| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.8, |
| "eval_steps": 20, |
| "global_step": 160, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.025, |
| "grad_norm": 0.24584950506687164, |
| "learning_rate": 1.6e-06, |
| "loss": 22.009127807617187, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.2564426362514496, |
| "learning_rate": 3.6e-06, |
| "loss": 22.05052947998047, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.075, |
| "grad_norm": 0.2390100657939911, |
| "learning_rate": 3.995627254437549e-06, |
| "loss": 22.014682006835937, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.2513236105442047, |
| "learning_rate": 3.9778957412029366e-06, |
| "loss": 22.021099853515626, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.1, |
| "eval_accuracy": 3.1746031746031745e-05, |
| "eval_loss": 11.020200729370117, |
| "eval_runtime": 2.4621, |
| "eval_samples_per_second": 406.152, |
| "eval_steps_per_second": 67.827, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.125, |
| "grad_norm": 0.25184789299964905, |
| "learning_rate": 3.9466531944960116e-06, |
| "loss": 22.0181884765625, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.268789142370224, |
| "learning_rate": 3.902113032590307e-06, |
| "loss": 22.01494598388672, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.175, |
| "grad_norm": 0.2609691917896271, |
| "learning_rate": 3.844579509954769e-06, |
| "loss": 22.0348876953125, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.2492043823003769, |
| "learning_rate": 3.7744456388872234e-06, |
| "loss": 21.99768524169922, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2, |
| "eval_accuracy": 3.1746031746031745e-05, |
| "eval_loss": 11.018282890319824, |
| "eval_runtime": 2.6799, |
| "eval_samples_per_second": 373.142, |
| "eval_steps_per_second": 62.315, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.225, |
| "grad_norm": 0.2999836802482605, |
| "learning_rate": 3.6921905048418706e-06, |
| "loss": 21.986573791503908, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.2840990126132965, |
| "learning_rate": 3.598375993789849e-06, |
| "loss": 22.012301635742187, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.275, |
| "grad_norm": 0.28335806727409363, |
| "learning_rate": 3.4936429539683075e-06, |
| "loss": 22.00952606201172, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.2717016935348511, |
| "learning_rate": 3.3787068182371314e-06, |
| "loss": 21.99034423828125, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.3, |
| "eval_accuracy": 3.1746031746031745e-05, |
| "eval_loss": 11.01639175415039, |
| "eval_runtime": 2.4905, |
| "eval_samples_per_second": 401.523, |
| "eval_steps_per_second": 67.054, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.325, |
| "grad_norm": 0.26950836181640625, |
| "learning_rate": 3.254352716947074e-06, |
| "loss": 22.037962341308592, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.25924476981163025, |
| "learning_rate": 3.1214301147033453e-06, |
| "loss": 22.014053344726562, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.375, |
| "grad_norm": 0.31555065512657166, |
| "learning_rate": 2.9808470076610163e-06, |
| "loss": 21.961640930175783, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.2712528705596924, |
| "learning_rate": 2.833563720990581e-06, |
| "loss": 21.988558959960937, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_accuracy": 3.1746031746031745e-05, |
| "eval_loss": 11.01443099975586, |
| "eval_runtime": 2.612, |
| "eval_samples_per_second": 382.842, |
| "eval_steps_per_second": 63.935, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.425, |
| "grad_norm": 0.260957270860672, |
| "learning_rate": 2.680586348883286e-06, |
| "loss": 22.034954833984376, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.2659424841403961, |
| "learning_rate": 2.5229598819076393e-06, |
| "loss": 22.037962341308592, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.475, |
| "grad_norm": 0.2600838541984558, |
| "learning_rate": 2.36176106866422e-06, |
| "loss": 21.996064758300783, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.2419586181640625, |
| "learning_rate": 2.198091060500926e-06, |
| "loss": 22.00383605957031, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.5, |
| "eval_accuracy": 3.1746031746031745e-05, |
| "eval_loss": 11.012611389160156, |
| "eval_runtime": 2.6096, |
| "eval_samples_per_second": 383.201, |
| "eval_steps_per_second": 63.995, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.525, |
| "grad_norm": 0.24510444700717926, |
| "learning_rate": 2.033067889532717e-06, |
| "loss": 21.980421447753905, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.24764317274093628, |
| "learning_rate": 1.8678188313486012e-06, |
| "loss": 21.973478698730467, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.575, |
| "grad_norm": 0.28122493624687195, |
| "learning_rate": 1.7034727045763157e-06, |
| "loss": 21.949703979492188, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.250843346118927, |
| "learning_rate": 1.541152159906497e-06, |
| "loss": 21.94451141357422, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.6, |
| "eval_accuracy": 3.1746031746031745e-05, |
| "eval_loss": 11.010734558105469, |
| "eval_runtime": 2.7011, |
| "eval_samples_per_second": 370.215, |
| "eval_steps_per_second": 61.826, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.625, |
| "grad_norm": 0.24475905299186707, |
| "learning_rate": 1.3819660112501052e-06, |
| "loss": 22.0078369140625, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 0.2379191815853119, |
| "learning_rate": 1.227001661415096e-06, |
| "loss": 22.009359741210936, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.675, |
| "grad_norm": 0.26111480593681335, |
| "learning_rate": 1.0773176740426246e-06, |
| "loss": 21.976290893554687, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.28270959854125977, |
| "learning_rate": 9.339365425440129e-07, |
| "loss": 22.019345092773438, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.7, |
| "eval_accuracy": 3.1746031746031745e-05, |
| "eval_loss": 11.009251594543457, |
| "eval_runtime": 2.5123, |
| "eval_samples_per_second": 398.045, |
| "eval_steps_per_second": 66.473, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.725, |
| "grad_norm": 0.2701219916343689, |
| "learning_rate": 7.978377054339498e-07, |
| "loss": 21.985748291015625, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.24651674926280975, |
| "learning_rate": 6.699508557723032e-07, |
| "loss": 22.00152130126953, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.775, |
| "grad_norm": 0.26024770736694336, |
| "learning_rate": 5.511495904178221e-07, |
| "loss": 22.02308044433594, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.25778868794441223, |
| "learning_rate": 4.4224544247577535e-07, |
| "loss": 21.997288513183594, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_accuracy": 3.1746031746031745e-05, |
| "eval_loss": 11.007829666137695, |
| "eval_runtime": 2.7386, |
| "eval_samples_per_second": 365.156, |
| "eval_steps_per_second": 60.981, |
| "step": 160 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 200, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "save_steps": 20, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 6, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
