| { | |
| "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": 2.3803133964538574, | |
| "eval_runtime": 144.7679, | |
| "eval_samples_per_second": 34.006, | |
| "eval_steps_per_second": 17.007, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008553039536425257, | |
| "grad_norm": 5.870095252990723, | |
| "learning_rate": 0.0002, | |
| "loss": 8.9446, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017106079072850514, | |
| "grad_norm": 4.383564472198486, | |
| "learning_rate": 0.0002, | |
| "loss": 8.8167, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002565911860927577, | |
| "grad_norm": 7.525699615478516, | |
| "learning_rate": 0.0002, | |
| "loss": 9.0408, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.003421215814570103, | |
| "grad_norm": 4.683404922485352, | |
| "learning_rate": 0.0002, | |
| "loss": 8.1013, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004276519768212628, | |
| "grad_norm": 7.45261812210083, | |
| "learning_rate": 0.0002, | |
| "loss": 8.7849, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004276519768212628, | |
| "eval_loss": 2.1148810386657715, | |
| "eval_runtime": 142.9461, | |
| "eval_samples_per_second": 34.44, | |
| "eval_steps_per_second": 17.223, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.005131823721855154, | |
| "grad_norm": 4.496049880981445, | |
| "learning_rate": 0.0002, | |
| "loss": 8.26, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.00598712767549768, | |
| "grad_norm": 3.857893466949463, | |
| "learning_rate": 0.0002, | |
| "loss": 8.4083, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.006842431629140206, | |
| "grad_norm": 5.40677547454834, | |
| "learning_rate": 0.0002, | |
| "loss": 8.095, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.007697735582782732, | |
| "grad_norm": 5.3933563232421875, | |
| "learning_rate": 0.0002, | |
| "loss": 8.202, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.008553039536425257, | |
| "grad_norm": 5.276631832122803, | |
| "learning_rate": 0.0002, | |
| "loss": 8.2085, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.008553039536425257, | |
| "eval_loss": 2.0359315872192383, | |
| "eval_runtime": 143.1344, | |
| "eval_samples_per_second": 34.394, | |
| "eval_steps_per_second": 17.201, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.009408343490067783, | |
| "grad_norm": 5.116215705871582, | |
| "learning_rate": 0.0002, | |
| "loss": 7.4807, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.010263647443710309, | |
| "grad_norm": 6.443859100341797, | |
| "learning_rate": 0.0002, | |
| "loss": 8.0507, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.011118951397352835, | |
| "grad_norm": 4.91663122177124, | |
| "learning_rate": 0.0002, | |
| "loss": 8.4953, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.01197425535099536, | |
| "grad_norm": 4.3198699951171875, | |
| "learning_rate": 0.0002, | |
| "loss": 7.7724, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.012829559304637885, | |
| "grad_norm": 5.600128650665283, | |
| "learning_rate": 0.0002, | |
| "loss": 7.558, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.012829559304637885, | |
| "eval_loss": 1.9934526681900024, | |
| "eval_runtime": 143.0887, | |
| "eval_samples_per_second": 34.405, | |
| "eval_steps_per_second": 17.206, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.013684863258280411, | |
| "grad_norm": 4.960232257843018, | |
| "learning_rate": 0.0002, | |
| "loss": 7.9318, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.014540167211922937, | |
| "grad_norm": 5.194616794586182, | |
| "learning_rate": 0.0002, | |
| "loss": 7.9618, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.015395471165565463, | |
| "grad_norm": 4.613633632659912, | |
| "learning_rate": 0.0002, | |
| "loss": 7.2951, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.01625077511920799, | |
| "grad_norm": 5.5177507400512695, | |
| "learning_rate": 0.0002, | |
| "loss": 7.6231, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.017106079072850514, | |
| "grad_norm": 13.841983795166016, | |
| "learning_rate": 0.0002, | |
| "loss": 8.0881, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.017106079072850514, | |
| "eval_loss": 1.9552608728408813, | |
| "eval_runtime": 143.1864, | |
| "eval_samples_per_second": 34.382, | |
| "eval_steps_per_second": 17.194, | |
| "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 | |
| } | |