| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07374631268436578, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0029498525073746312, | |
| "grad_norm": 2.6695961952209473, | |
| "learning_rate": 1e-05, | |
| "loss": 4.059, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0029498525073746312, | |
| "eval_loss": 2.0677247047424316, | |
| "eval_runtime": 44.3994, | |
| "eval_samples_per_second": 6.442, | |
| "eval_steps_per_second": 0.811, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0058997050147492625, | |
| "grad_norm": 1.780763030052185, | |
| "learning_rate": 2e-05, | |
| "loss": 3.1111, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008849557522123894, | |
| "grad_norm": 3.134167194366455, | |
| "learning_rate": 3e-05, | |
| "loss": 3.5404, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011799410029498525, | |
| "grad_norm": 4.528249263763428, | |
| "learning_rate": 4e-05, | |
| "loss": 4.5936, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.014749262536873156, | |
| "grad_norm": 3.391472339630127, | |
| "learning_rate": 5e-05, | |
| "loss": 4.1795, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.017699115044247787, | |
| "grad_norm": 2.1838064193725586, | |
| "learning_rate": 6e-05, | |
| "loss": 3.0666, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02064896755162242, | |
| "grad_norm": 2.6701786518096924, | |
| "learning_rate": 7e-05, | |
| "loss": 3.5408, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02359882005899705, | |
| "grad_norm": 2.9336118698120117, | |
| "learning_rate": 8e-05, | |
| "loss": 3.67, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02654867256637168, | |
| "grad_norm": 5.5627264976501465, | |
| "learning_rate": 9e-05, | |
| "loss": 3.7612, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02654867256637168, | |
| "eval_loss": 1.4617587327957153, | |
| "eval_runtime": 44.4212, | |
| "eval_samples_per_second": 6.438, | |
| "eval_steps_per_second": 0.81, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.029498525073746312, | |
| "grad_norm": 3.2141149044036865, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1932, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.032448377581120944, | |
| "grad_norm": 2.183711051940918, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 2.4995, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.035398230088495575, | |
| "grad_norm": 2.1251938343048096, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.4882, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.038348082595870206, | |
| "grad_norm": 2.368736743927002, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 1.8657, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04129793510324484, | |
| "grad_norm": 3.1230757236480713, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 2.2617, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04424778761061947, | |
| "grad_norm": 2.4695842266082764, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 2.24, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0471976401179941, | |
| "grad_norm": 3.388068199157715, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.9291, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05014749262536873, | |
| "grad_norm": 3.315546989440918, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 2.5513, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05309734513274336, | |
| "grad_norm": 3.138029098510742, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 2.061, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05309734513274336, | |
| "eval_loss": 1.0333534479141235, | |
| "eval_runtime": 44.4437, | |
| "eval_samples_per_second": 6.435, | |
| "eval_steps_per_second": 0.81, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05604719764011799, | |
| "grad_norm": 2.192615509033203, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.6975, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.058997050147492625, | |
| "grad_norm": 2.5154130458831787, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.3443, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.061946902654867256, | |
| "grad_norm": 2.76058030128479, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 2.3646, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06489675516224189, | |
| "grad_norm": 1.8679944276809692, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 2.1289, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06784660766961652, | |
| "grad_norm": 1.9377188682556152, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 2.1156, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07079646017699115, | |
| "grad_norm": 2.5624561309814453, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.9728, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07374631268436578, | |
| "grad_norm": 1.7926393747329712, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.9014, | |
| "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": 3.173894848512e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |