| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 29, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.034482758620689655, | |
| "grad_norm": 4.296210765838623, | |
| "learning_rate": 3.333333333333333e-07, | |
| "loss": 1.5533, | |
| "mean_token_accuracy": 0.6920064091682434, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06896551724137931, | |
| "grad_norm": 5.163259029388428, | |
| "learning_rate": 6.666666666666666e-07, | |
| "loss": 1.7853, | |
| "mean_token_accuracy": 0.6263327598571777, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10344827586206896, | |
| "grad_norm": 4.452831745147705, | |
| "learning_rate": 1e-06, | |
| "loss": 1.5075, | |
| "mean_token_accuracy": 0.7126692533493042, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.13793103448275862, | |
| "grad_norm": 6.790956497192383, | |
| "learning_rate": 9.963544370490268e-07, | |
| "loss": 1.9253, | |
| "mean_token_accuracy": 0.6712393760681152, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1724137931034483, | |
| "grad_norm": 3.9182674884796143, | |
| "learning_rate": 9.85470908713026e-07, | |
| "loss": 1.6858, | |
| "mean_token_accuracy": 0.559170126914978, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.20689655172413793, | |
| "grad_norm": 3.839620351791382, | |
| "learning_rate": 9.675081213427074e-07, | |
| "loss": 1.5418, | |
| "mean_token_accuracy": 0.6354226469993591, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2413793103448276, | |
| "grad_norm": 4.464385986328125, | |
| "learning_rate": 9.427280128266049e-07, | |
| "loss": 1.5432, | |
| "mean_token_accuracy": 0.6771755814552307, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.27586206896551724, | |
| "grad_norm": 3.300748348236084, | |
| "learning_rate": 9.114919329468282e-07, | |
| "loss": 1.3202, | |
| "mean_token_accuracy": 0.6744688153266907, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3103448275862069, | |
| "grad_norm": 4.529242515563965, | |
| "learning_rate": 8.742553740855505e-07, | |
| "loss": 1.5632, | |
| "mean_token_accuracy": 0.7091418504714966, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3448275862068966, | |
| "grad_norm": 4.9364800453186035, | |
| "learning_rate": 8.315613291203976e-07, | |
| "loss": 1.3939, | |
| "mean_token_accuracy": 0.676058828830719, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3793103448275862, | |
| "grad_norm": 4.520140171051025, | |
| "learning_rate": 7.840323733655778e-07, | |
| "loss": 1.6434, | |
| "mean_token_accuracy": 0.6085848808288574, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.41379310344827586, | |
| "grad_norm": 3.786013126373291, | |
| "learning_rate": 7.323615860218842e-07, | |
| "loss": 1.4203, | |
| "mean_token_accuracy": 0.6495858430862427, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4482758620689655, | |
| "grad_norm": 4.0102105140686035, | |
| "learning_rate": 6.773024435212677e-07, | |
| "loss": 1.4744, | |
| "mean_token_accuracy": 0.715476393699646, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4827586206896552, | |
| "grad_norm": 6.1422576904296875, | |
| "learning_rate": 6.196578321437789e-07, | |
| "loss": 1.7096, | |
| "mean_token_accuracy": 0.6734651327133179, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5172413793103449, | |
| "grad_norm": 4.225828647613525, | |
| "learning_rate": 5.602683401276614e-07, | |
| "loss": 1.6184, | |
| "mean_token_accuracy": 0.6401326656341553, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5517241379310345, | |
| "grad_norm": 2.499864101409912, | |
| "learning_rate": 5e-07, | |
| "loss": 1.0916, | |
| "mean_token_accuracy": 0.712737500667572, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5862068965517241, | |
| "grad_norm": 3.797278881072998, | |
| "learning_rate": 4.397316598723385e-07, | |
| "loss": 1.5532, | |
| "mean_token_accuracy": 0.6137330532073975, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6206896551724138, | |
| "grad_norm": 3.9196736812591553, | |
| "learning_rate": 3.8034216785622125e-07, | |
| "loss": 1.5172, | |
| "mean_token_accuracy": 0.6513392925262451, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6551724137931034, | |
| "grad_norm": 3.312458038330078, | |
| "learning_rate": 3.2269755647873214e-07, | |
| "loss": 1.4259, | |
| "mean_token_accuracy": 0.6606206893920898, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6896551724137931, | |
| "grad_norm": 4.863149642944336, | |
| "learning_rate": 2.676384139781157e-07, | |
| "loss": 1.801, | |
| "mean_token_accuracy": 0.6028177738189697, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7241379310344828, | |
| "grad_norm": 6.340369701385498, | |
| "learning_rate": 2.1596762663442213e-07, | |
| "loss": 1.8937, | |
| "mean_token_accuracy": 0.6635770797729492, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7586206896551724, | |
| "grad_norm": 2.400047540664673, | |
| "learning_rate": 1.6843867087960251e-07, | |
| "loss": 1.1017, | |
| "mean_token_accuracy": 0.7170366048812866, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7931034482758621, | |
| "grad_norm": 6.618093490600586, | |
| "learning_rate": 1.257446259144494e-07, | |
| "loss": 1.8901, | |
| "mean_token_accuracy": 0.6319121718406677, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8275862068965517, | |
| "grad_norm": 3.391517400741577, | |
| "learning_rate": 8.850806705317182e-08, | |
| "loss": 1.3663, | |
| "mean_token_accuracy": 0.6898515224456787, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8620689655172413, | |
| "grad_norm": 4.413179874420166, | |
| "learning_rate": 5.72719871733951e-08, | |
| "loss": 1.5641, | |
| "mean_token_accuracy": 0.6674157381057739, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.896551724137931, | |
| "grad_norm": 4.75150728225708, | |
| "learning_rate": 3.2491878657292635e-08, | |
| "loss": 1.6575, | |
| "mean_token_accuracy": 0.6414722204208374, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9310344827586207, | |
| "grad_norm": 3.682435989379883, | |
| "learning_rate": 1.4529091286973993e-08, | |
| "loss": 1.3724, | |
| "mean_token_accuracy": 0.674655020236969, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9655172413793104, | |
| "grad_norm": 3.129405975341797, | |
| "learning_rate": 3.6455629509730135e-09, | |
| "loss": 1.5536, | |
| "mean_token_accuracy": 0.5809841752052307, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 2.9102606773376465, | |
| "learning_rate": 0.0, | |
| "loss": 1.2491, | |
| "mean_token_accuracy": 0.6780526041984558, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 29, | |
| "total_flos": 955996483584.0, | |
| "train_loss": 1.542164264054134, | |
| "train_runtime": 1339.7897, | |
| "train_samples_per_second": 0.085, | |
| "train_steps_per_second": 0.022 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 29, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 955996483584.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |