| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0025351112913856917, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00010140445165542768, | |
| "grad_norm": 8.04444694519043, | |
| "learning_rate": 1e-05, | |
| "loss": 15.717, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00010140445165542768, | |
| "eval_loss": 8.308691024780273, | |
| "eval_runtime": 2539.4691, | |
| "eval_samples_per_second": 3.27, | |
| "eval_steps_per_second": 0.409, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00020280890331085536, | |
| "grad_norm": 7.203917980194092, | |
| "learning_rate": 2e-05, | |
| "loss": 14.1263, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000304213354966283, | |
| "grad_norm": 7.024128437042236, | |
| "learning_rate": 3e-05, | |
| "loss": 15.3502, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004056178066217107, | |
| "grad_norm": 8.651090621948242, | |
| "learning_rate": 4e-05, | |
| "loss": 17.9991, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005070222582771384, | |
| "grad_norm": 7.7485151290893555, | |
| "learning_rate": 5e-05, | |
| "loss": 17.5751, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000608426709932566, | |
| "grad_norm": 8.532367706298828, | |
| "learning_rate": 6e-05, | |
| "loss": 15.1637, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0007098311615879937, | |
| "grad_norm": 9.773588180541992, | |
| "learning_rate": 7e-05, | |
| "loss": 15.8518, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0008112356132434214, | |
| "grad_norm": 14.653646469116211, | |
| "learning_rate": 8e-05, | |
| "loss": 13.1565, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.000912640064898849, | |
| "grad_norm": 13.511507987976074, | |
| "learning_rate": 9e-05, | |
| "loss": 16.018, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000912640064898849, | |
| "eval_loss": 6.607507705688477, | |
| "eval_runtime": 2532.554, | |
| "eval_samples_per_second": 3.279, | |
| "eval_steps_per_second": 0.41, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0010140445165542768, | |
| "grad_norm": 14.838384628295898, | |
| "learning_rate": 0.0001, | |
| "loss": 13.0172, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0011154489682097045, | |
| "grad_norm": 10.868144035339355, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 11.4453, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001216853419865132, | |
| "grad_norm": 12.606634140014648, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 10.4203, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0013182578715205597, | |
| "grad_norm": 13.766972541809082, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 7.9603, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0014196623231759874, | |
| "grad_norm": 9.558253288269043, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 6.3498, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0015210667748314151, | |
| "grad_norm": 17.133962631225586, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 7.24, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0016224712264868428, | |
| "grad_norm": 12.555543899536133, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 5.7092, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0017238756781422703, | |
| "grad_norm": 13.254968643188477, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 5.4401, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.001825280129797698, | |
| "grad_norm": 15.194214820861816, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 3.2668, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.001825280129797698, | |
| "eval_loss": 1.8347294330596924, | |
| "eval_runtime": 2535.231, | |
| "eval_samples_per_second": 3.276, | |
| "eval_steps_per_second": 0.41, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0019266845814531258, | |
| "grad_norm": 12.147256851196289, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.8558, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0020280890331085535, | |
| "grad_norm": 12.598443031311035, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.3306, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0021294934847639812, | |
| "grad_norm": 13.3068265914917, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 2.489, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.002230897936419409, | |
| "grad_norm": 12.66015338897705, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 2.642, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0023323023880748367, | |
| "grad_norm": 14.067517280578613, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 2.4228, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.002433706839730264, | |
| "grad_norm": 15.590002059936523, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 3.6261, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0025351112913856917, | |
| "grad_norm": 17.668914794921875, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.724, | |
| "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": 6.15735600611328e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |