| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.9984, |
| "eval_steps": 500, |
| "global_step": 1250, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08, |
| "grad_norm": 12.125, |
| "learning_rate": 1.555555555555556e-05, |
| "loss": 1.2021, |
| "mean_token_accuracy": 0.7523527503013611, |
| "num_input_tokens_seen": 462464, |
| "num_tokens": 462464.0, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 7.5625, |
| "learning_rate": 1.9954642956864198e-05, |
| "loss": 0.6381, |
| "mean_token_accuracy": 0.828709350824356, |
| "num_input_tokens_seen": 895104, |
| "num_tokens": 895104.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 9.0625, |
| "learning_rate": 1.9742077388709354e-05, |
| "loss": 0.6022, |
| "mean_token_accuracy": 0.8348629665374756, |
| "num_input_tokens_seen": 1447552, |
| "num_tokens": 1447552.0, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 4.03125, |
| "learning_rate": 1.9359156377376714e-05, |
| "loss": 0.508, |
| "mean_token_accuracy": 0.8551409709453582, |
| "num_input_tokens_seen": 2040064, |
| "num_tokens": 2040064.0, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 14.9375, |
| "learning_rate": 1.8812575894986476e-05, |
| "loss": 0.5894, |
| "mean_token_accuracy": 0.8338349997997284, |
| "num_input_tokens_seen": 2481312, |
| "num_tokens": 2481312.0, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 6.875, |
| "learning_rate": 1.811189375519529e-05, |
| "loss": 0.555, |
| "mean_token_accuracy": 0.8397143912315369, |
| "num_input_tokens_seen": 2908288, |
| "num_tokens": 2908288.0, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 21.75, |
| "learning_rate": 1.7269362479892304e-05, |
| "loss": 0.6172, |
| "mean_token_accuracy": 0.8344850993156433, |
| "num_input_tokens_seen": 3346848, |
| "num_tokens": 3346848.0, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 7.34375, |
| "learning_rate": 1.629971504471182e-05, |
| "loss": 0.6697, |
| "mean_token_accuracy": 0.8219912588596344, |
| "num_input_tokens_seen": 3815936, |
| "num_tokens": 3815936.0, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 11.5, |
| "learning_rate": 1.5219907249937036e-05, |
| "loss": 0.5813, |
| "mean_token_accuracy": 0.84231409907341, |
| "num_input_tokens_seen": 4219808, |
| "num_tokens": 4219808.0, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 10.8125, |
| "learning_rate": 1.4048821221842053e-05, |
| "loss": 0.5867, |
| "mean_token_accuracy": 0.8388340866565704, |
| "num_input_tokens_seen": 4729216, |
| "num_tokens": 4729216.0, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 21.5, |
| "learning_rate": 1.2806935229214456e-05, |
| "loss": 0.6442, |
| "mean_token_accuracy": 0.8239680206775666, |
| "num_input_tokens_seen": 5136224, |
| "num_tokens": 5136224.0, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 15.5625, |
| "learning_rate": 1.1515965588832394e-05, |
| "loss": 0.6695, |
| "mean_token_accuracy": 0.8146113741397858, |
| "num_input_tokens_seen": 5558144, |
| "num_tokens": 5558144.0, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.0384, |
| "grad_norm": 14.8125, |
| "learning_rate": 1.0198486921738313e-05, |
| "loss": 0.5815, |
| "mean_token_accuracy": 0.838525402545929, |
| "num_input_tokens_seen": 6015168, |
| "num_tokens": 6015168.0, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.1184, |
| "grad_norm": 14.625, |
| "learning_rate": 8.87753740072175e-06, |
| "loss": 0.4959, |
| "mean_token_accuracy": 0.8590600204467773, |
| "num_input_tokens_seen": 6525472, |
| "num_tokens": 6525472.0, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.1984, |
| "grad_norm": 6.4375, |
| "learning_rate": 7.5762158918755844e-06, |
| "loss": 0.209, |
| "mean_token_accuracy": 0.9405078291893005, |
| "num_input_tokens_seen": 6961280, |
| "num_tokens": 6961280.0, |
| "step": 750 |
| }, |
| { |
| "epoch": 1.2784, |
| "grad_norm": 15.4375, |
| "learning_rate": 6.317278034835077e-06, |
| "loss": 0.2078, |
| "mean_token_accuracy": 0.9385969924926758, |
| "num_input_tokens_seen": 7553248, |
| "num_tokens": 7553248.0, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.3584, |
| "grad_norm": 6.25, |
| "learning_rate": 5.122738324867738e-06, |
| "loss": 0.1648, |
| "mean_token_accuracy": 0.9483961355686188, |
| "num_input_tokens_seen": 8028480, |
| "num_tokens": 8028480.0, |
| "step": 850 |
| }, |
| { |
| "epoch": 1.4384000000000001, |
| "grad_norm": 20.375, |
| "learning_rate": 4.01348515503035e-06, |
| "loss": 0.1534, |
| "mean_token_accuracy": 0.954008765220642, |
| "num_input_tokens_seen": 8481600, |
| "num_tokens": 8481600.0, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.5184, |
| "grad_norm": 11.875, |
| "learning_rate": 3.008915549982461e-06, |
| "loss": 0.1688, |
| "mean_token_accuracy": 0.9496164512634278, |
| "num_input_tokens_seen": 8863616, |
| "num_tokens": 8863616.0, |
| "step": 950 |
| }, |
| { |
| "epoch": 1.5984, |
| "grad_norm": 9.75, |
| "learning_rate": 2.126595978706265e-06, |
| "loss": 0.2746, |
| "mean_token_accuracy": 0.9160845911502838, |
| "num_input_tokens_seen": 9401952, |
| "num_tokens": 9401952.0, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.6784, |
| "grad_norm": 13.0625, |
| "learning_rate": 1.3819551773523687e-06, |
| "loss": 0.2955, |
| "mean_token_accuracy": 0.9055855929851532, |
| "num_input_tokens_seen": 9802240, |
| "num_tokens": 9802240.0, |
| "step": 1050 |
| }, |
| { |
| "epoch": 1.7584, |
| "grad_norm": 10.375, |
| "learning_rate": 7.880143536839091e-07, |
| "loss": 0.4093, |
| "mean_token_accuracy": 0.8785555076599121, |
| "num_input_tokens_seen": 10295392, |
| "num_tokens": 10295392.0, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.8384, |
| "grad_norm": 6.96875, |
| "learning_rate": 3.5515949091578514e-07, |
| "loss": 0.403, |
| "mean_token_accuracy": 0.8825811994075775, |
| "num_input_tokens_seen": 10749696, |
| "num_tokens": 10749696.0, |
| "step": 1150 |
| }, |
| { |
| "epoch": 1.9184, |
| "grad_norm": 9.5, |
| "learning_rate": 9.095973257215118e-08, |
| "loss": 0.468, |
| "mean_token_accuracy": 0.8632709145545959, |
| "num_input_tokens_seen": 11138752, |
| "num_tokens": 11138752.0, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.9984, |
| "grad_norm": 5.4375, |
| "learning_rate": 3.502418662093554e-11, |
| "loss": 0.4481, |
| "mean_token_accuracy": 0.8703732848167419, |
| "num_input_tokens_seen": 11596480, |
| "num_tokens": 11596480.0, |
| "step": 1250 |
| }, |
| { |
| "epoch": 1.9984, |
| "num_input_tokens_seen": 11596480, |
| "step": 1250, |
| "total_flos": 6.737991978870374e+16, |
| "train_loss": 0.48572284927368164, |
| "train_runtime": 2793.6323, |
| "train_samples_per_second": 7.159, |
| "train_steps_per_second": 0.447, |
| "train_tokens_per_second": 323.951 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1250, |
| "num_input_tokens_seen": 11596480, |
| "num_train_epochs": 2, |
| "save_steps": 0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": false, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6.737991978870374e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
