| { |
| "best_metric": 0.8372765183448792, |
| "best_model_checkpoint": "/content/Nasa_Mars_Model_Outputs/checkpoint-10", |
| "epoch": 0.05001705126747755, |
| "eval_steps": 10, |
| "global_step": 110, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.004547004660679777, |
| "grad_norm": 8.836596488952637, |
| "learning_rate": 2e-05, |
| "loss": 0.6073, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.004547004660679777, |
| "eval_loss": 0.8372765183448792, |
| "eval_runtime": 20.6797, |
| "eval_samples_per_second": 2.418, |
| "eval_steps_per_second": 2.418, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.009094009321359554, |
| "grad_norm": 9.525543212890625, |
| "learning_rate": 4e-05, |
| "loss": 0.5308, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.009094009321359554, |
| "eval_loss": 0.8388195037841797, |
| "eval_runtime": 20.8936, |
| "eval_samples_per_second": 2.393, |
| "eval_steps_per_second": 2.393, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.013641013982039332, |
| "grad_norm": 8.243130683898926, |
| "learning_rate": 6e-05, |
| "loss": 0.4263, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.013641013982039332, |
| "eval_loss": 0.9063456654548645, |
| "eval_runtime": 20.8341, |
| "eval_samples_per_second": 2.4, |
| "eval_steps_per_second": 2.4, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.018188018642719107, |
| "grad_norm": 5.157824993133545, |
| "learning_rate": 8e-05, |
| "loss": 0.3455, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.018188018642719107, |
| "eval_loss": 0.9459993839263916, |
| "eval_runtime": 20.8498, |
| "eval_samples_per_second": 2.398, |
| "eval_steps_per_second": 2.398, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.022735023303398886, |
| "grad_norm": 9.51492977142334, |
| "learning_rate": 0.0001, |
| "loss": 0.317, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.022735023303398886, |
| "eval_loss": 0.9320575594902039, |
| "eval_runtime": 20.8158, |
| "eval_samples_per_second": 2.402, |
| "eval_steps_per_second": 2.402, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.027282027964078664, |
| "grad_norm": 8.233291625976562, |
| "learning_rate": 9.977000919963202e-05, |
| "loss": 0.3006, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.027282027964078664, |
| "eval_loss": 0.9950161576271057, |
| "eval_runtime": 20.7989, |
| "eval_samples_per_second": 2.404, |
| "eval_steps_per_second": 2.404, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.03182903262475844, |
| "grad_norm": 11.2651948928833, |
| "learning_rate": 9.954001839926403e-05, |
| "loss": 0.3331, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.03182903262475844, |
| "eval_loss": 0.9437124729156494, |
| "eval_runtime": 20.8698, |
| "eval_samples_per_second": 2.396, |
| "eval_steps_per_second": 2.396, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.036376037285438215, |
| "grad_norm": 7.479197025299072, |
| "learning_rate": 9.931002759889605e-05, |
| "loss": 0.2957, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.036376037285438215, |
| "eval_loss": 0.9456791877746582, |
| "eval_runtime": 20.8644, |
| "eval_samples_per_second": 2.396, |
| "eval_steps_per_second": 2.396, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.040923041946118, |
| "grad_norm": 8.659111976623535, |
| "learning_rate": 9.908003679852806e-05, |
| "loss": 0.3325, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.040923041946118, |
| "eval_loss": 0.9326030015945435, |
| "eval_runtime": 20.8374, |
| "eval_samples_per_second": 2.4, |
| "eval_steps_per_second": 2.4, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.04547004660679777, |
| "grad_norm": 4.722876071929932, |
| "learning_rate": 9.885004599816008e-05, |
| "loss": 0.2857, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.04547004660679777, |
| "eval_loss": 0.9288083910942078, |
| "eval_runtime": 20.844, |
| "eval_samples_per_second": 2.399, |
| "eval_steps_per_second": 2.399, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.05001705126747755, |
| "grad_norm": 6.449366569519043, |
| "learning_rate": 9.86200551977921e-05, |
| "loss": 0.3643, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.05001705126747755, |
| "eval_loss": 0.9256532192230225, |
| "eval_runtime": 20.8316, |
| "eval_samples_per_second": 2.4, |
| "eval_steps_per_second": 2.4, |
| "step": 110 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 4398, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 10, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9148674554486016.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
