| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08503401360544217, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0017006802721088435, | |
| "eval_loss": 0.6790878772735596, | |
| "eval_runtime": 30.7826, | |
| "eval_samples_per_second": 32.161, | |
| "eval_steps_per_second": 4.028, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00510204081632653, | |
| "grad_norm": 0.29884544014930725, | |
| "learning_rate": 3e-05, | |
| "loss": 0.6448, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008503401360544218, | |
| "eval_loss": 0.6690245866775513, | |
| "eval_runtime": 29.9344, | |
| "eval_samples_per_second": 33.072, | |
| "eval_steps_per_second": 4.142, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01020408163265306, | |
| "grad_norm": 0.3204270005226135, | |
| "learning_rate": 6e-05, | |
| "loss": 0.684, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015306122448979591, | |
| "grad_norm": 0.33724015951156616, | |
| "learning_rate": 9e-05, | |
| "loss": 0.685, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.017006802721088437, | |
| "eval_loss": 0.6461840867996216, | |
| "eval_runtime": 30.1061, | |
| "eval_samples_per_second": 32.884, | |
| "eval_steps_per_second": 4.119, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02040816326530612, | |
| "grad_norm": 0.38525715470314026, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.6202, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.025510204081632654, | |
| "grad_norm": 0.2738827168941498, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6247, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.025510204081632654, | |
| "eval_loss": 0.6376128196716309, | |
| "eval_runtime": 30.1654, | |
| "eval_samples_per_second": 32.819, | |
| "eval_steps_per_second": 4.111, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.030612244897959183, | |
| "grad_norm": 0.27250945568084717, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.6256, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.034013605442176874, | |
| "eval_loss": 0.631576418876648, | |
| "eval_runtime": 30.1788, | |
| "eval_samples_per_second": 32.804, | |
| "eval_steps_per_second": 4.109, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03571428571428571, | |
| "grad_norm": 0.2690052390098572, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.6719, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04081632653061224, | |
| "grad_norm": 0.24357149004936218, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.6188, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04251700680272109, | |
| "eval_loss": 0.6278196573257446, | |
| "eval_runtime": 30.1206, | |
| "eval_samples_per_second": 32.868, | |
| "eval_steps_per_second": 4.117, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04591836734693878, | |
| "grad_norm": 0.26157546043395996, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.6177, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05102040816326531, | |
| "grad_norm": 0.2460842728614807, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6157, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05102040816326531, | |
| "eval_loss": 0.6252167820930481, | |
| "eval_runtime": 30.1482, | |
| "eval_samples_per_second": 32.838, | |
| "eval_steps_per_second": 4.113, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05612244897959184, | |
| "grad_norm": 0.252172589302063, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.6398, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05952380952380952, | |
| "eval_loss": 0.6236237287521362, | |
| "eval_runtime": 30.1893, | |
| "eval_samples_per_second": 32.793, | |
| "eval_steps_per_second": 4.107, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.061224489795918366, | |
| "grad_norm": 0.2600609064102173, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.5937, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0663265306122449, | |
| "grad_norm": 0.24371257424354553, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.627, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06802721088435375, | |
| "eval_loss": 0.6226524114608765, | |
| "eval_runtime": 30.1439, | |
| "eval_samples_per_second": 32.842, | |
| "eval_steps_per_second": 4.114, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07142857142857142, | |
| "grad_norm": 0.2628726661205292, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.6496, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07653061224489796, | |
| "grad_norm": 0.24390390515327454, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.6305, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07653061224489796, | |
| "eval_loss": 0.6220273971557617, | |
| "eval_runtime": 30.195, | |
| "eval_samples_per_second": 32.787, | |
| "eval_steps_per_second": 4.107, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": 0.24077658355236053, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.637, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08503401360544217, | |
| "eval_loss": 0.6219064593315125, | |
| "eval_runtime": 30.1818, | |
| "eval_samples_per_second": 32.801, | |
| "eval_steps_per_second": 4.108, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.449170690899968e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |