| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.5594541910331383, | |
| "eval_steps": 500, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.031189083820662766, | |
| "grad_norm": 0.0576171875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.674, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06237816764132553, | |
| "grad_norm": 0.052490234375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5118, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0935672514619883, | |
| "grad_norm": 0.03857421875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4572, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12475633528265107, | |
| "grad_norm": 0.039794921875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4645, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15594541910331383, | |
| "grad_norm": 0.0537109375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4772, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1871345029239766, | |
| "grad_norm": 0.059814453125, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4466, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21832358674463936, | |
| "grad_norm": 0.0478515625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4365, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.24951267056530213, | |
| "grad_norm": 0.138671875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4622, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2807017543859649, | |
| "grad_norm": 0.046875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3409, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.31189083820662766, | |
| "grad_norm": 0.0289306640625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3158, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.34307992202729043, | |
| "grad_norm": 0.029541015625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3236, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.3742690058479532, | |
| "grad_norm": 0.0274658203125, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3273, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.40545808966861596, | |
| "grad_norm": 0.031494140625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3142, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.43664717348927873, | |
| "grad_norm": 0.0269775390625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3276, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4678362573099415, | |
| "grad_norm": 0.02978515625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.334, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.49902534113060426, | |
| "grad_norm": 0.0703125, | |
| "learning_rate": 0.0001, | |
| "loss": 0.356, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.530214424951267, | |
| "grad_norm": 0.03271484375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3176, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.5614035087719298, | |
| "grad_norm": 0.0322265625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2829, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.02587890625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2984, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.6237816764132553, | |
| "grad_norm": 0.0296630859375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3067, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6549707602339181, | |
| "grad_norm": 0.0264892578125, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2979, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.6861598440545809, | |
| "grad_norm": 0.02783203125, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3012, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.7173489278752436, | |
| "grad_norm": 0.031494140625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3222, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.7485380116959064, | |
| "grad_norm": 0.06982421875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3439, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7797270955165692, | |
| "grad_norm": 0.031982421875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2875, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.8109161793372319, | |
| "grad_norm": 0.029296875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2803, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 0.029541015625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2999, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.8732943469785575, | |
| "grad_norm": 0.02734375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2986, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9044834307992202, | |
| "grad_norm": 0.028076171875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.302, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.935672514619883, | |
| "grad_norm": 0.0322265625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2936, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.9668615984405458, | |
| "grad_norm": 0.034423828125, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3017, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.9980506822612085, | |
| "grad_norm": 0.060546875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3486, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.0292397660818713, | |
| "grad_norm": 0.033935546875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2867, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.060428849902534, | |
| "grad_norm": 0.031494140625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2628, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.0916179337231968, | |
| "grad_norm": 0.0289306640625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.278, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.1228070175438596, | |
| "grad_norm": 0.031982421875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2915, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.1539961013645224, | |
| "grad_norm": 0.031005859375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2902, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.03271484375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2785, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.2163742690058479, | |
| "grad_norm": 0.042236328125, | |
| "learning_rate": 0.0001, | |
| "loss": 0.295, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.2475633528265107, | |
| "grad_norm": 0.05615234375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3039, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.2787524366471734, | |
| "grad_norm": 0.03759765625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2725, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.3099415204678362, | |
| "grad_norm": 0.035400390625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2738, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.341130604288499, | |
| "grad_norm": 0.031494140625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2861, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.3723196881091617, | |
| "grad_norm": 0.036865234375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2859, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.4035087719298245, | |
| "grad_norm": 0.03515625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.285, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.4346978557504872, | |
| "grad_norm": 0.03466796875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2713, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.46588693957115, | |
| "grad_norm": 0.042724609375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2982, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.4970760233918128, | |
| "grad_norm": 0.0673828125, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3026, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.5282651072124755, | |
| "grad_norm": 0.04150390625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2916, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.5594541910331383, | |
| "grad_norm": 0.034912109375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2548, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.5594541910331383, | |
| "step": 250, | |
| "total_flos": 4.824681746497536e+17, | |
| "train_loss": 0.3312075719833374, | |
| "train_runtime": 19317.2857, | |
| "train_samples_per_second": 0.828, | |
| "train_steps_per_second": 0.013 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 90, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.824681746497536e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |