| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00023179940079854893, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.3179940079854893e-05, | |
| "grad_norm": 1.0077486038208008, | |
| "learning_rate": 2e-05, | |
| "loss": 0.451, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.3179940079854893e-05, | |
| "eval_loss": 0.533516526222229, | |
| "eval_runtime": 976.7669, | |
| "eval_samples_per_second": 18.597, | |
| "eval_steps_per_second": 9.299, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.6359880159709785e-05, | |
| "grad_norm": 1.2165539264678955, | |
| "learning_rate": 4e-05, | |
| "loss": 0.5161, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 6.953982023956468e-05, | |
| "grad_norm": 2.0040361881256104, | |
| "learning_rate": 6e-05, | |
| "loss": 0.8641, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 6.953982023956468e-05, | |
| "eval_loss": 0.5213726758956909, | |
| "eval_runtime": 974.9167, | |
| "eval_samples_per_second": 18.632, | |
| "eval_steps_per_second": 9.317, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.271976031941957e-05, | |
| "grad_norm": 0.7971104383468628, | |
| "learning_rate": 8e-05, | |
| "loss": 0.3608, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00011589970039927446, | |
| "grad_norm": 0.8727761507034302, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4841, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00013907964047912936, | |
| "grad_norm": 0.7129486203193665, | |
| "learning_rate": 0.00012, | |
| "loss": 0.4473, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00013907964047912936, | |
| "eval_loss": 0.36517366766929626, | |
| "eval_runtime": 975.0807, | |
| "eval_samples_per_second": 18.629, | |
| "eval_steps_per_second": 9.315, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00016225958055898426, | |
| "grad_norm": 0.7307805418968201, | |
| "learning_rate": 0.00014, | |
| "loss": 0.2766, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00018543952063883914, | |
| "grad_norm": 0.3102991282939911, | |
| "learning_rate": 0.00016, | |
| "loss": 0.1606, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00020861946071869405, | |
| "grad_norm": 0.4250812530517578, | |
| "learning_rate": 0.00018, | |
| "loss": 0.1873, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00020861946071869405, | |
| "eval_loss": 0.22364288568496704, | |
| "eval_runtime": 975.2905, | |
| "eval_samples_per_second": 18.625, | |
| "eval_steps_per_second": 9.313, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00023179940079854893, | |
| "grad_norm": 0.7938255667686462, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1618, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3560411177680896.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |