| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003737269924320284, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003737269924320284, | |
| "grad_norm": 1.9629660844802856, | |
| "learning_rate": 2e-05, | |
| "loss": 44.5056, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003737269924320284, | |
| "eval_loss": 11.121556282043457, | |
| "eval_runtime": 4.62, | |
| "eval_samples_per_second": 243.94, | |
| "eval_steps_per_second": 122.078, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007474539848640568, | |
| "grad_norm": 2.0691192150115967, | |
| "learning_rate": 4e-05, | |
| "loss": 44.5521, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011211809772960853, | |
| "grad_norm": 2.097630500793457, | |
| "learning_rate": 6e-05, | |
| "loss": 44.5856, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011211809772960853, | |
| "eval_loss": 11.120737075805664, | |
| "eval_runtime": 3.189, | |
| "eval_samples_per_second": 353.404, | |
| "eval_steps_per_second": 176.859, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014949079697281135, | |
| "grad_norm": 2.0556488037109375, | |
| "learning_rate": 8e-05, | |
| "loss": 44.433, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001868634962160142, | |
| "grad_norm": 1.9328457117080688, | |
| "learning_rate": 0.0001, | |
| "loss": 44.4442, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0022423619545921705, | |
| "grad_norm": 2.117732524871826, | |
| "learning_rate": 0.00012, | |
| "loss": 44.4806, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0022423619545921705, | |
| "eval_loss": 11.112125396728516, | |
| "eval_runtime": 3.2626, | |
| "eval_samples_per_second": 345.427, | |
| "eval_steps_per_second": 172.867, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002616088947024199, | |
| "grad_norm": 2.0057151317596436, | |
| "learning_rate": 0.00014, | |
| "loss": 44.418, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002989815939456227, | |
| "grad_norm": 2.0858817100524902, | |
| "learning_rate": 0.00016, | |
| "loss": 44.5023, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0033635429318882555, | |
| "grad_norm": 2.0623550415039062, | |
| "learning_rate": 0.00018, | |
| "loss": 44.389, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0033635429318882555, | |
| "eval_loss": 11.097463607788086, | |
| "eval_runtime": 3.2775, | |
| "eval_samples_per_second": 343.858, | |
| "eval_steps_per_second": 172.081, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003737269924320284, | |
| "grad_norm": 1.9272708892822266, | |
| "learning_rate": 0.0002, | |
| "loss": 44.3268, | |
| "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": 115737624576.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |