|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.5594541910331383, |
|
"eval_steps": 500, |
|
"global_step": 250, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.031189083820662766, |
|
"grad_norm": 0.0859375, |
|
"learning_rate": 0.0001, |
|
"loss": 0.6539, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.06237816764132553, |
|
"grad_norm": 0.048828125, |
|
"learning_rate": 0.0001, |
|
"loss": 0.4137, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.0935672514619883, |
|
"grad_norm": 0.044921875, |
|
"learning_rate": 0.0001, |
|
"loss": 0.4041, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.12475633528265107, |
|
"grad_norm": 0.047607421875, |
|
"learning_rate": 0.0001, |
|
"loss": 0.4286, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.15594541910331383, |
|
"grad_norm": 0.05712890625, |
|
"learning_rate": 0.0001, |
|
"loss": 0.4432, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.1871345029239766, |
|
"grad_norm": 0.05517578125, |
|
"learning_rate": 0.0001, |
|
"loss": 0.4199, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.21832358674463936, |
|
"grad_norm": 0.051025390625, |
|
"learning_rate": 0.0001, |
|
"loss": 0.4192, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.24951267056530213, |
|
"grad_norm": 0.19921875, |
|
"learning_rate": 0.0001, |
|
"loss": 0.4418, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.2807017543859649, |
|
"grad_norm": 0.06201171875, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3354, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.31189083820662766, |
|
"grad_norm": 0.0311279296875, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3194, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.34307992202729043, |
|
"grad_norm": 0.0277099609375, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3244, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.3742690058479532, |
|
"grad_norm": 0.0291748046875, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3296, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.40545808966861596, |
|
"grad_norm": 0.030029296875, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3166, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.43664717348927873, |
|
"grad_norm": 0.029541015625, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3296, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.4678362573099415, |
|
"grad_norm": 0.03271484375, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3367, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.49902534113060426, |
|
"grad_norm": 0.07275390625, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3594, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.530214424951267, |
|
"grad_norm": 0.044921875, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3167, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.5614035087719298, |
|
"grad_norm": 0.031982421875, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2832, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.5925925925925926, |
|
"grad_norm": 0.0281982421875, |
|
"learning_rate": 0.0001, |
|
"loss": 0.299, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.6237816764132553, |
|
"grad_norm": 0.0299072265625, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3073, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.6549707602339181, |
|
"grad_norm": 0.029541015625, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2995, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.6861598440545809, |
|
"grad_norm": 0.0308837890625, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3026, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.7173489278752436, |
|
"grad_norm": 0.033935546875, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3234, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.7485380116959064, |
|
"grad_norm": 0.07421875, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3463, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.7797270955165692, |
|
"grad_norm": 0.033935546875, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2892, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.8109161793372319, |
|
"grad_norm": 0.0294189453125, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2819, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.8421052631578947, |
|
"grad_norm": 0.0284423828125, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3008, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 0.8732943469785575, |
|
"grad_norm": 0.0262451171875, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3002, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.9044834307992202, |
|
"grad_norm": 0.0294189453125, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3035, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 0.935672514619883, |
|
"grad_norm": 0.033935546875, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2954, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.9668615984405458, |
|
"grad_norm": 0.03515625, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3033, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 0.9980506822612085, |
|
"grad_norm": 0.07763671875, |
|
"learning_rate": 0.0001, |
|
"loss": 0.352, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 1.0292397660818713, |
|
"grad_norm": 0.041748046875, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2887, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 1.060428849902534, |
|
"grad_norm": 0.0322265625, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2654, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 1.0916179337231968, |
|
"grad_norm": 0.029296875, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2809, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 1.1228070175438596, |
|
"grad_norm": 0.0311279296875, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2943, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 1.1539961013645224, |
|
"grad_norm": 0.0306396484375, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2927, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 1.1851851851851851, |
|
"grad_norm": 0.032958984375, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2813, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 1.2163742690058479, |
|
"grad_norm": 0.0380859375, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2982, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 1.2475633528265107, |
|
"grad_norm": 0.0576171875, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3076, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.2787524366471734, |
|
"grad_norm": 0.095703125, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2739, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 1.3099415204678362, |
|
"grad_norm": 0.03515625, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2761, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 1.341130604288499, |
|
"grad_norm": 0.032958984375, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2882, |
|
"step": 215 |
|
}, |
|
{ |
|
"epoch": 1.3723196881091617, |
|
"grad_norm": 0.034423828125, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2885, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 1.4035087719298245, |
|
"grad_norm": 0.034912109375, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2881, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 1.4346978557504872, |
|
"grad_norm": 0.03466796875, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2745, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 1.46588693957115, |
|
"grad_norm": 0.042236328125, |
|
"learning_rate": 0.0001, |
|
"loss": 0.301, |
|
"step": 235 |
|
}, |
|
{ |
|
"epoch": 1.4970760233918128, |
|
"grad_norm": 0.0673828125, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3076, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 1.5282651072124755, |
|
"grad_norm": 0.04345703125, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2945, |
|
"step": 245 |
|
}, |
|
{ |
|
"epoch": 1.5594541910331383, |
|
"grad_norm": 0.032958984375, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2577, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 1.5594541910331383, |
|
"step": 250, |
|
"total_flos": 4.824681746497536e+17, |
|
"train_loss": 0.32678396368026735, |
|
"train_runtime": 14418.506, |
|
"train_samples_per_second": 1.11, |
|
"train_steps_per_second": 0.017 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 250, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"save_steps": 90, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 4.824681746497536e+17, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|