| { |
| "best_metric": 1.4253113269805908, |
| "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-13500", |
| "epoch": 19.202761872684405, |
| "eval_steps": 750, |
| "global_step": 14250, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "step": 742, |
| "total_flos": 3.211629347340288e+16, |
| "train_loss": 5.698867345434636, |
| "train_runtime": 6114.1675, |
| "train_samples_per_second": 15.538, |
| "train_steps_per_second": 0.121 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 4.9989218328840974e-05, |
| "loss": 10.3965, |
| "step": 750 |
| }, |
| { |
| "epoch": 1.01, |
| "eval_loss": 9.694682121276855, |
| "eval_runtime": 84.6491, |
| "eval_samples_per_second": 59.067, |
| "eval_steps_per_second": 0.933, |
| "step": 750 |
| }, |
| { |
| "epoch": 2.02, |
| "learning_rate": 4.897978436657682e-05, |
| "loss": 4.9343, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.02, |
| "eval_loss": 3.2859976291656494, |
| "eval_runtime": 84.3631, |
| "eval_samples_per_second": 59.268, |
| "eval_steps_per_second": 0.936, |
| "step": 1500 |
| }, |
| { |
| "epoch": 3.03, |
| "learning_rate": 4.796900269541779e-05, |
| "loss": 2.8798, |
| "step": 2250 |
| }, |
| { |
| "epoch": 3.03, |
| "eval_loss": 2.4815261363983154, |
| "eval_runtime": 84.3896, |
| "eval_samples_per_second": 59.249, |
| "eval_steps_per_second": 0.936, |
| "step": 2250 |
| }, |
| { |
| "epoch": 4.04, |
| "learning_rate": 4.6958221024258764e-05, |
| "loss": 2.1885, |
| "step": 3000 |
| }, |
| { |
| "epoch": 4.04, |
| "eval_loss": 1.9960429668426514, |
| "eval_runtime": 84.3112, |
| "eval_samples_per_second": 59.304, |
| "eval_steps_per_second": 0.937, |
| "step": 3000 |
| }, |
| { |
| "epoch": 5.05, |
| "learning_rate": 4.594743935309973e-05, |
| "loss": 1.7594, |
| "step": 3750 |
| }, |
| { |
| "epoch": 5.05, |
| "eval_loss": 1.7031219005584717, |
| "eval_runtime": 84.3933, |
| "eval_samples_per_second": 59.246, |
| "eval_steps_per_second": 0.936, |
| "step": 3750 |
| }, |
| { |
| "epoch": 6.06, |
| "learning_rate": 4.4936657681940705e-05, |
| "loss": 1.4881, |
| "step": 4500 |
| }, |
| { |
| "epoch": 6.06, |
| "eval_loss": 1.558716893196106, |
| "eval_runtime": 84.4241, |
| "eval_samples_per_second": 59.225, |
| "eval_steps_per_second": 0.936, |
| "step": 4500 |
| }, |
| { |
| "epoch": 7.07, |
| "learning_rate": 4.392587601078167e-05, |
| "loss": 1.2897, |
| "step": 5250 |
| }, |
| { |
| "epoch": 7.07, |
| "eval_loss": 1.5603703260421753, |
| "eval_runtime": 84.4569, |
| "eval_samples_per_second": 59.202, |
| "eval_steps_per_second": 0.935, |
| "step": 5250 |
| }, |
| { |
| "epoch": 8.09, |
| "learning_rate": 4.8989218328840976e-05, |
| "loss": 3.6553, |
| "step": 6000 |
| }, |
| { |
| "epoch": 8.09, |
| "eval_loss": 2.3138411045074463, |
| "eval_runtime": 85.1227, |
| "eval_samples_per_second": 58.739, |
| "eval_steps_per_second": 0.928, |
| "step": 6000 |
| }, |
| { |
| "epoch": 9.1, |
| "learning_rate": 4.7979784366576826e-05, |
| "loss": 1.8488, |
| "step": 6750 |
| }, |
| { |
| "epoch": 9.1, |
| "eval_loss": 1.7765036821365356, |
| "eval_runtime": 84.6118, |
| "eval_samples_per_second": 59.093, |
| "eval_steps_per_second": 0.934, |
| "step": 6750 |
| }, |
| { |
| "epoch": 10.11, |
| "learning_rate": 4.696900269541779e-05, |
| "loss": 1.4372, |
| "step": 7500 |
| }, |
| { |
| "epoch": 10.11, |
| "eval_loss": 1.5598968267440796, |
| "eval_runtime": 84.6222, |
| "eval_samples_per_second": 59.086, |
| "eval_steps_per_second": 0.934, |
| "step": 7500 |
| }, |
| { |
| "epoch": 11.12, |
| "learning_rate": 4.595822102425876e-05, |
| "loss": 1.2011, |
| "step": 8250 |
| }, |
| { |
| "epoch": 11.12, |
| "eval_loss": 1.4957914352416992, |
| "eval_runtime": 84.6871, |
| "eval_samples_per_second": 59.041, |
| "eval_steps_per_second": 0.933, |
| "step": 8250 |
| }, |
| { |
| "epoch": 12.13, |
| "learning_rate": 4.4947439353099734e-05, |
| "loss": 1.0493, |
| "step": 9000 |
| }, |
| { |
| "epoch": 12.13, |
| "eval_loss": 1.4617092609405518, |
| "eval_runtime": 84.4178, |
| "eval_samples_per_second": 59.229, |
| "eval_steps_per_second": 0.936, |
| "step": 9000 |
| }, |
| { |
| "epoch": 13.14, |
| "learning_rate": 4.39366576819407e-05, |
| "loss": 0.922, |
| "step": 9750 |
| }, |
| { |
| "epoch": 13.14, |
| "eval_loss": 1.3600549697875977, |
| "eval_runtime": 84.2691, |
| "eval_samples_per_second": 59.334, |
| "eval_steps_per_second": 0.937, |
| "step": 9750 |
| }, |
| { |
| "epoch": 14.15, |
| "learning_rate": 4.949528301886793e-05, |
| "loss": 3.0742, |
| "step": 10500 |
| }, |
| { |
| "epoch": 14.15, |
| "eval_loss": 2.005005359649658, |
| "eval_runtime": 84.8703, |
| "eval_samples_per_second": 58.913, |
| "eval_steps_per_second": 0.931, |
| "step": 10500 |
| }, |
| { |
| "epoch": 15.16, |
| "learning_rate": 4.898989218328841e-05, |
| "loss": 1.4983, |
| "step": 11250 |
| }, |
| { |
| "epoch": 15.16, |
| "eval_loss": 1.668813705444336, |
| "eval_runtime": 84.5947, |
| "eval_samples_per_second": 59.105, |
| "eval_steps_per_second": 0.934, |
| "step": 11250 |
| }, |
| { |
| "epoch": 16.17, |
| "learning_rate": 4.84845013477089e-05, |
| "loss": 1.1598, |
| "step": 12000 |
| }, |
| { |
| "epoch": 16.17, |
| "eval_loss": 1.5255405902862549, |
| "eval_runtime": 84.5763, |
| "eval_samples_per_second": 59.118, |
| "eval_steps_per_second": 0.934, |
| "step": 12000 |
| }, |
| { |
| "epoch": 17.18, |
| "learning_rate": 4.7979110512129385e-05, |
| "loss": 0.9732, |
| "step": 12750 |
| }, |
| { |
| "epoch": 17.18, |
| "eval_loss": 1.4376968145370483, |
| "eval_runtime": 84.6742, |
| "eval_samples_per_second": 59.05, |
| "eval_steps_per_second": 0.933, |
| "step": 12750 |
| }, |
| { |
| "epoch": 18.19, |
| "learning_rate": 4.7473719676549865e-05, |
| "loss": 0.8466, |
| "step": 13500 |
| }, |
| { |
| "epoch": 18.19, |
| "eval_loss": 1.4253113269805908, |
| "eval_runtime": 84.5693, |
| "eval_samples_per_second": 59.123, |
| "eval_steps_per_second": 0.934, |
| "step": 13500 |
| }, |
| { |
| "epoch": 19.2, |
| "learning_rate": 4.696900269541779e-05, |
| "loss": 0.7497, |
| "step": 14250 |
| }, |
| { |
| "epoch": 19.2, |
| "eval_loss": 1.3664312362670898, |
| "eval_runtime": 84.6297, |
| "eval_samples_per_second": 59.081, |
| "eval_steps_per_second": 0.933, |
| "step": 14250 |
| } |
| ], |
| "logging_steps": 750, |
| "max_steps": 74200, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 100, |
| "save_steps": 750, |
| "total_flos": 6.167399611399373e+17, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
