| { | |
| "best_metric": 2.039912396867294e-05, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.05650515609549371, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0022602062438197485, | |
| "grad_norm": 36.595455169677734, | |
| "learning_rate": 5e-05, | |
| "loss": 34.7665, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022602062438197485, | |
| "eval_loss": 2.0630860328674316, | |
| "eval_runtime": 1.719, | |
| "eval_samples_per_second": 29.086, | |
| "eval_steps_per_second": 7.562, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004520412487639497, | |
| "grad_norm": 39.6614875793457, | |
| "learning_rate": 0.0001, | |
| "loss": 33.471, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006780618731459246, | |
| "grad_norm": 32.70667266845703, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 31.7103, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009040824975278994, | |
| "grad_norm": 36.67475891113281, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 25.9939, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011301031219098742, | |
| "grad_norm": 36.65296936035156, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 19.2306, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013561237462918492, | |
| "grad_norm": 31.071895599365234, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 12.5263, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01582144370673824, | |
| "grad_norm": 21.966489791870117, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 7.6308, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.018081649950557988, | |
| "grad_norm": 16.192794799804688, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 4.9293, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.020341856194377738, | |
| "grad_norm": 15.897909164428711, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.8646, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.022602062438197484, | |
| "grad_norm": 8.273239135742188, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.566, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.024862268682017234, | |
| "grad_norm": 6.1374125480651855, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.6113, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.027122474925836984, | |
| "grad_norm": 2.8855037689208984, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.2869, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02938268116965673, | |
| "grad_norm": 1.617836833000183, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.2442, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03164288741347648, | |
| "grad_norm": 0.9079189896583557, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0921, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03390309365729623, | |
| "grad_norm": 0.7938075661659241, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.0645, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.036163299901115976, | |
| "grad_norm": 0.4913981854915619, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0119, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.038423506144935726, | |
| "grad_norm": 0.8335649967193604, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0098, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.040683712388755476, | |
| "grad_norm": 1.2266008853912354, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0091, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.042943918632575226, | |
| "grad_norm": 0.26017099618911743, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0042, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04520412487639497, | |
| "grad_norm": 0.37957748770713806, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0031, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04746433112021472, | |
| "grad_norm": 0.07026153057813644, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0014, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04972453736403447, | |
| "grad_norm": 0.02709748037159443, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0012, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05198474360785422, | |
| "grad_norm": 0.2505216896533966, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.0013, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05424494985167397, | |
| "grad_norm": 0.022128494456410408, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0007, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05650515609549371, | |
| "grad_norm": 0.019597666338086128, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0006, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05650515609549371, | |
| "eval_loss": 2.039912396867294e-05, | |
| "eval_runtime": 1.7431, | |
| "eval_samples_per_second": 28.684, | |
| "eval_steps_per_second": 7.458, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 2.629578157719552e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |