| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.027820280984837947, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005564056196967589, | |
| "eval_loss": 1.269508719444275, | |
| "eval_runtime": 165.5025, | |
| "eval_samples_per_second": 18.29, | |
| "eval_steps_per_second": 2.29, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016692168590902768, | |
| "grad_norm": 0.648344099521637, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2255, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0027820280984837947, | |
| "eval_loss": 1.206318736076355, | |
| "eval_runtime": 166.6813, | |
| "eval_samples_per_second": 18.16, | |
| "eval_steps_per_second": 2.274, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0033384337181805537, | |
| "grad_norm": 0.47053614258766174, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2331, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005007650577270831, | |
| "grad_norm": 0.6042889356613159, | |
| "learning_rate": 9e-05, | |
| "loss": 1.1899, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005564056196967589, | |
| "eval_loss": 1.1343153715133667, | |
| "eval_runtime": 166.6168, | |
| "eval_samples_per_second": 18.167, | |
| "eval_steps_per_second": 2.275, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006676867436361107, | |
| "grad_norm": 0.44560614228248596, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 1.1477, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008346084295451384, | |
| "grad_norm": 0.37463411688804626, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.1432, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008346084295451384, | |
| "eval_loss": 1.0934879779815674, | |
| "eval_runtime": 166.7796, | |
| "eval_samples_per_second": 18.15, | |
| "eval_steps_per_second": 2.272, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010015301154541661, | |
| "grad_norm": 0.35686883330345154, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.0246, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.011128112393935179, | |
| "eval_loss": 1.0731762647628784, | |
| "eval_runtime": 166.7141, | |
| "eval_samples_per_second": 18.157, | |
| "eval_steps_per_second": 2.273, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011684518013631937, | |
| "grad_norm": 0.3086533844470978, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 1.0549, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.013353734872722215, | |
| "grad_norm": 0.31386634707450867, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 1.0216, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.013910140492418973, | |
| "eval_loss": 1.0609967708587646, | |
| "eval_runtime": 166.7059, | |
| "eval_samples_per_second": 18.158, | |
| "eval_steps_per_second": 2.273, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01502295173181249, | |
| "grad_norm": 0.3252800405025482, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 1.1287, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.016692168590902768, | |
| "grad_norm": 0.3297823667526245, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0485, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.016692168590902768, | |
| "eval_loss": 1.053066611289978, | |
| "eval_runtime": 166.6611, | |
| "eval_samples_per_second": 18.163, | |
| "eval_steps_per_second": 2.274, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.018361385449993044, | |
| "grad_norm": 0.331866055727005, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 1.0903, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.019474196689386564, | |
| "eval_loss": 1.047993540763855, | |
| "eval_runtime": 166.5681, | |
| "eval_samples_per_second": 18.173, | |
| "eval_steps_per_second": 2.275, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.020030602309083323, | |
| "grad_norm": 0.29449304938316345, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 1.04, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0216998191681736, | |
| "grad_norm": 0.3140169382095337, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 1.091, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.022256224787870357, | |
| "eval_loss": 1.0448905229568481, | |
| "eval_runtime": 166.5581, | |
| "eval_samples_per_second": 18.174, | |
| "eval_steps_per_second": 2.275, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.023369036027263874, | |
| "grad_norm": 0.3020647466182709, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.0034, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.025038252886354154, | |
| "grad_norm": 0.29544344544410706, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.0153, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.025038252886354154, | |
| "eval_loss": 1.043650507926941, | |
| "eval_runtime": 166.7168, | |
| "eval_samples_per_second": 18.157, | |
| "eval_steps_per_second": 2.273, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02670746974544443, | |
| "grad_norm": 0.3063053786754608, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 1.0497, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.027820280984837947, | |
| "eval_loss": 1.0434459447860718, | |
| "eval_runtime": 166.6361, | |
| "eval_samples_per_second": 18.165, | |
| "eval_steps_per_second": 2.274, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.11747382607872e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |