| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.8850574712643677, |
| "eval_steps": 6, |
| "global_step": 42, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.04597701149425287, |
| "grad_norm": 2.537923574447632, |
| "learning_rate": 0.0001, |
| "loss": 1.4151, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.04597701149425287, |
| "eval_loss": 0.6549283862113953, |
| "eval_runtime": 59.8262, |
| "eval_samples_per_second": 3.31, |
| "eval_steps_per_second": 0.418, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.09195402298850575, |
| "grad_norm": 2.5883562564849854, |
| "learning_rate": 0.0002, |
| "loss": 1.3772, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.13793103448275862, |
| "grad_norm": 2.2641923427581787, |
| "learning_rate": 0.0001996917333733128, |
| "loss": 1.3153, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.1839080459770115, |
| "grad_norm": 5.304536819458008, |
| "learning_rate": 0.00019876883405951377, |
| "loss": 1.1035, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.22988505747126436, |
| "grad_norm": 1.074016809463501, |
| "learning_rate": 0.00019723699203976766, |
| "loss": 0.9059, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.27586206896551724, |
| "grad_norm": 0.8219733834266663, |
| "learning_rate": 0.00019510565162951537, |
| "loss": 0.8678, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.27586206896551724, |
| "eval_loss": 0.6351205706596375, |
| "eval_runtime": 59.9835, |
| "eval_samples_per_second": 3.301, |
| "eval_steps_per_second": 0.417, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.3218390804597701, |
| "grad_norm": 1.478880524635315, |
| "learning_rate": 0.0001923879532511287, |
| "loss": 0.8782, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.367816091954023, |
| "grad_norm": 0.7757106423377991, |
| "learning_rate": 0.0001891006524188368, |
| "loss": 0.7993, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.41379310344827586, |
| "grad_norm": 0.5512004494667053, |
| "learning_rate": 0.00018526401643540922, |
| "loss": 0.7126, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.45977011494252873, |
| "grad_norm": 1.5733872652053833, |
| "learning_rate": 0.00018090169943749476, |
| "loss": 0.685, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.5057471264367817, |
| "grad_norm": 0.34443506598472595, |
| "learning_rate": 0.0001760405965600031, |
| "loss": 0.653, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.5517241379310345, |
| "grad_norm": 0.5645097494125366, |
| "learning_rate": 0.00017071067811865476, |
| "loss": 0.6408, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5517241379310345, |
| "eval_loss": 0.6028693318367004, |
| "eval_runtime": 59.4134, |
| "eval_samples_per_second": 3.333, |
| "eval_steps_per_second": 0.421, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5977011494252874, |
| "grad_norm": 0.5011037588119507, |
| "learning_rate": 0.00016494480483301836, |
| "loss": 0.6326, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6436781609195402, |
| "grad_norm": 0.2876424789428711, |
| "learning_rate": 0.00015877852522924732, |
| "loss": 0.6937, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.6896551724137931, |
| "grad_norm": 0.47212648391723633, |
| "learning_rate": 0.0001522498564715949, |
| "loss": 0.6298, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.735632183908046, |
| "grad_norm": 0.6836615800857544, |
| "learning_rate": 0.00014539904997395468, |
| "loss": 0.5569, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.7816091954022989, |
| "grad_norm": 0.26638293266296387, |
| "learning_rate": 0.000138268343236509, |
| "loss": 0.6057, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.8275862068965517, |
| "grad_norm": 0.5527795553207397, |
| "learning_rate": 0.00013090169943749476, |
| "loss": 0.6546, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.8275862068965517, |
| "eval_loss": 0.5754240155220032, |
| "eval_runtime": 59.3448, |
| "eval_samples_per_second": 3.336, |
| "eval_steps_per_second": 0.421, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.8735632183908046, |
| "grad_norm": 0.3253306746482849, |
| "learning_rate": 0.00012334453638559057, |
| "loss": 0.5521, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.9195402298850575, |
| "grad_norm": 0.17234736680984497, |
| "learning_rate": 0.0001156434465040231, |
| "loss": 0.5802, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.9655172413793104, |
| "grad_norm": 0.2543017864227295, |
| "learning_rate": 0.0001078459095727845, |
| "loss": 0.5579, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.0114942528735633, |
| "grad_norm": 0.8507859706878662, |
| "learning_rate": 0.0001, |
| "loss": 0.5795, |
| "step": 22 |
| }, |
| { |
| "epoch": 1.0114942528735633, |
| "grad_norm": 0.29268795251846313, |
| "learning_rate": 9.215409042721552e-05, |
| "loss": 0.6311, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.0574712643678161, |
| "grad_norm": 0.18724839389324188, |
| "learning_rate": 8.435655349597689e-05, |
| "loss": 0.574, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.0574712643678161, |
| "eval_loss": 0.5620841979980469, |
| "eval_runtime": 59.4173, |
| "eval_samples_per_second": 3.332, |
| "eval_steps_per_second": 0.421, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.103448275862069, |
| "grad_norm": 0.21775011718273163, |
| "learning_rate": 7.66554636144095e-05, |
| "loss": 0.5818, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.1494252873563218, |
| "grad_norm": 0.24518676102161407, |
| "learning_rate": 6.909830056250527e-05, |
| "loss": 0.5618, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.1954022988505748, |
| "grad_norm": 0.24137045443058014, |
| "learning_rate": 6.173165676349103e-05, |
| "loss": 0.6078, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.2413793103448276, |
| "grad_norm": 0.17265664041042328, |
| "learning_rate": 5.4600950026045326e-05, |
| "loss": 0.5907, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.2873563218390804, |
| "grad_norm": 0.1558091938495636, |
| "learning_rate": 4.7750143528405126e-05, |
| "loss": 0.553, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "grad_norm": 0.15223024785518646, |
| "learning_rate": 4.12214747707527e-05, |
| "loss": 0.5518, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "eval_loss": 0.5595065951347351, |
| "eval_runtime": 59.4325, |
| "eval_samples_per_second": 3.332, |
| "eval_steps_per_second": 0.421, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.3793103448275863, |
| "grad_norm": 0.25727611780166626, |
| "learning_rate": 3.5055195166981645e-05, |
| "loss": 0.5463, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.4252873563218391, |
| "grad_norm": 0.13202741742134094, |
| "learning_rate": 2.9289321881345254e-05, |
| "loss": 0.5598, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.471264367816092, |
| "grad_norm": 0.20626722276210785, |
| "learning_rate": 2.3959403439996907e-05, |
| "loss": 0.5242, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.5172413793103448, |
| "grad_norm": 0.16128551959991455, |
| "learning_rate": 1.9098300562505266e-05, |
| "loss": 0.5715, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.5632183908045976, |
| "grad_norm": 0.346206396818161, |
| "learning_rate": 1.4735983564590783e-05, |
| "loss": 0.5265, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.6091954022988506, |
| "grad_norm": 0.1324978768825531, |
| "learning_rate": 1.0899347581163221e-05, |
| "loss": 0.5446, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.6091954022988506, |
| "eval_loss": 0.5576122403144836, |
| "eval_runtime": 59.5124, |
| "eval_samples_per_second": 3.327, |
| "eval_steps_per_second": 0.42, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.6551724137931034, |
| "grad_norm": 0.1254015415906906, |
| "learning_rate": 7.612046748871327e-06, |
| "loss": 0.5739, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.7011494252873565, |
| "grad_norm": 0.18170268833637238, |
| "learning_rate": 4.8943483704846475e-06, |
| "loss": 0.5717, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.7471264367816093, |
| "grad_norm": 0.12662401795387268, |
| "learning_rate": 2.7630079602323442e-06, |
| "loss": 0.5424, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.793103448275862, |
| "grad_norm": 0.1479385495185852, |
| "learning_rate": 1.231165940486234e-06, |
| "loss": 0.563, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.839080459770115, |
| "grad_norm": 0.13152529299259186, |
| "learning_rate": 3.0826662668720364e-07, |
| "loss": 0.5698, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.8850574712643677, |
| "grad_norm": 0.17284046113491058, |
| "learning_rate": 0.0, |
| "loss": 0.6227, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.8850574712643677, |
| "eval_loss": 0.5568149089813232, |
| "eval_runtime": 59.8384, |
| "eval_samples_per_second": 3.309, |
| "eval_steps_per_second": 0.418, |
| "step": 42 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 42, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 21, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.3746008314177126e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
