 0.00038344075437635183, | |
| "eval_runtime": 17.1892, | |
| "eval_samples_per_second": 24.667, | |
| "eval_steps_per_second": 12.333, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05967180507210343, | |
| "grad_norm": 0.00040479126619175076, | |
| "learning_rate": 0.00016324453755953773, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.069617105917454, | |
| "grad_norm": 0.0010634174104779959, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0027, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.07956240676280457, | |
| "grad_norm": 0.0016953607555478811, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 0.0052, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.08950770760815514, | |
| "grad_norm": 0.00024003616999834776, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 0.0001, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.09945300845350571, | |
| "grad_norm": 0.0002944810257758945, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 0.0021, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09945300845350571, | |
| "eval_loss": 0.00019088714907411486, | |
| "eval_runtime": 17.1377, | |
| "eval_samples_per_second": 24.741, | |
| "eval_steps_per_second": 12.37, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.10939830929885629, | |
| "grad_norm": 0.0002713771245907992, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 0.0003, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.11934361014420686, | |
| "grad_norm": 0.00031669007148593664, | |
| "learning_rate": 7.217825360835473e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.12928891098955744, | |
| "grad_norm": 0.0003192306903656572, | |
| "learning_rate": 5.713074385969457e-05, | |
| "loss": 0.0012, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.139234211834908, | |
| "grad_norm": 0.23460803925991058, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 0.0001, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.14917951268025859, | |
| "grad_norm": 0.002061684150248766, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.14917951268025859, | |
| "eval_loss": 0.0003408108896110207, | |
| "eval_runtime": 17.1663, | |
| "eval_samples_per_second": 24.7, | |
| "eval_steps_per_second": 12.35, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.15912481352560914, | |
| "grad_norm": 0.000430845539085567, | |
| "learning_rate": 2.0055723659649904e-05, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.16907011437095973, | |
| "grad_norm": 0.00024463460431434214, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.1790154152163103, | |
| "grad_norm": 0.007861273363232613, | |
| "learning_rate": 5.146355805285452e-06, | |
| "loss": 0.0039, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.18896071606166087, | |
| "grad_norm": 0.00012755903298966587, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 0.0021, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.19890601690701143, | |
| "grad_norm": 0.0007723955204710364, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.19890601690701143, | |
| "eval_loss": 0.0003575802256818861, | |
| "eval_runtime": 17.1979, | |
| "eval_samples_per_second": 24.654, | |
| "eval_steps_per_second": 12.327, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.494263021928448e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |