| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.034601788313578706, | |
| "eval_steps": 50, | |
| "global_step": 26, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013308380120607194, | |
| "grad_norm": 3.5958077907562256, | |
| "learning_rate": 7.499999999999999e-06, | |
| "loss": 53.6584, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013308380120607194, | |
| "eval_loss": 1.6596457958221436, | |
| "eval_runtime": 576.7284, | |
| "eval_samples_per_second": 4.389, | |
| "eval_steps_per_second": 2.195, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026616760241214388, | |
| "grad_norm": 4.593629360198975, | |
| "learning_rate": 1.4999999999999999e-05, | |
| "loss": 53.83, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003992514036182159, | |
| "grad_norm": 3.8698318004608154, | |
| "learning_rate": 2.2499999999999998e-05, | |
| "loss": 53.7949, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0053233520482428775, | |
| "grad_norm": 3.574679136276245, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 51.8953, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006654190060303597, | |
| "grad_norm": 3.828587532043457, | |
| "learning_rate": 3.75e-05, | |
| "loss": 54.6933, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007985028072364318, | |
| "grad_norm": 4.688767433166504, | |
| "learning_rate": 4.4999999999999996e-05, | |
| "loss": 53.4681, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009315866084425037, | |
| "grad_norm": 3.8683738708496094, | |
| "learning_rate": 5.2499999999999995e-05, | |
| "loss": 52.2187, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010646704096485755, | |
| "grad_norm": 4.84136962890625, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 51.3524, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011977542108546475, | |
| "grad_norm": 4.16347599029541, | |
| "learning_rate": 6.75e-05, | |
| "loss": 52.5617, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013308380120607194, | |
| "grad_norm": 4.299065589904785, | |
| "learning_rate": 7.5e-05, | |
| "loss": 51.664, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014639218132667914, | |
| "grad_norm": 4.201577663421631, | |
| "learning_rate": 8.25e-05, | |
| "loss": 48.1549, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015970056144728635, | |
| "grad_norm": 4.490873336791992, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 51.543, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017300894156789353, | |
| "grad_norm": 5.399848461151123, | |
| "learning_rate": 9.75e-05, | |
| "loss": 50.0357, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.018631732168850074, | |
| "grad_norm": 5.014857769012451, | |
| "learning_rate": 0.00010499999999999999, | |
| "loss": 52.9329, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.019962570180910792, | |
| "grad_norm": 4.966302871704102, | |
| "learning_rate": 0.0001125, | |
| "loss": 49.8081, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02129340819297151, | |
| "grad_norm": 5.2359299659729, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 50.2341, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02262424620503223, | |
| "grad_norm": 5.209284782409668, | |
| "learning_rate": 0.00012749999999999998, | |
| "loss": 47.965, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02395508421709295, | |
| "grad_norm": 5.249284267425537, | |
| "learning_rate": 0.000135, | |
| "loss": 51.0081, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02528592222915367, | |
| "grad_norm": 6.256328582763672, | |
| "learning_rate": 0.0001425, | |
| "loss": 51.1662, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02661676024121439, | |
| "grad_norm": 5.501735687255859, | |
| "learning_rate": 0.00015, | |
| "loss": 47.9934, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02794759825327511, | |
| "grad_norm": 5.087883472442627, | |
| "learning_rate": 0.00014997810105601446, | |
| "loss": 49.7915, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.029278436265335828, | |
| "grad_norm": 7.2340874671936035, | |
| "learning_rate": 0.0001499124170124245, | |
| "loss": 49.9978, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03060927427739655, | |
| "grad_norm": 5.028345584869385, | |
| "learning_rate": 0.00014980298622686183, | |
| "loss": 50.2118, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03194011228945727, | |
| "grad_norm": 4.296029090881348, | |
| "learning_rate": 0.00014964987260382363, | |
| "loss": 46.4395, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.033270950301517985, | |
| "grad_norm": 4.090815544128418, | |
| "learning_rate": 0.00014945316555735403, | |
| "loss": 50.296, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.034601788313578706, | |
| "grad_norm": 4.5317063331604, | |
| "learning_rate": 0.0001492129799588288, | |
| "loss": 49.3161, | |
| "step": 26 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 150, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.484068172762972e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |