| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 1225, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 2.65348322480917, |
| "epoch": 0.08163265306122448, |
| "grad_norm": 0.3858589231967926, |
| "learning_rate": 9.839710975789937e-05, |
| "loss": 1.8520664978027344, |
| "mean_token_accuracy": 0.4766763444710523, |
| "num_tokens": 73931.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 2.221065641641617, |
| "epoch": 0.16326530612244897, |
| "grad_norm": 0.4490025043487549, |
| "learning_rate": 9.362871573431047e-05, |
| "loss": 1.7005967712402343, |
| "mean_token_accuracy": 0.5576045931689442, |
| "num_tokens": 156572.0, |
| "step": 200 |
| }, |
| { |
| "entropy": 2.128404154591262, |
| "epoch": 0.24489795918367346, |
| "grad_norm": 0.568897008895874, |
| "learning_rate": 8.600655546367782e-05, |
| "loss": 1.6693995666503907, |
| "mean_token_accuracy": 0.5640898733213544, |
| "num_tokens": 244559.0, |
| "step": 300 |
| }, |
| { |
| "entropy": 2.096652089692652, |
| "epoch": 0.32653061224489793, |
| "grad_norm": 0.6031016111373901, |
| "learning_rate": 7.602919653718044e-05, |
| "loss": 1.5418077087402344, |
| "mean_token_accuracy": 0.5770933660492301, |
| "num_tokens": 334289.0, |
| "step": 400 |
| }, |
| { |
| "entropy": 2.0537689401954413, |
| "epoch": 0.40816326530612246, |
| "grad_norm": 0.5750653743743896, |
| "learning_rate": 6.434926073521803e-05, |
| "loss": 1.5946527099609376, |
| "mean_token_accuracy": 0.5710043688677251, |
| "num_tokens": 415705.0, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.40816326530612246, |
| "eval_entropy": 1.5940086383085985, |
| "eval_loss": 1.6339383125305176, |
| "eval_mean_token_accuracy": 0.6421380157654102, |
| "eval_num_tokens": 415705.0, |
| "eval_runtime": 3.1459, |
| "eval_samples_per_second": 31.787, |
| "eval_steps_per_second": 4.132, |
| "step": 500 |
| }, |
| { |
| "entropy": 2.0754134288430213, |
| "epoch": 0.4897959183673469, |
| "grad_norm": 1.2727973461151123, |
| "learning_rate": 5.173073585798768e-05, |
| "loss": 1.6228317260742187, |
| "mean_token_accuracy": 0.564216209501028, |
| "num_tokens": 494295.0, |
| "step": 600 |
| }, |
| { |
| "entropy": 2.012790724672377, |
| "epoch": 0.5714285714285714, |
| "grad_norm": 0.2896394729614258, |
| "learning_rate": 3.899900307419982e-05, |
| "loss": 1.5738545227050782, |
| "mean_token_accuracy": 0.5796110359393061, |
| "num_tokens": 577751.0, |
| "step": 700 |
| }, |
| { |
| "entropy": 1.9897139368206262, |
| "epoch": 0.6530612244897959, |
| "grad_norm": 0.5676203370094299, |
| "learning_rate": 2.6986848512742967e-05, |
| "loss": 1.5871757507324218, |
| "mean_token_accuracy": 0.5866536642797291, |
| "num_tokens": 658206.0, |
| "step": 800 |
| }, |
| { |
| "entropy": 2.0891294856369496, |
| "epoch": 0.7346938775510204, |
| "grad_norm": 0.4007723033428192, |
| "learning_rate": 1.647999049387474e-05, |
| "loss": 1.6784550476074218, |
| "mean_token_accuracy": 0.5773500371165574, |
| "num_tokens": 738593.0, |
| "step": 900 |
| }, |
| { |
| "entropy": 2.0181680861487985, |
| "epoch": 0.8163265306122449, |
| "grad_norm": 0.4596865475177765, |
| "learning_rate": 8.165685478668238e-06, |
| "loss": 1.6400236511230468, |
| "mean_token_accuracy": 0.5852108645252884, |
| "num_tokens": 817014.0, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.8163265306122449, |
| "eval_entropy": 1.5638046906544611, |
| "eval_loss": 1.6097618341445923, |
| "eval_mean_token_accuracy": 0.6478444796342117, |
| "eval_num_tokens": 817014.0, |
| "eval_runtime": 3.1122, |
| "eval_samples_per_second": 32.132, |
| "eval_steps_per_second": 4.177, |
| "step": 1000 |
| }, |
| { |
| "entropy": 2.016655530370772, |
| "epoch": 0.8979591836734694, |
| "grad_norm": 0.6038398742675781, |
| "learning_rate": 2.587774435638679e-06, |
| "loss": 1.6814262390136718, |
| "mean_token_accuracy": 0.579078944325447, |
| "num_tokens": 896645.0, |
| "step": 1100 |
| }, |
| { |
| "entropy": 2.061556413136423, |
| "epoch": 0.9795918367346939, |
| "grad_norm": 0.6863688826560974, |
| "learning_rate": 1.1111005402286711e-07, |
| "loss": 1.64010009765625, |
| "mean_token_accuracy": 0.5714908703416586, |
| "num_tokens": 973715.0, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_entropy": 1.5626688462037306, |
| "eval_loss": 1.609505295753479, |
| "eval_mean_token_accuracy": 0.6479680950825031, |
| "eval_num_tokens": 992320.0, |
| "eval_runtime": 3.1267, |
| "eval_samples_per_second": 31.982, |
| "eval_steps_per_second": 4.158, |
| "step": 1225 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 1225, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3710062484688384.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
