| { | |
| "best_metric": 0.9295913577079773, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 1.221884498480243, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0486322188449848, | |
| "grad_norm": 122.75741577148438, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2344, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0486322188449848, | |
| "eval_loss": 5.1622395515441895, | |
| "eval_runtime": 3.688, | |
| "eval_samples_per_second": 37.69, | |
| "eval_steps_per_second": 4.881, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0972644376899696, | |
| "grad_norm": 69.6625747680664, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1183, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1458966565349544, | |
| "grad_norm": 94.78073120117188, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.9245, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1945288753799392, | |
| "grad_norm": 109.74983978271484, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.4097, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.24316109422492402, | |
| "grad_norm": 123.89290618896484, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 5.9994, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2917933130699088, | |
| "grad_norm": 58.025917053222656, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.7611, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": 58.173011779785156, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.4281, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3890577507598784, | |
| "grad_norm": 61.43299865722656, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.3761, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4376899696048632, | |
| "grad_norm": 86.56910705566406, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.6181, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.48632218844984804, | |
| "grad_norm": 123.04452514648438, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.0133, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5349544072948328, | |
| "grad_norm": 64.24591064453125, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.0057, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5835866261398176, | |
| "grad_norm": 50.80318832397461, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.7955, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6322188449848024, | |
| "grad_norm": 103.4283447265625, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.5451, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": 101.22402954101562, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.5553, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.729483282674772, | |
| "grad_norm": 70.3960189819336, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.5866, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7781155015197568, | |
| "grad_norm": 107.30152130126953, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.894, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8267477203647416, | |
| "grad_norm": 185.14161682128906, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.0501, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8753799392097265, | |
| "grad_norm": 63.85137176513672, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.1898, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.9240121580547113, | |
| "grad_norm": 68.57901763916016, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.1855, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.9726443768996961, | |
| "grad_norm": 81.24263000488281, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.1483, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.027355623100304, | |
| "grad_norm": 39.203556060791016, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.6328, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.0759878419452888, | |
| "grad_norm": 54.474021911621094, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.6113, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.1246200607902737, | |
| "grad_norm": 46.96053695678711, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.7844, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.1732522796352582, | |
| "grad_norm": 56.810081481933594, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.1084, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.221884498480243, | |
| "grad_norm": 121.81807708740234, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.0985, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.221884498480243, | |
| "eval_loss": 0.9295913577079773, | |
| "eval_runtime": 3.6736, | |
| "eval_samples_per_second": 37.837, | |
| "eval_steps_per_second": 4.9, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.85137494048768e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |