| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.08, |
| "eval_steps": 1000, |
| "global_step": 4000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.002, |
| "grad_norm": 2.427967071533203, |
| "learning_rate": 7.920000000000001e-05, |
| "loss": 8.595370483398437, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.004, |
| "grad_norm": 2.0173449516296387, |
| "learning_rate": 0.00015920000000000002, |
| "loss": 6.985690307617188, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.006, |
| "grad_norm": 2.1842076778411865, |
| "learning_rate": 0.00023920000000000001, |
| "loss": 6.733137817382812, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.008, |
| "grad_norm": 1.4833307266235352, |
| "learning_rate": 0.0003192, |
| "loss": 6.513255004882812, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 2.232273578643799, |
| "learning_rate": 0.0003992, |
| "loss": 6.504192504882813, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.012, |
| "grad_norm": 2.256459951400757, |
| "learning_rate": 0.00047920000000000005, |
| "loss": 6.356998901367188, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.014, |
| "grad_norm": 1.6759421825408936, |
| "learning_rate": 0.0005592, |
| "loss": 6.304365234375, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.016, |
| "grad_norm": 1.164450764656067, |
| "learning_rate": 0.0006392, |
| "loss": 6.234349975585937, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.018, |
| "grad_norm": 2.5291967391967773, |
| "learning_rate": 0.0007191999999999999, |
| "loss": 6.173318481445312, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 1.1007851362228394, |
| "learning_rate": 0.0007992, |
| "loss": 6.1113330078125, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.02, |
| "eval_accuracy": 0.14623679060665362, |
| "eval_loss": 6.150835037231445, |
| "eval_runtime": 13.1402, |
| "eval_samples_per_second": 76.102, |
| "eval_steps_per_second": 9.513, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.022, |
| "grad_norm": 0.8226528167724609, |
| "learning_rate": 0.0008792, |
| "loss": 6.04904052734375, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.024, |
| "grad_norm": 1.1409642696380615, |
| "learning_rate": 0.0009592000000000001, |
| "loss": 5.977291259765625, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.026, |
| "grad_norm": 0.9230883121490479, |
| "learning_rate": 0.0010391999999999999, |
| "loss": 5.983433837890625, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.028, |
| "grad_norm": 0.7991492748260498, |
| "learning_rate": 0.0011192, |
| "loss": 5.960853271484375, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 0.9952593445777893, |
| "learning_rate": 0.0011992, |
| "loss": 5.900661010742187, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.032, |
| "grad_norm": 2.6635053157806396, |
| "learning_rate": 0.0012791999999999999, |
| "loss": 5.839690551757813, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.034, |
| "grad_norm": 0.7056213021278381, |
| "learning_rate": 0.0013592, |
| "loss": 5.864632568359375, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.036, |
| "grad_norm": 0.7523426413536072, |
| "learning_rate": 0.0014392, |
| "loss": 5.8030767822265625, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.038, |
| "grad_norm": 0.572576105594635, |
| "learning_rate": 0.0015192, |
| "loss": 5.829718017578125, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.8802671432495117, |
| "learning_rate": 0.0015992, |
| "loss": 5.767376098632813, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.04, |
| "eval_accuracy": 0.163426614481409, |
| "eval_loss": 5.823215484619141, |
| "eval_runtime": 6.7868, |
| "eval_samples_per_second": 147.345, |
| "eval_steps_per_second": 18.418, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.042, |
| "grad_norm": 0.6110609173774719, |
| "learning_rate": 0.0016792, |
| "loss": 5.67332275390625, |
| "step": 2100 |
| }, |
| { |
| "epoch": 0.044, |
| "grad_norm": 0.579617977142334, |
| "learning_rate": 0.0017592, |
| "loss": 5.706051025390625, |
| "step": 2200 |
| }, |
| { |
| "epoch": 0.046, |
| "grad_norm": 0.5633976459503174, |
| "learning_rate": 0.0018392, |
| "loss": 5.6666259765625, |
| "step": 2300 |
| }, |
| { |
| "epoch": 0.048, |
| "grad_norm": 0.6478831768035889, |
| "learning_rate": 0.0019192, |
| "loss": 5.682818603515625, |
| "step": 2400 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.8043723702430725, |
| "learning_rate": 0.0019992, |
| "loss": 5.635286254882812, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.052, |
| "grad_norm": 0.554682195186615, |
| "learning_rate": 0.001999978563623903, |
| "loss": 5.5472607421875, |
| "step": 2600 |
| }, |
| { |
| "epoch": 0.054, |
| "grad_norm": 0.6824977397918701, |
| "learning_rate": 0.0019999133871331223, |
| "loss": 5.5920654296875, |
| "step": 2700 |
| }, |
| { |
| "epoch": 0.056, |
| "grad_norm": 0.40844905376434326, |
| "learning_rate": 0.0019998044711915177, |
| "loss": 5.528501586914063, |
| "step": 2800 |
| }, |
| { |
| "epoch": 0.058, |
| "grad_norm": 0.6135262250900269, |
| "learning_rate": 0.0019996518205634257, |
| "loss": 5.487052612304687, |
| "step": 2900 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 0.4022127687931061, |
| "learning_rate": 0.0019994554419262797, |
| "loss": 5.5177392578125, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.06, |
| "eval_accuracy": 0.18825440313111547, |
| "eval_loss": 5.509125232696533, |
| "eval_runtime": 6.779, |
| "eval_samples_per_second": 147.515, |
| "eval_steps_per_second": 18.439, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.062, |
| "grad_norm": 0.7171342968940735, |
| "learning_rate": 0.001999215343870317, |
| "loss": 5.417413330078125, |
| "step": 3100 |
| }, |
| { |
| "epoch": 0.064, |
| "grad_norm": 0.4542510509490967, |
| "learning_rate": 0.0019989315368982054, |
| "loss": 5.4095831298828125, |
| "step": 3200 |
| }, |
| { |
| "epoch": 0.066, |
| "grad_norm": 0.5080035924911499, |
| "learning_rate": 0.0019986040334245797, |
| "loss": 5.417955932617187, |
| "step": 3300 |
| }, |
| { |
| "epoch": 0.068, |
| "grad_norm": 0.3587779700756073, |
| "learning_rate": 0.001998232847775504, |
| "loss": 5.3721466064453125, |
| "step": 3400 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.45940911769866943, |
| "learning_rate": 0.0019978179961878404, |
| "loss": 5.320546875, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.072, |
| "grad_norm": 0.3420865535736084, |
| "learning_rate": 0.001997359496808541, |
| "loss": 5.28208984375, |
| "step": 3600 |
| }, |
| { |
| "epoch": 0.074, |
| "grad_norm": 0.42247381806373596, |
| "learning_rate": 0.001996857369693855, |
| "loss": 5.29147216796875, |
| "step": 3700 |
| }, |
| { |
| "epoch": 0.076, |
| "grad_norm": 0.3335079550743103, |
| "learning_rate": 0.0019963116368084486, |
| "loss": 5.352775268554687, |
| "step": 3800 |
| }, |
| { |
| "epoch": 0.078, |
| "grad_norm": 0.6875544786453247, |
| "learning_rate": 0.001995722322024446, |
| "loss": 5.303611450195312, |
| "step": 3900 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.3652666211128235, |
| "learning_rate": 0.001995089451120385, |
| "loss": 5.26600830078125, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.08, |
| "eval_accuracy": 0.19674755381604697, |
| "eval_loss": 5.325084686279297, |
| "eval_runtime": 6.607, |
| "eval_samples_per_second": 151.355, |
| "eval_steps_per_second": 18.919, |
| "step": 4000 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 50000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "save_steps": 2000, |
| "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": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
