| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 0.707854887843132, |
| "epoch": 0.1, |
| "grad_norm": 1.4789700508117676, |
| "learning_rate": 4.5e-05, |
| "loss": 2.083025360107422, |
| "mean_token_accuracy": 0.6964636638760566, |
| "num_tokens": 23374.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 0.9212535813450813, |
| "epoch": 0.2, |
| "grad_norm": 0.6974025368690491, |
| "learning_rate": 4.972369676503672e-05, |
| "loss": 1.153501033782959, |
| "mean_token_accuracy": 0.7658602714538574, |
| "num_tokens": 47056.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 0.6718886934220791, |
| "epoch": 0.3, |
| "grad_norm": 0.5641660094261169, |
| "learning_rate": 4.877641290737884e-05, |
| "loss": 0.6673425674438477, |
| "mean_token_accuracy": 0.8570197850465775, |
| "num_tokens": 70332.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 0.5051603138446807, |
| "epoch": 0.4, |
| "grad_norm": 0.4287518858909607, |
| "learning_rate": 4.71805704860903e-05, |
| "loss": 0.49802455902099607, |
| "mean_token_accuracy": 0.887857261300087, |
| "num_tokens": 93950.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 0.48869766741991044, |
| "epoch": 0.5, |
| "grad_norm": 0.38886094093322754, |
| "learning_rate": 4.497969992237312e-05, |
| "loss": 0.48790874481201174, |
| "mean_token_accuracy": 0.8859360262751579, |
| "num_tokens": 117707.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 0.4417721003293991, |
| "epoch": 0.6, |
| "grad_norm": 0.3435150384902954, |
| "learning_rate": 4.223383522796415e-05, |
| "loss": 0.4268824100494385, |
| "mean_token_accuracy": 0.8983871400356293, |
| "num_tokens": 141268.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 0.4217384122312069, |
| "epoch": 0.7, |
| "grad_norm": 0.42083045840263367, |
| "learning_rate": 3.901787643379182e-05, |
| "loss": 0.41396050453186034, |
| "mean_token_accuracy": 0.8986505523324013, |
| "num_tokens": 164883.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 0.4161409936845303, |
| "epoch": 0.8, |
| "grad_norm": 0.3508182168006897, |
| "learning_rate": 3.5419546512382266e-05, |
| "loss": 0.41231813430786135, |
| "mean_token_accuracy": 0.8985344961285591, |
| "num_tokens": 187904.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 0.4316503643989563, |
| "epoch": 0.9, |
| "grad_norm": 0.3890114724636078, |
| "learning_rate": 3.1536998523845494e-05, |
| "loss": 0.4260415554046631, |
| "mean_token_accuracy": 0.8960150480270386, |
| "num_tokens": 211682.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 0.424409294128418, |
| "epoch": 1.0, |
| "grad_norm": 0.34862327575683594, |
| "learning_rate": 2.7476138256261575e-05, |
| "loss": 0.40468835830688477, |
| "mean_token_accuracy": 0.9002996236085892, |
| "num_tokens": 235287.0, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 200, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.074610195117056e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
