| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.017106079072850514, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.553039536425257e-05, | |
| "eval_loss": 2.381143808364868, | |
| "eval_runtime": 144.1703, | |
| "eval_samples_per_second": 34.147, | |
| "eval_steps_per_second": 17.077, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008553039536425257, | |
| "grad_norm": 5.450172424316406, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 9.0162, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017106079072850514, | |
| "grad_norm": 4.5537848472595215, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 8.8664, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002565911860927577, | |
| "grad_norm": 7.618182182312012, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 9.0587, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.003421215814570103, | |
| "grad_norm": 5.113912582397461, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 8.1141, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004276519768212628, | |
| "grad_norm": 7.7498955726623535, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 8.7842, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004276519768212628, | |
| "eval_loss": 2.1146717071533203, | |
| "eval_runtime": 142.2534, | |
| "eval_samples_per_second": 34.607, | |
| "eval_steps_per_second": 17.307, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.005131823721855154, | |
| "grad_norm": 4.736423969268799, | |
| "learning_rate": 0.00016324453755953773, | |
| "loss": 8.2631, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.00598712767549768, | |
| "grad_norm": 3.9354634284973145, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 8.4239, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.006842431629140206, | |
| "grad_norm": 5.779056072235107, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 8.0989, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.007697735582782732, | |
| "grad_norm": 5.675789833068848, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 8.2106, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.008553039536425257, | |
| "grad_norm": 5.744926452636719, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 8.2246, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.008553039536425257, | |
| "eval_loss": 2.0408310890197754, | |
| "eval_runtime": 142.0789, | |
| "eval_samples_per_second": 34.65, | |
| "eval_steps_per_second": 17.328, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.009408343490067783, | |
| "grad_norm": 5.404253005981445, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 7.483, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.010263647443710309, | |
| "grad_norm": 7.058231830596924, | |
| "learning_rate": 7.217825360835473e-05, | |
| "loss": 8.0571, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.011118951397352835, | |
| "grad_norm": 5.664774417877197, | |
| "learning_rate": 5.713074385969457e-05, | |
| "loss": 8.5309, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.01197425535099536, | |
| "grad_norm": 4.67970085144043, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 7.8239, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.012829559304637885, | |
| "grad_norm": 6.211084365844727, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 7.6217, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.012829559304637885, | |
| "eval_loss": 2.0031981468200684, | |
| "eval_runtime": 141.879, | |
| "eval_samples_per_second": 34.699, | |
| "eval_steps_per_second": 17.353, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.013684863258280411, | |
| "grad_norm": 5.578930377960205, | |
| "learning_rate": 2.0055723659649904e-05, | |
| "loss": 7.9683, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.014540167211922937, | |
| "grad_norm": 5.688002109527588, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 8.0386, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.015395471165565463, | |
| "grad_norm": 4.525981903076172, | |
| "learning_rate": 5.146355805285452e-06, | |
| "loss": 7.3559, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.01625077511920799, | |
| "grad_norm": 5.752941608428955, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 7.7123, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.017106079072850514, | |
| "grad_norm": 15.219685554504395, | |
| "learning_rate": 0.0, | |
| "loss": 8.2222, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.017106079072850514, | |
| "eval_loss": 1.9949531555175781, | |
| "eval_runtime": 142.5551, | |
| "eval_samples_per_second": 34.534, | |
| "eval_steps_per_second": 17.271, | |
| "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": 3.534314936519885e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |