| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 174, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08695652173913043, | |
| "grad_norm": 0.5434810519218445, | |
| "learning_rate": 8e-06, | |
| "loss": 1.8239, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.17391304347826086, | |
| "grad_norm": 0.5637189745903015, | |
| "learning_rate": 1.8e-05, | |
| "loss": 1.8411, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2608695652173913, | |
| "grad_norm": 0.49630191922187805, | |
| "learning_rate": 2.8e-05, | |
| "loss": 1.7664, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.34782608695652173, | |
| "grad_norm": 0.4293997585773468, | |
| "learning_rate": 2.9984341865073467e-05, | |
| "loss": 1.746, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.43478260869565216, | |
| "grad_norm": 0.4636119306087494, | |
| "learning_rate": 2.9920786714609776e-05, | |
| "loss": 1.6808, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5217391304347826, | |
| "grad_norm": 0.46787315607070923, | |
| "learning_rate": 2.9808563059202443e-05, | |
| "loss": 1.6527, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6086956521739131, | |
| "grad_norm": 0.48989933729171753, | |
| "learning_rate": 2.9648036949089453e-05, | |
| "loss": 1.547, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6956521739130435, | |
| "grad_norm": 0.5395526885986328, | |
| "learning_rate": 2.9439731987076293e-05, | |
| "loss": 1.5191, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.782608695652174, | |
| "grad_norm": 0.5619059205055237, | |
| "learning_rate": 2.9184327620652376e-05, | |
| "loss": 1.4313, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8695652173913043, | |
| "grad_norm": 0.6329588890075684, | |
| "learning_rate": 2.88826569257746e-05, | |
| "loss": 1.3837, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.9565217391304348, | |
| "grad_norm": 0.7499159574508667, | |
| "learning_rate": 2.853570388954673e-05, | |
| "loss": 1.3192, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.0347826086956522, | |
| "grad_norm": 0.9072374105453491, | |
| "learning_rate": 2.8144600200657953e-05, | |
| "loss": 1.2751, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.1217391304347826, | |
| "grad_norm": 0.869915783405304, | |
| "learning_rate": 2.771062155804964e-05, | |
| "loss": 1.1411, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.208695652173913, | |
| "grad_norm": 0.9894439578056335, | |
| "learning_rate": 2.7235183509850527e-05, | |
| "loss": 1.1209, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.2956521739130435, | |
| "grad_norm": 1.3562583923339844, | |
| "learning_rate": 2.6719836836152968e-05, | |
| "loss": 1.1144, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.382608695652174, | |
| "grad_norm": 1.0571166276931763, | |
| "learning_rate": 2.616626249069058e-05, | |
| "loss": 1.025, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.4695652173913043, | |
| "grad_norm": 1.101731777191162, | |
| "learning_rate": 2.5576266117916586e-05, | |
| "loss": 0.9973, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.5565217391304347, | |
| "grad_norm": 1.7998214960098267, | |
| "learning_rate": 2.4951772163366876e-05, | |
| "loss": 0.971, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.643478260869565, | |
| "grad_norm": 1.0925252437591553, | |
| "learning_rate": 2.4294817596518718e-05, | |
| "loss": 0.9329, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.7304347826086957, | |
| "grad_norm": 1.5454200506210327, | |
| "learning_rate": 2.360754526661966e-05, | |
| "loss": 0.9672, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.8173913043478263, | |
| "grad_norm": 1.376658320426941, | |
| "learning_rate": 2.289219691315873e-05, | |
| "loss": 0.8261, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.9043478260869566, | |
| "grad_norm": 1.2025381326675415, | |
| "learning_rate": 2.2151105853778124e-05, | |
| "loss": 0.8384, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.991304347826087, | |
| "grad_norm": 1.3411906957626343, | |
| "learning_rate": 2.138668937347609e-05, | |
| "loss": 0.7766, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 2.0695652173913044, | |
| "grad_norm": 1.6666730642318726, | |
| "learning_rate": 2.0601440839925675e-05, | |
| "loss": 0.6619, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.1565217391304348, | |
| "grad_norm": 1.5320314168930054, | |
| "learning_rate": 1.9797921570627614e-05, | |
| "loss": 0.6609, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.243478260869565, | |
| "grad_norm": 1.6747761964797974, | |
| "learning_rate": 1.8978752478425067e-05, | |
| "loss": 0.6227, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.3304347826086955, | |
| "grad_norm": 1.4979124069213867, | |
| "learning_rate": 1.8146605522630642e-05, | |
| "loss": 0.6132, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.417391304347826, | |
| "grad_norm": 1.6996585130691528, | |
| "learning_rate": 1.7304194993650494e-05, | |
| "loss": 0.5993, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.5043478260869563, | |
| "grad_norm": 1.6078176498413086, | |
| "learning_rate": 1.6454268659533224e-05, | |
| "loss": 0.5825, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.591304347826087, | |
| "grad_norm": 1.5988578796386719, | |
| "learning_rate": 1.5599598803321602e-05, | |
| "loss": 0.5731, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.6782608695652175, | |
| "grad_norm": 1.552137851715088, | |
| "learning_rate": 1.4742973180441512e-05, | |
| "loss": 0.5678, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.765217391304348, | |
| "grad_norm": 1.6322020292282104, | |
| "learning_rate": 1.388718592562322e-05, | |
| "loss": 0.5441, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.8521739130434782, | |
| "grad_norm": 1.80694580078125, | |
| "learning_rate": 1.3035028439014606e-05, | |
| "loss": 0.5623, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.9391304347826086, | |
| "grad_norm": 1.6158785820007324, | |
| "learning_rate": 1.2189280281214128e-05, | |
| "loss": 0.5497, | |
| "step": 170 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 290, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 2000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.8228859106308915e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |