| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.09017132551848513, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018034265103697023, | |
| "eval_loss": 1.5323797464370728, | |
| "eval_runtime": 15.1643, | |
| "eval_samples_per_second": 15.431, | |
| "eval_steps_per_second": 7.715, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009017132551848512, | |
| "grad_norm": 8.76136302947998, | |
| "learning_rate": 5e-05, | |
| "loss": 6.1682, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.018034265103697024, | |
| "grad_norm": 8.025477409362793, | |
| "learning_rate": 0.0001, | |
| "loss": 5.5289, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018034265103697024, | |
| "eval_loss": 1.2459672689437866, | |
| "eval_runtime": 15.635, | |
| "eval_samples_per_second": 14.966, | |
| "eval_steps_per_second": 7.483, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027051397655545536, | |
| "grad_norm": 6.852028846740723, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.7056, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03606853020739405, | |
| "grad_norm": 5.969870090484619, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.1946, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03606853020739405, | |
| "eval_loss": 1.0455502271652222, | |
| "eval_runtime": 15.6064, | |
| "eval_samples_per_second": 14.994, | |
| "eval_steps_per_second": 7.497, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04508566275924256, | |
| "grad_norm": 6.2113494873046875, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.0385, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05410279531109107, | |
| "grad_norm": 5.920165538787842, | |
| "learning_rate": 5e-05, | |
| "loss": 4.0129, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05410279531109107, | |
| "eval_loss": 0.9842101335525513, | |
| "eval_runtime": 15.6988, | |
| "eval_samples_per_second": 14.906, | |
| "eval_steps_per_second": 7.453, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06311992786293959, | |
| "grad_norm": 6.285253524780273, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.9661, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0721370604147881, | |
| "grad_norm": 5.879969120025635, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.7932, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0721370604147881, | |
| "eval_loss": 0.959617555141449, | |
| "eval_runtime": 15.7241, | |
| "eval_samples_per_second": 14.882, | |
| "eval_steps_per_second": 7.441, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0811541929666366, | |
| "grad_norm": 6.4072957038879395, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.7872, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09017132551848513, | |
| "grad_norm": 6.380867958068848, | |
| "learning_rate": 0.0, | |
| "loss": 3.6417, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09017132551848513, | |
| "eval_loss": 0.9541131258010864, | |
| "eval_runtime": 15.5353, | |
| "eval_samples_per_second": 15.062, | |
| "eval_steps_per_second": 7.531, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8894809381011456.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |