| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012790995139421847, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005116398055768739, | |
| "grad_norm": 1.6488349437713623, | |
| "learning_rate": 1e-05, | |
| "loss": 2.1352, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005116398055768739, | |
| "eval_loss": 1.228289008140564, | |
| "eval_runtime": 274.3879, | |
| "eval_samples_per_second": 5.999, | |
| "eval_steps_per_second": 0.751, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010232796111537478, | |
| "grad_norm": 1.8014962673187256, | |
| "learning_rate": 2e-05, | |
| "loss": 2.439, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0015349194167306216, | |
| "grad_norm": 1.226792573928833, | |
| "learning_rate": 3e-05, | |
| "loss": 2.2876, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0020465592223074956, | |
| "grad_norm": 1.5848373174667358, | |
| "learning_rate": 4e-05, | |
| "loss": 2.1205, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0025581990278843694, | |
| "grad_norm": 3.6875414848327637, | |
| "learning_rate": 5e-05, | |
| "loss": 2.973, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0030698388334612432, | |
| "grad_norm": 1.861879587173462, | |
| "learning_rate": 6e-05, | |
| "loss": 2.2063, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003581478639038117, | |
| "grad_norm": 2.6092193126678467, | |
| "learning_rate": 7e-05, | |
| "loss": 2.5909, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004093118444614991, | |
| "grad_norm": 2.884692668914795, | |
| "learning_rate": 8e-05, | |
| "loss": 2.3501, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004604758250191865, | |
| "grad_norm": 1.9096957445144653, | |
| "learning_rate": 9e-05, | |
| "loss": 1.7905, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004604758250191865, | |
| "eval_loss": 1.1009039878845215, | |
| "eval_runtime": 274.3445, | |
| "eval_samples_per_second": 6.0, | |
| "eval_steps_per_second": 0.751, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005116398055768739, | |
| "grad_norm": 2.686815023422241, | |
| "learning_rate": 0.0001, | |
| "loss": 2.0176, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005628037861345613, | |
| "grad_norm": 1.8589001893997192, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 1.8315, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0061396776669224865, | |
| "grad_norm": 1.6375495195388794, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.8289, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00665131747249936, | |
| "grad_norm": 1.9399513006210327, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 1.5838, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.007162957278076234, | |
| "grad_norm": 2.0972728729248047, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.514, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007674597083653108, | |
| "grad_norm": 2.4550724029541016, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 1.8727, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008186236889229983, | |
| "grad_norm": 2.246565580368042, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.5098, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008697876694806856, | |
| "grad_norm": 2.1880674362182617, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 1.5074, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00920951650038373, | |
| "grad_norm": 2.00897216796875, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.7004, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00920951650038373, | |
| "eval_loss": 0.8399195671081543, | |
| "eval_runtime": 274.0678, | |
| "eval_samples_per_second": 6.006, | |
| "eval_steps_per_second": 0.752, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009721156305960604, | |
| "grad_norm": 1.782171368598938, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.3817, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.010232796111537478, | |
| "grad_norm": 1.8624811172485352, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.4014, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010744435917114352, | |
| "grad_norm": 2.667515516281128, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 1.771, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.011256075722691225, | |
| "grad_norm": 2.9106290340423584, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.4126, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0117677155282681, | |
| "grad_norm": 2.704364776611328, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 1.3825, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.012279355333844973, | |
| "grad_norm": 2.78434419631958, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.5669, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.012790995139421847, | |
| "grad_norm": 2.526869058609009, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.4226, | |
| "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": 3.30085064245248e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |