| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004153168867846167, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016612675471384668, | |
| "grad_norm": 0.9919585585594177, | |
| "learning_rate": 1e-05, | |
| "loss": 1.8966, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016612675471384668, | |
| "eval_loss": 1.0414841175079346, | |
| "eval_runtime": 673.9747, | |
| "eval_samples_per_second": 7.521, | |
| "eval_steps_per_second": 0.941, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00033225350942769335, | |
| "grad_norm": 1.5468533039093018, | |
| "learning_rate": 2e-05, | |
| "loss": 2.8453, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00049838026414154, | |
| "grad_norm": 1.3301949501037598, | |
| "learning_rate": 3e-05, | |
| "loss": 2.3285, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006645070188553867, | |
| "grad_norm": 1.870064377784729, | |
| "learning_rate": 4e-05, | |
| "loss": 2.5663, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008306337735692333, | |
| "grad_norm": 1.6597638130187988, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1576, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00099676052828308, | |
| "grad_norm": 0.5557398796081543, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2538, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011628872829969267, | |
| "grad_norm": 0.991572916507721, | |
| "learning_rate": 7e-05, | |
| "loss": 1.6291, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013290140377107734, | |
| "grad_norm": 0.6162525415420532, | |
| "learning_rate": 8e-05, | |
| "loss": 1.8258, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00149514079242462, | |
| "grad_norm": 1.4342612028121948, | |
| "learning_rate": 9e-05, | |
| "loss": 2.7709, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00149514079242462, | |
| "eval_loss": 0.9687274694442749, | |
| "eval_runtime": 675.7106, | |
| "eval_samples_per_second": 7.502, | |
| "eval_steps_per_second": 0.938, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016612675471384666, | |
| "grad_norm": 1.043684720993042, | |
| "learning_rate": 0.0001, | |
| "loss": 1.713, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0018273943018523133, | |
| "grad_norm": 1.1158920526504517, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 1.2303, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00199352105656616, | |
| "grad_norm": 0.8735452890396118, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.0613, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0021596478112800065, | |
| "grad_norm": 0.6356571912765503, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 1.1697, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0023257745659938534, | |
| "grad_norm": 0.5694183111190796, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.2002, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0024919013207077, | |
| "grad_norm": 0.589718759059906, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 1.5224, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002658028075421547, | |
| "grad_norm": 1.3405238389968872, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.5344, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0028241548301353933, | |
| "grad_norm": 2.1417508125305176, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 2.131, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00299028158484924, | |
| "grad_norm": 1.19926917552948, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.9731, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00299028158484924, | |
| "eval_loss": 0.7821024656295776, | |
| "eval_runtime": 675.4552, | |
| "eval_samples_per_second": 7.505, | |
| "eval_steps_per_second": 0.939, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0031564083395630867, | |
| "grad_norm": 0.885982871055603, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.3646, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.003322535094276933, | |
| "grad_norm": 1.1024696826934814, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.4764, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00348866184899078, | |
| "grad_norm": 3.787921667098999, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 2.868, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0036547886037046266, | |
| "grad_norm": 1.1288354396820068, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.7279, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.003820915358418473, | |
| "grad_norm": 1.6195688247680664, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 1.1748, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00398704211313232, | |
| "grad_norm": 3.927457094192505, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.8016, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004153168867846167, | |
| "grad_norm": 2.22636342048645, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.4189, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.613832807612416e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |