317 lines
8.2 KiB
JSON
317 lines
8.2 KiB
JSON
{
|
|
"best_global_step": 2996,
|
|
"best_metric": 2.225428342819214,
|
|
"best_model_checkpoint": "/kaggle/working/gemma-3-270m-uzen-base/checkpoint-2996",
|
|
"epoch": 0.7010749542961608,
|
|
"eval_steps": 428,
|
|
"global_step": 2996,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0,
|
|
"eval_loss": 3.3726205825805664,
|
|
"eval_perplexity": 29.00750160217285,
|
|
"eval_runtime": 1376.8644,
|
|
"eval_samples_per_second": 8.027,
|
|
"eval_steps_per_second": 1.004,
|
|
"step": 0
|
|
},
|
|
{
|
|
"epoch": 0.0002340036563071298,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0,
|
|
"loss": 221.65936279296875,
|
|
"step": 1
|
|
},
|
|
{
|
|
"epoch": 0.02340036563071298,
|
|
"grad_norm": 125.02448272705078,
|
|
"learning_rate": 1.3455579942126144e-05,
|
|
"loss": 186.75027619949495,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 0.04680073126142596,
|
|
"grad_norm": 119.42086029052734,
|
|
"learning_rate": 9.391758525703705e-06,
|
|
"loss": 162.133095703125,
|
|
"step": 200
|
|
},
|
|
{
|
|
"epoch": 0.07020109689213894,
|
|
"grad_norm": 122.48279571533203,
|
|
"learning_rate": 7.64875162105191e-06,
|
|
"loss": 155.50732421875,
|
|
"step": 300
|
|
},
|
|
{
|
|
"epoch": 0.09360146252285192,
|
|
"grad_norm": 117.2989273071289,
|
|
"learning_rate": 6.607179605173858e-06,
|
|
"loss": 152.238125,
|
|
"step": 400
|
|
},
|
|
{
|
|
"epoch": 0.10015356489945156,
|
|
"eval_loss": 2.4410510063171387,
|
|
"eval_perplexity": 11.5115966796875,
|
|
"eval_runtime": 1493.6491,
|
|
"eval_samples_per_second": 7.399,
|
|
"eval_steps_per_second": 0.925,
|
|
"step": 428
|
|
},
|
|
{
|
|
"epoch": 0.1170018281535649,
|
|
"grad_norm": 112.73179626464844,
|
|
"learning_rate": 5.900662146334273e-06,
|
|
"loss": 150.016318359375,
|
|
"step": 500
|
|
},
|
|
{
|
|
"epoch": 0.14040219378427787,
|
|
"grad_norm": 120.18157958984375,
|
|
"learning_rate": 5.381099233077658e-06,
|
|
"loss": 147.887568359375,
|
|
"step": 600
|
|
},
|
|
{
|
|
"epoch": 0.16380255941499086,
|
|
"grad_norm": 126.22393035888672,
|
|
"learning_rate": 4.978339248330686e-06,
|
|
"loss": 147.1618359375,
|
|
"step": 700
|
|
},
|
|
{
|
|
"epoch": 0.18720292504570385,
|
|
"grad_norm": 119.209228515625,
|
|
"learning_rate": 4.657229393557059e-06,
|
|
"loss": 145.39865234375,
|
|
"step": 800
|
|
},
|
|
{
|
|
"epoch": 0.2003071297989031,
|
|
"eval_loss": 2.3490686416625977,
|
|
"eval_perplexity": 10.503242492675781,
|
|
"eval_runtime": 1490.1057,
|
|
"eval_samples_per_second": 7.417,
|
|
"eval_steps_per_second": 0.927,
|
|
"step": 856
|
|
},
|
|
{
|
|
"epoch": 0.2106032906764168,
|
|
"grad_norm": 124.55681610107422,
|
|
"learning_rate": 4.39118562699897e-06,
|
|
"loss": 153.693115234375,
|
|
"step": 900
|
|
},
|
|
{
|
|
"epoch": 0.2340036563071298,
|
|
"grad_norm": 119.34051513671875,
|
|
"learning_rate": 4.1639776269114805e-06,
|
|
"loss": 146.270078125,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"epoch": 0.2574040219378428,
|
|
"grad_norm": 114.71582794189453,
|
|
"learning_rate": 3.968742338690654e-06,
|
|
"loss": 144.3760546875,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"epoch": 0.28080438756855575,
|
|
"grad_norm": 119.8339614868164,
|
|
"learning_rate": 3.79862214511292e-06,
|
|
"loss": 143.744560546875,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"epoch": 0.3004606946983547,
|
|
"eval_loss": 2.3285601139068604,
|
|
"eval_perplexity": 10.293147087097168,
|
|
"eval_runtime": 1270.7866,
|
|
"eval_samples_per_second": 8.697,
|
|
"eval_steps_per_second": 1.088,
|
|
"step": 1284
|
|
},
|
|
{
|
|
"epoch": 0.30420475319926876,
|
|
"grad_norm": 114.1391830444336,
|
|
"learning_rate": 3.648656396326189e-06,
|
|
"loss": 143.26626953125,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"epoch": 0.3276051188299817,
|
|
"grad_norm": 118.7150650024414,
|
|
"learning_rate": 3.5151560191662133e-06,
|
|
"loss": 142.079208984375,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"epoch": 0.3510054844606947,
|
|
"grad_norm": 113.54842376708984,
|
|
"learning_rate": 3.395312965552404e-06,
|
|
"loss": 141.61373046875,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"epoch": 0.3744058500914077,
|
|
"grad_norm": 113.5634994506836,
|
|
"learning_rate": 3.2869469269372928e-06,
|
|
"loss": 141.197421875,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"epoch": 0.39780621572212066,
|
|
"grad_norm": 117.68986511230469,
|
|
"learning_rate": 3.188335715317592e-06,
|
|
"loss": 140.76587890625,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"epoch": 0.4006142595978062,
|
|
"eval_loss": 2.2911739349365234,
|
|
"eval_perplexity": 9.915882110595703,
|
|
"eval_runtime": 1272.1824,
|
|
"eval_samples_per_second": 8.687,
|
|
"eval_steps_per_second": 1.086,
|
|
"step": 1712
|
|
},
|
|
{
|
|
"epoch": 0.4212065813528336,
|
|
"grad_norm": 114.08328247070312,
|
|
"learning_rate": 3.0980984951602635e-06,
|
|
"loss": 140.2319140625,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"epoch": 0.44460694698354664,
|
|
"grad_norm": 110.51737976074219,
|
|
"learning_rate": 3.0151134457776365e-06,
|
|
"loss": 139.54671875,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"epoch": 0.4680073126142596,
|
|
"grad_norm": 114.35932159423828,
|
|
"learning_rate": 2.9384584653539762e-06,
|
|
"loss": 139.24345703125,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"epoch": 0.49140767824497256,
|
|
"grad_norm": 113.81220245361328,
|
|
"learning_rate": 2.867367664450403e-06,
|
|
"loss": 139.157421875,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"epoch": 0.5007678244972578,
|
|
"eval_loss": 2.2643067836761475,
|
|
"eval_perplexity": 9.653481483459473,
|
|
"eval_runtime": 1272.3391,
|
|
"eval_samples_per_second": 8.686,
|
|
"eval_steps_per_second": 1.086,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"epoch": 0.5148080438756856,
|
|
"grad_norm": 118.33269500732422,
|
|
"learning_rate": 2.801198909122156e-06,
|
|
"loss": 138.7333984375,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"epoch": 0.5382084095063986,
|
|
"grad_norm": 111.53887176513672,
|
|
"learning_rate": 2.7394092432028485e-06,
|
|
"loss": 138.593310546875,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"epoch": 0.5616087751371115,
|
|
"grad_norm": 116.05701446533203,
|
|
"learning_rate": 2.6815360246517324e-06,
|
|
"loss": 137.77955078125,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"epoch": 0.5850091407678245,
|
|
"grad_norm": 117.56316375732422,
|
|
"learning_rate": 2.627182269536618e-06,
|
|
"loss": 137.41365234375,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"epoch": 0.6009213893967094,
|
|
"eval_loss": 2.2431113719940186,
|
|
"eval_perplexity": 9.451156616210938,
|
|
"eval_runtime": 1281.4279,
|
|
"eval_samples_per_second": 8.625,
|
|
"eval_steps_per_second": 1.078,
|
|
"step": 2568
|
|
},
|
|
{
|
|
"epoch": 0.6084095063985375,
|
|
"grad_norm": 119.91163635253906,
|
|
"learning_rate": 2.576005137637696e-06,
|
|
"loss": 137.66705078125,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"epoch": 0.6318098720292504,
|
|
"grad_norm": 112.58194732666016,
|
|
"learning_rate": 2.5277067936120503e-06,
|
|
"loss": 137.92888671875,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"epoch": 0.6552102376599634,
|
|
"grad_norm": 118.54427337646484,
|
|
"learning_rate": 2.48202708541266e-06,
|
|
"loss": 136.8133984375,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"epoch": 0.6786106032906765,
|
|
"grad_norm": 112.7831802368164,
|
|
"learning_rate": 2.4387376277801515e-06,
|
|
"loss": 136.398330078125,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"epoch": 0.7010749542961608,
|
|
"eval_loss": 2.225428342819214,
|
|
"eval_perplexity": 9.285932540893555,
|
|
"eval_runtime": 1259.9334,
|
|
"eval_samples_per_second": 8.772,
|
|
"eval_steps_per_second": 1.097,
|
|
"step": 2996
|
|
}
|
|
],
|
|
"logging_steps": 100,
|
|
"max_steps": 4274,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 1,
|
|
"save_steps": 428,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.660641467170816e+17,
|
|
"train_batch_size": 2,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|