| { | |
| "best_metric": 0.19687849283218384, | |
| "best_model_checkpoint": "autotrain-y5fnj-qjq2l/checkpoint-66", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 66, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.045454545454545456, | |
| "grad_norm": 10.229093551635742, | |
| "learning_rate": 7.142857142857143e-06, | |
| "loss": 0.2103, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": 22.845165252685547, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 1.0428, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.13636363636363635, | |
| "grad_norm": 4.096180438995361, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 0.1254, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 17.625638961791992, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 0.934, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.22727272727272727, | |
| "grad_norm": 12.085053443908691, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.8395, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2727272727272727, | |
| "grad_norm": 18.615018844604492, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 0.5229, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3181818181818182, | |
| "grad_norm": 18.63450050354004, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5533, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 17.580198287963867, | |
| "learning_rate": 4.915254237288136e-05, | |
| "loss": 0.8831, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4090909090909091, | |
| "grad_norm": 8.56959056854248, | |
| "learning_rate": 4.8305084745762714e-05, | |
| "loss": 0.0529, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 16.458581924438477, | |
| "learning_rate": 4.745762711864407e-05, | |
| "loss": 0.676, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 18.144201278686523, | |
| "learning_rate": 4.6610169491525425e-05, | |
| "loss": 0.6531, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 5.568901062011719, | |
| "learning_rate": 4.5762711864406784e-05, | |
| "loss": 0.1753, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5909090909090909, | |
| "grad_norm": 8.597810745239258, | |
| "learning_rate": 4.491525423728814e-05, | |
| "loss": 0.5251, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6363636363636364, | |
| "grad_norm": 6.5929694175720215, | |
| "learning_rate": 4.4067796610169495e-05, | |
| "loss": 0.1306, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6818181818181818, | |
| "grad_norm": 5.372793674468994, | |
| "learning_rate": 4.3220338983050854e-05, | |
| "loss": 0.3919, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 12.74032974243164, | |
| "learning_rate": 4.2372881355932206e-05, | |
| "loss": 0.6617, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.7727272727272727, | |
| "grad_norm": 4.323923110961914, | |
| "learning_rate": 4.152542372881356e-05, | |
| "loss": 0.5658, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8181818181818182, | |
| "grad_norm": 10.929731369018555, | |
| "learning_rate": 4.067796610169492e-05, | |
| "loss": 0.7611, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8636363636363636, | |
| "grad_norm": 7.1887006759643555, | |
| "learning_rate": 3.983050847457627e-05, | |
| "loss": 0.1684, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 5.684032440185547, | |
| "learning_rate": 3.898305084745763e-05, | |
| "loss": 0.5265, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9545454545454546, | |
| "grad_norm": 13.379312515258789, | |
| "learning_rate": 3.813559322033898e-05, | |
| "loss": 0.9614, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 7.999670028686523, | |
| "learning_rate": 3.728813559322034e-05, | |
| "loss": 0.5465, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_explained_variance": 0.03604179620742798, | |
| "eval_loss": 0.2765257656574249, | |
| "eval_mae": 0.449463814496994, | |
| "eval_mse": 0.2765257656574249, | |
| "eval_r2": -0.037507448771466834, | |
| "eval_rmse": 0.525857150554657, | |
| "eval_runtime": 0.6632, | |
| "eval_samples_per_second": 66.345, | |
| "eval_steps_per_second": 4.524, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.0454545454545454, | |
| "grad_norm": 7.3439531326293945, | |
| "learning_rate": 3.644067796610169e-05, | |
| "loss": 0.3011, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0909090909090908, | |
| "grad_norm": 5.934049129486084, | |
| "learning_rate": 3.559322033898305e-05, | |
| "loss": 0.4443, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.1363636363636362, | |
| "grad_norm": 13.472294807434082, | |
| "learning_rate": 3.474576271186441e-05, | |
| "loss": 1.0194, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1818181818181819, | |
| "grad_norm": 3.9795279502868652, | |
| "learning_rate": 3.389830508474576e-05, | |
| "loss": 0.4727, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.2272727272727273, | |
| "grad_norm": 14.359926223754883, | |
| "learning_rate": 3.305084745762712e-05, | |
| "loss": 0.147, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.2727272727272727, | |
| "grad_norm": 12.326262474060059, | |
| "learning_rate": 3.2203389830508473e-05, | |
| "loss": 0.8002, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.3181818181818181, | |
| "grad_norm": 9.748495101928711, | |
| "learning_rate": 3.135593220338983e-05, | |
| "loss": 0.7462, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.3636363636363638, | |
| "grad_norm": 7.03469705581665, | |
| "learning_rate": 3.050847457627119e-05, | |
| "loss": 0.1601, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.4090909090909092, | |
| "grad_norm": 83.44405364990234, | |
| "learning_rate": 2.9661016949152544e-05, | |
| "loss": 1.3339, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.4545454545454546, | |
| "grad_norm": 10.450496673583984, | |
| "learning_rate": 2.88135593220339e-05, | |
| "loss": 0.5066, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 17.28018569946289, | |
| "learning_rate": 2.7966101694915255e-05, | |
| "loss": 0.1735, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.5454545454545454, | |
| "grad_norm": 9.559082984924316, | |
| "learning_rate": 2.711864406779661e-05, | |
| "loss": 0.138, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.5909090909090908, | |
| "grad_norm": 4.343846797943115, | |
| "learning_rate": 2.627118644067797e-05, | |
| "loss": 0.3694, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.6363636363636362, | |
| "grad_norm": 3.035878896713257, | |
| "learning_rate": 2.5423728813559322e-05, | |
| "loss": 0.172, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.6818181818181817, | |
| "grad_norm": 8.587645530700684, | |
| "learning_rate": 2.457627118644068e-05, | |
| "loss": 0.6394, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.7272727272727273, | |
| "grad_norm": 4.444578647613525, | |
| "learning_rate": 2.3728813559322036e-05, | |
| "loss": 0.5123, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.7727272727272727, | |
| "grad_norm": 13.137991905212402, | |
| "learning_rate": 2.2881355932203392e-05, | |
| "loss": 0.8485, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.8181818181818183, | |
| "grad_norm": 3.9930429458618164, | |
| "learning_rate": 2.2033898305084748e-05, | |
| "loss": 0.4104, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.8636363636363638, | |
| "grad_norm": 12.926916122436523, | |
| "learning_rate": 2.1186440677966103e-05, | |
| "loss": 0.133, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.9090909090909092, | |
| "grad_norm": 340.0639953613281, | |
| "learning_rate": 2.033898305084746e-05, | |
| "loss": 0.2554, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.9545454545454546, | |
| "grad_norm": 3.31027889251709, | |
| "learning_rate": 1.9491525423728814e-05, | |
| "loss": 0.1767, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 4.212459564208984, | |
| "learning_rate": 1.864406779661017e-05, | |
| "loss": 0.3367, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_explained_variance": 0.19774705171585083, | |
| "eval_loss": 0.23613856732845306, | |
| "eval_mae": 0.4021577537059784, | |
| "eval_mse": 0.23613858222961426, | |
| "eval_r2": 0.11402264383641758, | |
| "eval_rmse": 0.48594093322753906, | |
| "eval_runtime": 0.1551, | |
| "eval_samples_per_second": 283.767, | |
| "eval_steps_per_second": 19.348, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.0454545454545454, | |
| "grad_norm": 12.102192878723145, | |
| "learning_rate": 1.7796610169491526e-05, | |
| "loss": 0.1745, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.090909090909091, | |
| "grad_norm": 9.342068672180176, | |
| "learning_rate": 1.694915254237288e-05, | |
| "loss": 0.7482, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.1363636363636362, | |
| "grad_norm": 9.230262756347656, | |
| "learning_rate": 1.6101694915254237e-05, | |
| "loss": 0.5335, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.1818181818181817, | |
| "grad_norm": 9.847858428955078, | |
| "learning_rate": 1.5254237288135596e-05, | |
| "loss": 0.7199, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.227272727272727, | |
| "grad_norm": 15.958962440490723, | |
| "learning_rate": 1.440677966101695e-05, | |
| "loss": 0.1243, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.2727272727272725, | |
| "grad_norm": 4.7927680015563965, | |
| "learning_rate": 1.3559322033898305e-05, | |
| "loss": 0.3531, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.3181818181818183, | |
| "grad_norm": 9.752751350402832, | |
| "learning_rate": 1.2711864406779661e-05, | |
| "loss": 0.5788, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.3636363636363638, | |
| "grad_norm": 57.86676025390625, | |
| "learning_rate": 1.1864406779661018e-05, | |
| "loss": 0.5495, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.409090909090909, | |
| "grad_norm": 14.14869499206543, | |
| "learning_rate": 1.1016949152542374e-05, | |
| "loss": 0.3548, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.4545454545454546, | |
| "grad_norm": 11.623541831970215, | |
| "learning_rate": 1.016949152542373e-05, | |
| "loss": 0.1877, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 18.557632446289062, | |
| "learning_rate": 9.322033898305085e-06, | |
| "loss": 0.1552, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.5454545454545454, | |
| "grad_norm": 12.741007804870605, | |
| "learning_rate": 8.47457627118644e-06, | |
| "loss": 0.2064, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.590909090909091, | |
| "grad_norm": 14.985441207885742, | |
| "learning_rate": 7.627118644067798e-06, | |
| "loss": 0.5428, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.6363636363636362, | |
| "grad_norm": 6.256850719451904, | |
| "learning_rate": 6.779661016949153e-06, | |
| "loss": 0.4934, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.6818181818181817, | |
| "grad_norm": 13.29955005645752, | |
| "learning_rate": 5.932203389830509e-06, | |
| "loss": 0.1479, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.7272727272727275, | |
| "grad_norm": 11.591996192932129, | |
| "learning_rate": 5.084745762711865e-06, | |
| "loss": 0.4157, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.7727272727272725, | |
| "grad_norm": 6.75338077545166, | |
| "learning_rate": 4.23728813559322e-06, | |
| "loss": 0.3989, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.8181818181818183, | |
| "grad_norm": 20.437047958374023, | |
| "learning_rate": 3.3898305084745763e-06, | |
| "loss": 1.0043, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.8636363636363638, | |
| "grad_norm": 9.836654663085938, | |
| "learning_rate": 2.5423728813559323e-06, | |
| "loss": 0.0952, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.909090909090909, | |
| "grad_norm": 8.069482803344727, | |
| "learning_rate": 1.6949152542372882e-06, | |
| "loss": 0.2437, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.9545454545454546, | |
| "grad_norm": 4.515679359436035, | |
| "learning_rate": 8.474576271186441e-07, | |
| "loss": 0.0323, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 5.198877334594727, | |
| "learning_rate": 0.0, | |
| "loss": 0.4612, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_explained_variance": 0.26253634691238403, | |
| "eval_loss": 0.19687849283218384, | |
| "eval_mae": 0.2855921685695648, | |
| "eval_mse": 0.19687849283218384, | |
| "eval_r2": 0.2613240842619654, | |
| "eval_rmse": 0.4437099099159241, | |
| "eval_runtime": 0.1522, | |
| "eval_samples_per_second": 289.029, | |
| "eval_steps_per_second": 19.706, | |
| "step": 66 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 66, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 34730347474944.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |