| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007590564927794751, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.795282463897376e-05, | |
| "eval_loss": 1.6482040882110596, | |
| "eval_runtime": 124.9716, | |
| "eval_samples_per_second": 88.78, | |
| "eval_steps_per_second": 44.394, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00037952824638973757, | |
| "grad_norm": 7.470829486846924, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 4.9266, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007590564927794751, | |
| "grad_norm": 5.788771629333496, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 1.8729, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0011385847391692126, | |
| "grad_norm": 6.233973979949951, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 1.0846, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0015181129855589503, | |
| "grad_norm": 5.445612907409668, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 0.5393, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0018976412319486877, | |
| "grad_norm": 5.85573148727417, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 0.5118, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0018976412319486877, | |
| "eval_loss": 0.10395737737417221, | |
| "eval_runtime": 124.7323, | |
| "eval_samples_per_second": 88.951, | |
| "eval_steps_per_second": 44.479, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.002277169478338425, | |
| "grad_norm": 4.383733749389648, | |
| "learning_rate": 0.00016324453755953773, | |
| "loss": 0.4487, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.002656697724728163, | |
| "grad_norm": 2.5093071460723877, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.306, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0030362259711179005, | |
| "grad_norm": 6.711397647857666, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 0.3747, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.003415754217507638, | |
| "grad_norm": 2.3839523792266846, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 0.3563, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0037952824638973755, | |
| "grad_norm": 2.5638654232025146, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 0.3081, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0037952824638973755, | |
| "eval_loss": 0.064681276679039, | |
| "eval_runtime": 125.0521, | |
| "eval_samples_per_second": 88.723, | |
| "eval_steps_per_second": 44.365, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.004174810710287113, | |
| "grad_norm": 5.275169849395752, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 0.1927, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.00455433895667685, | |
| "grad_norm": 3.027852773666382, | |
| "learning_rate": 7.217825360835473e-05, | |
| "loss": 0.2492, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0049338672030665885, | |
| "grad_norm": 22.369112014770508, | |
| "learning_rate": 5.713074385969457e-05, | |
| "loss": 0.3438, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.005313395449456326, | |
| "grad_norm": 5.542289733886719, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 0.2183, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.005692923695846063, | |
| "grad_norm": 0.9455445408821106, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 0.1863, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.005692923695846063, | |
| "eval_loss": 0.05306173115968704, | |
| "eval_runtime": 126.2787, | |
| "eval_samples_per_second": 87.861, | |
| "eval_steps_per_second": 43.935, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.006072451942235801, | |
| "grad_norm": 2.1838719844818115, | |
| "learning_rate": 2.0055723659649904e-05, | |
| "loss": 0.1598, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.006451980188625538, | |
| "grad_norm": 0.6331111788749695, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 0.2209, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.006831508435015276, | |
| "grad_norm": 2.03953218460083, | |
| "learning_rate": 5.146355805285452e-06, | |
| "loss": 0.1126, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.007211036681405014, | |
| "grad_norm": 3.976135492324829, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 0.2813, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.007590564927794751, | |
| "grad_norm": 1.570008635520935, | |
| "learning_rate": 0.0, | |
| "loss": 0.1904, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.007590564927794751, | |
| "eval_loss": 0.05086271092295647, | |
| "eval_runtime": 124.6253, | |
| "eval_samples_per_second": 89.027, | |
| "eval_steps_per_second": 44.517, | |
| "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": 1505146542489600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |