| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 13, |
| "global_step": 69, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.043478260869565216, |
| "grad_norm": 0.06574621796607971, |
| "learning_rate": 0.0, |
| "loss": 0.683349609375, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.08695652173913043, |
| "grad_norm": 0.05150672793388367, |
| "learning_rate": 1.4285714285714286e-06, |
| "loss": 0.66162109375, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.13043478260869565, |
| "grad_norm": 0.05505973473191261, |
| "learning_rate": 2.8571428571428573e-06, |
| "loss": 0.66796875, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.17391304347826086, |
| "grad_norm": 0.0745709016919136, |
| "learning_rate": 4.2857142857142855e-06, |
| "loss": 0.677734375, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.21739130434782608, |
| "grad_norm": 0.08272148668766022, |
| "learning_rate": 5.7142857142857145e-06, |
| "loss": 0.6865234375, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2608695652173913, |
| "grad_norm": 0.07590784132480621, |
| "learning_rate": 7.1428571428571436e-06, |
| "loss": 0.6802978515625, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.30434782608695654, |
| "grad_norm": 0.07782676070928574, |
| "learning_rate": 8.571428571428571e-06, |
| "loss": 0.69140625, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.34782608695652173, |
| "grad_norm": 0.06320719420909882, |
| "learning_rate": 1e-05, |
| "loss": 0.691650390625, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.391304347826087, |
| "grad_norm": 0.06206236779689789, |
| "learning_rate": 9.994224282269737e-06, |
| "loss": 0.685302734375, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.43478260869565216, |
| "grad_norm": 0.0787166878581047, |
| "learning_rate": 9.976911955263528e-06, |
| "loss": 0.66796875, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4782608695652174, |
| "grad_norm": 0.0858655646443367, |
| "learning_rate": 9.948107459476502e-06, |
| "loss": 0.68408203125, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.5217391304347826, |
| "grad_norm": 0.05600776895880699, |
| "learning_rate": 9.907884735636226e-06, |
| "loss": 0.650146484375, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5652173913043478, |
| "grad_norm": 0.09197074174880981, |
| "learning_rate": 9.85634703489792e-06, |
| "loss": 0.640380859375, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6086956521739131, |
| "grad_norm": 0.051537591964006424, |
| "learning_rate": 9.79362665380022e-06, |
| "loss": 0.61328125, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.6521739130434783, |
| "grad_norm": 0.05343881994485855, |
| "learning_rate": 9.719884594661864e-06, |
| "loss": 0.65966796875, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6956521739130435, |
| "grad_norm": 0.06316563487052917, |
| "learning_rate": 9.635310152291038e-06, |
| "loss": 0.634765625, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.7391304347826086, |
| "grad_norm": 0.04639754444360733, |
| "learning_rate": 9.540120428068337e-06, |
| "loss": 0.65234375, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.7391304347826086, |
| "eval_loss": 0.65130615234375, |
| "eval_runtime": 2.0495, |
| "eval_samples_per_second": 1.464, |
| "eval_steps_per_second": 0.488, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.782608695652174, |
| "grad_norm": 0.08494574576616287, |
| "learning_rate": 9.43455977265062e-06, |
| "loss": 0.680419921875, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.8260869565217391, |
| "grad_norm": 0.0556136891245842, |
| "learning_rate": 9.31889915872638e-06, |
| "loss": 0.654052734375, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.8695652173913043, |
| "grad_norm": 0.050713956356048584, |
| "learning_rate": 9.193435485432744e-06, |
| "loss": 0.66650390625, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.9130434782608695, |
| "grad_norm": 0.0457201823592186, |
| "learning_rate": 9.058490816219644e-06, |
| "loss": 0.643310546875, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.9565217391304348, |
| "grad_norm": 0.0635598674416542, |
| "learning_rate": 8.91441155211756e-06, |
| "loss": 0.654052734375, |
| "step": 22 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.04849772900342941, |
| "learning_rate": 8.76156754253104e-06, |
| "loss": 0.65966796875, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.0434782608695652, |
| "grad_norm": 0.04802418127655983, |
| "learning_rate": 8.60035113584059e-06, |
| "loss": 0.65966796875, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.0869565217391304, |
| "grad_norm": 0.03913020342588425, |
| "learning_rate": 8.431176172250002e-06, |
| "loss": 0.643798828125, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.1304347826086956, |
| "grad_norm": 0.04047388955950737, |
| "learning_rate": 8.254476921464483e-06, |
| "loss": 0.64501953125, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.1739130434782608, |
| "grad_norm": 0.04983432590961456, |
| "learning_rate": 8.070706967926565e-06, |
| "loss": 0.64453125, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.2173913043478262, |
| "grad_norm": 0.053629934787750244, |
| "learning_rate": 7.880338046471331e-06, |
| "loss": 0.646484375, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.2608695652173914, |
| "grad_norm": 0.048355311155319214, |
| "learning_rate": 7.683858831389866e-06, |
| "loss": 0.64288330078125, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.3043478260869565, |
| "grad_norm": 0.04861477389931679, |
| "learning_rate": 7.481773682009356e-06, |
| "loss": 0.650146484375, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.3043478260869565, |
| "eval_loss": 0.6319580078125, |
| "eval_runtime": 2.0542, |
| "eval_samples_per_second": 1.46, |
| "eval_steps_per_second": 0.487, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.3478260869565217, |
| "grad_norm": 0.04120055213570595, |
| "learning_rate": 7.274601348009934e-06, |
| "loss": 0.65966796875, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.391304347826087, |
| "grad_norm": 0.04094763100147247, |
| "learning_rate": 7.062873637801692e-06, |
| "loss": 0.6552734375, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.434782608695652, |
| "grad_norm": 0.045276131480932236, |
| "learning_rate": 6.847134053380113e-06, |
| "loss": 0.6279296875, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.4782608695652173, |
| "grad_norm": 0.047124769538640976, |
| "learning_rate": 6.627936395164243e-06, |
| "loss": 0.640625, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.5217391304347827, |
| "grad_norm": 0.03720078617334366, |
| "learning_rate": 6.405843340398971e-06, |
| "loss": 0.623291015625, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.5652173913043477, |
| "grad_norm": 0.04636256396770477, |
| "learning_rate": 6.181424998770595e-06, |
| "loss": 0.59619140625, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.608695652173913, |
| "grad_norm": 0.03454005345702171, |
| "learning_rate": 5.955257448943446e-06, |
| "loss": 0.588623046875, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.6521739130434783, |
| "grad_norm": 0.03595034033060074, |
| "learning_rate": 5.727921259774208e-06, |
| "loss": 0.6328125, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.6956521739130435, |
| "grad_norm": 0.03682588040828705, |
| "learning_rate": 5.500000000000001e-06, |
| "loss": 0.60498046875, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.7391304347826086, |
| "grad_norm": 0.03514236584305763, |
| "learning_rate": 5.272078740225793e-06, |
| "loss": 0.629638671875, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.7826086956521738, |
| "grad_norm": 0.04472735896706581, |
| "learning_rate": 5.0447425510565564e-06, |
| "loss": 0.641357421875, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.8260869565217392, |
| "grad_norm": 0.03495565056800842, |
| "learning_rate": 4.818575001229406e-06, |
| "loss": 0.626708984375, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.8695652173913042, |
| "grad_norm": 0.035717420279979706, |
| "learning_rate": 4.594156659601029e-06, |
| "loss": 0.643310546875, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.8695652173913042, |
| "eval_loss": 0.6201171875, |
| "eval_runtime": 2.0449, |
| "eval_samples_per_second": 1.467, |
| "eval_steps_per_second": 0.489, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.9130434782608696, |
| "grad_norm": 0.03499886021018028, |
| "learning_rate": 4.372063604835758e-06, |
| "loss": 0.623046875, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.9565217391304348, |
| "grad_norm": 0.04084884747862816, |
| "learning_rate": 4.15286594661989e-06, |
| "loss": 0.62548828125, |
| "step": 45 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.036120329052209854, |
| "learning_rate": 3.93712636219831e-06, |
| "loss": 0.6376953125, |
| "step": 46 |
| }, |
| { |
| "epoch": 2.0434782608695654, |
| "grad_norm": 0.03603987395763397, |
| "learning_rate": 3.7253986519900674e-06, |
| "loss": 0.6376953125, |
| "step": 47 |
| }, |
| { |
| "epoch": 2.0869565217391304, |
| "grad_norm": 0.03318258747458458, |
| "learning_rate": 3.5182263179906462e-06, |
| "loss": 0.62841796875, |
| "step": 48 |
| }, |
| { |
| "epoch": 2.130434782608696, |
| "grad_norm": 0.03247852995991707, |
| "learning_rate": 3.316141168610136e-06, |
| "loss": 0.629638671875, |
| "step": 49 |
| }, |
| { |
| "epoch": 2.1739130434782608, |
| "grad_norm": 0.03627059981226921, |
| "learning_rate": 3.119661953528671e-06, |
| "loss": 0.62451171875, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.217391304347826, |
| "grad_norm": 0.03881670534610748, |
| "learning_rate": 2.9292930320734337e-06, |
| "loss": 0.62548828125, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.260869565217391, |
| "grad_norm": 0.03561678156256676, |
| "learning_rate": 2.745523078535517e-06, |
| "loss": 0.62567138671875, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.3043478260869565, |
| "grad_norm": 0.036425329744815826, |
| "learning_rate": 2.568823827750001e-06, |
| "loss": 0.633056640625, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.3478260869565215, |
| "grad_norm": 0.033790528774261475, |
| "learning_rate": 2.3996488641594104e-06, |
| "loss": 0.6455078125, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.391304347826087, |
| "grad_norm": 0.03458794951438904, |
| "learning_rate": 2.2384324574689614e-06, |
| "loss": 0.64013671875, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.4347826086956523, |
| "grad_norm": 0.03604791685938835, |
| "learning_rate": 2.085588447882441e-06, |
| "loss": 0.612548828125, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.4347826086956523, |
| "eval_loss": 0.617156982421875, |
| "eval_runtime": 2.0468, |
| "eval_samples_per_second": 1.466, |
| "eval_steps_per_second": 0.489, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.4782608695652173, |
| "grad_norm": 0.037638068199157715, |
| "learning_rate": 1.9415091837803574e-06, |
| "loss": 0.6259765625, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.5217391304347827, |
| "grad_norm": 0.032444193959236145, |
| "learning_rate": 1.8065645145672578e-06, |
| "loss": 0.61279296875, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.5652173913043477, |
| "grad_norm": 0.03685029596090317, |
| "learning_rate": 1.6811008412736207e-06, |
| "loss": 0.582763671875, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.608695652173913, |
| "grad_norm": 0.030133027583360672, |
| "learning_rate": 1.5654402273493808e-06, |
| "loss": 0.57958984375, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.6521739130434785, |
| "grad_norm": 0.031628984957933426, |
| "learning_rate": 1.459879571931663e-06, |
| "loss": 0.6240234375, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.6956521739130435, |
| "grad_norm": 0.03223630040884018, |
| "learning_rate": 1.3646898477089627e-06, |
| "loss": 0.594970703125, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.7391304347826084, |
| "grad_norm": 0.03134209290146828, |
| "learning_rate": 1.2801154053381386e-06, |
| "loss": 0.621337890625, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.782608695652174, |
| "grad_norm": 0.038812585175037384, |
| "learning_rate": 1.2063733461997804e-06, |
| "loss": 0.631103515625, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.8260869565217392, |
| "grad_norm": 0.031380850821733475, |
| "learning_rate": 1.1436529651020813e-06, |
| "loss": 0.619384765625, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.869565217391304, |
| "grad_norm": 0.0320647768676281, |
| "learning_rate": 1.092115264363775e-06, |
| "loss": 0.636474609375, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.9130434782608696, |
| "grad_norm": 0.031743913888931274, |
| "learning_rate": 1.0518925405234988e-06, |
| "loss": 0.61572265625, |
| "step": 67 |
| }, |
| { |
| "epoch": 2.9565217391304346, |
| "grad_norm": 0.037360724061727524, |
| "learning_rate": 1.0230880447364719e-06, |
| "loss": 0.619140625, |
| "step": 68 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.03293885663151741, |
| "learning_rate": 1.0057757177302628e-06, |
| "loss": 0.631103515625, |
| "step": 69 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.6156768798828125, |
| "eval_runtime": 2.0475, |
| "eval_samples_per_second": 1.465, |
| "eval_steps_per_second": 0.488, |
| "step": 69 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 69, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 1.2309274178963374e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
