| { | |
| "best_metric": 1.940571904182434, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.017780938833570414, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007112375533428165, | |
| "grad_norm": 1.0226768255233765, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7332, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007112375533428165, | |
| "eval_loss": 2.303349733352661, | |
| "eval_runtime": 72.4237, | |
| "eval_samples_per_second": 4.101, | |
| "eval_steps_per_second": 2.057, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001422475106685633, | |
| "grad_norm": 2.3948476314544678, | |
| "learning_rate": 4e-05, | |
| "loss": 2.1298, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0021337126600284497, | |
| "grad_norm": 1.2849642038345337, | |
| "learning_rate": 6e-05, | |
| "loss": 1.1402, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002844950213371266, | |
| "grad_norm": 2.489079713821411, | |
| "learning_rate": 8e-05, | |
| "loss": 2.6149, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0035561877667140826, | |
| "grad_norm": 2.7179102897644043, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2787, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0035561877667140826, | |
| "eval_loss": 2.282101631164551, | |
| "eval_runtime": 67.7302, | |
| "eval_samples_per_second": 4.385, | |
| "eval_steps_per_second": 2.2, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004267425320056899, | |
| "grad_norm": 2.3609611988067627, | |
| "learning_rate": 0.00012, | |
| "loss": 2.0602, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004978662873399715, | |
| "grad_norm": 1.9805982112884521, | |
| "learning_rate": 0.00014, | |
| "loss": 1.8368, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005689900426742532, | |
| "grad_norm": 2.595736026763916, | |
| "learning_rate": 0.00016, | |
| "loss": 3.2253, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006401137980085348, | |
| "grad_norm": 2.229645252227783, | |
| "learning_rate": 0.00018, | |
| "loss": 2.575, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007112375533428165, | |
| "grad_norm": 2.968641519546509, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1571, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007112375533428165, | |
| "eval_loss": 2.119755506515503, | |
| "eval_runtime": 66.6043, | |
| "eval_samples_per_second": 4.459, | |
| "eval_steps_per_second": 2.237, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007823613086770981, | |
| "grad_norm": 2.978506326675415, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 2.7264, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.008534850640113799, | |
| "grad_norm": 1.6808420419692993, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.2978, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.009246088193456615, | |
| "grad_norm": 2.562319040298462, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 2.1881, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00995732574679943, | |
| "grad_norm": 1.3067262172698975, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.9299, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.010668563300142247, | |
| "grad_norm": 3.9195621013641357, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 3.0389, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010668563300142247, | |
| "eval_loss": 2.0008676052093506, | |
| "eval_runtime": 67.9244, | |
| "eval_samples_per_second": 4.373, | |
| "eval_steps_per_second": 2.194, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011379800853485065, | |
| "grad_norm": 3.2669296264648438, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.4851, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01209103840682788, | |
| "grad_norm": 2.9829790592193604, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.9611, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.012802275960170697, | |
| "grad_norm": 2.3141636848449707, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.4134, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.013513513513513514, | |
| "grad_norm": 3.255260705947876, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 2.1647, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01422475106685633, | |
| "grad_norm": 3.2143447399139404, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 2.3063, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01422475106685633, | |
| "eval_loss": 1.9506233930587769, | |
| "eval_runtime": 70.032, | |
| "eval_samples_per_second": 4.241, | |
| "eval_steps_per_second": 2.128, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014935988620199146, | |
| "grad_norm": 2.624873638153076, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 1.3516, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.015647226173541962, | |
| "grad_norm": 2.866389513015747, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.6004, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.016358463726884778, | |
| "grad_norm": 3.0391550064086914, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 2.0461, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.017069701280227598, | |
| "grad_norm": 1.268661618232727, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.0511, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.017780938833570414, | |
| "grad_norm": 3.030973434448242, | |
| "learning_rate": 0.0, | |
| "loss": 1.9056, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017780938833570414, | |
| "eval_loss": 1.940571904182434, | |
| "eval_runtime": 67.9672, | |
| "eval_samples_per_second": 4.37, | |
| "eval_steps_per_second": 2.192, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 149138924371968.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |