| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08790242830458192, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004395121415229096, | |
| "eval_loss": 4.934887886047363, | |
| "eval_runtime": 52.8404, | |
| "eval_samples_per_second": 18.149, | |
| "eval_steps_per_second": 9.084, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004395121415229096, | |
| "grad_norm": 16.140071868896484, | |
| "learning_rate": 0.0002, | |
| "loss": 14.1671, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008790242830458192, | |
| "grad_norm": 12.486281394958496, | |
| "learning_rate": 0.0002, | |
| "loss": 4.3222, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013185364245687286, | |
| "grad_norm": 9.944640159606934, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4907, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.017580485660916384, | |
| "grad_norm": 5.2189178466796875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02197560707614548, | |
| "grad_norm": 11.882987976074219, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4725, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02197560707614548, | |
| "eval_loss": 0.0736045315861702, | |
| "eval_runtime": 52.7897, | |
| "eval_samples_per_second": 18.166, | |
| "eval_steps_per_second": 9.093, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.026370728491374573, | |
| "grad_norm": 8.649742126464844, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3513, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03076584990660367, | |
| "grad_norm": 11.820034980773926, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4011, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03516097132183277, | |
| "grad_norm": 4.739223957061768, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3105, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.039556092737061864, | |
| "grad_norm": 3.959333896636963, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3885, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.04395121415229096, | |
| "grad_norm": 7.995823860168457, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4986, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04395121415229096, | |
| "eval_loss": 0.08041178435087204, | |
| "eval_runtime": 52.7416, | |
| "eval_samples_per_second": 18.183, | |
| "eval_steps_per_second": 9.101, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.048346335567520056, | |
| "grad_norm": 2.872164011001587, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4823, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.052741456982749145, | |
| "grad_norm": 1.444300889968872, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3751, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.05713657839797824, | |
| "grad_norm": 6.023801803588867, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4278, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.06153169981320734, | |
| "grad_norm": 5.9031782150268555, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2955, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.06592682122843643, | |
| "grad_norm": 4.795778274536133, | |
| "learning_rate": 0.0002, | |
| "loss": 0.282, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.06592682122843643, | |
| "eval_loss": 0.07622317224740982, | |
| "eval_runtime": 52.8602, | |
| "eval_samples_per_second": 18.142, | |
| "eval_steps_per_second": 9.081, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.07032194264366554, | |
| "grad_norm": 2.814330816268921, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2583, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.07471706405889462, | |
| "grad_norm": 5.426441669464111, | |
| "learning_rate": 0.0002, | |
| "loss": 0.267, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.07911218547412373, | |
| "grad_norm": 10.835411071777344, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2031, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.08350730688935282, | |
| "grad_norm": 6.394276142120361, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3164, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.08790242830458192, | |
| "grad_norm": 3.249331474304199, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2643, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.08790242830458192, | |
| "eval_loss": 0.07121116667985916, | |
| "eval_runtime": 52.7891, | |
| "eval_samples_per_second": 18.167, | |
| "eval_steps_per_second": 9.093, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.216069447634125e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |