| { | |
| "best_metric": 2.2034003734588623, | |
| "best_model_checkpoint": "./Qwen2-4B-Chat-hinglish-sft/checkpoint-650", | |
| "epoch": 2.6812313803376364, | |
| "eval_steps": 25, | |
| "global_step": 675, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 1.1830133199691772, | |
| "learning_rate": 0.00019999629591162656, | |
| "loss": 4.7862, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 4.098670482635498, | |
| "eval_runtime": 4.1063, | |
| "eval_samples_per_second": 2.679, | |
| "eval_steps_per_second": 2.679, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 1.0619295835494995, | |
| "learning_rate": 0.00019932568492674144, | |
| "loss": 2.9161, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 3.1406357288360596, | |
| "eval_runtime": 4.0777, | |
| "eval_samples_per_second": 2.698, | |
| "eval_steps_per_second": 2.698, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 1.1028335094451904, | |
| "learning_rate": 0.0001975064532257195, | |
| "loss": 2.4282, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 2.8003995418548584, | |
| "eval_runtime": 4.076, | |
| "eval_samples_per_second": 2.699, | |
| "eval_steps_per_second": 2.699, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.9855464100837708, | |
| "learning_rate": 0.00019455963874271426, | |
| "loss": 2.2815, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 2.6393470764160156, | |
| "eval_runtime": 4.084, | |
| "eval_samples_per_second": 2.693, | |
| "eval_steps_per_second": 2.693, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 1.154259204864502, | |
| "learning_rate": 0.00019051931898913976, | |
| "loss": 2.1485, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 2.5862808227539062, | |
| "eval_runtime": 4.0324, | |
| "eval_samples_per_second": 2.728, | |
| "eval_steps_per_second": 2.728, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 1.2115691900253296, | |
| "learning_rate": 0.0001854322169749827, | |
| "loss": 2.0884, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 2.491671323776245, | |
| "eval_runtime": 4.0837, | |
| "eval_samples_per_second": 2.694, | |
| "eval_steps_per_second": 2.694, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 1.0713191032409668, | |
| "learning_rate": 0.00017935716089521474, | |
| "loss": 2.1055, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 2.4541499614715576, | |
| "eval_runtime": 4.0493, | |
| "eval_samples_per_second": 2.717, | |
| "eval_steps_per_second": 2.717, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 1.1404445171356201, | |
| "learning_rate": 0.00017236440382959126, | |
| "loss": 2.1012, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 2.42814040184021, | |
| "eval_runtime": 4.0309, | |
| "eval_samples_per_second": 2.729, | |
| "eval_steps_per_second": 2.729, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 1.1801480054855347, | |
| "learning_rate": 0.00016453481132295506, | |
| "loss": 1.9956, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 2.3967058658599854, | |
| "eval_runtime": 4.0145, | |
| "eval_samples_per_second": 2.74, | |
| "eval_steps_per_second": 2.74, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 1.2651640176773071, | |
| "learning_rate": 0.00015595892624101765, | |
| "loss": 1.9931, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 2.3804991245269775, | |
| "eval_runtime": 4.0509, | |
| "eval_samples_per_second": 2.715, | |
| "eval_steps_per_second": 2.715, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 1.2018358707427979, | |
| "learning_rate": 0.00014673592171580025, | |
| "loss": 1.7605, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 2.358070135116577, | |
| "eval_runtime": 4.0302, | |
| "eval_samples_per_second": 2.729, | |
| "eval_steps_per_second": 2.729, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 1.2622418403625488, | |
| "learning_rate": 0.00013697245428906732, | |
| "loss": 1.9231, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 2.3286843299865723, | |
| "eval_runtime": 4.0327, | |
| "eval_samples_per_second": 2.728, | |
| "eval_steps_per_second": 2.728, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 1.324831247329712, | |
| "learning_rate": 0.00012678143051621742, | |
| "loss": 1.8805, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 2.3032760620117188, | |
| "eval_runtime": 4.0494, | |
| "eval_samples_per_second": 2.716, | |
| "eval_steps_per_second": 2.716, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 1.242129921913147, | |
| "learning_rate": 0.00011628070129385169, | |
| "loss": 1.8475, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_loss": 2.2904257774353027, | |
| "eval_runtime": 4.0806, | |
| "eval_samples_per_second": 2.696, | |
| "eval_steps_per_second": 2.696, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 1.2501651048660278, | |
| "learning_rate": 0.00010559169901006034, | |
| "loss": 1.8282, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "eval_loss": 2.2831265926361084, | |
| "eval_runtime": 4.0586, | |
| "eval_samples_per_second": 2.71, | |
| "eval_steps_per_second": 2.71, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 1.2264453172683716, | |
| "learning_rate": 9.483803327767462e-05, | |
| "loss": 1.8311, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 2.2586615085601807, | |
| "eval_runtime": 4.0884, | |
| "eval_samples_per_second": 2.691, | |
| "eval_steps_per_second": 2.691, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 1.2421507835388184, | |
| "learning_rate": 8.414406148968657e-05, | |
| "loss": 1.8051, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_loss": 2.2608296871185303, | |
| "eval_runtime": 4.0277, | |
| "eval_samples_per_second": 2.731, | |
| "eval_steps_per_second": 2.731, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 1.4312422275543213, | |
| "learning_rate": 7.363345072719929e-05, | |
| "loss": 1.8093, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 2.249046564102173, | |
| "eval_runtime": 4.1182, | |
| "eval_samples_per_second": 2.671, | |
| "eval_steps_per_second": 2.671, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 1.3606431484222412, | |
| "learning_rate": 6.342774765027309e-05, | |
| "loss": 1.6944, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_loss": 2.2398183345794678, | |
| "eval_runtime": 4.0501, | |
| "eval_samples_per_second": 2.716, | |
| "eval_steps_per_second": 2.716, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "grad_norm": 1.4951516389846802, | |
| "learning_rate": 5.3644972909714906e-05, | |
| "loss": 1.7418, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 2.2147467136383057, | |
| "eval_runtime": 4.0963, | |
| "eval_samples_per_second": 2.685, | |
| "eval_steps_per_second": 2.685, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "grad_norm": 1.3656489849090576, | |
| "learning_rate": 4.439825633429557e-05, | |
| "loss": 1.741, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_loss": 2.20865797996521, | |
| "eval_runtime": 4.08, | |
| "eval_samples_per_second": 2.696, | |
| "eval_steps_per_second": 2.696, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "grad_norm": 1.3683630228042603, | |
| "learning_rate": 3.579452867634364e-05, | |
| "loss": 1.6561, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "eval_loss": 2.2086095809936523, | |
| "eval_runtime": 4.0702, | |
| "eval_samples_per_second": 2.703, | |
| "eval_steps_per_second": 2.703, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "grad_norm": 1.668961524963379, | |
| "learning_rate": 2.793328504461391e-05, | |
| "loss": 1.6894, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_loss": 2.2114932537078857, | |
| "eval_runtime": 4.085, | |
| "eval_samples_per_second": 2.693, | |
| "eval_steps_per_second": 2.693, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "grad_norm": 1.3654729127883911, | |
| "learning_rate": 2.0905434324322283e-05, | |
| "loss": 1.5617, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "eval_loss": 2.2105047702789307, | |
| "eval_runtime": 4.0226, | |
| "eval_samples_per_second": 2.735, | |
| "eval_steps_per_second": 2.735, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "grad_norm": 1.1611803770065308, | |
| "learning_rate": 1.4792247889869071e-05, | |
| "loss": 1.6809, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "eval_loss": 2.2049694061279297, | |
| "eval_runtime": 4.0427, | |
| "eval_samples_per_second": 2.721, | |
| "eval_steps_per_second": 2.721, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "grad_norm": 1.6043980121612549, | |
| "learning_rate": 9.664419767531564e-06, | |
| "loss": 1.7355, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "eval_loss": 2.2034003734588623, | |
| "eval_runtime": 4.0162, | |
| "eval_samples_per_second": 2.739, | |
| "eval_steps_per_second": 2.739, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "grad_norm": 1.660874843597412, | |
| "learning_rate": 5.5812491165800675e-06, | |
| "loss": 1.595, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "eval_loss": 2.2044949531555176, | |
| "eval_runtime": 4.0854, | |
| "eval_samples_per_second": 2.693, | |
| "eval_steps_per_second": 2.693, | |
| "step": 675 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 753, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 25, | |
| "total_flos": 4830070723799040.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |