| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006549646319098768, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00026198585276395077, | |
| "grad_norm": 8.06531810760498, | |
| "learning_rate": 1e-05, | |
| "loss": 5.4551, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00026198585276395077, | |
| "eval_loss": 5.552332878112793, | |
| "eval_runtime": 352.8496, | |
| "eval_samples_per_second": 9.112, | |
| "eval_steps_per_second": 1.139, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005239717055279015, | |
| "grad_norm": 7.758414268493652, | |
| "learning_rate": 2e-05, | |
| "loss": 5.0221, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007859575582918522, | |
| "grad_norm": 9.16843318939209, | |
| "learning_rate": 3e-05, | |
| "loss": 5.2987, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001047943411055803, | |
| "grad_norm": 9.832208633422852, | |
| "learning_rate": 4e-05, | |
| "loss": 5.4247, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013099292638197536, | |
| "grad_norm": 7.5622029304504395, | |
| "learning_rate": 5e-05, | |
| "loss": 4.8809, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0015719151165837044, | |
| "grad_norm": 6.857791423797607, | |
| "learning_rate": 6e-05, | |
| "loss": 4.3287, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0018339009693476552, | |
| "grad_norm": 9.882523536682129, | |
| "learning_rate": 7e-05, | |
| "loss": 4.8656, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002095886822111606, | |
| "grad_norm": 9.96164608001709, | |
| "learning_rate": 8e-05, | |
| "loss": 4.2639, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002357872674875557, | |
| "grad_norm": 9.73707103729248, | |
| "learning_rate": 9e-05, | |
| "loss": 2.8029, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002357872674875557, | |
| "eval_loss": 2.4069762229919434, | |
| "eval_runtime": 352.9261, | |
| "eval_samples_per_second": 9.11, | |
| "eval_steps_per_second": 1.139, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0026198585276395073, | |
| "grad_norm": 12.502920150756836, | |
| "learning_rate": 0.0001, | |
| "loss": 2.4574, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002881844380403458, | |
| "grad_norm": 10.564509391784668, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 2.0574, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003143830233167409, | |
| "grad_norm": 11.528499603271484, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.5046, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0034058160859313596, | |
| "grad_norm": 5.828344345092773, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 0.8369, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0036678019386953103, | |
| "grad_norm": 3.885608196258545, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.7905, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0039297877914592615, | |
| "grad_norm": 4.5050787925720215, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.6641, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004191773644223212, | |
| "grad_norm": 2.9515435695648193, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.5273, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004453759496987163, | |
| "grad_norm": 3.4887335300445557, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 0.5964, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004715745349751114, | |
| "grad_norm": 5.508411407470703, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.6012, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004715745349751114, | |
| "eval_loss": 0.5490872263908386, | |
| "eval_runtime": 352.8627, | |
| "eval_samples_per_second": 9.111, | |
| "eval_steps_per_second": 1.139, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004977731202515065, | |
| "grad_norm": 4.160599231719971, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.5502, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0052397170552790145, | |
| "grad_norm": 3.6146748065948486, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.4695, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005501702908042965, | |
| "grad_norm": 4.098548412322998, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.6587, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005763688760806916, | |
| "grad_norm": 5.742251396179199, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.7347, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006025674613570867, | |
| "grad_norm": 3.5661041736602783, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 0.4111, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006287660466334818, | |
| "grad_norm": 2.88602614402771, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.5704, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006549646319098768, | |
| "grad_norm": 2.903674602508545, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.5034, | |
| "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": 1.85471820890112e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |