| { | |
| "best_metric": 1.22141432762146, | |
| "best_model_checkpoint": "outputs/checkpoint-45", | |
| "epoch": 1.0, | |
| "eval_steps": 15, | |
| "global_step": 59, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01694915254237288, | |
| "grad_norm": 42.25, | |
| "learning_rate": 0.001, | |
| "loss": 2.0126, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03389830508474576, | |
| "grad_norm": 14.375, | |
| "learning_rate": 0.001, | |
| "loss": 1.8512, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05084745762711865, | |
| "grad_norm": 7.09375, | |
| "learning_rate": 0.001, | |
| "loss": 1.4776, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06779661016949153, | |
| "grad_norm": 6.9375, | |
| "learning_rate": 0.001, | |
| "loss": 1.4508, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0847457627118644, | |
| "grad_norm": 1.5625, | |
| "learning_rate": 0.001, | |
| "loss": 1.342, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1016949152542373, | |
| "grad_norm": 1.5234375, | |
| "learning_rate": 0.001, | |
| "loss": 1.3831, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11864406779661017, | |
| "grad_norm": 3.671875, | |
| "learning_rate": 0.001, | |
| "loss": 1.3233, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.13559322033898305, | |
| "grad_norm": 16.875, | |
| "learning_rate": 0.001, | |
| "loss": 1.8094, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.15254237288135594, | |
| "grad_norm": 6.8125, | |
| "learning_rate": 0.001, | |
| "loss": 1.4678, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1694915254237288, | |
| "grad_norm": 1.6796875, | |
| "learning_rate": 0.001, | |
| "loss": 1.3086, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1864406779661017, | |
| "grad_norm": 1.09375, | |
| "learning_rate": 0.001, | |
| "loss": 1.1842, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2033898305084746, | |
| "grad_norm": 1.28125, | |
| "learning_rate": 0.001, | |
| "loss": 1.2429, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.22033898305084745, | |
| "grad_norm": 1.796875, | |
| "learning_rate": 0.001, | |
| "loss": 1.368, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.23728813559322035, | |
| "grad_norm": 1.09375, | |
| "learning_rate": 0.001, | |
| "loss": 1.2236, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2542372881355932, | |
| "grad_norm": 1.21875, | |
| "learning_rate": 0.001, | |
| "loss": 1.2481, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2542372881355932, | |
| "eval_loss": 1.2657548189163208, | |
| "eval_runtime": 2.241, | |
| "eval_samples_per_second": 83.891, | |
| "eval_steps_per_second": 10.71, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2711864406779661, | |
| "grad_norm": 1.3359375, | |
| "learning_rate": 0.001, | |
| "loss": 1.2124, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.288135593220339, | |
| "grad_norm": 1.34375, | |
| "learning_rate": 0.001, | |
| "loss": 1.3263, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3050847457627119, | |
| "grad_norm": 1.140625, | |
| "learning_rate": 0.001, | |
| "loss": 1.2269, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3220338983050847, | |
| "grad_norm": 1.421875, | |
| "learning_rate": 0.001, | |
| "loss": 1.3701, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3389830508474576, | |
| "grad_norm": 1.53125, | |
| "learning_rate": 0.001, | |
| "loss": 1.2618, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3559322033898305, | |
| "grad_norm": 1.6484375, | |
| "learning_rate": 0.001, | |
| "loss": 1.3644, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3728813559322034, | |
| "grad_norm": 1.4921875, | |
| "learning_rate": 0.001, | |
| "loss": 1.3143, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3898305084745763, | |
| "grad_norm": 1.8125, | |
| "learning_rate": 0.001, | |
| "loss": 1.2497, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.4067796610169492, | |
| "grad_norm": 1.3828125, | |
| "learning_rate": 0.001, | |
| "loss": 1.1473, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.423728813559322, | |
| "grad_norm": 1.109375, | |
| "learning_rate": 0.001, | |
| "loss": 1.1923, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4406779661016949, | |
| "grad_norm": 1.390625, | |
| "learning_rate": 0.001, | |
| "loss": 1.2122, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4576271186440678, | |
| "grad_norm": 1.4375, | |
| "learning_rate": 0.001, | |
| "loss": 1.1393, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4745762711864407, | |
| "grad_norm": 1.1796875, | |
| "learning_rate": 0.001, | |
| "loss": 1.1894, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4915254237288136, | |
| "grad_norm": 7.3125, | |
| "learning_rate": 0.001, | |
| "loss": 1.2592, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5084745762711864, | |
| "grad_norm": 2.109375, | |
| "learning_rate": 0.001, | |
| "loss": 1.2445, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5084745762711864, | |
| "eval_loss": 1.2405431270599365, | |
| "eval_runtime": 2.2457, | |
| "eval_samples_per_second": 83.715, | |
| "eval_steps_per_second": 10.687, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5254237288135594, | |
| "grad_norm": 3.921875, | |
| "learning_rate": 0.001, | |
| "loss": 1.2998, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5423728813559322, | |
| "grad_norm": 39.25, | |
| "learning_rate": 0.001, | |
| "loss": 1.626, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.559322033898305, | |
| "grad_norm": 5.4375, | |
| "learning_rate": 0.001, | |
| "loss": 1.2702, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.576271186440678, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 0.001, | |
| "loss": 1.2658, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5932203389830508, | |
| "grad_norm": 28.5, | |
| "learning_rate": 0.001, | |
| "loss": 1.2946, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6101694915254238, | |
| "grad_norm": 31.25, | |
| "learning_rate": 0.001, | |
| "loss": 1.4802, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6271186440677966, | |
| "grad_norm": 5.59375, | |
| "learning_rate": 0.001, | |
| "loss": 1.5868, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6440677966101694, | |
| "grad_norm": 3.1875, | |
| "learning_rate": 0.001, | |
| "loss": 1.4699, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6610169491525424, | |
| "grad_norm": 2.625, | |
| "learning_rate": 0.001, | |
| "loss": 1.359, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6779661016949152, | |
| "grad_norm": 2.515625, | |
| "learning_rate": 0.001, | |
| "loss": 1.4783, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6949152542372882, | |
| "grad_norm": 1.6640625, | |
| "learning_rate": 0.001, | |
| "loss": 1.304, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.711864406779661, | |
| "grad_norm": 1.6953125, | |
| "learning_rate": 0.001, | |
| "loss": 1.3992, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7288135593220338, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 0.001, | |
| "loss": 1.4327, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.7457627118644068, | |
| "grad_norm": 3.9375, | |
| "learning_rate": 0.001, | |
| "loss": 1.2919, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7627118644067796, | |
| "grad_norm": 8.3125, | |
| "learning_rate": 0.001, | |
| "loss": 1.5113, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7627118644067796, | |
| "eval_loss": 1.22141432762146, | |
| "eval_runtime": 2.2509, | |
| "eval_samples_per_second": 83.524, | |
| "eval_steps_per_second": 10.663, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7796610169491526, | |
| "grad_norm": 3.3125, | |
| "learning_rate": 0.001, | |
| "loss": 1.3297, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7966101694915254, | |
| "grad_norm": 6.25, | |
| "learning_rate": 0.001, | |
| "loss": 1.3788, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8135593220338984, | |
| "grad_norm": 2.359375, | |
| "learning_rate": 0.001, | |
| "loss": 1.3912, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8305084745762712, | |
| "grad_norm": 1.25, | |
| "learning_rate": 0.001, | |
| "loss": 1.3249, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.847457627118644, | |
| "grad_norm": 1.625, | |
| "learning_rate": 0.001, | |
| "loss": 1.3285, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.864406779661017, | |
| "grad_norm": 1.4140625, | |
| "learning_rate": 0.001, | |
| "loss": 1.2734, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.8813559322033898, | |
| "grad_norm": 1.3828125, | |
| "learning_rate": 0.001, | |
| "loss": 1.2826, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.8983050847457628, | |
| "grad_norm": 1.5, | |
| "learning_rate": 0.001, | |
| "loss": 1.1952, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.9152542372881356, | |
| "grad_norm": 1.2109375, | |
| "learning_rate": 0.001, | |
| "loss": 1.4186, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.9322033898305084, | |
| "grad_norm": 1.5078125, | |
| "learning_rate": 0.001, | |
| "loss": 1.3943, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.9491525423728814, | |
| "grad_norm": 1.796875, | |
| "learning_rate": 0.001, | |
| "loss": 1.3948, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.9661016949152542, | |
| "grad_norm": 1.7734375, | |
| "learning_rate": 0.001, | |
| "loss": 1.3806, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.9830508474576272, | |
| "grad_norm": 1.4609375, | |
| "learning_rate": 0.001, | |
| "loss": 1.4173, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.5234375, | |
| "learning_rate": 0.001, | |
| "loss": 1.3113, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 59, | |
| "total_flos": 8392016473620480.0, | |
| "train_loss": 1.3609151254265994, | |
| "train_runtime": 66.1562, | |
| "train_samples_per_second": 28.327, | |
| "train_steps_per_second": 0.892 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 59, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 15, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8392016473620480.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |