| { | |
| "best_global_step": 2, | |
| "best_metric": 3.8960189819335938, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1711229946524064, | |
| "eval_steps": 2, | |
| "global_step": 32, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0106951871657754, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0008999841241675994, | |
| "loss": 3.7831, | |
| "mean_token_accuracy": 0.5624366104602814, | |
| "num_tokens": 4369.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0106951871657754, | |
| "eval_loss": 3.8960189819335938, | |
| "eval_mean_token_accuracy": 0.55588099360466, | |
| "eval_num_tokens": 4369.0, | |
| "eval_runtime": 12.0177, | |
| "eval_samples_per_second": 1.664, | |
| "eval_steps_per_second": 0.166, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0213903743315508, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0008998571242294379, | |
| "loss": 3.6904, | |
| "mean_token_accuracy": 0.5642752200365067, | |
| "num_tokens": 8944.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0213903743315508, | |
| "eval_loss": 3.8960189819335938, | |
| "eval_mean_token_accuracy": 0.55588099360466, | |
| "eval_num_tokens": 8944.0, | |
| "eval_runtime": 12.1652, | |
| "eval_samples_per_second": 1.644, | |
| "eval_steps_per_second": 0.164, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03208556149732621, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.000899603160196567, | |
| "loss": 3.8616, | |
| "mean_token_accuracy": 0.5486461520195007, | |
| "num_tokens": 13866.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03208556149732621, | |
| "eval_loss": 3.8960189819335938, | |
| "eval_mean_token_accuracy": 0.55588099360466, | |
| "eval_num_tokens": 13866.0, | |
| "eval_runtime": 12.331, | |
| "eval_samples_per_second": 1.622, | |
| "eval_steps_per_second": 0.162, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0427807486631016, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0008992223037457738, | |
| "loss": 3.8405, | |
| "mean_token_accuracy": 0.5545942336320877, | |
| "num_tokens": 18338.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0427807486631016, | |
| "eval_loss": 3.8960189819335938, | |
| "eval_mean_token_accuracy": 0.55588099360466, | |
| "eval_num_tokens": 18338.0, | |
| "eval_runtime": 12.2655, | |
| "eval_samples_per_second": 1.631, | |
| "eval_steps_per_second": 0.163, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.053475935828877004, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0008987146623669524, | |
| "loss": 3.7968, | |
| "mean_token_accuracy": 0.5595056265592575, | |
| "num_tokens": 23083.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.053475935828877004, | |
| "eval_loss": 3.8960189819335938, | |
| "eval_mean_token_accuracy": 0.55588099360466, | |
| "eval_num_tokens": 23083.0, | |
| "eval_runtime": 12.0373, | |
| "eval_samples_per_second": 1.661, | |
| "eval_steps_per_second": 0.166, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06417112299465241, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0008980803793327655, | |
| "loss": 3.7388, | |
| "mean_token_accuracy": 0.557638630270958, | |
| "num_tokens": 28012.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06417112299465241, | |
| "eval_loss": 3.8960189819335938, | |
| "eval_mean_token_accuracy": 0.55588099360466, | |
| "eval_num_tokens": 28012.0, | |
| "eval_runtime": 12.2491, | |
| "eval_samples_per_second": 1.633, | |
| "eval_steps_per_second": 0.163, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0748663101604278, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0008973196336582091, | |
| "loss": 3.7867, | |
| "mean_token_accuracy": 0.5598014146089554, | |
| "num_tokens": 32826.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0748663101604278, | |
| "eval_loss": 3.8960189819335938, | |
| "eval_mean_token_accuracy": 0.55588099360466, | |
| "eval_num_tokens": 32826.0, | |
| "eval_runtime": 12.3425, | |
| "eval_samples_per_second": 1.62, | |
| "eval_steps_per_second": 0.162, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0855614973262032, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0008964326400500881, | |
| "loss": 3.905, | |
| "mean_token_accuracy": 0.5460383147001266, | |
| "num_tokens": 37494.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0855614973262032, | |
| "eval_loss": 3.8960189819335938, | |
| "eval_mean_token_accuracy": 0.55588099360466, | |
| "eval_num_tokens": 37494.0, | |
| "eval_runtime": 12.2851, | |
| "eval_samples_per_second": 1.628, | |
| "eval_steps_per_second": 0.163, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0962566844919786, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0008954196488464197, | |
| "loss": 3.7338, | |
| "mean_token_accuracy": 0.5698530972003937, | |
| "num_tokens": 42166.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0962566844919786, | |
| "eval_loss": 3.8960189819335938, | |
| "eval_mean_token_accuracy": 0.55588099360466, | |
| "eval_num_tokens": 42166.0, | |
| "eval_runtime": 12.1294, | |
| "eval_samples_per_second": 1.649, | |
| "eval_steps_per_second": 0.165, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10695187165775401, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0008942809459457797, | |
| "loss": 3.7823, | |
| "mean_token_accuracy": 0.5629921406507492, | |
| "num_tokens": 46857.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10695187165775401, | |
| "eval_loss": 3.8960189819335938, | |
| "eval_mean_token_accuracy": 0.55588099360466, | |
| "eval_num_tokens": 46857.0, | |
| "eval_runtime": 12.2334, | |
| "eval_samples_per_second": 1.635, | |
| "eval_steps_per_second": 0.163, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0008930168527266127, | |
| "loss": 3.7864, | |
| "mean_token_accuracy": 0.5499628484249115, | |
| "num_tokens": 51942.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "eval_loss": 3.8960189819335938, | |
| "eval_mean_token_accuracy": 0.55588099360466, | |
| "eval_num_tokens": 51942.0, | |
| "eval_runtime": 12.2575, | |
| "eval_samples_per_second": 1.632, | |
| "eval_steps_per_second": 0.163, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.12834224598930483, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0008916277259565292, | |
| "loss": 3.6372, | |
| "mean_token_accuracy": 0.5657302439212799, | |
| "num_tokens": 56880.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12834224598930483, | |
| "eval_loss": 3.8960189819335938, | |
| "eval_mean_token_accuracy": 0.55588099360466, | |
| "eval_num_tokens": 56880.0, | |
| "eval_runtime": 12.28, | |
| "eval_samples_per_second": 1.629, | |
| "eval_steps_per_second": 0.163, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.13903743315508021, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0008901139576916137, | |
| "loss": 3.788, | |
| "mean_token_accuracy": 0.5580856949090958, | |
| "num_tokens": 61710.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.13903743315508021, | |
| "eval_loss": 3.8960189819335938, | |
| "eval_mean_token_accuracy": 0.55588099360466, | |
| "eval_num_tokens": 61710.0, | |
| "eval_runtime": 12.054, | |
| "eval_samples_per_second": 1.659, | |
| "eval_steps_per_second": 0.166, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1497326203208556, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0008884759751657747, | |
| "loss": 3.7585, | |
| "mean_token_accuracy": 0.5520788580179214, | |
| "num_tokens": 66437.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1497326203208556, | |
| "eval_loss": 3.8960189819335938, | |
| "eval_mean_token_accuracy": 0.55588099360466, | |
| "eval_num_tokens": 66437.0, | |
| "eval_runtime": 12.2403, | |
| "eval_samples_per_second": 1.634, | |
| "eval_steps_per_second": 0.163, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.16042780748663102, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0008867142406701649, | |
| "loss": 3.7385, | |
| "mean_token_accuracy": 0.5634956657886505, | |
| "num_tokens": 71387.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16042780748663102, | |
| "eval_loss": 3.8960189819335938, | |
| "eval_mean_token_accuracy": 0.55588099360466, | |
| "eval_num_tokens": 71387.0, | |
| "eval_runtime": 12.2751, | |
| "eval_samples_per_second": 1.629, | |
| "eval_steps_per_second": 0.163, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1711229946524064, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0008848292514227081, | |
| "loss": 3.8708, | |
| "mean_token_accuracy": 0.5420819222927094, | |
| "num_tokens": 76271.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1711229946524064, | |
| "eval_loss": 3.8960189819335938, | |
| "eval_mean_token_accuracy": 0.55588099360466, | |
| "eval_num_tokens": 76271.0, | |
| "eval_runtime": 12.3155, | |
| "eval_samples_per_second": 1.624, | |
| "eval_steps_per_second": 0.162, | |
| "step": 32 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 374, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 8, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2335294658641920.0, | |
| "train_batch_size": 10, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |