| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.8691588785046729, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07476635514018691, | |
| "grad_norm": 123.8866195678711, | |
| "learning_rate": 5e-05, | |
| "loss": 122.9282, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07476635514018691, | |
| "eval_loss": 7.675048828125, | |
| "eval_runtime": 4.6227, | |
| "eval_samples_per_second": 4.975, | |
| "eval_steps_per_second": 2.596, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.14953271028037382, | |
| "grad_norm": 123.39942169189453, | |
| "learning_rate": 0.0001, | |
| "loss": 122.9184, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.22429906542056074, | |
| "grad_norm": 124.43255615234375, | |
| "learning_rate": 9.983786540671051e-05, | |
| "loss": 125.1949, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.29906542056074764, | |
| "grad_norm": 179.55319213867188, | |
| "learning_rate": 9.935251313189564e-05, | |
| "loss": 93.22, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.37383177570093457, | |
| "grad_norm": 187.29672241210938, | |
| "learning_rate": 9.85470908713026e-05, | |
| "loss": 62.3989, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4485981308411215, | |
| "grad_norm": 168.5250701904297, | |
| "learning_rate": 9.742682209735727e-05, | |
| "loss": 35.4113, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5233644859813084, | |
| "grad_norm": 87.70977020263672, | |
| "learning_rate": 9.599897218294122e-05, | |
| "loss": 17.1692, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5981308411214953, | |
| "grad_norm": 31.452831268310547, | |
| "learning_rate": 9.42728012826605e-05, | |
| "loss": 12.8463, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6728971962616822, | |
| "grad_norm": 51.64335632324219, | |
| "learning_rate": 9.225950427718975e-05, | |
| "loss": 12.3417, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7476635514018691, | |
| "grad_norm": 19.907733917236328, | |
| "learning_rate": 8.997213817017507e-05, | |
| "loss": 11.1715, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.822429906542056, | |
| "grad_norm": 19.996755599975586, | |
| "learning_rate": 8.742553740855506e-05, | |
| "loss": 11.8429, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.897196261682243, | |
| "grad_norm": 11.934599876403809, | |
| "learning_rate": 8.463621767547998e-05, | |
| "loss": 10.8062, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9719626168224299, | |
| "grad_norm": 28.822046279907227, | |
| "learning_rate": 8.162226877976887e-05, | |
| "loss": 12.1965, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.0467289719626167, | |
| "grad_norm": 14.415942192077637, | |
| "learning_rate": 7.840323733655778e-05, | |
| "loss": 11.0528, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.1214953271028036, | |
| "grad_norm": 16.18528175354004, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.0053, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.1962616822429906, | |
| "grad_norm": 20.95121955871582, | |
| "learning_rate": 7.143462807015271e-05, | |
| "loss": 11.5001, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.2710280373831775, | |
| "grad_norm": 24.226356506347656, | |
| "learning_rate": 6.773024435212678e-05, | |
| "loss": 11.0841, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.3457943925233644, | |
| "grad_norm": 8.302922248840332, | |
| "learning_rate": 6.391087319582264e-05, | |
| "loss": 10.9346, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.4205607476635513, | |
| "grad_norm": 27.48256492614746, | |
| "learning_rate": 6.0001284688802226e-05, | |
| "loss": 11.4139, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.4953271028037383, | |
| "grad_norm": 32.03191375732422, | |
| "learning_rate": 5.602683401276615e-05, | |
| "loss": 11.5324, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.5700934579439252, | |
| "grad_norm": 13.780621528625488, | |
| "learning_rate": 5.201329700547076e-05, | |
| "loss": 10.8227, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.644859813084112, | |
| "grad_norm": 15.400556564331055, | |
| "learning_rate": 4.798670299452926e-05, | |
| "loss": 11.0594, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.719626168224299, | |
| "grad_norm": 23.47677993774414, | |
| "learning_rate": 4.397316598723385e-05, | |
| "loss": 11.7991, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.794392523364486, | |
| "grad_norm": 25.131492614746094, | |
| "learning_rate": 3.9998715311197785e-05, | |
| "loss": 11.6227, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.8691588785046729, | |
| "grad_norm": 23.62856674194336, | |
| "learning_rate": 3.608912680417737e-05, | |
| "loss": 11.2985, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.8691588785046729, | |
| "eval_loss": 0.6977319121360779, | |
| "eval_runtime": 4.6729, | |
| "eval_samples_per_second": 4.922, | |
| "eval_steps_per_second": 2.568, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 41, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.565663618577203e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |