| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03222168519413565, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012888674077654262, | |
| "grad_norm": 2.766613245010376, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7738, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012888674077654262, | |
| "eval_loss": 1.8183860778808594, | |
| "eval_runtime": 1.8889, | |
| "eval_samples_per_second": 26.47, | |
| "eval_steps_per_second": 6.882, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025777348155308524, | |
| "grad_norm": 3.0379271507263184, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7691, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0038666022232962784, | |
| "grad_norm": 2.022273063659668, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.6256, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005155469631061705, | |
| "grad_norm": 2.1837451457977295, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.4897, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00644433703882713, | |
| "grad_norm": 1.3172669410705566, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.3688, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007733204446592557, | |
| "grad_norm": 1.0160404443740845, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.3307, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009022071854357983, | |
| "grad_norm": 0.7926989197731018, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.3408, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01031093926212341, | |
| "grad_norm": 0.6409326791763306, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.3078, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011599806669888834, | |
| "grad_norm": 0.6306732892990112, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.2909, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01288867407765426, | |
| "grad_norm": 0.554283618927002, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.2566, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014177541485419687, | |
| "grad_norm": 0.5179027915000916, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.278, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015466408893185114, | |
| "grad_norm": 0.5059335231781006, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.2939, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01675527630095054, | |
| "grad_norm": 0.4588373005390167, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.2758, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.018044143708715966, | |
| "grad_norm": 0.4461840093135834, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.279, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01933301111648139, | |
| "grad_norm": 0.40647274255752563, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.2465, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02062187852424682, | |
| "grad_norm": 0.4707936942577362, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.2558, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.021910745932012244, | |
| "grad_norm": 0.4289848804473877, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.2069, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02319961333977767, | |
| "grad_norm": 0.3997207283973694, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.2114, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.024488480747543097, | |
| "grad_norm": 0.4331037104129791, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.2551, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02577734815530852, | |
| "grad_norm": 0.4272749125957489, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.199, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02706621556307395, | |
| "grad_norm": 0.4014737904071808, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.2502, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.028355082970839374, | |
| "grad_norm": 0.40306416153907776, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.2364, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.029643950378604803, | |
| "grad_norm": 0.4330591559410095, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.2051, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.030932817786370227, | |
| "grad_norm": 0.4139660596847534, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.2276, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03222168519413565, | |
| "grad_norm": 0.42047977447509766, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.2147, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03222168519413565, | |
| "eval_loss": 1.168257713317871, | |
| "eval_runtime": 1.8869, | |
| "eval_samples_per_second": 26.498, | |
| "eval_steps_per_second": 6.89, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.1240447254528e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |