| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.205761316872428, | |
| "eval_steps": 500, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0027434842249657062, | |
| "grad_norm": 0.6255580186843872, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 2.1501, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0054869684499314125, | |
| "grad_norm": 0.5966613292694092, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.1396, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00823045267489712, | |
| "grad_norm": 0.6047211289405823, | |
| "learning_rate": 6e-06, | |
| "loss": 2.1381, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010973936899862825, | |
| "grad_norm": 0.5786992311477661, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 2.0521, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013717421124828532, | |
| "grad_norm": 0.5930487513542175, | |
| "learning_rate": 1e-05, | |
| "loss": 2.1488, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01646090534979424, | |
| "grad_norm": 0.6468656063079834, | |
| "learning_rate": 1.2e-05, | |
| "loss": 2.1839, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.019204389574759947, | |
| "grad_norm": 0.6152164340019226, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 2.1315, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02194787379972565, | |
| "grad_norm": 0.5863370299339294, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 2.0977, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.024691358024691357, | |
| "grad_norm": 0.5273774862289429, | |
| "learning_rate": 1.8e-05, | |
| "loss": 2.0164, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.027434842249657063, | |
| "grad_norm": 0.539458155632019, | |
| "learning_rate": 2e-05, | |
| "loss": 2.0963, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03017832647462277, | |
| "grad_norm": 0.5333603620529175, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 2.0824, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03292181069958848, | |
| "grad_norm": 0.505551815032959, | |
| "learning_rate": 2.4e-05, | |
| "loss": 1.995, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03566529492455418, | |
| "grad_norm": 0.523439347743988, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 2.0304, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.038408779149519894, | |
| "grad_norm": 0.471587210893631, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 2.021, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0411522633744856, | |
| "grad_norm": 0.4423275887966156, | |
| "learning_rate": 3e-05, | |
| "loss": 1.9335, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0438957475994513, | |
| "grad_norm": 0.42515936493873596, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 2.022, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04663923182441701, | |
| "grad_norm": 0.41880151629447937, | |
| "learning_rate": 3.4000000000000007e-05, | |
| "loss": 1.9723, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04938271604938271, | |
| "grad_norm": 0.4344858229160309, | |
| "learning_rate": 3.6e-05, | |
| "loss": 2.0162, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05212620027434842, | |
| "grad_norm": 0.3777664601802826, | |
| "learning_rate": 3.8e-05, | |
| "loss": 1.9406, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05486968449931413, | |
| "grad_norm": 0.3823831081390381, | |
| "learning_rate": 4e-05, | |
| "loss": 1.9227, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05761316872427984, | |
| "grad_norm": 0.39637988805770874, | |
| "learning_rate": 4.2e-05, | |
| "loss": 1.9796, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06035665294924554, | |
| "grad_norm": 0.3595951795578003, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 1.8776, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06310013717421124, | |
| "grad_norm": 0.3291175365447998, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 1.8456, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06584362139917696, | |
| "grad_norm": 0.3699107766151428, | |
| "learning_rate": 4.8e-05, | |
| "loss": 1.8606, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06858710562414266, | |
| "grad_norm": 0.36269885301589966, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8443, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07133058984910837, | |
| "grad_norm": 0.3507707118988037, | |
| "learning_rate": 5.2000000000000004e-05, | |
| "loss": 1.7648, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07407407407407407, | |
| "grad_norm": 0.3639073371887207, | |
| "learning_rate": 5.4000000000000005e-05, | |
| "loss": 1.8047, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07681755829903979, | |
| "grad_norm": 0.3715658485889435, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 1.7764, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07956104252400549, | |
| "grad_norm": 0.3636416792869568, | |
| "learning_rate": 5.8e-05, | |
| "loss": 1.8089, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0823045267489712, | |
| "grad_norm": 0.4226425290107727, | |
| "learning_rate": 6e-05, | |
| "loss": 1.7236, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0850480109739369, | |
| "grad_norm": 0.37769123911857605, | |
| "learning_rate": 6.2e-05, | |
| "loss": 1.6935, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0877914951989026, | |
| "grad_norm": 0.37444913387298584, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 1.6441, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.09053497942386832, | |
| "grad_norm": 0.37308382987976074, | |
| "learning_rate": 6.6e-05, | |
| "loss": 1.6189, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.09327846364883402, | |
| "grad_norm": 0.4107051193714142, | |
| "learning_rate": 6.800000000000001e-05, | |
| "loss": 1.662, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.09602194787379972, | |
| "grad_norm": 0.4351920783519745, | |
| "learning_rate": 7e-05, | |
| "loss": 1.6044, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09876543209876543, | |
| "grad_norm": 0.4590749740600586, | |
| "learning_rate": 7.2e-05, | |
| "loss": 1.5397, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.10150891632373114, | |
| "grad_norm": 0.43422356247901917, | |
| "learning_rate": 7.4e-05, | |
| "loss": 1.5517, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.10425240054869685, | |
| "grad_norm": 0.44985321164131165, | |
| "learning_rate": 7.6e-05, | |
| "loss": 1.4565, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.10699588477366255, | |
| "grad_norm": 0.4231052100658417, | |
| "learning_rate": 7.800000000000001e-05, | |
| "loss": 1.4592, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.10973936899862825, | |
| "grad_norm": 0.3938014507293701, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5119, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11248285322359397, | |
| "grad_norm": 0.4007266163825989, | |
| "learning_rate": 8.2e-05, | |
| "loss": 1.4205, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.11522633744855967, | |
| "grad_norm": 0.40789809823036194, | |
| "learning_rate": 8.4e-05, | |
| "loss": 1.44, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11796982167352538, | |
| "grad_norm": 0.3244912326335907, | |
| "learning_rate": 8.6e-05, | |
| "loss": 1.3924, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.12071330589849108, | |
| "grad_norm": 0.34083986282348633, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 1.4029, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.12345679012345678, | |
| "grad_norm": 0.36940997838974, | |
| "learning_rate": 9e-05, | |
| "loss": 1.333, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1262002743484225, | |
| "grad_norm": 0.35098233819007874, | |
| "learning_rate": 9.200000000000001e-05, | |
| "loss": 1.4171, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1289437585733882, | |
| "grad_norm": 0.3776918053627014, | |
| "learning_rate": 9.4e-05, | |
| "loss": 1.3849, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.13168724279835392, | |
| "grad_norm": 0.48279502987861633, | |
| "learning_rate": 9.6e-05, | |
| "loss": 1.329, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.13443072702331962, | |
| "grad_norm": 0.4614526033401489, | |
| "learning_rate": 9.8e-05, | |
| "loss": 1.3562, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.13717421124828533, | |
| "grad_norm": 0.3900231122970581, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3945, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13991769547325103, | |
| "grad_norm": 0.20536381006240845, | |
| "learning_rate": 0.00010200000000000001, | |
| "loss": 1.3483, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.14266117969821673, | |
| "grad_norm": 0.15070989727973938, | |
| "learning_rate": 0.00010400000000000001, | |
| "loss": 1.3259, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.14540466392318244, | |
| "grad_norm": 0.14189720153808594, | |
| "learning_rate": 0.00010600000000000002, | |
| "loss": 1.2869, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 0.14223229885101318, | |
| "learning_rate": 0.00010800000000000001, | |
| "loss": 1.3437, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.15089163237311384, | |
| "grad_norm": 0.13781367242336273, | |
| "learning_rate": 0.00011000000000000002, | |
| "loss": 1.3451, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.15363511659807957, | |
| "grad_norm": 0.11993853747844696, | |
| "learning_rate": 0.00011200000000000001, | |
| "loss": 1.3052, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.15637860082304528, | |
| "grad_norm": 0.11463834345340729, | |
| "learning_rate": 0.00011399999999999999, | |
| "loss": 1.3202, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.15912208504801098, | |
| "grad_norm": 0.12319689244031906, | |
| "learning_rate": 0.000116, | |
| "loss": 1.2739, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.16186556927297668, | |
| "grad_norm": 0.11980075389146805, | |
| "learning_rate": 0.000118, | |
| "loss": 1.3162, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.1646090534979424, | |
| "grad_norm": 0.11416748911142349, | |
| "learning_rate": 0.00012, | |
| "loss": 1.3558, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1673525377229081, | |
| "grad_norm": 0.12114512920379639, | |
| "learning_rate": 0.000122, | |
| "loss": 1.3582, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.1700960219478738, | |
| "grad_norm": 0.11863748729228973, | |
| "learning_rate": 0.000124, | |
| "loss": 1.2973, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.1728395061728395, | |
| "grad_norm": 0.10819629579782486, | |
| "learning_rate": 0.000126, | |
| "loss": 1.291, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.1755829903978052, | |
| "grad_norm": 0.11032682657241821, | |
| "learning_rate": 0.00012800000000000002, | |
| "loss": 1.2807, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.17832647462277093, | |
| "grad_norm": 0.10899264365434647, | |
| "learning_rate": 0.00013000000000000002, | |
| "loss": 1.2973, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.18106995884773663, | |
| "grad_norm": 0.1106266900897026, | |
| "learning_rate": 0.000132, | |
| "loss": 1.2992, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.18381344307270234, | |
| "grad_norm": 0.11511031538248062, | |
| "learning_rate": 0.000134, | |
| "loss": 1.301, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.18655692729766804, | |
| "grad_norm": 0.10725060850381851, | |
| "learning_rate": 0.00013600000000000003, | |
| "loss": 1.3199, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.18930041152263374, | |
| "grad_norm": 0.1098162978887558, | |
| "learning_rate": 0.000138, | |
| "loss": 1.2724, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.19204389574759945, | |
| "grad_norm": 0.11557920277118683, | |
| "learning_rate": 0.00014, | |
| "loss": 1.2343, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.19478737997256515, | |
| "grad_norm": 0.1220446228981018, | |
| "learning_rate": 0.000142, | |
| "loss": 1.2399, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 0.11786019057035446, | |
| "learning_rate": 0.000144, | |
| "loss": 1.2704, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.20027434842249658, | |
| "grad_norm": 0.11220725625753403, | |
| "learning_rate": 0.000146, | |
| "loss": 1.2782, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.2030178326474623, | |
| "grad_norm": 0.10791537165641785, | |
| "learning_rate": 0.000148, | |
| "loss": 1.304, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.205761316872428, | |
| "grad_norm": 0.12175633758306503, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.3144, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 364, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.139644296272282e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |