| { | |
| "best_global_step": 800, | |
| "best_metric": 0.5450772643089294, | |
| "best_model_checkpoint": "Llama-3.2-1B-it-Medical-LoRA/checkpoint-800", | |
| "epoch": 1.8131370328425822, | |
| "eval_steps": 100, | |
| "global_step": 800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11325028312570781, | |
| "grad_norm": 0.6456167697906494, | |
| "learning_rate": 0.00019075425790754258, | |
| "loss": 0.643, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22650056625141562, | |
| "grad_norm": 1.0792498588562012, | |
| "learning_rate": 0.0001664233576642336, | |
| "loss": 0.6465, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22650056625141562, | |
| "eval_loss": 0.5826964378356934, | |
| "eval_runtime": 394.3597, | |
| "eval_samples_per_second": 3.979, | |
| "eval_steps_per_second": 0.5, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.33975084937712347, | |
| "grad_norm": 0.5628879070281982, | |
| "learning_rate": 0.0001420924574209246, | |
| "loss": 0.5815, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.45300113250283125, | |
| "grad_norm": 0.5532649755477905, | |
| "learning_rate": 0.00011776155717761557, | |
| "loss": 0.5435, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.45300113250283125, | |
| "eval_loss": 0.5700864791870117, | |
| "eval_runtime": 394.4221, | |
| "eval_samples_per_second": 3.978, | |
| "eval_steps_per_second": 0.499, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5662514156285391, | |
| "grad_norm": 0.7321934700012207, | |
| "learning_rate": 9.343065693430657e-05, | |
| "loss": 0.5816, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6795016987542469, | |
| "grad_norm": 0.43280959129333496, | |
| "learning_rate": 6.909975669099758e-05, | |
| "loss": 0.5611, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6795016987542469, | |
| "eval_loss": 0.5585977435112, | |
| "eval_runtime": 393.6528, | |
| "eval_samples_per_second": 3.986, | |
| "eval_steps_per_second": 0.5, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7927519818799547, | |
| "grad_norm": 0.5519748330116272, | |
| "learning_rate": 4.476885644768857e-05, | |
| "loss": 0.5964, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.9060022650056625, | |
| "grad_norm": 0.43155646324157715, | |
| "learning_rate": 2.0437956204379563e-05, | |
| "loss": 0.5656, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9060022650056625, | |
| "eval_loss": 0.5522705912590027, | |
| "eval_runtime": 393.6183, | |
| "eval_samples_per_second": 3.986, | |
| "eval_steps_per_second": 0.5, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.0203850509626273, | |
| "grad_norm": 0.5300919413566589, | |
| "learning_rate": 0.0001614712643678161, | |
| "loss": 0.5, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.1336353340883352, | |
| "grad_norm": 0.6625114679336548, | |
| "learning_rate": 0.00015687356321839082, | |
| "loss": 0.4964, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.1336353340883352, | |
| "eval_loss": 0.5636059045791626, | |
| "eval_runtime": 394.3412, | |
| "eval_samples_per_second": 3.979, | |
| "eval_steps_per_second": 0.5, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.246885617214043, | |
| "grad_norm": 0.635853111743927, | |
| "learning_rate": 0.0001522758620689655, | |
| "loss": 0.5245, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.3601359003397508, | |
| "grad_norm": 0.6611766219139099, | |
| "learning_rate": 0.00014767816091954024, | |
| "loss": 0.5212, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.3601359003397508, | |
| "eval_loss": 0.5590068101882935, | |
| "eval_runtime": 394.5384, | |
| "eval_samples_per_second": 3.977, | |
| "eval_steps_per_second": 0.499, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.4733861834654587, | |
| "grad_norm": 0.5332358479499817, | |
| "learning_rate": 0.00014308045977011496, | |
| "loss": 0.5143, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.5866364665911665, | |
| "grad_norm": 0.7008891701698303, | |
| "learning_rate": 0.00013848275862068967, | |
| "loss": 0.506, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.5866364665911665, | |
| "eval_loss": 0.5510138869285583, | |
| "eval_runtime": 394.522, | |
| "eval_samples_per_second": 3.977, | |
| "eval_steps_per_second": 0.499, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.6998867497168741, | |
| "grad_norm": 0.6186133623123169, | |
| "learning_rate": 0.00013388505747126436, | |
| "loss": 0.5094, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.8131370328425822, | |
| "grad_norm": 0.5614038109779358, | |
| "learning_rate": 0.00012928735632183907, | |
| "loss": 0.5112, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.8131370328425822, | |
| "eval_loss": 0.5450772643089294, | |
| "eval_runtime": 394.4384, | |
| "eval_samples_per_second": 3.978, | |
| "eval_steps_per_second": 0.499, | |
| "step": 800 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 2205, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.048744699120845e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |