| { | |
| "best_metric": 1.3635696172714233, | |
| "best_model_checkpoint": "./llama3/21-04-24-Weni-WeniGPT-Agents-Llama3-1.0.9-SFT_Experiment with SFT and Llama3 and updates in requirements-2_max_steps-330_batch_8_2024-04-21_ppid_9/checkpoint-90", | |
| "epoch": 1.6071428571428572, | |
| "eval_steps": 30, | |
| "global_step": 90, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17857142857142858, | |
| "grad_norm": 0.6299236416816711, | |
| "learning_rate": 0.00015555555555555556, | |
| "loss": 1.9266, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "grad_norm": 0.4194231629371643, | |
| "learning_rate": 0.00019969365006623072, | |
| "loss": 1.5439, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5357142857142857, | |
| "grad_norm": 0.44722992181777954, | |
| "learning_rate": 0.00019845231970029773, | |
| "loss": 1.3488, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5357142857142857, | |
| "eval_loss": 1.3763371706008911, | |
| "eval_runtime": 4.9516, | |
| "eval_samples_per_second": 9.29, | |
| "eval_steps_per_second": 2.423, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.4362790286540985, | |
| "learning_rate": 0.00019626873324023915, | |
| "loss": 1.3256, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8928571428571429, | |
| "grad_norm": 0.435635507106781, | |
| "learning_rate": 0.00019316378910323102, | |
| "loss": 1.2663, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0714285714285714, | |
| "grad_norm": 0.5550065636634827, | |
| "learning_rate": 0.00018916720373012426, | |
| "loss": 1.1798, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0714285714285714, | |
| "eval_loss": 1.3427196741104126, | |
| "eval_runtime": 4.9453, | |
| "eval_samples_per_second": 9.302, | |
| "eval_steps_per_second": 2.427, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.571713387966156, | |
| "learning_rate": 0.00018431722717876384, | |
| "loss": 1.0592, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 0.5714108943939209, | |
| "learning_rate": 0.0001786602770447513, | |
| "loss": 0.98, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.6071428571428572, | |
| "grad_norm": 0.5294617414474487, | |
| "learning_rate": 0.00017225049421328023, | |
| "loss": 0.9664, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.6071428571428572, | |
| "eval_loss": 1.3635696172714233, | |
| "eval_runtime": 4.9445, | |
| "eval_samples_per_second": 9.303, | |
| "eval_steps_per_second": 2.427, | |
| "step": 90 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 330, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 90, | |
| "total_flos": 7.318524682829824e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |