| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 11, |
| "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": 3.206836223602295, |
| "learning_rate": 0.0, |
| "loss": 3.482421875, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.03389830508474576, |
| "grad_norm": 2.847381353378296, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 3.3974609375, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.05084745762711865, |
| "grad_norm": 1.4680771827697754, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 3.1318359375, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.06779661016949153, |
| "grad_norm": 2.6396775245666504, |
| "learning_rate": 5e-05, |
| "loss": 3.4658203125, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.0847457627118644, |
| "grad_norm": 23.652711868286133, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 3.5107421875, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.1016949152542373, |
| "grad_norm": 48.07037353515625, |
| "learning_rate": 8.333333333333334e-05, |
| "loss": 2.72869873046875, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.11864406779661017, |
| "grad_norm": 4.403927803039551, |
| "learning_rate": 0.0001, |
| "loss": 3.408203125, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.13559322033898305, |
| "grad_norm": 9.01473331451416, |
| "learning_rate": 9.992096792939448e-05, |
| "loss": 3.171875, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.15254237288135594, |
| "grad_norm": 3.0288233757019043, |
| "learning_rate": 9.968414932060826e-05, |
| "loss": 3.2919921875, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.1694915254237288, |
| "grad_norm": 6.546408176422119, |
| "learning_rate": 9.929037600764186e-05, |
| "loss": 2.862548828125, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.1864406779661017, |
| "grad_norm": 13.21324634552002, |
| "learning_rate": 9.874103113361849e-05, |
| "loss": 3.15625, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.2033898305084746, |
| "grad_norm": 4.1443328857421875, |
| "learning_rate": 9.80380442924435e-05, |
| "loss": 2.89453125, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.22033898305084745, |
| "grad_norm": 2.7522470951080322, |
| "learning_rate": 9.718388475103545e-05, |
| "loss": 2.748046875, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.23728813559322035, |
| "grad_norm": 172.51380920410156, |
| "learning_rate": 9.618155277593583e-05, |
| "loss": 2.4990234375, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.2542372881355932, |
| "grad_norm": 645.0208129882812, |
| "learning_rate": 9.503456909476364e-05, |
| "loss": 2.1456298828125, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.2542372881355932, |
| "eval_loss": 2.36572265625, |
| "eval_runtime": 8.5667, |
| "eval_samples_per_second": 0.584, |
| "eval_steps_per_second": 0.117, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.2711864406779661, |
| "grad_norm": 2.9692535400390625, |
| "learning_rate": 9.374696252953101e-05, |
| "loss": 2.47412109375, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.288135593220339, |
| "grad_norm": 4.023967266082764, |
| "learning_rate": 9.23232558452591e-05, |
| "loss": 2.4521484375, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.3050847457627119, |
| "grad_norm": 2.6005005836486816, |
| "learning_rate": 9.07684498636009e-05, |
| "loss": 2.07373046875, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.3220338983050847, |
| "grad_norm": 2.6452620029449463, |
| "learning_rate": 8.90880058972729e-05, |
| "loss": 2.11328125, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.3389830508474576, |
| "grad_norm": 2.769963026046753, |
| "learning_rate": 8.72878265669949e-05, |
| "loss": 1.9404296875, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.3559322033898305, |
| "grad_norm": 1.5048216581344604, |
| "learning_rate": 8.537423506831948e-05, |
| "loss": 1.5035400390625, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.3728813559322034, |
| "grad_norm": 2.622932195663452, |
| "learning_rate": 8.335395296117701e-05, |
| "loss": 1.643157958984375, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.3898305084745763, |
| "grad_norm": 2.5172510147094727, |
| "learning_rate": 8.123407656015125e-05, |
| "loss": 1.89501953125, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.4067796610169492, |
| "grad_norm": 1.6744011640548706, |
| "learning_rate": 7.902205200841559e-05, |
| "loss": 1.7744140625, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.423728813559322, |
| "grad_norm": 3.4982826709747314, |
| "learning_rate": 7.672564912288352e-05, |
| "loss": 1.69921875, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.4406779661016949, |
| "grad_norm": 138.6426544189453, |
| "learning_rate": 7.435293410244342e-05, |
| "loss": 1.6044921875, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.4406779661016949, |
| "eval_loss": 1.561767578125, |
| "eval_runtime": 8.5591, |
| "eval_samples_per_second": 0.584, |
| "eval_steps_per_second": 0.117, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.4576271186440678, |
| "grad_norm": 1.965626835823059, |
| "learning_rate": 7.191224119514072e-05, |
| "loss": 1.5244140625, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.4745762711864407, |
| "grad_norm": 1.6944293975830078, |
| "learning_rate": 6.94121434238277e-05, |
| "loss": 1.533203125, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.4915254237288136, |
| "grad_norm": 3.656485080718994, |
| "learning_rate": 6.686142247310805e-05, |
| "loss": 1.517822265625, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.5084745762711864, |
| "grad_norm": 0.9953148365020752, |
| "learning_rate": 6.426903784334943e-05, |
| "loss": 1.4697265625, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.5254237288135594, |
| "grad_norm": 0.8330620527267456, |
| "learning_rate": 6.164409538011167e-05, |
| "loss": 1.4814453125, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.5423728813559322, |
| "grad_norm": 0.7230986952781677, |
| "learning_rate": 5.899581528953207e-05, |
| "loss": 1.2818603515625, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.559322033898305, |
| "grad_norm": 1.0042716264724731, |
| "learning_rate": 5.633349975201519e-05, |
| "loss": 1.5009765625, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.576271186440678, |
| "grad_norm": 7.553008556365967, |
| "learning_rate": 5.366650024798482e-05, |
| "loss": 1.47021484375, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.5932203389830508, |
| "grad_norm": 0.7747316956520081, |
| "learning_rate": 5.100418471046794e-05, |
| "loss": 1.36279296875, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.6101694915254238, |
| "grad_norm": 0.7788944840431213, |
| "learning_rate": 4.835590461988836e-05, |
| "loss": 1.51953125, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.6271186440677966, |
| "grad_norm": 0.8589951992034912, |
| "learning_rate": 4.573096215665058e-05, |
| "loss": 1.33056640625, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.6271186440677966, |
| "eval_loss": 1.320556640625, |
| "eval_runtime": 8.5885, |
| "eval_samples_per_second": 0.582, |
| "eval_steps_per_second": 0.116, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.6440677966101694, |
| "grad_norm": 677.2100219726562, |
| "learning_rate": 4.3138577526891964e-05, |
| "loss": 1.2919921875, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.6610169491525424, |
| "grad_norm": 0.5605570077896118, |
| "learning_rate": 4.058785657617232e-05, |
| "loss": 1.18408203125, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.6779661016949152, |
| "grad_norm": 389.38153076171875, |
| "learning_rate": 3.8087758804859295e-05, |
| "loss": 1.28271484375, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.6949152542372882, |
| "grad_norm": 0.6740171909332275, |
| "learning_rate": 3.5647065897556596e-05, |
| "loss": 1.31640625, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.711864406779661, |
| "grad_norm": 0.5668186545372009, |
| "learning_rate": 3.327435087711649e-05, |
| "loss": 1.2705078125, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.7288135593220338, |
| "grad_norm": 0.6506308913230896, |
| "learning_rate": 3.097794799158444e-05, |
| "loss": 1.35009765625, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.7457627118644068, |
| "grad_norm": 1.9056968688964844, |
| "learning_rate": 2.8765923439848764e-05, |
| "loss": 1.0797576904296875, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.7627118644067796, |
| "grad_norm": 3.448936939239502, |
| "learning_rate": 2.6646047038823007e-05, |
| "loss": 1.28173828125, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.7796610169491526, |
| "grad_norm": 0.5010473728179932, |
| "learning_rate": 2.4625764931680536e-05, |
| "loss": 1.1314711570739746, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.7966101694915254, |
| "grad_norm": 0.5115064382553101, |
| "learning_rate": 2.271217343300509e-05, |
| "loss": 1.20849609375, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.8135593220338984, |
| "grad_norm": 0.4829571545124054, |
| "learning_rate": 2.0911994102727095e-05, |
| "loss": 1.28466796875, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.8135593220338984, |
| "eval_loss": 1.24169921875, |
| "eval_runtime": 8.578, |
| "eval_samples_per_second": 0.583, |
| "eval_steps_per_second": 0.117, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.8305084745762712, |
| "grad_norm": 0.3891683518886566, |
| "learning_rate": 1.9231550136399102e-05, |
| "loss": 1.206298828125, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.847457627118644, |
| "grad_norm": 0.39190465211868286, |
| "learning_rate": 1.7676744154740922e-05, |
| "loss": 1.257568359375, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.864406779661017, |
| "grad_norm": 0.6265923380851746, |
| "learning_rate": 1.6253037470469e-05, |
| "loss": 1.22509765625, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.8813559322033898, |
| "grad_norm": 1.132917881011963, |
| "learning_rate": 1.4965430905236377e-05, |
| "loss": 1.23193359375, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.8983050847457628, |
| "grad_norm": 1.4995769262313843, |
| "learning_rate": 1.381844722406417e-05, |
| "loss": 1.137939453125, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.9152542372881356, |
| "grad_norm": 0.8267571330070496, |
| "learning_rate": 1.281611524896456e-05, |
| "loss": 1.262939453125, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.9322033898305084, |
| "grad_norm": 0.4488615393638611, |
| "learning_rate": 1.1961955707556493e-05, |
| "loss": 1.243896484375, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.9491525423728814, |
| "grad_norm": 0.7780895233154297, |
| "learning_rate": 1.1258968866381517e-05, |
| "loss": 1.293701171875, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.9661016949152542, |
| "grad_norm": 0.5684336423873901, |
| "learning_rate": 1.0709623992358144e-05, |
| "loss": 1.24169921875, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.9830508474576272, |
| "grad_norm": 1.7781082391738892, |
| "learning_rate": 1.031585067939174e-05, |
| "loss": 1.258056640625, |
| "step": 58 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 40.05562973022461, |
| "learning_rate": 1.007903207060554e-05, |
| "loss": 1.238037109375, |
| "step": 59 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.219970703125, |
| "eval_runtime": 8.5876, |
| "eval_samples_per_second": 0.582, |
| "eval_steps_per_second": 0.116, |
| "step": 59 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 59, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.0731125942761554e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
