| { | |
| "best_metric": 0.9388719201087952, | |
| "best_model_checkpoint": "/home/datta0/models/lora_final/Qwen2-7B_magiccoder_ortho/checkpoint-12", | |
| "epoch": 0.07830342577487764, | |
| "eval_steps": 4, | |
| "global_step": 12, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0065252854812398045, | |
| "grad_norm": 4.3915696144104, | |
| "learning_rate": 7.5e-05, | |
| "loss": 0.8061, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013050570962479609, | |
| "grad_norm": 3.7475483417510986, | |
| "learning_rate": 0.00015, | |
| "loss": 0.931, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.026101141924959218, | |
| "grad_norm": 5.367969989776611, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8262, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.026101141924959218, | |
| "eval_loss": 1.0883674621582031, | |
| "eval_runtime": 24.5353, | |
| "eval_samples_per_second": 19.931, | |
| "eval_steps_per_second": 2.527, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03915171288743882, | |
| "grad_norm": 11.019035339355469, | |
| "learning_rate": 0.00029986665273697545, | |
| "loss": 1.0003, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.052202283849918436, | |
| "grad_norm": 2.1015965938568115, | |
| "learning_rate": 0.0002994668480344693, | |
| "loss": 0.9776, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.052202283849918436, | |
| "eval_loss": 0.9662861227989197, | |
| "eval_runtime": 24.6827, | |
| "eval_samples_per_second": 19.811, | |
| "eval_steps_per_second": 2.512, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06525285481239804, | |
| "grad_norm": 1.750746726989746, | |
| "learning_rate": 0.0002988012967306524, | |
| "loss": 0.9319, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07830342577487764, | |
| "grad_norm": 2.2127320766448975, | |
| "learning_rate": 0.000297871182151455, | |
| "loss": 0.9345, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07830342577487764, | |
| "eval_loss": 0.9388719201087952, | |
| "eval_runtime": 24.6723, | |
| "eval_samples_per_second": 19.82, | |
| "eval_steps_per_second": 2.513, | |
| "step": 12 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 153, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 4, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.934708016368845e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |