| { | |
| "best_metric": 0.6983290314674377, | |
| "best_model_checkpoint": "./xlam_1epoch_pythonic_turn5e-6/checkpoint-294", | |
| "epoch": 0.9981543004798819, | |
| "eval_steps": 42, | |
| "global_step": 338, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.029531192321889995, | |
| "grad_norm": 0.27272307872772217, | |
| "learning_rate": 4.5454545454545455e-06, | |
| "loss": 0.249, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05906238464377999, | |
| "grad_norm": 0.2998972237110138, | |
| "learning_rate": 4.990660391382924e-06, | |
| "loss": 0.2557, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08859357696567, | |
| "grad_norm": 0.20621594786643982, | |
| "learning_rate": 4.958464904721778e-06, | |
| "loss": 0.2502, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11812476928755998, | |
| "grad_norm": 0.11265894770622253, | |
| "learning_rate": 4.903595102807423e-06, | |
| "loss": 0.2291, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12403100775193798, | |
| "eval_loss": 0.7797804474830627, | |
| "eval_runtime": 40.6918, | |
| "eval_samples_per_second": 2.335, | |
| "eval_steps_per_second": 2.335, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.14765596160945, | |
| "grad_norm": 0.27329352498054504, | |
| "learning_rate": 4.826557047444564e-06, | |
| "loss": 0.2228, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17718715393134, | |
| "grad_norm": 0.44345590472221375, | |
| "learning_rate": 4.72806125727857e-06, | |
| "loss": 0.2571, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.20671834625322996, | |
| "grad_norm": 0.364957332611084, | |
| "learning_rate": 4.609016154712806e-06, | |
| "loss": 0.2054, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.23624953857511996, | |
| "grad_norm": 0.39865991473197937, | |
| "learning_rate": 4.470519687568185e-06, | |
| "loss": 0.238, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.24806201550387597, | |
| "eval_loss": 0.7582277655601501, | |
| "eval_runtime": 40.6918, | |
| "eval_samples_per_second": 2.335, | |
| "eval_steps_per_second": 2.335, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.26578073089701, | |
| "grad_norm": 0.45341649651527405, | |
| "learning_rate": 4.3138492027580035e-06, | |
| "loss": 0.1948, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2953119232189, | |
| "grad_norm": 0.40793997049331665, | |
| "learning_rate": 4.140449665372726e-06, | |
| "loss": 0.2363, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.32484311554079, | |
| "grad_norm": 0.4665416479110718, | |
| "learning_rate": 3.951920331829593e-06, | |
| "loss": 0.2035, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.35437430786268, | |
| "grad_norm": 0.2355736345052719, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 0.1848, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.37209302325581395, | |
| "eval_loss": 0.7323265671730042, | |
| "eval_runtime": 40.6881, | |
| "eval_samples_per_second": 2.335, | |
| "eval_steps_per_second": 2.335, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.3839055001845699, | |
| "grad_norm": 0.2675202786922455, | |
| "learning_rate": 3.5365509723521046e-06, | |
| "loss": 0.1868, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.4134366925064599, | |
| "grad_norm": 0.521271824836731, | |
| "learning_rate": 3.3135418800158776e-06, | |
| "loss": 0.2172, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.4429678848283499, | |
| "grad_norm": 0.3350629210472107, | |
| "learning_rate": 3.0830295261835276e-06, | |
| "loss": 0.1834, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.4724990771502399, | |
| "grad_norm": 0.27388790249824524, | |
| "learning_rate": 2.8471399163028102e-06, | |
| "loss": 0.1907, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.49612403100775193, | |
| "eval_loss": 0.7150933742523193, | |
| "eval_runtime": 40.7241, | |
| "eval_samples_per_second": 2.333, | |
| "eval_steps_per_second": 2.333, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.5020302694721299, | |
| "grad_norm": 0.36372843384742737, | |
| "learning_rate": 2.608048650020935e-06, | |
| "loss": 0.1778, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.53156146179402, | |
| "grad_norm": 0.27681082487106323, | |
| "learning_rate": 2.3679608557233246e-06, | |
| "loss": 0.1482, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.5610926541159099, | |
| "grad_norm": 0.28764036297798157, | |
| "learning_rate": 2.129090852730094e-06, | |
| "loss": 0.1521, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5906238464378, | |
| "grad_norm": 0.3415660560131073, | |
| "learning_rate": 1.8936417287249447e-06, | |
| "loss": 0.1634, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6201550387596899, | |
| "grad_norm": 0.4162391722202301, | |
| "learning_rate": 1.6637850207729484e-06, | |
| "loss": 0.2028, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.6201550387596899, | |
| "eval_loss": 0.7053791880607605, | |
| "eval_runtime": 40.7096, | |
| "eval_samples_per_second": 2.334, | |
| "eval_steps_per_second": 2.334, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.64968623108158, | |
| "grad_norm": 0.3097800016403198, | |
| "learning_rate": 1.4416406873283273e-06, | |
| "loss": 0.1813, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.6792174234034699, | |
| "grad_norm": 0.19078122079372406, | |
| "learning_rate": 1.2292575559495143e-06, | |
| "loss": 0.1805, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.70874861572536, | |
| "grad_norm": 0.3096450865268707, | |
| "learning_rate": 1.0285944270513929e-06, | |
| "loss": 0.1666, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.7382798080472499, | |
| "grad_norm": 0.31330665946006775, | |
| "learning_rate": 8.415020079739761e-07, | |
| "loss": 0.1457, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.7441860465116279, | |
| "eval_loss": 0.6999288201332092, | |
| "eval_runtime": 40.6457, | |
| "eval_samples_per_second": 2.337, | |
| "eval_steps_per_second": 2.337, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.7678110003691399, | |
| "grad_norm": 0.28197088837623596, | |
| "learning_rate": 6.697058439888285e-07, | |
| "loss": 0.1615, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.7973421926910299, | |
| "grad_norm": 0.3669886589050293, | |
| "learning_rate": 5.147904036698176e-07, | |
| "loss": 0.143, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.8268733850129198, | |
| "grad_norm": 0.3345685303211212, | |
| "learning_rate": 3.7818446540814014e-07, | |
| "loss": 0.1705, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.8564045773348099, | |
| "grad_norm": 0.3705250322818756, | |
| "learning_rate": 2.611479398511518e-07, | |
| "loss": 0.1507, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.8682170542635659, | |
| "eval_loss": 0.6983290314674377, | |
| "eval_runtime": 40.667, | |
| "eval_samples_per_second": 2.336, | |
| "eval_steps_per_second": 2.336, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.8859357696566998, | |
| "grad_norm": 0.3097485601902008, | |
| "learning_rate": 1.6476024980107392e-07, | |
| "loss": 0.1624, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9154669619785899, | |
| "grad_norm": 0.23429091274738312, | |
| "learning_rate": 8.991037474527897e-08, | |
| "loss": 0.1345, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.9449981543004798, | |
| "grad_norm": 0.43888694047927856, | |
| "learning_rate": 3.728865183701275e-08, | |
| "loss": 0.1846, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.9745293466223699, | |
| "grad_norm": 0.35810691118240356, | |
| "learning_rate": 7.380408945750483e-09, | |
| "loss": 0.1663, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.9922480620155039, | |
| "eval_loss": 0.6983665227890015, | |
| "eval_runtime": 40.727, | |
| "eval_samples_per_second": 2.333, | |
| "eval_steps_per_second": 2.333, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.9981543004798819, | |
| "step": 338, | |
| "total_flos": 6.26298436248168e+18, | |
| "train_loss": 0.1894198331607164, | |
| "train_runtime": 51464.0129, | |
| "train_samples_per_second": 0.211, | |
| "train_steps_per_second": 0.007 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 338, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 42, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.26298436248168e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |