| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9337068160597572, | |
| "eval_steps": 50, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.6599863767623901, | |
| "eval_runtime": 3.0665, | |
| "eval_samples_per_second": 32.611, | |
| "eval_steps_per_second": 4.239, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.5268713235855103, | |
| "eval_runtime": 3.0649, | |
| "eval_samples_per_second": 32.627, | |
| "eval_steps_per_second": 4.242, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.4272453784942627, | |
| "eval_runtime": 3.0703, | |
| "eval_samples_per_second": 32.57, | |
| "eval_steps_per_second": 4.234, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 1.3691519498825073, | |
| "eval_runtime": 3.0755, | |
| "eval_samples_per_second": 32.515, | |
| "eval_steps_per_second": 4.227, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 1.3439632654190063, | |
| "eval_runtime": 3.0781, | |
| "eval_samples_per_second": 32.488, | |
| "eval_steps_per_second": 4.223, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.2951898574829102, | |
| "eval_runtime": 3.0608, | |
| "eval_samples_per_second": 32.671, | |
| "eval_steps_per_second": 4.247, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.2598179578781128, | |
| "eval_runtime": 3.0651, | |
| "eval_samples_per_second": 32.626, | |
| "eval_steps_per_second": 4.241, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 1.2034798860549927, | |
| "eval_runtime": 3.0667, | |
| "eval_samples_per_second": 32.608, | |
| "eval_steps_per_second": 4.239, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.1628668308258057, | |
| "eval_runtime": 3.0674, | |
| "eval_samples_per_second": 32.601, | |
| "eval_steps_per_second": 4.238, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 8.75e-05, | |
| "loss": 1.6585, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.1156766414642334, | |
| "eval_runtime": 3.0714, | |
| "eval_samples_per_second": 32.558, | |
| "eval_steps_per_second": 4.233, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.0700278282165527, | |
| "eval_runtime": 3.0584, | |
| "eval_samples_per_second": 32.696, | |
| "eval_steps_per_second": 4.251, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 1.0359002351760864, | |
| "eval_runtime": 3.0694, | |
| "eval_samples_per_second": 32.58, | |
| "eval_steps_per_second": 4.235, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 1.019242286682129, | |
| "eval_runtime": 3.0562, | |
| "eval_samples_per_second": 32.72, | |
| "eval_steps_per_second": 4.254, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 0.9841110706329346, | |
| "eval_runtime": 3.0664, | |
| "eval_samples_per_second": 32.611, | |
| "eval_steps_per_second": 4.239, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 0.993296205997467, | |
| "eval_runtime": 3.074, | |
| "eval_samples_per_second": 32.531, | |
| "eval_steps_per_second": 4.229, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 0.9330427646636963, | |
| "eval_runtime": 3.0586, | |
| "eval_samples_per_second": 32.695, | |
| "eval_steps_per_second": 4.25, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 0.9203641414642334, | |
| "eval_runtime": 3.0859, | |
| "eval_samples_per_second": 32.405, | |
| "eval_steps_per_second": 4.213, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 0.9058796763420105, | |
| "eval_runtime": 3.068, | |
| "eval_samples_per_second": 32.595, | |
| "eval_steps_per_second": 4.237, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 0.9017823934555054, | |
| "eval_runtime": 3.0852, | |
| "eval_samples_per_second": 32.413, | |
| "eval_steps_per_second": 4.214, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.3142, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 0.8834471702575684, | |
| "eval_runtime": 3.0917, | |
| "eval_samples_per_second": 32.344, | |
| "eval_steps_per_second": 4.205, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 4000, | |
| "num_train_epochs": 4, | |
| "save_steps": 1000, | |
| "total_flos": 1.369514704896e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |