| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.5842293906810037, | |
| "eval_steps": 500, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14336917562724014, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019936113105200085, | |
| "loss": 25.3924, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2867383512544803, | |
| "grad_norm": 3.884701728820801, | |
| "learning_rate": 0.00019745268727865774, | |
| "loss": 8.0947, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.43010752688172044, | |
| "grad_norm": 4.083174705505371, | |
| "learning_rate": 0.00019387338576538744, | |
| "loss": 8.0048, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5734767025089605, | |
| "grad_norm": 8.547293663024902, | |
| "learning_rate": 0.00018881364488135448, | |
| "loss": 8.2356, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7168458781362007, | |
| "grad_norm": 5.096670150756836, | |
| "learning_rate": 0.00018235325976284275, | |
| "loss": 7.6645, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8602150537634409, | |
| "grad_norm": 2.093186855316162, | |
| "learning_rate": 0.00017459411454241822, | |
| "loss": 6.8675, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.003584229390681, | |
| "grad_norm": 6.611547946929932, | |
| "learning_rate": 0.00016565857557529566, | |
| "loss": 7.6999, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.146953405017921, | |
| "grad_norm": 8.38244915008545, | |
| "learning_rate": 0.00015568756164881882, | |
| "loss": 5.8161, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.2903225806451613, | |
| "grad_norm": 7.428552150726318, | |
| "learning_rate": 0.00014483832160900326, | |
| "loss": 5.076, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.4336917562724014, | |
| "grad_norm": 9.673376083374023, | |
| "learning_rate": 0.00013328195445229868, | |
| "loss": 5.8924, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.5770609318996416, | |
| "grad_norm": 9.069914817810059, | |
| "learning_rate": 0.00012120071099220549, | |
| "loss": 11.4614, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.7204301075268817, | |
| "grad_norm": 0.6971492767333984, | |
| "learning_rate": 0.00010878511965507434, | |
| "loss": 6.7866, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.863799283154122, | |
| "grad_norm": 5.74509334564209, | |
| "learning_rate": 9.623098173300654e-05, | |
| "loss": 5.4278, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.007168458781362, | |
| "grad_norm": 6.082172870635986, | |
| "learning_rate": 8.497744108792429e-05, | |
| "loss": 6.2175, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.150537634408602, | |
| "grad_norm": 9.069826126098633, | |
| "learning_rate": 7.270480644826749e-05, | |
| "loss": 3.6583, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.293906810035842, | |
| "grad_norm": 5.0468926429748535, | |
| "learning_rate": 6.086263331627976e-05, | |
| "loss": 7.1881, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.4372759856630823, | |
| "grad_norm": 8.837244987487793, | |
| "learning_rate": 4.9637679836423924e-05, | |
| "loss": 5.8196, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.5806451612903225, | |
| "grad_norm": 6.962499618530273, | |
| "learning_rate": 3.920697023053949e-05, | |
| "loss": 6.0987, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.7240143369175627, | |
| "grad_norm": 7.161827564239502, | |
| "learning_rate": 2.9735003020115092e-05, | |
| "loss": 6.0444, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.867383512544803, | |
| "grad_norm": 4.73717737197876, | |
| "learning_rate": 2.137115678633811e-05, | |
| "loss": 5.409, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.010752688172043, | |
| "grad_norm": 4.852635860443115, | |
| "learning_rate": 1.4247334380634792e-05, | |
| "loss": 3.4152, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.154121863799283, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.475882737908248e-06, | |
| "loss": 2.9892, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.2974910394265233, | |
| "grad_norm": 5.022617816925049, | |
| "learning_rate": 4.147821098262405e-06, | |
| "loss": 3.2551, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.4408602150537635, | |
| "grad_norm": 8.784795761108398, | |
| "learning_rate": 1.3314055792131964e-06, | |
| "loss": 3.7666, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.5842293906810037, | |
| "grad_norm": 13.812480926513672, | |
| "learning_rate": 7.105273594107953e-08, | |
| "loss": 7.4014, | |
| "step": 250 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 20000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 553129082880000.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |