| { | |
| "best_metric": 4.476396560668945, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.10751243112484882, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0021502486224969763, | |
| "grad_norm": 1.4781171083450317, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9436, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021502486224969763, | |
| "eval_loss": 8.227113723754883, | |
| "eval_runtime": 1.4558, | |
| "eval_samples_per_second": 34.346, | |
| "eval_steps_per_second": 8.93, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0043004972449939526, | |
| "grad_norm": 1.8031319379806519, | |
| "learning_rate": 0.0001, | |
| "loss": 7.689, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006450745867490929, | |
| "grad_norm": 1.8073604106903076, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 7.7242, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008600994489987905, | |
| "grad_norm": 1.850464940071106, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 7.4152, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010751243112484881, | |
| "grad_norm": 2.3805034160614014, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 7.026, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012901491734981858, | |
| "grad_norm": 2.1438822746276855, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 6.6295, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015051740357478834, | |
| "grad_norm": 1.6822739839553833, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 6.2499, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01720198897997581, | |
| "grad_norm": 1.8163131475448608, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 6.1776, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.019352237602472785, | |
| "grad_norm": 2.1011786460876465, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 6.1028, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.021502486224969763, | |
| "grad_norm": 2.2820935249328613, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 5.9431, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.023652734847466737, | |
| "grad_norm": 2.4154911041259766, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 5.6964, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.025802983469963715, | |
| "grad_norm": 2.85208797454834, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 5.642, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02795323209246069, | |
| "grad_norm": 3.405471086502075, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 5.3364, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.030103480714957668, | |
| "grad_norm": 3.721980333328247, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 5.1152, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03225372933745464, | |
| "grad_norm": 2.19675350189209, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 5.0258, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03440397795995162, | |
| "grad_norm": 2.308140516281128, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 4.9537, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0365542265824486, | |
| "grad_norm": 2.413560390472412, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 4.9422, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03870447520494557, | |
| "grad_norm": 1.9585868120193481, | |
| "learning_rate": 7.75e-05, | |
| "loss": 4.8783, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04085472382744255, | |
| "grad_norm": 1.4311752319335938, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 4.8623, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.043004972449939526, | |
| "grad_norm": 1.6291133165359497, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 4.9489, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.045155221072436504, | |
| "grad_norm": 1.5990395545959473, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 4.8276, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.047305469694933475, | |
| "grad_norm": 1.5631839036941528, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 4.7752, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04945571831743045, | |
| "grad_norm": 2.221445322036743, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 4.8108, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05160596693992743, | |
| "grad_norm": 2.973601818084717, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 4.8329, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05375621556242441, | |
| "grad_norm": 4.1278300285339355, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 5.2737, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05375621556242441, | |
| "eval_loss": 4.893651008605957, | |
| "eval_runtime": 1.4445, | |
| "eval_samples_per_second": 34.615, | |
| "eval_steps_per_second": 9.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05590646418492138, | |
| "grad_norm": 6.720362186431885, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 4.8796, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05805671280741836, | |
| "grad_norm": 6.6319499015808105, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 4.8505, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.060206961429915336, | |
| "grad_norm": 6.37089729309082, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 4.8001, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06235721005241231, | |
| "grad_norm": 5.236145496368408, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 4.7555, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06450745867490928, | |
| "grad_norm": 4.066835403442383, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 4.5387, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06665770729740626, | |
| "grad_norm": 2.819272041320801, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 4.6675, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.06880795591990324, | |
| "grad_norm": 1.8012014627456665, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 4.5881, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07095820454240022, | |
| "grad_norm": 1.616188645362854, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 4.4681, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0731084531648972, | |
| "grad_norm": 1.6810884475708008, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 4.4601, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.07525870178739416, | |
| "grad_norm": 2.0555830001831055, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 4.5417, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07740895040989114, | |
| "grad_norm": 2.8344008922576904, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 4.7851, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07955919903238812, | |
| "grad_norm": 3.864741325378418, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 4.9669, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0817094476548851, | |
| "grad_norm": 1.7793840169906616, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 4.6599, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.08385969627738207, | |
| "grad_norm": 1.3759382963180542, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 4.2021, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.08600994489987905, | |
| "grad_norm": 1.3663908243179321, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 4.4005, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08816019352237603, | |
| "grad_norm": 1.2785991430282593, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 4.2243, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.09031044214487301, | |
| "grad_norm": 1.2903536558151245, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 4.4202, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.09246069076736997, | |
| "grad_norm": 1.398136019706726, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 4.377, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.09461093938986695, | |
| "grad_norm": 1.6057686805725098, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 4.4098, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.09676118801236393, | |
| "grad_norm": 1.499598503112793, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 4.4333, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0989114366348609, | |
| "grad_norm": 1.7191181182861328, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 4.3681, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10106168525735788, | |
| "grad_norm": 1.7606230974197388, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 4.3406, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.10321193387985486, | |
| "grad_norm": 2.182579755783081, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 4.4751, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.10536218250235184, | |
| "grad_norm": 2.8871469497680664, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 4.6591, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.10751243112484882, | |
| "grad_norm": 4.577729225158691, | |
| "learning_rate": 1e-05, | |
| "loss": 5.0534, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10751243112484882, | |
| "eval_loss": 4.476396560668945, | |
| "eval_runtime": 1.4456, | |
| "eval_samples_per_second": 34.589, | |
| "eval_steps_per_second": 8.993, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.624057810649088e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |