Theoreticallyhugo's picture
Training in progress, epoch 7, checkpoint
994a2d9 verified
raw
history blame
13.5 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 7.0,
"eval_steps": 500,
"global_step": 567,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_B-Claim": {
"f1-score": 0.32421052631578945,
"precision": 0.42777777777777776,
"recall": 0.26101694915254237,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.192090395480226,
"precision": 0.8095238095238095,
"recall": 0.10897435897435898,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8566265060240965,
"precision": 0.7620578778135049,
"recall": 0.9779917469050894,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.5001390820584144,
"precision": 0.5900886117492615,
"recall": 0.43398503499879315,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.776470588235294,
"precision": 0.6649333766655834,
"recall": 0.93296853625171,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.8861458374413376,
"precision": 0.8781460059402845,
"recall": 0.8942927644670858,
"support": 12563.0
},
"eval_O": {
"f1-score": 0.9987647926046939,
"precision": 0.9977708781147998,
"recall": 0.9997606892150607,
"support": 12536.0
},
"eval_accuracy": 0.8713396498328887,
"eval_loss": 0.3092103600502014,
"eval_macro avg": {
"f1-score": 0.647778246879979,
"precision": 0.732899762512146,
"recall": 0.6584271542806628,
"support": 32613.0
},
"eval_runtime": 4.965,
"eval_samples_per_second": 16.314,
"eval_steps_per_second": 2.215,
"eval_weighted avg": {
"f1-score": 0.8639627599323451,
"precision": 0.8662078389010613,
"recall": 0.8713396498328887,
"support": 32613.0
},
"step": 81
},
{
"epoch": 2.0,
"eval_B-Claim": {
"f1-score": 0.6186291739894552,
"precision": 0.6423357664233577,
"recall": 0.5966101694915255,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.8113879003558718,
"precision": 0.912,
"recall": 0.7307692307692307,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8871181938911022,
"precision": 0.8575096277278562,
"recall": 0.9188445667125172,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.656253149249219,
"precision": 0.5633217993079584,
"recall": 0.7859039343470915,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.8368159203980099,
"precision": 0.9206349206349206,
"recall": 0.7669858641130871,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.8831027253668763,
"precision": 0.933020288827855,
"recall": 0.8382551938231314,
"support": 12563.0
},
"eval_O": {
"f1-score": 0.9998006141085457,
"precision": 0.9996013077107089,
"recall": 1.0,
"support": 12536.0
},
"eval_accuracy": 0.8880814399165977,
"eval_loss": 0.2581149935722351,
"eval_macro avg": {
"f1-score": 0.8133010967655829,
"precision": 0.8326319586618081,
"recall": 0.8053384227509405,
"support": 32613.0
},
"eval_runtime": 5.0296,
"eval_samples_per_second": 16.105,
"eval_steps_per_second": 2.187,
"eval_weighted avg": {
"f1-score": 0.8933836566327042,
"precision": 0.9064023864086126,
"recall": 0.8880814399165977,
"support": 32613.0
},
"step": 162
},
{
"epoch": 3.0,
"eval_B-Claim": {
"f1-score": 0.6576271186440678,
"precision": 0.6576271186440678,
"recall": 0.6576271186440678,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.8673139158576051,
"precision": 0.8758169934640523,
"recall": 0.8589743589743589,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8838487972508591,
"precision": 0.8832417582417582,
"recall": 0.8844566712517193,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6468460321049062,
"precision": 0.6083351052519669,
"recall": 0.6905623944001931,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.8695855771482088,
"precision": 0.8936477382098171,
"recall": 0.8467852257181943,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.8926256077795786,
"precision": 0.9090533960551291,
"recall": 0.8767810236408501,
"support": 12563.0
},
"eval_O": {
"f1-score": 0.9998803589232302,
"precision": 0.9997607464710104,
"recall": 1.0,
"support": 12536.0
},
"eval_accuracy": 0.8965749854352559,
"eval_loss": 0.2399493306875229,
"eval_macro avg": {
"f1-score": 0.8311039153869222,
"precision": 0.8324975509054003,
"recall": 0.8307409703756262,
"support": 32613.0
},
"eval_runtime": 5.0024,
"eval_samples_per_second": 16.192,
"eval_steps_per_second": 2.199,
"eval_weighted avg": {
"f1-score": 0.8986385496019461,
"precision": 0.9016737059631544,
"recall": 0.8965749854352559,
"support": 32613.0
},
"step": 243
},
{
"epoch": 4.0,
"eval_B-Claim": {
"f1-score": 0.6106346483704975,
"precision": 0.6180555555555556,
"recall": 0.6033898305084746,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.8498583569405098,
"precision": 0.7614213197969543,
"recall": 0.9615384615384616,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8746478873239436,
"precision": 0.8961038961038961,
"recall": 0.8541953232462174,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.5964912280701754,
"precision": 0.6109845608706657,
"recall": 0.5826695631185131,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.8631961259079903,
"precision": 0.7741585233441911,
"recall": 0.9753761969904241,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.8933694290678411,
"precision": 0.9071885770556376,
"recall": 0.8799649765183475,
"support": 12563.0
},
"eval_O": {
"f1-score": 0.9999601132782897,
"precision": 1.0,
"recall": 0.9999202297383536,
"support": 12536.0
},
"eval_accuracy": 0.8920369177935179,
"eval_loss": 0.2815629839897156,
"eval_macro avg": {
"f1-score": 0.8125939698513209,
"precision": 0.7954160618181286,
"recall": 0.8367220830941131,
"support": 32613.0
},
"eval_runtime": 4.9474,
"eval_samples_per_second": 16.372,
"eval_steps_per_second": 2.223,
"eval_weighted avg": {
"f1-score": 0.8914155863760895,
"precision": 0.892730641712682,
"recall": 0.8920369177935179,
"support": 32613.0
},
"step": 324
},
{
"epoch": 5.0,
"eval_B-Claim": {
"f1-score": 0.6796116504854369,
"precision": 0.6501547987616099,
"recall": 0.711864406779661,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.8746177370030581,
"precision": 0.8362573099415205,
"recall": 0.9166666666666666,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8836879432624114,
"precision": 0.9121522693997072,
"recall": 0.8569463548830811,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6557152635181382,
"precision": 0.6216742375081116,
"recall": 0.6937002172338885,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.8859746610357857,
"precision": 0.8642671292281006,
"recall": 0.9088007295941632,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.8956745077255495,
"precision": 0.9180177168644492,
"recall": 0.874393058982727,
"support": 12563.0
},
"eval_O": {
"f1-score": 0.9998006141085457,
"precision": 0.9996013077107089,
"recall": 1.0,
"support": 12536.0
},
"eval_accuracy": 0.9003771502161715,
"eval_loss": 0.2959797978401184,
"eval_macro avg": {
"f1-score": 0.839297482448418,
"precision": 0.8288749670591724,
"recall": 0.8517673477343124,
"support": 32613.0
},
"eval_runtime": 4.9768,
"eval_samples_per_second": 16.275,
"eval_steps_per_second": 2.21,
"eval_weighted avg": {
"f1-score": 0.9022413468876027,
"precision": 0.9051721478141229,
"recall": 0.9003771502161715,
"support": 32613.0
},
"step": 405
},
{
"epoch": 6.0,
"eval_B-Claim": {
"f1-score": 0.6655518394648828,
"precision": 0.6567656765676567,
"recall": 0.6745762711864407,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.8807339449541285,
"precision": 0.8421052631578947,
"recall": 0.9230769230769231,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8812849162011174,
"precision": 0.8950354609929078,
"recall": 0.8679504814305364,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.634203994799669,
"precision": 0.6213524779990737,
"recall": 0.647598358677287,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.8926454445664106,
"precision": 0.8607112616426758,
"recall": 0.9270405836753306,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.8911586596689544,
"precision": 0.9041533546325878,
"recall": 0.8785321977234737,
"support": 12563.0
},
"eval_O": {
"f1-score": 0.9995614559661922,
"precision": 0.9991232964055152,
"recall": 1.0,
"support": 12536.0
},
"eval_accuracy": 0.8972802256768774,
"eval_loss": 0.33718833327293396,
"eval_macro avg": {
"f1-score": 0.8350200365173363,
"precision": 0.8256066844854731,
"recall": 0.8455392593957132,
"support": 32613.0
},
"eval_runtime": 4.9878,
"eval_samples_per_second": 16.24,
"eval_steps_per_second": 2.205,
"eval_weighted avg": {
"f1-score": 0.8979742337698349,
"precision": 0.8990738793396261,
"recall": 0.8972802256768774,
"support": 32613.0
},
"step": 486
},
{
"epoch": 6.17,
"grad_norm": 10.722956657409668,
"learning_rate": 1.7530864197530865e-05,
"loss": 0.2434,
"step": 500
},
{
"epoch": 7.0,
"eval_B-Claim": {
"f1-score": 0.6608695652173914,
"precision": 0.6785714285714286,
"recall": 0.6440677966101694,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.875,
"precision": 0.8536585365853658,
"recall": 0.8974358974358975,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8905608755129958,
"precision": 0.8857142857142857,
"recall": 0.8954607977991746,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6306948332909138,
"precision": 0.6670255720053836,
"recall": 0.5981173062997828,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.890302764370338,
"precision": 0.8579281183932347,
"recall": 0.9252165982672138,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.9037468972853708,
"precision": 0.8947573724449992,
"recall": 0.9129188888004458,
"support": 12563.0
},
"eval_O": {
"f1-score": 1.0,
"precision": 1.0,
"recall": 1.0,
"support": 12536.0
},
"eval_accuracy": 0.9043326280930917,
"eval_loss": 0.43479764461517334,
"eval_macro avg": {
"f1-score": 0.8358821336681442,
"precision": 0.8339507591020997,
"recall": 0.8390310407446692,
"support": 32613.0
},
"eval_runtime": 4.9479,
"eval_samples_per_second": 16.371,
"eval_steps_per_second": 2.223,
"eval_weighted avg": {
"f1-score": 0.9025256555797259,
"precision": 0.9014510706568353,
"recall": 0.9043326280930917,
"support": 32613.0
},
"step": 567
}
],
"logging_steps": 500,
"max_steps": 4050,
"num_input_tokens_seen": 0,
"num_train_epochs": 50,
"save_steps": 500,
"total_flos": 1003409801793000.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}