| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0745489786789921, | |
| "eval_steps": 25, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.3797595190380762e-05, | |
| "loss": 2.1701, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 1.8664429187774658, | |
| "eval_runtime": 75.4556, | |
| "eval_samples_per_second": 4.373, | |
| "eval_steps_per_second": 0.557, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.2545090180360722e-05, | |
| "loss": 1.7051, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 1.69643235206604, | |
| "eval_runtime": 75.4572, | |
| "eval_samples_per_second": 4.373, | |
| "eval_steps_per_second": 0.557, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.1292585170340683e-05, | |
| "loss": 1.6906, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 1.5493319034576416, | |
| "eval_runtime": 75.4583, | |
| "eval_samples_per_second": 4.373, | |
| "eval_steps_per_second": 0.557, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.0040080160320643e-05, | |
| "loss": 1.4741, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 1.4430667161941528, | |
| "eval_runtime": 75.4567, | |
| "eval_samples_per_second": 4.373, | |
| "eval_steps_per_second": 0.557, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.87875751503006e-05, | |
| "loss": 1.3295, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 1.3759217262268066, | |
| "eval_runtime": 75.4578, | |
| "eval_samples_per_second": 4.373, | |
| "eval_steps_per_second": 0.557, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.7535070140280564e-05, | |
| "loss": 1.1882, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 1.3191803693771362, | |
| "eval_runtime": 75.4544, | |
| "eval_samples_per_second": 4.374, | |
| "eval_steps_per_second": 0.557, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.628256513026052e-05, | |
| "loss": 1.2584, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.2361661195755005, | |
| "eval_runtime": 75.4588, | |
| "eval_samples_per_second": 4.373, | |
| "eval_steps_per_second": 0.557, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.5030060120240483e-05, | |
| "loss": 1.1446, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.1712000370025635, | |
| "eval_runtime": 75.4515, | |
| "eval_samples_per_second": 4.374, | |
| "eval_steps_per_second": 0.557, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.3777555110220442e-05, | |
| "loss": 1.0563, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.1068586111068726, | |
| "eval_runtime": 75.4592, | |
| "eval_samples_per_second": 4.373, | |
| "eval_steps_per_second": 0.557, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.25250501002004e-05, | |
| "loss": 0.9986, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.0612759590148926, | |
| "eval_runtime": 75.4602, | |
| "eval_samples_per_second": 4.373, | |
| "eval_steps_per_second": 0.557, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.1272545090180361e-05, | |
| "loss": 0.9068, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.0247318744659424, | |
| "eval_runtime": 75.4522, | |
| "eval_samples_per_second": 4.374, | |
| "eval_steps_per_second": 0.557, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.0020040080160322e-05, | |
| "loss": 0.931, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 0.9830127954483032, | |
| "eval_runtime": 75.4571, | |
| "eval_samples_per_second": 4.373, | |
| "eval_steps_per_second": 0.557, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 8.767535070140282e-06, | |
| "loss": 0.9168, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 0.9444506168365479, | |
| "eval_runtime": 75.4606, | |
| "eval_samples_per_second": 4.373, | |
| "eval_steps_per_second": 0.557, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 7.515030060120242e-06, | |
| "loss": 0.6838, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 0.9132566452026367, | |
| "eval_runtime": 75.459, | |
| "eval_samples_per_second": 4.373, | |
| "eval_steps_per_second": 0.557, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 6.2625250501002e-06, | |
| "loss": 0.8248, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 0.8770744800567627, | |
| "eval_runtime": 75.4708, | |
| "eval_samples_per_second": 4.373, | |
| "eval_steps_per_second": 0.557, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5.010020040080161e-06, | |
| "loss": 0.8234, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 0.8546050786972046, | |
| "eval_runtime": 75.4678, | |
| "eval_samples_per_second": 4.373, | |
| "eval_steps_per_second": 0.557, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 3.757515030060121e-06, | |
| "loss": 0.643, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 0.8464756608009338, | |
| "eval_runtime": 75.4668, | |
| "eval_samples_per_second": 4.373, | |
| "eval_steps_per_second": 0.557, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2.5050100200400804e-06, | |
| "loss": 0.5577, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 0.8301312923431396, | |
| "eval_runtime": 75.4707, | |
| "eval_samples_per_second": 4.373, | |
| "eval_steps_per_second": 0.557, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.2525050100200402e-06, | |
| "loss": 0.7513, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 0.8151108026504517, | |
| "eval_runtime": 75.4545, | |
| "eval_samples_per_second": 4.373, | |
| "eval_steps_per_second": 0.557, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0, | |
| "loss": 0.672, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 0.8106139898300171, | |
| "eval_runtime": 75.455, | |
| "eval_samples_per_second": 4.373, | |
| "eval_steps_per_second": 0.557, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "total_flos": 2.23129632768e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |