| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.10982976386600769, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004393190554640308, | |
| "grad_norm": 0.05475381389260292, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4794, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004393190554640308, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.4744, | |
| "eval_samples_per_second": 14.391, | |
| "eval_steps_per_second": 3.742, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008786381109280615, | |
| "grad_norm": 0.05656403303146362, | |
| "learning_rate": 0.0001, | |
| "loss": 0.505, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013179571663920923, | |
| "grad_norm": 0.052167490124702454, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.4598, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01757276221856123, | |
| "grad_norm": 0.04929260537028313, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.47, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.021965952773201538, | |
| "grad_norm": 0.04034111276268959, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.4465, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.026359143327841845, | |
| "grad_norm": 0.045049283653497696, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.4537, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.030752333882482153, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03514552443712246, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.039538714991762765, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.043931905546403076, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04832509610104338, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05271828665568369, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.057111477210323995, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.061504667764964306, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06589785831960461, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07029104887424492, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07468423942888523, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07907742998352553, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08347062053816584, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08786381109280615, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09225700164744646, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09665019220208676, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10104338275672707, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10543657331136738, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.10982976386600769, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10982976386600769, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.6616, | |
| "eval_samples_per_second": 30.091, | |
| "eval_steps_per_second": 7.824, | |
| "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": 2.812028905324544e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |