| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 46, |
| "global_step": 46, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.043478260869565216, |
| "grad_norm": 1.3204933404922485, |
| "learning_rate": 1e-05, |
| "loss": 5.87890625, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.08695652173913043, |
| "grad_norm": 1.7354029417037964, |
| "learning_rate": 9.988343845952697e-06, |
| "loss": 6.98046875, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.13043478260869565, |
| "grad_norm": 1.7187978029251099, |
| "learning_rate": 9.953429730181653e-06, |
| "loss": 6.796875, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.17391304347826086, |
| "grad_norm": 1.8150417804718018, |
| "learning_rate": 9.895420438411616e-06, |
| "loss": 6.59765625, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.21739130434782608, |
| "grad_norm": 1.3067541122436523, |
| "learning_rate": 9.814586436738998e-06, |
| "loss": 5.01953125, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2608695652173913, |
| "grad_norm": 2.2149245738983154, |
| "learning_rate": 9.711304610594104e-06, |
| "loss": 6.65625, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.30434782608695654, |
| "grad_norm": 1.9527572393417358, |
| "learning_rate": 9.586056507527266e-06, |
| "loss": 5.98046875, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.34782608695652173, |
| "grad_norm": 1.7640368938446045, |
| "learning_rate": 9.439426092011877e-06, |
| "loss": 5.263671875, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.391304347826087, |
| "grad_norm": 1.6902992725372314, |
| "learning_rate": 9.272097022732444e-06, |
| "loss": 5.01171875, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.43478260869565216, |
| "grad_norm": 1.9004840850830078, |
| "learning_rate": 9.08484946505221e-06, |
| "loss": 5.015625, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4782608695652174, |
| "grad_norm": 1.6428196430206299, |
| "learning_rate": 8.8785564535221e-06, |
| "loss": 4.306640625, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.5217391304347826, |
| "grad_norm": 2.6496338844299316, |
| "learning_rate": 8.65417982139062e-06, |
| "loss": 5.00390625, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5652173913043478, |
| "grad_norm": 1.8732898235321045, |
| "learning_rate": 8.412765716093273e-06, |
| "loss": 3.982421875, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6086956521739131, |
| "grad_norm": 1.3660883903503418, |
| "learning_rate": 8.155439721630265e-06, |
| "loss": 3.6015625, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.6521739130434783, |
| "grad_norm": 1.3932639360427856, |
| "learning_rate": 7.883401610574338e-06, |
| "loss": 3.578125, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6956521739130435, |
| "grad_norm": 1.1123762130737305, |
| "learning_rate": 7.597919750177168e-06, |
| "loss": 3.162109375, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.7391304347826086, |
| "grad_norm": 1.0200730562210083, |
| "learning_rate": 7.300325188655762e-06, |
| "loss": 3.19140625, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.782608695652174, |
| "grad_norm": 0.7737847566604614, |
| "learning_rate": 6.9920054492312086e-06, |
| "loss": 2.974609375, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.8260869565217391, |
| "grad_norm": 0.9270874261856079, |
| "learning_rate": 6.674398060854931e-06, |
| "loss": 3.05859375, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.8695652173913043, |
| "grad_norm": 0.8819101452827454, |
| "learning_rate": 6.348983855785122e-06, |
| "loss": 2.904296875, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.9130434782608695, |
| "grad_norm": 0.8757815361022949, |
| "learning_rate": 6.0172800652631706e-06, |
| "loss": 2.845703125, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.9565217391304348, |
| "grad_norm": 0.9578964114189148, |
| "learning_rate": 5.680833245481234e-06, |
| "loss": 2.837890625, |
| "step": 22 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.9321601390838623, |
| "learning_rate": 5.341212066823356e-06, |
| "loss": 2.73828125, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.0434782608695652, |
| "grad_norm": 0.6390194892883301, |
| "learning_rate": 5e-06, |
| "loss": 2.5712890625, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.0869565217391304, |
| "grad_norm": 0.7785202264785767, |
| "learning_rate": 4.6587879331766465e-06, |
| "loss": 2.58203125, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.1304347826086956, |
| "grad_norm": 0.7144135236740112, |
| "learning_rate": 4.319166754518768e-06, |
| "loss": 2.5751953125, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.1739130434782608, |
| "grad_norm": 0.6723203659057617, |
| "learning_rate": 3.982719934736832e-06, |
| "loss": 2.484375, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.2173913043478262, |
| "grad_norm": 0.47674691677093506, |
| "learning_rate": 3.6510161442148783e-06, |
| "loss": 2.2490234375, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.2608695652173914, |
| "grad_norm": 0.6761558055877686, |
| "learning_rate": 3.3256019391450696e-06, |
| "loss": 2.4501953125, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.3043478260869565, |
| "grad_norm": 0.5906397104263306, |
| "learning_rate": 3.007994550768793e-06, |
| "loss": 2.419921875, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.3478260869565217, |
| "grad_norm": 0.5150444507598877, |
| "learning_rate": 2.6996748113442397e-06, |
| "loss": 2.322265625, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.391304347826087, |
| "grad_norm": 0.4895986020565033, |
| "learning_rate": 2.4020802498228333e-06, |
| "loss": 2.4384765625, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.434782608695652, |
| "grad_norm": 0.5141778588294983, |
| "learning_rate": 2.1165983894256647e-06, |
| "loss": 2.3623046875, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.4782608695652173, |
| "grad_norm": 0.4545730948448181, |
| "learning_rate": 1.8445602783697375e-06, |
| "loss": 2.2919921875, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.5217391304347827, |
| "grad_norm": 0.6560953855514526, |
| "learning_rate": 1.5872342839067305e-06, |
| "loss": 2.2275390625, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.5652173913043477, |
| "grad_norm": 0.5090744495391846, |
| "learning_rate": 1.3458201786093795e-06, |
| "loss": 2.2958984375, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.608695652173913, |
| "grad_norm": 0.46399998664855957, |
| "learning_rate": 1.1214435464779006e-06, |
| "loss": 2.3056640625, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.6521739130434783, |
| "grad_norm": 0.5312969088554382, |
| "learning_rate": 9.151505349477901e-07, |
| "loss": 2.279296875, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.6956521739130435, |
| "grad_norm": 0.4883077144622803, |
| "learning_rate": 7.279029772675572e-07, |
| "loss": 2.1142578125, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.7391304347826086, |
| "grad_norm": 0.46691885590553284, |
| "learning_rate": 5.60573907988124e-07, |
| "loss": 2.2626953125, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.7826086956521738, |
| "grad_norm": 0.4006149172782898, |
| "learning_rate": 4.139434924727359e-07, |
| "loss": 2.337890625, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.8260869565217392, |
| "grad_norm": 0.4870384633541107, |
| "learning_rate": 2.88695389405898e-07, |
| "loss": 2.2939453125, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.8695652173913042, |
| "grad_norm": 0.4671219289302826, |
| "learning_rate": 1.8541356326100436e-07, |
| "loss": 2.232421875, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.9130434782608696, |
| "grad_norm": 0.4770534634590149, |
| "learning_rate": 1.0457956158838545e-07, |
| "loss": 2.2431640625, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.9565217391304348, |
| "grad_norm": 0.5379586219787598, |
| "learning_rate": 4.657026981834623e-08, |
| "loss": 2.2294921875, |
| "step": 45 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.5217427611351013, |
| "learning_rate": 1.1656154047303691e-08, |
| "loss": 2.208984375, |
| "step": 46 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 2.234375, |
| "eval_runtime": 4.4046, |
| "eval_samples_per_second": 0.227, |
| "eval_steps_per_second": 0.227, |
| "step": 46 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 46, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.4949216859253637e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
