| { | |
| "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": 2.0505969524383545, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9422, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001625619767536373, | |
| "eval_loss": 2.083211660385132, | |
| "eval_runtime": 70.7099, | |
| "eval_samples_per_second": 36.643, | |
| "eval_steps_per_second": 18.328, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003251239535072746, | |
| "grad_norm": 0.7015392780303955, | |
| "learning_rate": 4e-05, | |
| "loss": 6.0204, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000487685930260912, | |
| "grad_norm": 0.8823554515838623, | |
| "learning_rate": 6e-05, | |
| "loss": 7.986, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000487685930260912, | |
| "eval_loss": 2.0831565856933594, | |
| "eval_runtime": 69.2212, | |
| "eval_samples_per_second": 37.431, | |
| "eval_steps_per_second": 18.723, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006502479070145493, | |
| "grad_norm": 1.5695548057556152, | |
| "learning_rate": 8e-05, | |
| "loss": 8.7696, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008128098837681866, | |
| "grad_norm": 1.080654501914978, | |
| "learning_rate": 0.0001, | |
| "loss": 7.2986, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000975371860521824, | |
| "grad_norm": 1.2302272319793701, | |
| "learning_rate": 0.00012, | |
| "loss": 7.6666, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000975371860521824, | |
| "eval_loss": 2.0656354427337646, | |
| "eval_runtime": 69.4387, | |
| "eval_samples_per_second": 37.313, | |
| "eval_steps_per_second": 18.664, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011379338372754612, | |
| "grad_norm": 2.6334381103515625, | |
| "learning_rate": 0.00014, | |
| "loss": 8.1998, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013004958140290985, | |
| "grad_norm": 2.1267759799957275, | |
| "learning_rate": 0.00016, | |
| "loss": 6.1844, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001463057790782736, | |
| "grad_norm": 2.1368281841278076, | |
| "learning_rate": 0.00018, | |
| "loss": 6.9146, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001463057790782736, | |
| "eval_loss": 1.9331262111663818, | |
| "eval_runtime": 69.4231, | |
| "eval_samples_per_second": 37.322, | |
| "eval_steps_per_second": 18.668, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016256197675363732, | |
| "grad_norm": 3.226973533630371, | |
| "learning_rate": 0.0002, | |
| "loss": 6.5362, | |
| "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 | |
| } | |