| { | |
| "best_metric": 0.03272353485226631, | |
| "best_model_checkpoint": "./codellama_sql_model_forestry/checkpoint-400", | |
| "epoch": 2.5006257822277846, | |
| "eval_steps": 100, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05006257822277847, | |
| "grad_norm": 7.185255527496338, | |
| "learning_rate": 0.0001979899497487437, | |
| "loss": 32.456, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10012515644555695, | |
| "grad_norm": 0.1251622438430786, | |
| "learning_rate": 0.0001946398659966499, | |
| "loss": 0.4541, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15018773466833543, | |
| "grad_norm": 0.20880717039108276, | |
| "learning_rate": 0.0001912897822445561, | |
| "loss": 0.3029, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2002503128911139, | |
| "grad_norm": 0.16143666207790375, | |
| "learning_rate": 0.0001879396984924623, | |
| "loss": 0.2429, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2503128911138924, | |
| "grad_norm": 0.13474377989768982, | |
| "learning_rate": 0.0001845896147403685, | |
| "loss": 0.2332, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.30037546933667086, | |
| "grad_norm": 0.17662972211837769, | |
| "learning_rate": 0.0001812395309882747, | |
| "loss": 0.2085, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3504380475594493, | |
| "grad_norm": 0.17377126216888428, | |
| "learning_rate": 0.0001778894472361809, | |
| "loss": 0.1961, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4005006257822278, | |
| "grad_norm": 0.1938253790140152, | |
| "learning_rate": 0.0001745393634840871, | |
| "loss": 0.2032, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.45056320400500627, | |
| "grad_norm": 0.1416705697774887, | |
| "learning_rate": 0.0001711892797319933, | |
| "loss": 0.198, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5006257822277848, | |
| "grad_norm": 0.16024866700172424, | |
| "learning_rate": 0.0001678391959798995, | |
| "loss": 0.185, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5006257822277848, | |
| "eval_loss": 0.042159534990787506, | |
| "eval_runtime": 125.0369, | |
| "eval_samples_per_second": 0.344, | |
| "eval_steps_per_second": 0.344, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5506883604505632, | |
| "grad_norm": 0.1869831383228302, | |
| "learning_rate": 0.0001644891122278057, | |
| "loss": 0.1921, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6007509386733417, | |
| "grad_norm": 0.15546876192092896, | |
| "learning_rate": 0.0001611390284757119, | |
| "loss": 0.1741, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6508135168961201, | |
| "grad_norm": 0.1712736338376999, | |
| "learning_rate": 0.0001577889447236181, | |
| "loss": 0.174, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7008760951188986, | |
| "grad_norm": 0.1676545888185501, | |
| "learning_rate": 0.0001544388609715243, | |
| "loss": 0.1571, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.7509386733416771, | |
| "grad_norm": 0.17751628160476685, | |
| "learning_rate": 0.00015108877721943048, | |
| "loss": 0.1778, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8010012515644556, | |
| "grad_norm": 0.1387346237897873, | |
| "learning_rate": 0.00014773869346733668, | |
| "loss": 0.1532, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.851063829787234, | |
| "grad_norm": 0.17603643238544464, | |
| "learning_rate": 0.00014438860971524288, | |
| "loss": 0.1577, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.9011264080100125, | |
| "grad_norm": 0.1522763967514038, | |
| "learning_rate": 0.00014103852596314908, | |
| "loss": 0.1501, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.951188986232791, | |
| "grad_norm": 0.14780306816101074, | |
| "learning_rate": 0.00013768844221105528, | |
| "loss": 0.1499, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.11175049841403961, | |
| "learning_rate": 0.00013433835845896147, | |
| "loss": 0.1509, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.037981580942869186, | |
| "eval_runtime": 125.2439, | |
| "eval_samples_per_second": 0.343, | |
| "eval_steps_per_second": 0.343, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0500625782227784, | |
| "grad_norm": 0.15822191536426544, | |
| "learning_rate": 0.00013098827470686767, | |
| "loss": 0.1307, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.100125156445557, | |
| "grad_norm": 0.19546131789684296, | |
| "learning_rate": 0.00012763819095477387, | |
| "loss": 0.1189, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.1501877346683353, | |
| "grad_norm": 0.17685039341449738, | |
| "learning_rate": 0.00012428810720268007, | |
| "loss": 0.1296, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.200250312891114, | |
| "grad_norm": 0.17825502157211304, | |
| "learning_rate": 0.00012093802345058627, | |
| "loss": 0.1291, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.2503128911138923, | |
| "grad_norm": 0.19515497982501984, | |
| "learning_rate": 0.00011758793969849247, | |
| "loss": 0.1283, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.300375469336671, | |
| "grad_norm": 0.22185975313186646, | |
| "learning_rate": 0.00011423785594639866, | |
| "loss": 0.1358, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.3504380475594493, | |
| "grad_norm": 0.18015995621681213, | |
| "learning_rate": 0.00011088777219430486, | |
| "loss": 0.1284, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.400500625782228, | |
| "grad_norm": 0.2559189796447754, | |
| "learning_rate": 0.00010753768844221106, | |
| "loss": 0.1188, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.4505632040050063, | |
| "grad_norm": 0.17111122608184814, | |
| "learning_rate": 0.00010418760469011726, | |
| "loss": 0.1243, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.5006257822277846, | |
| "grad_norm": 0.19879887998104095, | |
| "learning_rate": 0.00010083752093802346, | |
| "loss": 0.1364, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.5006257822277846, | |
| "eval_loss": 0.03517143055796623, | |
| "eval_runtime": 124.8471, | |
| "eval_samples_per_second": 0.344, | |
| "eval_steps_per_second": 0.344, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.5506883604505632, | |
| "grad_norm": 0.21239443123340607, | |
| "learning_rate": 9.748743718592965e-05, | |
| "loss": 0.1198, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.6007509386733418, | |
| "grad_norm": 0.21676813066005707, | |
| "learning_rate": 9.413735343383585e-05, | |
| "loss": 0.1309, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.65081351689612, | |
| "grad_norm": 0.2111431062221527, | |
| "learning_rate": 9.078726968174205e-05, | |
| "loss": 0.123, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.7008760951188986, | |
| "grad_norm": 0.17868830263614655, | |
| "learning_rate": 8.743718592964825e-05, | |
| "loss": 0.1133, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.7509386733416772, | |
| "grad_norm": 0.20656318962574005, | |
| "learning_rate": 8.408710217755445e-05, | |
| "loss": 0.119, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.8010012515644556, | |
| "grad_norm": 0.25555238127708435, | |
| "learning_rate": 8.073701842546064e-05, | |
| "loss": 0.1142, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.851063829787234, | |
| "grad_norm": 0.17207714915275574, | |
| "learning_rate": 7.738693467336684e-05, | |
| "loss": 0.1085, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.9011264080100125, | |
| "grad_norm": 0.16670793294906616, | |
| "learning_rate": 7.403685092127304e-05, | |
| "loss": 0.11, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.9511889862327911, | |
| "grad_norm": 0.20777879655361176, | |
| "learning_rate": 7.068676716917924e-05, | |
| "loss": 0.1094, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.20488321781158447, | |
| "learning_rate": 6.733668341708544e-05, | |
| "loss": 0.1182, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.03272353485226631, | |
| "eval_runtime": 125.3359, | |
| "eval_samples_per_second": 0.343, | |
| "eval_steps_per_second": 0.343, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.0500625782227786, | |
| "grad_norm": 0.19323211908340454, | |
| "learning_rate": 6.398659966499163e-05, | |
| "loss": 0.0897, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.1001251564455568, | |
| "grad_norm": 0.21595624089241028, | |
| "learning_rate": 6.063651591289783e-05, | |
| "loss": 0.0761, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.1501877346683353, | |
| "grad_norm": 0.28912344574928284, | |
| "learning_rate": 5.728643216080403e-05, | |
| "loss": 0.0819, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.200250312891114, | |
| "grad_norm": 0.21744051575660706, | |
| "learning_rate": 5.393634840871022e-05, | |
| "loss": 0.0793, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.2503128911138925, | |
| "grad_norm": 0.2404051125049591, | |
| "learning_rate": 5.058626465661642e-05, | |
| "loss": 0.0793, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.3003754693366707, | |
| "grad_norm": 0.2571396827697754, | |
| "learning_rate": 4.723618090452262e-05, | |
| "loss": 0.0841, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.3504380475594493, | |
| "grad_norm": 0.19428133964538574, | |
| "learning_rate": 4.3886097152428815e-05, | |
| "loss": 0.0795, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.400500625782228, | |
| "grad_norm": 0.2305491715669632, | |
| "learning_rate": 4.053601340033501e-05, | |
| "loss": 0.0835, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.4505632040050065, | |
| "grad_norm": 0.25262993574142456, | |
| "learning_rate": 3.7185929648241204e-05, | |
| "loss": 0.0803, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.5006257822277846, | |
| "grad_norm": 0.22605903446674347, | |
| "learning_rate": 3.38358458961474e-05, | |
| "loss": 0.0852, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.5006257822277846, | |
| "eval_loss": 0.03292727842926979, | |
| "eval_runtime": 125.3579, | |
| "eval_samples_per_second": 0.343, | |
| "eval_steps_per_second": 0.343, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 597, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.632027949274235e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |