| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 25, | |
| "global_step": 49, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04081632653061224, | |
| "grad_norm": 3.7409868240356445, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 2.4126, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04081632653061224, | |
| "eval_loss": 2.0406322479248047, | |
| "eval_runtime": 0.9858, | |
| "eval_samples_per_second": 50.723, | |
| "eval_steps_per_second": 2.029, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": 4.715200901031494, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 2.083, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.12244897959183673, | |
| "grad_norm": 4.667435646057129, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 1.9379, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 4.7186198234558105, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 1.8942, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.20408163265306123, | |
| "grad_norm": 4.859522342681885, | |
| "learning_rate": 0.00015, | |
| "loss": 1.7121, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.24489795918367346, | |
| "grad_norm": 5.292018413543701, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 1.1783, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 3.016796827316284, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 1.739, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": 1.7277272939682007, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.7616, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3673469387755102, | |
| "grad_norm": 1.7451039552688599, | |
| "learning_rate": 0.00027, | |
| "loss": 0.5854, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.40816326530612246, | |
| "grad_norm": 1.457315444946289, | |
| "learning_rate": 0.0003, | |
| "loss": 0.5902, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4489795918367347, | |
| "grad_norm": 1.1877005100250244, | |
| "learning_rate": 0.0002995135962201315, | |
| "loss": 0.5042, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4897959183673469, | |
| "grad_norm": 1.2287006378173828, | |
| "learning_rate": 0.00029805753939568687, | |
| "loss": 0.4846, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5306122448979592, | |
| "grad_norm": 1.8204301595687866, | |
| "learning_rate": 0.00029564127261390776, | |
| "loss": 1.0965, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 1.368378758430481, | |
| "learning_rate": 0.00029228046629207175, | |
| "loss": 0.5163, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6122448979591837, | |
| "grad_norm": 2.1868021488189697, | |
| "learning_rate": 0.0002879969165488236, | |
| "loss": 0.5014, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6530612244897959, | |
| "grad_norm": 1.1822432279586792, | |
| "learning_rate": 0.0002828184038479814, | |
| "loss": 0.4647, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6938775510204082, | |
| "grad_norm": 1.014186143875122, | |
| "learning_rate": 0.0002767785128315692, | |
| "loss": 0.3608, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7346938775510204, | |
| "grad_norm": 1.0673483610153198, | |
| "learning_rate": 0.00026991641451052517, | |
| "loss": 0.3436, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7755102040816326, | |
| "grad_norm": 1.3452389240264893, | |
| "learning_rate": 0.00026227661222566516, | |
| "loss": 1.0037, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.8163265306122449, | |
| "grad_norm": 1.3451870679855347, | |
| "learning_rate": 0.0002539086530264399, | |
| "loss": 0.4711, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 1.1543673276901245, | |
| "learning_rate": 0.0002448668063393066, | |
| "loss": 0.4119, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8979591836734694, | |
| "grad_norm": 1.121870994567871, | |
| "learning_rate": 0.00023520971200967334, | |
| "loss": 0.4436, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.9387755102040817, | |
| "grad_norm": 1.2241188287734985, | |
| "learning_rate": 0.000225, | |
| "loss": 0.3726, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9795918367346939, | |
| "grad_norm": 1.0626543760299683, | |
| "learning_rate": 0.0002143038842104581, | |
| "loss": 0.3758, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.0204081632653061, | |
| "grad_norm": 1.8895132541656494, | |
| "learning_rate": 0.0002031907330563803, | |
| "loss": 1.1746, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0204081632653061, | |
| "eval_loss": 0.5979710221290588, | |
| "eval_runtime": 0.7424, | |
| "eval_samples_per_second": 67.347, | |
| "eval_steps_per_second": 2.694, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0612244897959184, | |
| "grad_norm": 0.9799502491950989, | |
| "learning_rate": 0.0001917326195874679, | |
| "loss": 0.435, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.1020408163265305, | |
| "grad_norm": 1.122646689414978, | |
| "learning_rate": 0.00018000385406640666, | |
| "loss": 0.2757, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 0.7942773103713989, | |
| "learning_rate": 0.00016808050203829842, | |
| "loss": 0.271, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.183673469387755, | |
| "grad_norm": 0.692020058631897, | |
| "learning_rate": 0.00015603989101641228, | |
| "loss": 0.2172, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.2244897959183674, | |
| "grad_norm": 0.8052120208740234, | |
| "learning_rate": 0.00014396010898358775, | |
| "loss": 0.2598, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2653061224489797, | |
| "grad_norm": 0.927700936794281, | |
| "learning_rate": 0.00013191949796170156, | |
| "loss": 0.5198, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.306122448979592, | |
| "grad_norm": 0.9306784272193909, | |
| "learning_rate": 0.00011999614593359334, | |
| "loss": 0.3138, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.346938775510204, | |
| "grad_norm": 1.0951112508773804, | |
| "learning_rate": 0.0001082673804125321, | |
| "loss": 0.3623, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.3877551020408163, | |
| "grad_norm": 0.8262572884559631, | |
| "learning_rate": 9.680926694361964e-05, | |
| "loss": 0.21, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 0.751383364200592, | |
| "learning_rate": 8.569611578954184e-05, | |
| "loss": 0.2422, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.469387755102041, | |
| "grad_norm": 0.6222977638244629, | |
| "learning_rate": 7.500000000000002e-05, | |
| "loss": 0.1601, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.510204081632653, | |
| "grad_norm": 1.0796877145767212, | |
| "learning_rate": 6.479028799032664e-05, | |
| "loss": 0.5077, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5510204081632653, | |
| "grad_norm": 0.7947916984558105, | |
| "learning_rate": 5.513319366069342e-05, | |
| "loss": 0.3029, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5918367346938775, | |
| "grad_norm": 0.8886685371398926, | |
| "learning_rate": 4.609134697356009e-05, | |
| "loss": 0.2717, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.6326530612244898, | |
| "grad_norm": 0.8579179644584656, | |
| "learning_rate": 3.7723387774334816e-05, | |
| "loss": 0.2594, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6734693877551021, | |
| "grad_norm": 0.8065491914749146, | |
| "learning_rate": 3.0083585489474855e-05, | |
| "loss": 0.2062, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 0.8417931795120239, | |
| "learning_rate": 2.3221487168430806e-05, | |
| "loss": 0.2325, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.7551020408163265, | |
| "grad_norm": 0.9621670246124268, | |
| "learning_rate": 1.718159615201853e-05, | |
| "loss": 0.4371, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7959183673469388, | |
| "grad_norm": 0.8321143388748169, | |
| "learning_rate": 1.2003083451176366e-05, | |
| "loss": 0.2868, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.836734693877551, | |
| "grad_norm": 0.8132133483886719, | |
| "learning_rate": 7.719533707928177e-06, | |
| "loss": 0.2633, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.8775510204081631, | |
| "grad_norm": 0.7980149984359741, | |
| "learning_rate": 4.358727386092198e-06, | |
| "loss": 0.2576, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.9183673469387754, | |
| "grad_norm": 0.7642199993133545, | |
| "learning_rate": 1.942460604313073e-06, | |
| "loss": 0.2237, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.9591836734693877, | |
| "grad_norm": 0.7160183191299438, | |
| "learning_rate": 4.864037798685105e-07, | |
| "loss": 0.1845, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.2111998796463013, | |
| "learning_rate": 0.0, | |
| "loss": 0.3578, | |
| "step": 49 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 49, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.309827495264256e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |