| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.5934065934065934, |
| "eval_steps": 500, |
| "global_step": 90, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.006593406593406593, |
| "grad_norm": 0.8349836468696594, |
| "learning_rate": 0.0, |
| "loss": 0.9434, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.013186813186813187, |
| "grad_norm": 0.8700987696647644, |
| "learning_rate": 4e-05, |
| "loss": 0.9905, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.01978021978021978, |
| "grad_norm": 0.9241365194320679, |
| "learning_rate": 8e-05, |
| "loss": 0.9438, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.026373626373626374, |
| "grad_norm": 0.9019892811775208, |
| "learning_rate": 0.00012, |
| "loss": 0.9216, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.03296703296703297, |
| "grad_norm": 0.8872910141944885, |
| "learning_rate": 0.00016, |
| "loss": 0.9374, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.03956043956043956, |
| "grad_norm": 0.5874530076980591, |
| "learning_rate": 0.0002, |
| "loss": 0.7673, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.046153846153846156, |
| "grad_norm": 0.5062956809997559, |
| "learning_rate": 0.00019955654101995565, |
| "loss": 0.8011, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.05274725274725275, |
| "grad_norm": 0.5953829288482666, |
| "learning_rate": 0.00019911308203991133, |
| "loss": 0.8455, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.05934065934065934, |
| "grad_norm": 0.5616072416305542, |
| "learning_rate": 0.00019866962305986697, |
| "loss": 0.8265, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.06593406593406594, |
| "grad_norm": 0.49180087447166443, |
| "learning_rate": 0.00019822616407982261, |
| "loss": 0.8561, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.07252747252747253, |
| "grad_norm": 0.42030951380729675, |
| "learning_rate": 0.00019778270509977829, |
| "loss": 0.8796, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.07912087912087912, |
| "grad_norm": 0.3004567325115204, |
| "learning_rate": 0.00019733924611973393, |
| "loss": 0.8636, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.08571428571428572, |
| "grad_norm": 0.2698984444141388, |
| "learning_rate": 0.0001968957871396896, |
| "loss": 0.718, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.09230769230769231, |
| "grad_norm": 0.25445133447647095, |
| "learning_rate": 0.00019645232815964525, |
| "loss": 0.7235, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.0989010989010989, |
| "grad_norm": 0.22418756783008575, |
| "learning_rate": 0.00019600886917960092, |
| "loss": 0.688, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.1054945054945055, |
| "grad_norm": 0.2096303105354309, |
| "learning_rate": 0.00019556541019955653, |
| "loss": 0.7267, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.11208791208791209, |
| "grad_norm": 0.3029191195964813, |
| "learning_rate": 0.0001951219512195122, |
| "loss": 0.7763, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.11868131868131868, |
| "grad_norm": 0.2644464075565338, |
| "learning_rate": 0.00019467849223946785, |
| "loss": 0.7618, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.12527472527472527, |
| "grad_norm": 0.2536560893058777, |
| "learning_rate": 0.00019423503325942352, |
| "loss": 0.7999, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.13186813186813187, |
| "grad_norm": 0.24718916416168213, |
| "learning_rate": 0.00019379157427937917, |
| "loss": 0.752, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.13846153846153847, |
| "grad_norm": 0.2625150680541992, |
| "learning_rate": 0.00019334811529933484, |
| "loss": 0.736, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.14505494505494507, |
| "grad_norm": 0.32164040207862854, |
| "learning_rate": 0.00019290465631929045, |
| "loss": 0.7043, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.15164835164835164, |
| "grad_norm": 0.3981449604034424, |
| "learning_rate": 0.00019246119733924613, |
| "loss": 0.7057, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.15824175824175823, |
| "grad_norm": 0.3817313015460968, |
| "learning_rate": 0.00019201773835920177, |
| "loss": 0.7413, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.16483516483516483, |
| "grad_norm": 0.29256680607795715, |
| "learning_rate": 0.00019157427937915744, |
| "loss": 0.693, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.17142857142857143, |
| "grad_norm": 0.27523350715637207, |
| "learning_rate": 0.00019113082039911309, |
| "loss": 0.6474, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.17802197802197803, |
| "grad_norm": 0.23511967062950134, |
| "learning_rate": 0.00019068736141906876, |
| "loss": 0.6519, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.18461538461538463, |
| "grad_norm": 0.2961374819278717, |
| "learning_rate": 0.0001902439024390244, |
| "loss": 0.6426, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.1912087912087912, |
| "grad_norm": 0.2760772407054901, |
| "learning_rate": 0.00018980044345898005, |
| "loss": 0.7388, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.1978021978021978, |
| "grad_norm": 0.2285313606262207, |
| "learning_rate": 0.00018935698447893572, |
| "loss": 0.7756, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.2043956043956044, |
| "grad_norm": 0.2657061517238617, |
| "learning_rate": 0.00018891352549889136, |
| "loss": 0.7275, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.210989010989011, |
| "grad_norm": 0.22572828829288483, |
| "learning_rate": 0.00018847006651884703, |
| "loss": 0.6793, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.2175824175824176, |
| "grad_norm": 0.26335304975509644, |
| "learning_rate": 0.00018802660753880268, |
| "loss": 0.7131, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.22417582417582418, |
| "grad_norm": 0.25231942534446716, |
| "learning_rate": 0.00018758314855875832, |
| "loss": 0.7715, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.23076923076923078, |
| "grad_norm": 0.2437426745891571, |
| "learning_rate": 0.00018713968957871397, |
| "loss": 0.7094, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.23736263736263735, |
| "grad_norm": 0.28558826446533203, |
| "learning_rate": 0.00018669623059866964, |
| "loss": 0.6937, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.24395604395604395, |
| "grad_norm": 0.2915894687175751, |
| "learning_rate": 0.00018625277161862528, |
| "loss": 0.7238, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.25054945054945055, |
| "grad_norm": 0.25342074036598206, |
| "learning_rate": 0.00018580931263858095, |
| "loss": 0.7323, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.2571428571428571, |
| "grad_norm": 0.22744007408618927, |
| "learning_rate": 0.0001853658536585366, |
| "loss": 0.703, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.26373626373626374, |
| "grad_norm": 0.25383231043815613, |
| "learning_rate": 0.00018492239467849224, |
| "loss": 0.7093, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2703296703296703, |
| "grad_norm": 0.2194337695837021, |
| "learning_rate": 0.0001844789356984479, |
| "loss": 0.7367, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.27692307692307694, |
| "grad_norm": 0.32021859288215637, |
| "learning_rate": 0.00018403547671840356, |
| "loss": 0.6652, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.2835164835164835, |
| "grad_norm": 0.2328304797410965, |
| "learning_rate": 0.0001835920177383592, |
| "loss": 0.7016, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.29010989010989013, |
| "grad_norm": 0.24166613817214966, |
| "learning_rate": 0.00018314855875831487, |
| "loss": 0.6717, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.2967032967032967, |
| "grad_norm": 0.2733803391456604, |
| "learning_rate": 0.00018270509977827052, |
| "loss": 0.6979, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.3032967032967033, |
| "grad_norm": 0.2689957320690155, |
| "learning_rate": 0.00018226164079822616, |
| "loss": 0.6977, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.3098901098901099, |
| "grad_norm": 0.2698104977607727, |
| "learning_rate": 0.00018181818181818183, |
| "loss": 0.723, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.31648351648351647, |
| "grad_norm": 0.25856417417526245, |
| "learning_rate": 0.00018137472283813748, |
| "loss": 0.723, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.3230769230769231, |
| "grad_norm": 0.22988826036453247, |
| "learning_rate": 0.00018093126385809312, |
| "loss": 0.7356, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.32967032967032966, |
| "grad_norm": 0.24859416484832764, |
| "learning_rate": 0.0001804878048780488, |
| "loss": 0.6671, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.3362637362637363, |
| "grad_norm": 0.24891626834869385, |
| "learning_rate": 0.00018004434589800444, |
| "loss": 0.6628, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.34285714285714286, |
| "grad_norm": 0.22740386426448822, |
| "learning_rate": 0.00017960088691796008, |
| "loss": 0.6377, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.34945054945054943, |
| "grad_norm": 0.2636365294456482, |
| "learning_rate": 0.00017915742793791575, |
| "loss": 0.6901, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.35604395604395606, |
| "grad_norm": 0.2437390238046646, |
| "learning_rate": 0.0001787139689578714, |
| "loss": 0.72, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.3626373626373626, |
| "grad_norm": 0.23658742010593414, |
| "learning_rate": 0.00017827050997782707, |
| "loss": 0.7365, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.36923076923076925, |
| "grad_norm": 0.23923538625240326, |
| "learning_rate": 0.00017782705099778271, |
| "loss": 0.706, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.3758241758241758, |
| "grad_norm": 0.2877054512500763, |
| "learning_rate": 0.00017738359201773839, |
| "loss": 0.7436, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.3824175824175824, |
| "grad_norm": 0.2839520573616028, |
| "learning_rate": 0.000176940133037694, |
| "loss": 0.6779, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.389010989010989, |
| "grad_norm": 0.2308293879032135, |
| "learning_rate": 0.00017649667405764967, |
| "loss": 0.6357, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.3956043956043956, |
| "grad_norm": 0.24402214586734772, |
| "learning_rate": 0.00017605321507760532, |
| "loss": 0.7508, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.4021978021978022, |
| "grad_norm": 0.23816415667533875, |
| "learning_rate": 0.000175609756097561, |
| "loss": 0.7249, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.4087912087912088, |
| "grad_norm": 0.28321942687034607, |
| "learning_rate": 0.00017516629711751663, |
| "loss": 0.7479, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.4153846153846154, |
| "grad_norm": 0.23680296540260315, |
| "learning_rate": 0.0001747228381374723, |
| "loss": 0.6413, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.421978021978022, |
| "grad_norm": 0.23129238188266754, |
| "learning_rate": 0.00017427937915742792, |
| "loss": 0.6786, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "grad_norm": 0.25140181183815, |
| "learning_rate": 0.0001738359201773836, |
| "loss": 0.7167, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.4351648351648352, |
| "grad_norm": 0.27190810441970825, |
| "learning_rate": 0.00017339246119733924, |
| "loss": 0.6267, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.44175824175824174, |
| "grad_norm": 0.23768772184848785, |
| "learning_rate": 0.0001729490022172949, |
| "loss": 0.7397, |
| "step": 67 |
| }, |
| { |
| "epoch": 0.44835164835164837, |
| "grad_norm": 0.2618238031864166, |
| "learning_rate": 0.00017250554323725056, |
| "loss": 0.6987, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.45494505494505494, |
| "grad_norm": 0.24789907038211823, |
| "learning_rate": 0.00017206208425720623, |
| "loss": 0.6223, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.46153846153846156, |
| "grad_norm": 0.2744330167770386, |
| "learning_rate": 0.00017161862527716187, |
| "loss": 0.6964, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.46813186813186813, |
| "grad_norm": 0.23732465505599976, |
| "learning_rate": 0.00017117516629711752, |
| "loss": 0.6524, |
| "step": 71 |
| }, |
| { |
| "epoch": 0.4747252747252747, |
| "grad_norm": 0.2278261035680771, |
| "learning_rate": 0.0001707317073170732, |
| "loss": 0.7437, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.48131868131868133, |
| "grad_norm": 0.24909941852092743, |
| "learning_rate": 0.00017028824833702883, |
| "loss": 0.6955, |
| "step": 73 |
| }, |
| { |
| "epoch": 0.4879120879120879, |
| "grad_norm": 0.3007880449295044, |
| "learning_rate": 0.0001698447893569845, |
| "loss": 0.625, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.4945054945054945, |
| "grad_norm": 0.2338089644908905, |
| "learning_rate": 0.00016940133037694015, |
| "loss": 0.6843, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.5010989010989011, |
| "grad_norm": 0.27349653840065, |
| "learning_rate": 0.00016895787139689582, |
| "loss": 0.6825, |
| "step": 76 |
| }, |
| { |
| "epoch": 0.5076923076923077, |
| "grad_norm": 0.2793181836605072, |
| "learning_rate": 0.00016851441241685144, |
| "loss": 0.6529, |
| "step": 77 |
| }, |
| { |
| "epoch": 0.5142857142857142, |
| "grad_norm": 0.2612224221229553, |
| "learning_rate": 0.0001680709534368071, |
| "loss": 0.6807, |
| "step": 78 |
| }, |
| { |
| "epoch": 0.5208791208791209, |
| "grad_norm": 0.2740105986595154, |
| "learning_rate": 0.00016762749445676275, |
| "loss": 0.6294, |
| "step": 79 |
| }, |
| { |
| "epoch": 0.5274725274725275, |
| "grad_norm": 0.2226412147283554, |
| "learning_rate": 0.00016718403547671842, |
| "loss": 0.6569, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.5340659340659341, |
| "grad_norm": 0.2254134714603424, |
| "learning_rate": 0.00016674057649667407, |
| "loss": 0.6569, |
| "step": 81 |
| }, |
| { |
| "epoch": 0.5406593406593406, |
| "grad_norm": 0.22373083233833313, |
| "learning_rate": 0.00016629711751662974, |
| "loss": 0.6733, |
| "step": 82 |
| }, |
| { |
| "epoch": 0.5472527472527473, |
| "grad_norm": 0.2485770583152771, |
| "learning_rate": 0.00016585365853658536, |
| "loss": 0.6422, |
| "step": 83 |
| }, |
| { |
| "epoch": 0.5538461538461539, |
| "grad_norm": 0.25764942169189453, |
| "learning_rate": 0.00016541019955654103, |
| "loss": 0.6682, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.5604395604395604, |
| "grad_norm": 0.24047411978244781, |
| "learning_rate": 0.00016496674057649667, |
| "loss": 0.7126, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.567032967032967, |
| "grad_norm": 0.21252930164337158, |
| "learning_rate": 0.00016452328159645234, |
| "loss": 0.7109, |
| "step": 86 |
| }, |
| { |
| "epoch": 0.5736263736263736, |
| "grad_norm": 0.25431081652641296, |
| "learning_rate": 0.000164079822616408, |
| "loss": 0.6416, |
| "step": 87 |
| }, |
| { |
| "epoch": 0.5802197802197803, |
| "grad_norm": 0.24909189343452454, |
| "learning_rate": 0.00016363636363636366, |
| "loss": 0.6963, |
| "step": 88 |
| }, |
| { |
| "epoch": 0.5868131868131868, |
| "grad_norm": 0.25534072518348694, |
| "learning_rate": 0.0001631929046563193, |
| "loss": 0.7898, |
| "step": 89 |
| }, |
| { |
| "epoch": 0.5934065934065934, |
| "grad_norm": 0.22847016155719757, |
| "learning_rate": 0.00016274944567627495, |
| "loss": 0.6903, |
| "step": 90 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 456, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 15, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.145108297405645e+16, |
| "train_batch_size": 22, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
