| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.23045267489711935, | |
| "eval_steps": 500, | |
| "global_step": 84, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0027434842249657062, | |
| "grad_norm": 1.902702808380127, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 2.0959, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0054869684499314125, | |
| "grad_norm": 1.8936893939971924, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.099, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00823045267489712, | |
| "grad_norm": 1.9235605001449585, | |
| "learning_rate": 6e-06, | |
| "loss": 2.1045, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010973936899862825, | |
| "grad_norm": 1.7873843908309937, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 2.0144, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013717421124828532, | |
| "grad_norm": 1.8321126699447632, | |
| "learning_rate": 1e-05, | |
| "loss": 2.0872, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01646090534979424, | |
| "grad_norm": 2.0333194732666016, | |
| "learning_rate": 1.2e-05, | |
| "loss": 2.1146, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.019204389574759947, | |
| "grad_norm": 1.763102650642395, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 2.036, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02194787379972565, | |
| "grad_norm": 1.5287824869155884, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 1.984, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.024691358024691357, | |
| "grad_norm": 1.2035481929779053, | |
| "learning_rate": 1.8e-05, | |
| "loss": 1.928, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.027434842249657063, | |
| "grad_norm": 1.0602883100509644, | |
| "learning_rate": 2e-05, | |
| "loss": 1.9322, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03017832647462277, | |
| "grad_norm": 0.9456723928451538, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 1.9257, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03292181069958848, | |
| "grad_norm": 0.7646191120147705, | |
| "learning_rate": 2.4e-05, | |
| "loss": 1.8057, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03566529492455418, | |
| "grad_norm": 0.6718866229057312, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 1.8535, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.038408779149519894, | |
| "grad_norm": 0.5136308073997498, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 1.8533, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0411522633744856, | |
| "grad_norm": 0.4066430628299713, | |
| "learning_rate": 3e-05, | |
| "loss": 1.7867, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0438957475994513, | |
| "grad_norm": 0.3591379225254059, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 1.8729, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04663923182441701, | |
| "grad_norm": 0.3689568340778351, | |
| "learning_rate": 3.4000000000000007e-05, | |
| "loss": 1.8186, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04938271604938271, | |
| "grad_norm": 0.3991197645664215, | |
| "learning_rate": 3.6e-05, | |
| "loss": 1.8485, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05212620027434842, | |
| "grad_norm": 0.3603827655315399, | |
| "learning_rate": 3.8e-05, | |
| "loss": 1.8081, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05486968449931413, | |
| "grad_norm": 0.3805089592933655, | |
| "learning_rate": 4e-05, | |
| "loss": 1.7553, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05761316872427984, | |
| "grad_norm": 0.42597419023513794, | |
| "learning_rate": 4.2e-05, | |
| "loss": 1.8115, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06035665294924554, | |
| "grad_norm": 0.37801623344421387, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 1.7161, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06310013717421124, | |
| "grad_norm": 0.35600143671035767, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 1.7315, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06584362139917696, | |
| "grad_norm": 0.4111214280128479, | |
| "learning_rate": 4.8e-05, | |
| "loss": 1.7091, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06858710562414266, | |
| "grad_norm": 0.4117395579814911, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7026, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07133058984910837, | |
| "grad_norm": 0.4069993197917938, | |
| "learning_rate": 5.2000000000000004e-05, | |
| "loss": 1.6733, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07407407407407407, | |
| "grad_norm": 0.4196024239063263, | |
| "learning_rate": 5.4000000000000005e-05, | |
| "loss": 1.6999, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07681755829903979, | |
| "grad_norm": 0.45915013551712036, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 1.6613, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07956104252400549, | |
| "grad_norm": 0.44673749804496765, | |
| "learning_rate": 5.8e-05, | |
| "loss": 1.7039, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0823045267489712, | |
| "grad_norm": 0.5381506085395813, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5768, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0850480109739369, | |
| "grad_norm": 0.4311385750770569, | |
| "learning_rate": 6.2e-05, | |
| "loss": 1.5598, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0877914951989026, | |
| "grad_norm": 0.38209667801856995, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 1.511, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.09053497942386832, | |
| "grad_norm": 0.35374918580055237, | |
| "learning_rate": 6.6e-05, | |
| "loss": 1.4692, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.09327846364883402, | |
| "grad_norm": 0.4020269215106964, | |
| "learning_rate": 6.800000000000001e-05, | |
| "loss": 1.5276, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.09602194787379972, | |
| "grad_norm": 0.46055856347084045, | |
| "learning_rate": 7e-05, | |
| "loss": 1.4634, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09876543209876543, | |
| "grad_norm": 0.4301123023033142, | |
| "learning_rate": 7.2e-05, | |
| "loss": 1.4151, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.10150891632373114, | |
| "grad_norm": 0.34214499592781067, | |
| "learning_rate": 7.4e-05, | |
| "loss": 1.4451, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.10425240054869685, | |
| "grad_norm": 0.24707239866256714, | |
| "learning_rate": 7.6e-05, | |
| "loss": 1.3434, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.10699588477366255, | |
| "grad_norm": 0.16371050477027893, | |
| "learning_rate": 7.800000000000001e-05, | |
| "loss": 1.4134, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.10973936899862825, | |
| "grad_norm": 0.11528003960847855, | |
| "learning_rate": 8e-05, | |
| "loss": 1.4896, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11248285322359397, | |
| "grad_norm": 0.11622235178947449, | |
| "learning_rate": 8.2e-05, | |
| "loss": 1.3957, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.11522633744855967, | |
| "grad_norm": 0.10983709245920181, | |
| "learning_rate": 8.4e-05, | |
| "loss": 1.421, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11796982167352538, | |
| "grad_norm": 0.10124485194683075, | |
| "learning_rate": 8.6e-05, | |
| "loss": 1.4127, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.12071330589849108, | |
| "grad_norm": 0.10291855037212372, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 1.4187, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.12345679012345678, | |
| "grad_norm": 0.10925430059432983, | |
| "learning_rate": 9e-05, | |
| "loss": 1.3476, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1262002743484225, | |
| "grad_norm": 0.10825473070144653, | |
| "learning_rate": 9.200000000000001e-05, | |
| "loss": 1.4427, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1289437585733882, | |
| "grad_norm": 0.10768264532089233, | |
| "learning_rate": 9.4e-05, | |
| "loss": 1.4292, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.13168724279835392, | |
| "grad_norm": 0.11937709152698517, | |
| "learning_rate": 9.6e-05, | |
| "loss": 1.3234, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.13443072702331962, | |
| "grad_norm": 0.11960555613040924, | |
| "learning_rate": 9.8e-05, | |
| "loss": 1.3566, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.13717421124828533, | |
| "grad_norm": 0.12491138279438019, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4201, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13991769547325103, | |
| "grad_norm": 0.11906778067350388, | |
| "learning_rate": 0.00010200000000000001, | |
| "loss": 1.3745, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.14266117969821673, | |
| "grad_norm": 0.12701214849948883, | |
| "learning_rate": 0.00010400000000000001, | |
| "loss": 1.3592, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.14540466392318244, | |
| "grad_norm": 0.14920316636562347, | |
| "learning_rate": 0.00010600000000000002, | |
| "loss": 1.3139, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 0.157944455742836, | |
| "learning_rate": 0.00010800000000000001, | |
| "loss": 1.3704, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.15089163237311384, | |
| "grad_norm": 0.15193891525268555, | |
| "learning_rate": 0.00011000000000000002, | |
| "loss": 1.3694, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.15363511659807957, | |
| "grad_norm": 0.15829141438007355, | |
| "learning_rate": 0.00011200000000000001, | |
| "loss": 1.3351, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.15637860082304528, | |
| "grad_norm": 0.16939309239387512, | |
| "learning_rate": 0.00011399999999999999, | |
| "loss": 1.3487, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.15912208504801098, | |
| "grad_norm": 0.19683969020843506, | |
| "learning_rate": 0.000116, | |
| "loss": 1.2837, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.16186556927297668, | |
| "grad_norm": 0.17148783802986145, | |
| "learning_rate": 0.000118, | |
| "loss": 1.3372, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.1646090534979424, | |
| "grad_norm": 0.17560726404190063, | |
| "learning_rate": 0.00012, | |
| "loss": 1.3896, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1673525377229081, | |
| "grad_norm": 0.17536282539367676, | |
| "learning_rate": 0.000122, | |
| "loss": 1.4028, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.1700960219478738, | |
| "grad_norm": 0.16491512954235077, | |
| "learning_rate": 0.000124, | |
| "loss": 1.3366, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.1728395061728395, | |
| "grad_norm": 0.1202845573425293, | |
| "learning_rate": 0.000126, | |
| "loss": 1.3201, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.1755829903978052, | |
| "grad_norm": 0.10146432369947433, | |
| "learning_rate": 0.00012800000000000002, | |
| "loss": 1.3083, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.17832647462277093, | |
| "grad_norm": 0.0989551916718483, | |
| "learning_rate": 0.00013000000000000002, | |
| "loss": 1.3216, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.18106995884773663, | |
| "grad_norm": 0.09368593990802765, | |
| "learning_rate": 0.000132, | |
| "loss": 1.3409, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.18381344307270234, | |
| "grad_norm": 0.09617207944393158, | |
| "learning_rate": 0.000134, | |
| "loss": 1.3192, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.18655692729766804, | |
| "grad_norm": 0.08890332281589508, | |
| "learning_rate": 0.00013600000000000003, | |
| "loss": 1.354, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.18930041152263374, | |
| "grad_norm": 0.11371646821498871, | |
| "learning_rate": 0.000138, | |
| "loss": 1.3201, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.19204389574759945, | |
| "grad_norm": 0.09785107523202896, | |
| "learning_rate": 0.00014, | |
| "loss": 1.2413, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.19478737997256515, | |
| "grad_norm": 0.09149904549121857, | |
| "learning_rate": 0.000142, | |
| "loss": 1.2548, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 0.08837990462779999, | |
| "learning_rate": 0.000144, | |
| "loss": 1.3014, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.20027434842249658, | |
| "grad_norm": 0.08963413536548615, | |
| "learning_rate": 0.000146, | |
| "loss": 1.3128, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.2030178326474623, | |
| "grad_norm": 0.08815225213766098, | |
| "learning_rate": 0.000148, | |
| "loss": 1.3321, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.205761316872428, | |
| "grad_norm": 0.09394700825214386, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.3341, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2085048010973937, | |
| "grad_norm": 0.10041660070419312, | |
| "learning_rate": 0.000152, | |
| "loss": 1.2944, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.2112482853223594, | |
| "grad_norm": 0.09344102442264557, | |
| "learning_rate": 0.000154, | |
| "loss": 1.3226, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.2139917695473251, | |
| "grad_norm": 0.09259933233261108, | |
| "learning_rate": 0.00015600000000000002, | |
| "loss": 1.2942, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.2167352537722908, | |
| "grad_norm": 0.09426167607307434, | |
| "learning_rate": 0.00015800000000000002, | |
| "loss": 1.333, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.2194787379972565, | |
| "grad_norm": 0.09674811363220215, | |
| "learning_rate": 0.00016, | |
| "loss": 1.3242, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 0.09802138805389404, | |
| "learning_rate": 0.000162, | |
| "loss": 1.3322, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.22496570644718794, | |
| "grad_norm": 0.09528470784425735, | |
| "learning_rate": 0.000164, | |
| "loss": 1.2384, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.22770919067215364, | |
| "grad_norm": 0.0997876301407814, | |
| "learning_rate": 0.000166, | |
| "loss": 1.3646, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.23045267489711935, | |
| "grad_norm": 0.09820306301116943, | |
| "learning_rate": 0.000168, | |
| "loss": 1.1982, | |
| "step": 84 | |
| } | |
| ], | |
| "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": 1.0405766029849805e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |