| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 5, |
| "global_step": 27, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.037037037037037035, |
| "grad_norm": 0.0323716439306736, |
| "learning_rate": 0.0, |
| "loss": 1.7031, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07407407407407407, |
| "grad_norm": 0.036634452641010284, |
| "learning_rate": 9.999999999999999e-05, |
| "loss": 1.7422, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.1111111111111111, |
| "grad_norm": 0.05483530834317207, |
| "learning_rate": 0.00019999999999999998, |
| "loss": 1.8389, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.14814814814814814, |
| "grad_norm": 0.03792310878634453, |
| "learning_rate": 0.0003, |
| "loss": 1.627, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.18518518518518517, |
| "grad_norm": 0.08982960134744644, |
| "learning_rate": 0.0002988450562854644, |
| "loss": 1.7754, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2222222222222222, |
| "grad_norm": 0.11018437892198563, |
| "learning_rate": 0.0002953999865490242, |
| "loss": 1.6992, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.25925925925925924, |
| "grad_norm": 0.11859811842441559, |
| "learning_rate": 0.0002897237368890237, |
| "loss": 1.7471, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.25925925925925924, |
| "eval_loss": 1.54296875, |
| "eval_runtime": 5.697, |
| "eval_samples_per_second": 0.878, |
| "eval_steps_per_second": 0.176, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.2962962962962963, |
| "grad_norm": 0.06322980672121048, |
| "learning_rate": 0.0002819134295108992, |
| "loss": 1.5508, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 0.048590220510959625, |
| "learning_rate": 0.0002721027009393167, |
| "loss": 1.5215, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.37037037037037035, |
| "grad_norm": 0.05578836426138878, |
| "learning_rate": 0.0002604594154601839, |
| "loss": 1.5449, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4074074074074074, |
| "grad_norm": 0.05479580909013748, |
| "learning_rate": 0.00024718279291617725, |
| "loss": 1.5073, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.4444444444444444, |
| "grad_norm": 0.0617070309817791, |
| "learning_rate": 0.00023249999999999999, |
| "loss": 1.4673, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.4444444444444444, |
| "eval_loss": 1.45703125, |
| "eval_runtime": 5.683, |
| "eval_samples_per_second": 0.88, |
| "eval_steps_per_second": 0.176, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.48148148148148145, |
| "grad_norm": 0.06931957602500916, |
| "learning_rate": 0.00021666226336928708, |
| "loss": 1.4482, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.5185185185185185, |
| "grad_norm": 0.06682772934436798, |
| "learning_rate": 0.0001999405710888403, |
| "loss": 1.4336, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.5555555555555556, |
| "grad_norm": 0.06568224728107452, |
| "learning_rate": 0.00018262103594970697, |
| "loss": 1.4062, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 0.06467080116271973, |
| "learning_rate": 0.000165, |
| "loss": 1.4062, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.6296296296296297, |
| "grad_norm": 0.06931172311306, |
| "learning_rate": 0.00014737896405029306, |
| "loss": 1.4707, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.6296296296296297, |
| "eval_loss": 1.412109375, |
| "eval_runtime": 5.6947, |
| "eval_samples_per_second": 0.878, |
| "eval_steps_per_second": 0.176, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 0.05858941003680229, |
| "learning_rate": 0.00013005942891115968, |
| "loss": 1.3745, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7037037037037037, |
| "grad_norm": 0.057609304785728455, |
| "learning_rate": 0.00011333773663071288, |
| "loss": 1.3682, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.7407407407407407, |
| "grad_norm": 0.054803647100925446, |
| "learning_rate": 9.750000000000003e-05, |
| "loss": 1.4116, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7777777777777778, |
| "grad_norm": 0.05181348696351051, |
| "learning_rate": 8.28172070838227e-05, |
| "loss": 1.3691, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.8148148148148148, |
| "grad_norm": 0.05536660552024841, |
| "learning_rate": 6.954058453981609e-05, |
| "loss": 1.4121, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.8148148148148148, |
| "eval_loss": 1.38525390625, |
| "eval_runtime": 5.7023, |
| "eval_samples_per_second": 0.877, |
| "eval_steps_per_second": 0.175, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.8518518518518519, |
| "grad_norm": 0.05110856145620346, |
| "learning_rate": 5.789729906068326e-05, |
| "loss": 1.3921, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.8888888888888888, |
| "grad_norm": 0.060252055525779724, |
| "learning_rate": 4.808657048910077e-05, |
| "loss": 1.4434, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.9259259259259259, |
| "grad_norm": 0.04292573779821396, |
| "learning_rate": 4.027626311097629e-05, |
| "loss": 1.313, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.9629629629629629, |
| "grad_norm": 0.04377671331167221, |
| "learning_rate": 3.4600013450975794e-05, |
| "loss": 1.3984, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.04255930334329605, |
| "learning_rate": 3.11549437145356e-05, |
| "loss": 1.4033, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.375, |
| "eval_runtime": 5.6774, |
| "eval_samples_per_second": 0.881, |
| "eval_steps_per_second": 0.176, |
| "step": 27 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 27, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.2107040891283702e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
