| { |
| "best_global_step": 500, |
| "best_metric": 0.21088281273841858, |
| "best_model_checkpoint": "./qwen2-7b-math-coder/checkpoint-500", |
| "epoch": 0.22904260192395787, |
| "eval_steps": 500, |
| "global_step": 500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.004580852038479157, |
| "grad_norm": 3.668745756149292, |
| "learning_rate": 4.5e-06, |
| "loss": 2.0337, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.009161704076958314, |
| "grad_norm": 3.277991533279419, |
| "learning_rate": 9.5e-06, |
| "loss": 1.7448, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.013742556115437472, |
| "grad_norm": 2.6093215942382812, |
| "learning_rate": 1.45e-05, |
| "loss": 1.2869, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.01832340815391663, |
| "grad_norm": 1.7964814901351929, |
| "learning_rate": 1.9500000000000003e-05, |
| "loss": 0.9077, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.022904260192395786, |
| "grad_norm": 1.5602203607559204, |
| "learning_rate": 2.45e-05, |
| "loss": 0.5228, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.027485112230874943, |
| "grad_norm": 2.1516997814178467, |
| "learning_rate": 2.95e-05, |
| "loss": 0.3872, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.0320659642693541, |
| "grad_norm": 1.4016958475112915, |
| "learning_rate": 3.45e-05, |
| "loss": 0.3371, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.03664681630783326, |
| "grad_norm": 1.5028544664382935, |
| "learning_rate": 3.9500000000000005e-05, |
| "loss": 0.31, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.04122766834631241, |
| "grad_norm": 1.7520164251327515, |
| "learning_rate": 4.4500000000000004e-05, |
| "loss": 0.2495, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.04580852038479157, |
| "grad_norm": 0.7592225074768066, |
| "learning_rate": 4.9500000000000004e-05, |
| "loss": 0.238, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.050389372423270726, |
| "grad_norm": 1.602748990058899, |
| "learning_rate": 4.978396543446952e-05, |
| "loss": 0.2472, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.054970224461749886, |
| "grad_norm": 0.8727825880050659, |
| "learning_rate": 4.954392702832453e-05, |
| "loss": 0.2455, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.05955107650022904, |
| "grad_norm": 0.8755759596824646, |
| "learning_rate": 4.930388862217955e-05, |
| "loss": 0.2514, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.0641319285387082, |
| "grad_norm": 1.3854660987854004, |
| "learning_rate": 4.906385021603457e-05, |
| "loss": 0.2415, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.06871278057718735, |
| "grad_norm": 0.6988345384597778, |
| "learning_rate": 4.8823811809889585e-05, |
| "loss": 0.248, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.07329363261566652, |
| "grad_norm": 0.7716445326805115, |
| "learning_rate": 4.8583773403744604e-05, |
| "loss": 0.2289, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.07787448465414568, |
| "grad_norm": 0.618770956993103, |
| "learning_rate": 4.8343734997599615e-05, |
| "loss": 0.2631, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.08245533669262482, |
| "grad_norm": 0.311239093542099, |
| "learning_rate": 4.8103696591454634e-05, |
| "loss": 0.2291, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.08703618873110398, |
| "grad_norm": 0.6665637493133545, |
| "learning_rate": 4.786365818530965e-05, |
| "loss": 0.2227, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.09161704076958314, |
| "grad_norm": 0.7171844840049744, |
| "learning_rate": 4.762361977916467e-05, |
| "loss": 0.2291, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.0961978928080623, |
| "grad_norm": 0.606952965259552, |
| "learning_rate": 4.738358137301969e-05, |
| "loss": 0.2496, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.10077874484654145, |
| "grad_norm": 0.6014417409896851, |
| "learning_rate": 4.71435429668747e-05, |
| "loss": 0.217, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.10535959688502061, |
| "grad_norm": 0.5063177943229675, |
| "learning_rate": 4.690350456072972e-05, |
| "loss": 0.2155, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.10994044892349977, |
| "grad_norm": 0.4963516294956207, |
| "learning_rate": 4.666346615458473e-05, |
| "loss": 0.2067, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.11452130096197893, |
| "grad_norm": 0.6876777410507202, |
| "learning_rate": 4.642342774843975e-05, |
| "loss": 0.2368, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.11910215300045808, |
| "grad_norm": 0.33562833070755005, |
| "learning_rate": 4.618338934229477e-05, |
| "loss": 0.2215, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.12368300503893724, |
| "grad_norm": 0.45656174421310425, |
| "learning_rate": 4.5943350936149786e-05, |
| "loss": 0.2051, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.1282638570774164, |
| "grad_norm": 0.5994214415550232, |
| "learning_rate": 4.5703312530004805e-05, |
| "loss": 0.2271, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.13284470911589555, |
| "grad_norm": 0.6960343718528748, |
| "learning_rate": 4.5463274123859816e-05, |
| "loss": 0.1914, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.1374255611543747, |
| "grad_norm": 0.5771898031234741, |
| "learning_rate": 4.5223235717714835e-05, |
| "loss": 0.2365, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.14200641319285387, |
| "grad_norm": 0.3877688944339752, |
| "learning_rate": 4.498319731156985e-05, |
| "loss": 0.2018, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.14658726523133303, |
| "grad_norm": 0.5205092430114746, |
| "learning_rate": 4.474315890542487e-05, |
| "loss": 0.2592, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.1511681172698122, |
| "grad_norm": 0.8437159061431885, |
| "learning_rate": 4.450312049927989e-05, |
| "loss": 0.2497, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.15574896930829135, |
| "grad_norm": 1.130053997039795, |
| "learning_rate": 4.426308209313491e-05, |
| "loss": 0.2258, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.1603298213467705, |
| "grad_norm": 0.4410316050052643, |
| "learning_rate": 4.402304368698992e-05, |
| "loss": 0.2134, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.16491067338524965, |
| "grad_norm": 0.7471569776535034, |
| "learning_rate": 4.378300528084494e-05, |
| "loss": 0.2121, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.1694915254237288, |
| "grad_norm": 0.6091960072517395, |
| "learning_rate": 4.354296687469995e-05, |
| "loss": 0.2367, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.17407237746220797, |
| "grad_norm": 0.37467148900032043, |
| "learning_rate": 4.330292846855497e-05, |
| "loss": 0.2127, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.17865322950068713, |
| "grad_norm": 0.4893397390842438, |
| "learning_rate": 4.306289006240999e-05, |
| "loss": 0.2018, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.1832340815391663, |
| "grad_norm": 0.41944998502731323, |
| "learning_rate": 4.2822851656265006e-05, |
| "loss": 0.2163, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.18781493357764545, |
| "grad_norm": 0.327027291059494, |
| "learning_rate": 4.2582813250120024e-05, |
| "loss": 0.2274, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.1923957856161246, |
| "grad_norm": 0.4042939245700836, |
| "learning_rate": 4.2342774843975036e-05, |
| "loss": 0.182, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.19697663765460377, |
| "grad_norm": 0.5198964476585388, |
| "learning_rate": 4.2102736437830054e-05, |
| "loss": 0.2229, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.2015574896930829, |
| "grad_norm": 0.5307021737098694, |
| "learning_rate": 4.186269803168507e-05, |
| "loss": 0.2123, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.20613834173156206, |
| "grad_norm": 0.3677486777305603, |
| "learning_rate": 4.162265962554009e-05, |
| "loss": 0.2166, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.21071919377004122, |
| "grad_norm": 0.38226303458213806, |
| "learning_rate": 4.138262121939511e-05, |
| "loss": 0.2389, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.21530004580852038, |
| "grad_norm": 0.4093310534954071, |
| "learning_rate": 4.114258281325012e-05, |
| "loss": 0.1985, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.21988089784699955, |
| "grad_norm": 0.3003683090209961, |
| "learning_rate": 4.090254440710514e-05, |
| "loss": 0.1982, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.2244617498854787, |
| "grad_norm": 0.48493343591690063, |
| "learning_rate": 4.066250600096015e-05, |
| "loss": 0.1956, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.22904260192395787, |
| "grad_norm": 0.44902732968330383, |
| "learning_rate": 4.042246759481517e-05, |
| "loss": 0.2145, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.22904260192395787, |
| "eval_loss": 0.21088281273841858, |
| "eval_runtime": 30.1602, |
| "eval_samples_per_second": 16.081, |
| "eval_steps_per_second": 8.057, |
| "step": 500 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 2183, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.1844959166464e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
