| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 15655, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.15969338869370808, | |
| "grad_norm": 0.4899541735649109, | |
| "learning_rate": 2.910507824976046e-06, | |
| "loss": 5.8222, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.31938677738741617, | |
| "grad_norm": 0.08963651955127716, | |
| "learning_rate": 2.8146917917598215e-06, | |
| "loss": 4.9707, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.47908016608112425, | |
| "grad_norm": 0.05247149616479874, | |
| "learning_rate": 2.7188757585435964e-06, | |
| "loss": 4.9317, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.6387735547748323, | |
| "grad_norm": 0.05341716483235359, | |
| "learning_rate": 2.6230597253273713e-06, | |
| "loss": 4.9183, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.7984669434685404, | |
| "grad_norm": 0.07143773138523102, | |
| "learning_rate": 2.5272436921111466e-06, | |
| "loss": 4.8527, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.9581603321622485, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.431427658894922e-06, | |
| "loss": 4.8384, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.1178537208559565, | |
| "grad_norm": 0.041869938373565674, | |
| "learning_rate": 2.335611625678697e-06, | |
| "loss": 4.8368, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.2775471095496647, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.239795592462472e-06, | |
| "loss": 4.8367, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.4372404982433729, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.1441711913126796e-06, | |
| "loss": 4.8323, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.5969338869370808, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.048355158096455e-06, | |
| "loss": 4.8311, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.7566272756307888, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.9525391248802303e-06, | |
| "loss": 4.8316, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.916320664324497, | |
| "grad_norm": 0.018847908824682236, | |
| "learning_rate": 1.856723091664005e-06, | |
| "loss": 4.8319, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.076014053018205, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.7610986905142128e-06, | |
| "loss": 4.8327, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.235707441711913, | |
| "grad_norm": 0.06726948916912079, | |
| "learning_rate": 1.665282657297988e-06, | |
| "loss": 4.8334, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.395400830405621, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.5694666240817628e-06, | |
| "loss": 4.8337, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.5550942190993293, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.4736505908655382e-06, | |
| "loss": 4.8333, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.7147876077930375, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.3780261897157458e-06, | |
| "loss": 4.8341, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.8744809964867457, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.282210156499521e-06, | |
| "loss": 4.8345, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.0341743851804535, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.1863941232832963e-06, | |
| "loss": 4.8347, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.1938677738741617, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.0905780900670712e-06, | |
| "loss": 4.8344, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 3.35356116256787, | |
| "grad_norm": 0.0715227872133255, | |
| "learning_rate": 9.947620568508465e-07, | |
| "loss": 4.8346, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 3.5132545512615776, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.99137655701054e-07, | |
| "loss": 4.8356, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 3.672947939955286, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.033216224848291e-07, | |
| "loss": 4.8365, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 3.832641328648994, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7.075055892686044e-07, | |
| "loss": 4.8364, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 3.992334717342702, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.116895560523795e-07, | |
| "loss": 4.8363, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 4.15202810603641, | |
| "grad_norm": 0.0428263284265995, | |
| "learning_rate": 5.158735228361546e-07, | |
| "loss": 4.8361, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 4.311721494730119, | |
| "grad_norm": 0.024692021310329437, | |
| "learning_rate": 4.200574896199297e-07, | |
| "loss": 4.8366, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 4.471414883423826, | |
| "grad_norm": 0.009164220653474331, | |
| "learning_rate": 3.242414564037049e-07, | |
| "loss": 4.8368, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 4.631108272117534, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.286170552539125e-07, | |
| "loss": 4.8366, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 4.790801660811242, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.3280102203768765e-07, | |
| "loss": 4.837, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 4.9504950495049505, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.698498882146279e-08, | |
| "loss": 4.837, | |
| "step": 15500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 15655, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |