nttx's picture
Training in progress, step 50, checkpoint
96e747b verified
raw
history blame
9.98 kB
{
"best_metric": 7.059117317199707,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.35778175313059035,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.007155635062611807,
"grad_norm": 63.07804870605469,
"learning_rate": 5.000000000000001e-07,
"loss": 55.8303,
"step": 1
},
{
"epoch": 0.007155635062611807,
"eval_loss": 8.064038276672363,
"eval_runtime": 21.6914,
"eval_samples_per_second": 10.88,
"eval_steps_per_second": 2.72,
"step": 1
},
{
"epoch": 0.014311270125223614,
"grad_norm": 47.44363784790039,
"learning_rate": 1.0000000000000002e-06,
"loss": 57.0338,
"step": 2
},
{
"epoch": 0.02146690518783542,
"grad_norm": 54.36549758911133,
"learning_rate": 1.5e-06,
"loss": 57.0304,
"step": 3
},
{
"epoch": 0.028622540250447227,
"grad_norm": 51.64623260498047,
"learning_rate": 2.0000000000000003e-06,
"loss": 52.5478,
"step": 4
},
{
"epoch": 0.03577817531305903,
"grad_norm": 59.063106536865234,
"learning_rate": 2.5e-06,
"loss": 57.2634,
"step": 5
},
{
"epoch": 0.04293381037567084,
"grad_norm": 50.631046295166016,
"learning_rate": 3e-06,
"loss": 55.0657,
"step": 6
},
{
"epoch": 0.05008944543828265,
"grad_norm": 65.40850830078125,
"learning_rate": 3.5e-06,
"loss": 58.9552,
"step": 7
},
{
"epoch": 0.057245080500894455,
"grad_norm": 52.03582000732422,
"learning_rate": 4.000000000000001e-06,
"loss": 60.8162,
"step": 8
},
{
"epoch": 0.06440071556350627,
"grad_norm": 71.69737243652344,
"learning_rate": 4.5e-06,
"loss": 63.0307,
"step": 9
},
{
"epoch": 0.07155635062611806,
"grad_norm": 66.26720428466797,
"learning_rate": 5e-06,
"loss": 62.048,
"step": 10
},
{
"epoch": 0.07871198568872988,
"grad_norm": 47.20499038696289,
"learning_rate": 4.99847706754774e-06,
"loss": 59.9577,
"step": 11
},
{
"epoch": 0.08586762075134168,
"grad_norm": 50.71089553833008,
"learning_rate": 4.993910125649561e-06,
"loss": 64.3391,
"step": 12
},
{
"epoch": 0.09302325581395349,
"grad_norm": 56.87615203857422,
"learning_rate": 4.986304738420684e-06,
"loss": 62.9932,
"step": 13
},
{
"epoch": 0.1001788908765653,
"grad_norm": 57.271766662597656,
"learning_rate": 4.975670171853926e-06,
"loss": 64.1028,
"step": 14
},
{
"epoch": 0.1073345259391771,
"grad_norm": 56.15481948852539,
"learning_rate": 4.962019382530521e-06,
"loss": 67.4748,
"step": 15
},
{
"epoch": 0.11449016100178891,
"grad_norm": 44.163082122802734,
"learning_rate": 4.9453690018345144e-06,
"loss": 53.8473,
"step": 16
},
{
"epoch": 0.12164579606440072,
"grad_norm": 54.03547668457031,
"learning_rate": 4.925739315689991e-06,
"loss": 57.9262,
"step": 17
},
{
"epoch": 0.12880143112701253,
"grad_norm": 68.97274780273438,
"learning_rate": 4.903154239845798e-06,
"loss": 61.3954,
"step": 18
},
{
"epoch": 0.13595706618962433,
"grad_norm": 53.48569869995117,
"learning_rate": 4.8776412907378845e-06,
"loss": 64.557,
"step": 19
},
{
"epoch": 0.14311270125223613,
"grad_norm": 64.57427978515625,
"learning_rate": 4.849231551964771e-06,
"loss": 67.3172,
"step": 20
},
{
"epoch": 0.15026833631484796,
"grad_norm": 58.888912200927734,
"learning_rate": 4.817959636416969e-06,
"loss": 59.5499,
"step": 21
},
{
"epoch": 0.15742397137745975,
"grad_norm": 53.7679443359375,
"learning_rate": 4.783863644106502e-06,
"loss": 61.4948,
"step": 22
},
{
"epoch": 0.16457960644007155,
"grad_norm": 60.130409240722656,
"learning_rate": 4.746985115747918e-06,
"loss": 64.6237,
"step": 23
},
{
"epoch": 0.17173524150268335,
"grad_norm": 48.91883850097656,
"learning_rate": 4.707368982147318e-06,
"loss": 69.1527,
"step": 24
},
{
"epoch": 0.17889087656529518,
"grad_norm": 46.37879943847656,
"learning_rate": 4.665063509461098e-06,
"loss": 62.3713,
"step": 25
},
{
"epoch": 0.18604651162790697,
"grad_norm": 50.134422302246094,
"learning_rate": 4.620120240391065e-06,
"loss": 64.926,
"step": 26
},
{
"epoch": 0.19320214669051877,
"grad_norm": 46.87827682495117,
"learning_rate": 4.572593931387604e-06,
"loss": 63.1828,
"step": 27
},
{
"epoch": 0.2003577817531306,
"grad_norm": 54.75893783569336,
"learning_rate": 4.522542485937369e-06,
"loss": 60.6643,
"step": 28
},
{
"epoch": 0.2075134168157424,
"grad_norm": 52.367431640625,
"learning_rate": 4.470026884016805e-06,
"loss": 68.0454,
"step": 29
},
{
"epoch": 0.2146690518783542,
"grad_norm": 50.618350982666016,
"learning_rate": 4.415111107797445e-06,
"loss": 71.5049,
"step": 30
},
{
"epoch": 0.22182468694096602,
"grad_norm": 47.27493667602539,
"learning_rate": 4.357862063693486e-06,
"loss": 61.6825,
"step": 31
},
{
"epoch": 0.22898032200357782,
"grad_norm": 51.643550872802734,
"learning_rate": 4.2983495008466285e-06,
"loss": 66.9774,
"step": 32
},
{
"epoch": 0.23613595706618962,
"grad_norm": 65.83971405029297,
"learning_rate": 4.236645926147493e-06,
"loss": 62.7222,
"step": 33
},
{
"epoch": 0.24329159212880144,
"grad_norm": 49.59482955932617,
"learning_rate": 4.172826515897146e-06,
"loss": 61.6222,
"step": 34
},
{
"epoch": 0.2504472271914132,
"grad_norm": 53.057708740234375,
"learning_rate": 4.106969024216348e-06,
"loss": 55.4643,
"step": 35
},
{
"epoch": 0.25760286225402507,
"grad_norm": 90.77571105957031,
"learning_rate": 4.039153688314146e-06,
"loss": 55.8806,
"step": 36
},
{
"epoch": 0.26475849731663686,
"grad_norm": 71.54025268554688,
"learning_rate": 3.969463130731183e-06,
"loss": 53.0835,
"step": 37
},
{
"epoch": 0.27191413237924866,
"grad_norm": 72.8661117553711,
"learning_rate": 3.897982258676867e-06,
"loss": 49.935,
"step": 38
},
{
"epoch": 0.27906976744186046,
"grad_norm": 61.325645446777344,
"learning_rate": 3.824798160583012e-06,
"loss": 52.0931,
"step": 39
},
{
"epoch": 0.28622540250447226,
"grad_norm": 95.67042541503906,
"learning_rate": 3.7500000000000005e-06,
"loss": 55.6016,
"step": 40
},
{
"epoch": 0.29338103756708406,
"grad_norm": 61.53566360473633,
"learning_rate": 3.6736789069647273e-06,
"loss": 54.4276,
"step": 41
},
{
"epoch": 0.3005366726296959,
"grad_norm": 95.13054656982422,
"learning_rate": 3.595927866972694e-06,
"loss": 51.2729,
"step": 42
},
{
"epoch": 0.3076923076923077,
"grad_norm": 73.37828826904297,
"learning_rate": 3.516841607689501e-06,
"loss": 55.4188,
"step": 43
},
{
"epoch": 0.3148479427549195,
"grad_norm": 73.3287124633789,
"learning_rate": 3.436516483539781e-06,
"loss": 53.3134,
"step": 44
},
{
"epoch": 0.3220035778175313,
"grad_norm": 69.86181640625,
"learning_rate": 3.3550503583141726e-06,
"loss": 51.2279,
"step": 45
},
{
"epoch": 0.3291592128801431,
"grad_norm": 88.11177062988281,
"learning_rate": 3.272542485937369e-06,
"loss": 52.3788,
"step": 46
},
{
"epoch": 0.3363148479427549,
"grad_norm": 77.78619384765625,
"learning_rate": 3.189093389542498e-06,
"loss": 55.5405,
"step": 47
},
{
"epoch": 0.3434704830053667,
"grad_norm": 54.31289291381836,
"learning_rate": 3.1048047389991693e-06,
"loss": 53.7706,
"step": 48
},
{
"epoch": 0.35062611806797855,
"grad_norm": 92.552734375,
"learning_rate": 3.019779227044398e-06,
"loss": 48.2176,
"step": 49
},
{
"epoch": 0.35778175313059035,
"grad_norm": 55.199222564697266,
"learning_rate": 2.9341204441673267e-06,
"loss": 55.8397,
"step": 50
},
{
"epoch": 0.35778175313059035,
"eval_loss": 7.059117317199707,
"eval_runtime": 22.0275,
"eval_samples_per_second": 10.714,
"eval_steps_per_second": 2.678,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 100,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 6.53464644354048e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}