| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.1520737327188941, |
| "eval_steps": 25, |
| "global_step": 250, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.12, |
| "learning_rate": 2.3797595190380762e-05, |
| "loss": 2.2542, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.12, |
| "eval_loss": 2.1287600994110107, |
| "eval_runtime": 18.2669, |
| "eval_samples_per_second": 5.967, |
| "eval_steps_per_second": 0.766, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 2.2545090180360722e-05, |
| "loss": 1.938, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.23, |
| "eval_loss": 2.0689284801483154, |
| "eval_runtime": 18.3984, |
| "eval_samples_per_second": 5.924, |
| "eval_steps_per_second": 0.761, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 2.1292585170340683e-05, |
| "loss": 1.8775, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.35, |
| "eval_loss": 2.041457414627075, |
| "eval_runtime": 18.446, |
| "eval_samples_per_second": 5.909, |
| "eval_steps_per_second": 0.759, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 2.0040080160320643e-05, |
| "loss": 1.9552, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.46, |
| "eval_loss": 2.0331594944000244, |
| "eval_runtime": 18.4787, |
| "eval_samples_per_second": 5.899, |
| "eval_steps_per_second": 0.758, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 1.87875751503006e-05, |
| "loss": 1.9249, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.58, |
| "eval_loss": 2.022515296936035, |
| "eval_runtime": 18.4573, |
| "eval_samples_per_second": 5.906, |
| "eval_steps_per_second": 0.759, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 1.7535070140280564e-05, |
| "loss": 1.9373, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.69, |
| "eval_loss": 2.023122549057007, |
| "eval_runtime": 18.4583, |
| "eval_samples_per_second": 5.905, |
| "eval_steps_per_second": 0.758, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 1.628256513026052e-05, |
| "loss": 1.8472, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.81, |
| "eval_loss": 2.031254529953003, |
| "eval_runtime": 18.4568, |
| "eval_samples_per_second": 5.906, |
| "eval_steps_per_second": 0.759, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 1.5030060120240483e-05, |
| "loss": 1.7905, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.92, |
| "eval_loss": 2.0129897594451904, |
| "eval_runtime": 18.4603, |
| "eval_samples_per_second": 5.905, |
| "eval_steps_per_second": 0.758, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 1.3777555110220442e-05, |
| "loss": 1.7504, |
| "step": 225 |
| }, |
| { |
| "epoch": 1.04, |
| "eval_loss": 2.0287795066833496, |
| "eval_runtime": 18.4619, |
| "eval_samples_per_second": 5.904, |
| "eval_steps_per_second": 0.758, |
| "step": 225 |
| }, |
| { |
| "epoch": 1.15, |
| "learning_rate": 1.25250501002004e-05, |
| "loss": 1.4639, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.15, |
| "eval_loss": 2.0487546920776367, |
| "eval_runtime": 18.4516, |
| "eval_samples_per_second": 5.907, |
| "eval_steps_per_second": 0.759, |
| "step": 250 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 500, |
| "num_train_epochs": 3, |
| "save_steps": 25, |
| "total_flos": 1.1030491922694144e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
