| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0016256197675363732, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001625619767536373, | |
| "grad_norm": 2.0388681888580322, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9422, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001625619767536373, | |
| "eval_loss": 2.083211660385132, | |
| "eval_runtime": 70.9921, | |
| "eval_samples_per_second": 36.497, | |
| "eval_steps_per_second": 18.256, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003251239535072746, | |
| "grad_norm": 0.6971363425254822, | |
| "learning_rate": 4e-05, | |
| "loss": 6.0204, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000487685930260912, | |
| "grad_norm": 0.864838719367981, | |
| "learning_rate": 6e-05, | |
| "loss": 7.9913, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000487685930260912, | |
| "eval_loss": 2.0830745697021484, | |
| "eval_runtime": 69.7719, | |
| "eval_samples_per_second": 37.135, | |
| "eval_steps_per_second": 18.575, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006502479070145493, | |
| "grad_norm": 1.5509084463119507, | |
| "learning_rate": 8e-05, | |
| "loss": 8.7708, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008128098837681866, | |
| "grad_norm": 1.0628870725631714, | |
| "learning_rate": 0.0001, | |
| "loss": 7.2972, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000975371860521824, | |
| "grad_norm": 1.2305057048797607, | |
| "learning_rate": 0.00012, | |
| "loss": 7.6671, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000975371860521824, | |
| "eval_loss": 2.066908836364746, | |
| "eval_runtime": 69.6909, | |
| "eval_samples_per_second": 37.178, | |
| "eval_steps_per_second": 18.596, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011379338372754612, | |
| "grad_norm": 2.619060516357422, | |
| "learning_rate": 0.00014, | |
| "loss": 8.2088, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013004958140290985, | |
| "grad_norm": 2.1115610599517822, | |
| "learning_rate": 0.00016, | |
| "loss": 6.1903, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001463057790782736, | |
| "grad_norm": 2.1327946186065674, | |
| "learning_rate": 0.00018, | |
| "loss": 6.917, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001463057790782736, | |
| "eval_loss": 1.9368618726730347, | |
| "eval_runtime": 69.7235, | |
| "eval_samples_per_second": 37.161, | |
| "eval_steps_per_second": 18.588, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016256197675363732, | |
| "grad_norm": 3.2231528759002686, | |
| "learning_rate": 0.0002, | |
| "loss": 6.5442, | |
| "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": 1632478030725120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |