| { | |
| "best_metric": 0.6048961877822876, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6914433880726015, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013828867761452032, | |
| "grad_norm": 19.41750144958496, | |
| "learning_rate": 5e-05, | |
| "loss": 9.436, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013828867761452032, | |
| "eval_loss": 13.041923522949219, | |
| "eval_runtime": 1.2348, | |
| "eval_samples_per_second": 40.491, | |
| "eval_steps_per_second": 10.528, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.027657735522904063, | |
| "grad_norm": 25.918766021728516, | |
| "learning_rate": 0.0001, | |
| "loss": 11.5124, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04148660328435609, | |
| "grad_norm": 26.469493865966797, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.5429, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.055315471045808126, | |
| "grad_norm": 22.559579849243164, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 7.996, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06914433880726016, | |
| "grad_norm": 15.623014450073242, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 5.618, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08297320656871218, | |
| "grad_norm": 9.235369682312012, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 3.7077, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09680207433016422, | |
| "grad_norm": 8.236522674560547, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.4361, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11063094209161625, | |
| "grad_norm": 7.002991199493408, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.8168, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12445980985306827, | |
| "grad_norm": 12.638449668884277, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.5927, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13828867761452032, | |
| "grad_norm": 7.3518195152282715, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.1107, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15211754537597233, | |
| "grad_norm": 5.5680928230285645, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.9105, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16594641313742436, | |
| "grad_norm": 6.217997074127197, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.9884, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1797752808988764, | |
| "grad_norm": 9.09010124206543, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.3279, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.19360414866032843, | |
| "grad_norm": 6.975824356079102, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.8612, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.20743301642178047, | |
| "grad_norm": 4.971433639526367, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.8165, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2212618841832325, | |
| "grad_norm": 3.8946895599365234, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.7621, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.23509075194468454, | |
| "grad_norm": 3.8504183292388916, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.7787, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.24891961970613655, | |
| "grad_norm": 1.9558743238449097, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.519, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2627484874675886, | |
| "grad_norm": 3.0583417415618896, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.6867, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.27657735522904064, | |
| "grad_norm": 2.4759700298309326, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.6008, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2904062229904927, | |
| "grad_norm": 3.5067899227142334, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.7189, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.30423509075194466, | |
| "grad_norm": 3.40570068359375, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.6846, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3180639585133967, | |
| "grad_norm": 4.560232639312744, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.6542, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.33189282627484873, | |
| "grad_norm": 2.7666003704071045, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.5633, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.34572169403630076, | |
| "grad_norm": 3.0316214561462402, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.8192, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.34572169403630076, | |
| "eval_loss": 0.7558532953262329, | |
| "eval_runtime": 1.2505, | |
| "eval_samples_per_second": 39.985, | |
| "eval_steps_per_second": 10.396, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3595505617977528, | |
| "grad_norm": 4.026302814483643, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.6363, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.37337942955920483, | |
| "grad_norm": 1.810630202293396, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.5036, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.38720829732065687, | |
| "grad_norm": 2.4514455795288086, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.4986, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4010371650821089, | |
| "grad_norm": 3.9547641277313232, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.7143, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.41486603284356094, | |
| "grad_norm": 3.1139731407165527, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.6038, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.428694900605013, | |
| "grad_norm": 2.0004587173461914, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.4481, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.442523768366465, | |
| "grad_norm": 1.9126585721969604, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.5361, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.45635263612791704, | |
| "grad_norm": 1.7938328981399536, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.4805, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4701815038893691, | |
| "grad_norm": 1.4720524549484253, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.4319, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4840103716508211, | |
| "grad_norm": 1.2695094347000122, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.466, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4978392394122731, | |
| "grad_norm": 1.4350192546844482, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.4778, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5116681071737251, | |
| "grad_norm": 2.107414722442627, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.6617, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5254969749351772, | |
| "grad_norm": 1.9258248805999756, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.5402, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5393258426966292, | |
| "grad_norm": 3.372992515563965, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.4107, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5531547104580813, | |
| "grad_norm": 2.1692512035369873, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.4895, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5669835782195333, | |
| "grad_norm": 2.00020170211792, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.504, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5808124459809854, | |
| "grad_norm": 2.7335145473480225, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.4922, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5946413137424373, | |
| "grad_norm": 2.1037230491638184, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.5219, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6084701815038893, | |
| "grad_norm": 1.8822736740112305, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.445, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6222990492653414, | |
| "grad_norm": 1.46221923828125, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.4146, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6361279170267934, | |
| "grad_norm": 1.7882673740386963, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.4299, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6499567847882455, | |
| "grad_norm": 1.2945713996887207, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.3671, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6637856525496975, | |
| "grad_norm": 2.039731740951538, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.5587, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6776145203111495, | |
| "grad_norm": 1.9501632452011108, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.471, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6914433880726015, | |
| "grad_norm": 2.397514820098877, | |
| "learning_rate": 1e-05, | |
| "loss": 0.747, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6914433880726015, | |
| "eval_loss": 0.6048961877822876, | |
| "eval_runtime": 1.2504, | |
| "eval_samples_per_second": 39.987, | |
| "eval_steps_per_second": 10.397, | |
| "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": 1.62480894509056e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |