Theoreticallyhugo's picture
Training in progress, epoch 37, checkpoint
1dec4db verified
raw
history blame
69 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 37.0,
"eval_steps": 500,
"global_step": 2997,
"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
},
{
"epoch": 8.0,
"eval_B-Claim": {
"f1-score": 0.6611295681063122,
"precision": 0.6482084690553745,
"recall": 0.6745762711864407,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.8925081433224756,
"precision": 0.9072847682119205,
"recall": 0.8782051282051282,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8810511756569848,
"precision": 0.885952712100139,
"recall": 0.8762035763411279,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6376404494382022,
"precision": 0.6189502385821404,
"recall": 0.6574945691527878,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.8858131487889275,
"precision": 0.896358543417367,
"recall": 0.8755129958960328,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.8946945982823662,
"precision": 0.9022258195062728,
"recall": 0.8872880681365916,
"support": 12563.0
},
"eval_O": {
"f1-score": 0.9999202361011406,
"precision": 0.9998404849258254,
"recall": 1.0,
"support": 12536.0
},
"eval_accuracy": 0.8984147425873118,
"eval_loss": 0.3937377631664276,
"eval_macro avg": {
"f1-score": 0.8361081885280585,
"precision": 0.836974433685577,
"recall": 0.8356115155597299,
"support": 32613.0
},
"eval_runtime": 5.0071,
"eval_samples_per_second": 16.177,
"eval_steps_per_second": 2.197,
"eval_weighted avg": {
"f1-score": 0.8994624730308206,
"precision": 0.9007308115646135,
"recall": 0.8984147425873118,
"support": 32613.0
},
"step": 648
},
{
"epoch": 9.0,
"eval_B-Claim": {
"f1-score": 0.6821192052980132,
"precision": 0.6666666666666666,
"recall": 0.6983050847457627,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.8510638297872339,
"precision": 0.9523809523809523,
"recall": 0.7692307692307693,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8959891230455472,
"precision": 0.885752688172043,
"recall": 0.90646492434663,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6547967670141736,
"precision": 0.636094674556213,
"recall": 0.6746319092445088,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.8507386653082017,
"precision": 0.9636468551644547,
"recall": 0.7615139078887369,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.9060476867203537,
"precision": 0.8987391338397682,
"recall": 0.9134760805540078,
"support": 12563.0
},
"eval_O": {
"f1-score": 0.9999202361011406,
"precision": 0.9998404849258254,
"recall": 1.0,
"support": 12536.0
},
"eval_accuracy": 0.9033820868978628,
"eval_loss": 0.4608707129955292,
"eval_macro avg": {
"f1-score": 0.8343822161820948,
"precision": 0.8575887793865605,
"recall": 0.8176603822872022,
"support": 32613.0
},
"eval_runtime": 4.9809,
"eval_samples_per_second": 16.262,
"eval_steps_per_second": 2.208,
"eval_weighted avg": {
"f1-score": 0.9039813964448579,
"precision": 0.9064685293306464,
"recall": 0.9033820868978628,
"support": 32613.0
},
"step": 729
},
{
"epoch": 10.0,
"eval_B-Claim": {
"f1-score": 0.6863354037267081,
"precision": 0.6332378223495702,
"recall": 0.7491525423728813,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.8976897689768977,
"precision": 0.9251700680272109,
"recall": 0.8717948717948718,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8780141843971632,
"precision": 0.9062957540263543,
"recall": 0.8514442916093535,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6615143369175628,
"precision": 0.6171368861024034,
"recall": 0.7127685252232682,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.9019424292066465,
"precision": 0.9264423076923077,
"recall": 0.8787049703602371,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.8934422897101273,
"precision": 0.9130796077779625,
"recall": 0.8746318554485394,
"support": 12563.0
},
"eval_O": {
"f1-score": 0.9999601132782897,
"precision": 1.0,
"recall": 0.9999202297383536,
"support": 12536.0
},
"eval_accuracy": 0.9008370895041854,
"eval_loss": 0.49426138401031494,
"eval_macro avg": {
"f1-score": 0.8455569323161993,
"precision": 0.8459089208536871,
"recall": 0.8483453266496436,
"support": 32613.0
},
"eval_runtime": 4.962,
"eval_samples_per_second": 16.324,
"eval_steps_per_second": 2.217,
"eval_weighted avg": {
"f1-score": 0.9032978864532892,
"precision": 0.9071693470023781,
"recall": 0.9008370895041854,
"support": 32613.0
},
"step": 810
},
{
"epoch": 11.0,
"eval_B-Claim": {
"f1-score": 0.6654991243432573,
"precision": 0.6884057971014492,
"recall": 0.6440677966101694,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.8888888888888888,
"precision": 0.9361702127659575,
"recall": 0.8461538461538461,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8911290322580646,
"precision": 0.871222076215506,
"recall": 0.9119669876203577,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6376628304034401,
"precision": 0.6697662061636557,
"recall": 0.6084962587496983,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.8884068450228971,
"precision": 0.9422290388548057,
"recall": 0.8404012767897857,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.904972804972805,
"precision": 0.8838885937618578,
"recall": 0.9270874791053092,
"support": 12563.0
},
"eval_O": {
"f1-score": 0.9999202361011406,
"precision": 0.9998404849258254,
"recall": 1.0,
"support": 12536.0
},
"eval_accuracy": 0.9055284702419281,
"eval_loss": 0.5303362607955933,
"eval_macro avg": {
"f1-score": 0.8394971088557848,
"precision": 0.8559317728270083,
"recall": 0.8254533778613096,
"support": 32613.0
},
"eval_runtime": 4.9749,
"eval_samples_per_second": 16.282,
"eval_steps_per_second": 2.211,
"eval_weighted avg": {
"f1-score": 0.9038459038093231,
"precision": 0.9033803424876604,
"recall": 0.9055284702419281,
"support": 32613.0
},
"step": 891
},
{
"epoch": 12.0,
"eval_B-Claim": {
"f1-score": 0.6374045801526718,
"precision": 0.7292576419213974,
"recall": 0.5661016949152542,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.9114754098360656,
"precision": 0.9328859060402684,
"recall": 0.8910256410256411,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8913612565445026,
"precision": 0.850187265917603,
"recall": 0.936726272352132,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.5983549421441516,
"precision": 0.7082508250825083,
"recall": 0.5179821385469466,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.9206057824690226,
"precision": 0.9265588914549654,
"recall": 0.9147286821705426,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.9017204628501827,
"precision": 0.8640309285870595,
"recall": 0.9428480458489215,
"support": 12563.0
},
"eval_O": {
"f1-score": 0.9997606319317004,
"precision": 1.0,
"recall": 0.9995213784301212,
"support": 12536.0
},
"eval_accuracy": 0.9049765430963113,
"eval_loss": 0.5691992044448853,
"eval_macro avg": {
"f1-score": 0.8372404379897568,
"precision": 0.8587387798576859,
"recall": 0.8241334076127942,
"support": 32613.0
},
"eval_runtime": 4.9632,
"eval_samples_per_second": 16.32,
"eval_steps_per_second": 2.216,
"eval_weighted avg": {
"f1-score": 0.8995624631750451,
"precision": 0.8995123024912762,
"recall": 0.9049765430963113,
"support": 32613.0
},
"step": 972
},
{
"epoch": 12.35,
"grad_norm": 8.504526138305664,
"learning_rate": 1.506172839506173e-05,
"loss": 0.0319,
"step": 1000
},
{
"epoch": 13.0,
"eval_B-Claim": {
"f1-score": 0.6779661016949152,
"precision": 0.6779661016949152,
"recall": 0.6779661016949152,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.9096774193548387,
"precision": 0.9155844155844156,
"recall": 0.9038461538461539,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8873626373626373,
"precision": 0.8861454046639232,
"recall": 0.8885832187070152,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.663892288861689,
"precision": 0.6734541842562701,
"recall": 0.6545981173062998,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.9122568973315242,
"precision": 0.9048900852400179,
"recall": 0.9197446420428637,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.9055930186433956,
"precision": 0.9025855934213648,
"recall": 0.9086205524158243,
"support": 12563.0
},
"eval_O": {
"f1-score": 0.9998404340194671,
"precision": 1.0,
"recall": 0.9996809189534142,
"support": 12536.0
},
"eval_accuracy": 0.9095452733572502,
"eval_loss": 0.5995727777481079,
"eval_macro avg": {
"f1-score": 0.8509412567526382,
"precision": 0.8515179692658439,
"recall": 0.8504342435666409,
"support": 32613.0
},
"eval_runtime": 4.967,
"eval_samples_per_second": 16.308,
"eval_steps_per_second": 2.215,
"eval_weighted avg": {
"f1-score": 0.9091182110651892,
"precision": 0.908741493590885,
"recall": 0.9095452733572502,
"support": 32613.0
},
"step": 1053
},
{
"epoch": 14.0,
"eval_B-Claim": {
"f1-score": 0.6543438077634012,
"precision": 0.7195121951219512,
"recall": 0.6,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.8918032786885245,
"precision": 0.912751677852349,
"recall": 0.8717948717948718,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.895364238410596,
"precision": 0.8633461047254151,
"recall": 0.9298486932599724,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.612272977435333,
"precision": 0.712,
"recall": 0.5370504465363264,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.9033142857142857,
"precision": 0.9055912007332723,
"recall": 0.9010487916096671,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.9070541005543873,
"precision": 0.8727192466156563,
"recall": 0.9442012258218578,
"support": 12563.0
},
"eval_O": {
"f1-score": 1.0,
"precision": 1.0,
"recall": 1.0,
"support": 12536.0
},
"eval_accuracy": 0.9072455769171802,
"eval_loss": 0.6337578892707825,
"eval_macro avg": {
"f1-score": 0.8377360983666469,
"precision": 0.8551314892926634,
"recall": 0.8262777184318136,
"support": 32613.0
},
"eval_runtime": 4.9902,
"eval_samples_per_second": 16.232,
"eval_steps_per_second": 2.204,
"eval_weighted avg": {
"f1-score": 0.9024627717609818,
"precision": 0.902034384321647,
"recall": 0.9072455769171802,
"support": 32613.0
},
"step": 1134
},
{
"epoch": 15.0,
"eval_B-Claim": {
"f1-score": 0.6715867158671587,
"precision": 0.7368421052631579,
"recall": 0.6169491525423729,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.8902077151335311,
"precision": 0.8287292817679558,
"recall": 0.9615384615384616,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.896551724137931,
"precision": 0.8816489361702128,
"recall": 0.9119669876203577,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6393111798735368,
"precision": 0.7221884498480243,
"recall": 0.5734974656046343,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.898728813559322,
"precision": 0.8393351800554016,
"recall": 0.9671682626538988,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.9101119213820535,
"precision": 0.892125382262997,
"recall": 0.9288386531879328,
"support": 12563.0
},
"eval_O": {
"f1-score": 1.0,
"precision": 1.0,
"recall": 1.0,
"support": 12536.0
},
"eval_accuracy": 0.9105878024100819,
"eval_loss": 0.6874175667762756,
"eval_macro avg": {
"f1-score": 0.8437854385647904,
"precision": 0.8429813336239642,
"recall": 0.8514227118782368,
"support": 32613.0
},
"eval_runtime": 4.9796,
"eval_samples_per_second": 16.266,
"eval_steps_per_second": 2.209,
"eval_weighted avg": {
"f1-score": 0.9069419606556991,
"precision": 0.9065117879543761,
"recall": 0.9105878024100819,
"support": 32613.0
},
"step": 1215
},
{
"epoch": 16.0,
"eval_B-Claim": {
"f1-score": 0.676923076923077,
"precision": 0.6827586206896552,
"recall": 0.6711864406779661,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.8980891719745223,
"precision": 0.8924050632911392,
"recall": 0.9038461538461539,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8902606310013718,
"precision": 0.8878248974008208,
"recall": 0.8927097661623109,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6403442166540116,
"precision": 0.6730513434424049,
"recall": 0.6106685976345644,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.9115737631520036,
"precision": 0.8953386103781882,
"recall": 0.9284085727314182,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.9030989460437312,
"precision": 0.8924990283715507,
"recall": 0.9139536734856324,
"support": 12563.0
},
"eval_O": {
"f1-score": 1.0,
"precision": 1.0,
"recall": 1.0,
"support": 12536.0
},
"eval_accuracy": 0.9067549750099654,
"eval_loss": 0.6374069452285767,
"eval_macro avg": {
"f1-score": 0.8457556865355311,
"precision": 0.8462682233676798,
"recall": 0.8458247435054351,
"support": 32613.0
},
"eval_runtime": 5.004,
"eval_samples_per_second": 16.187,
"eval_steps_per_second": 2.198,
"eval_weighted avg": {
"f1-score": 0.905181158084066,
"precision": 0.9041324706485238,
"recall": 0.9067549750099654,
"support": 32613.0
},
"step": 1296
},
{
"epoch": 17.0,
"eval_B-Claim": {
"f1-score": 0.7001620745542951,
"precision": 0.6708074534161491,
"recall": 0.7322033898305085,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.910828025477707,
"precision": 0.9050632911392406,
"recall": 0.9166666666666666,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8870175438596491,
"precision": 0.9054441260744985,
"recall": 0.8693259972489684,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6722241519045965,
"precision": 0.6459724076546507,
"recall": 0.7006999758629012,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.9159550561797752,
"precision": 0.9029685423128047,
"recall": 0.9293205654354765,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.8987500505642975,
"precision": 0.9137193617371279,
"recall": 0.884263312902969,
"support": 12563.0
},
"eval_O": {
"f1-score": 0.999600989545926,
"precision": 1.0,
"recall": 0.9992022973835354,
"support": 12536.0
},
"eval_accuracy": 0.9066016619139607,
"eval_loss": 0.5605483055114746,
"eval_macro avg": {
"f1-score": 0.8549339845837495,
"precision": 0.8491393117620675,
"recall": 0.8616688864758607,
"support": 32613.0
},
"eval_runtime": 5.0022,
"eval_samples_per_second": 16.193,
"eval_steps_per_second": 2.199,
"eval_weighted avg": {
"f1-score": 0.9078958614075368,
"precision": 0.9097251400220888,
"recall": 0.9066016619139607,
"support": 32613.0
},
"step": 1377
},
{
"epoch": 18.0,
"eval_B-Claim": {
"f1-score": 0.7140495867768595,
"precision": 0.6967741935483871,
"recall": 0.7322033898305085,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.9066666666666667,
"precision": 0.9444444444444444,
"recall": 0.8717948717948718,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8988300068823124,
"precision": 0.8994490358126722,
"recall": 0.8982118294360385,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6946223564954682,
"precision": 0.6955469506292352,
"recall": 0.6937002172338885,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.9217432052483598,
"precision": 0.9479518072289157,
"recall": 0.8969448244414044,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.9124099152609487,
"precision": 0.9078086833188874,
"recall": 0.9170580275411924,
"support": 12563.0
},
"eval_O": {
"f1-score": 0.9999601132782897,
"precision": 1.0,
"recall": 0.9999202297383536,
"support": 12536.0
},
"eval_accuracy": 0.916873639346273,
"eval_loss": 0.636456310749054,
"eval_macro avg": {
"f1-score": 0.8640402643727008,
"precision": 0.8702821592832203,
"recall": 0.8585476271451797,
"support": 32613.0
},
"eval_runtime": 4.9811,
"eval_samples_per_second": 16.261,
"eval_steps_per_second": 2.208,
"eval_weighted avg": {
"f1-score": 0.9168994897940371,
"precision": 0.917060404983014,
"recall": 0.916873639346273,
"support": 32613.0
},
"step": 1458
},
{
"epoch": 18.52,
"grad_norm": 2.2237088680267334,
"learning_rate": 1.2592592592592593e-05,
"loss": 0.0112,
"step": 1500
},
{
"epoch": 19.0,
"eval_B-Claim": {
"f1-score": 0.6907216494845362,
"precision": 0.7003484320557491,
"recall": 0.6813559322033899,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.9067524115755627,
"precision": 0.9096774193548387,
"recall": 0.9038461538461539,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8940533151059467,
"precision": 0.8885869565217391,
"recall": 0.8995873452544704,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6695981433980701,
"precision": 0.6777942631058358,
"recall": 0.6615978759353126,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.9135184342284934,
"precision": 0.9118582462517038,
"recall": 0.9151846785225718,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.9059761272157671,
"precision": 0.9027185079816659,
"recall": 0.9092573429913238,
"support": 12563.0
},
"eval_O": {
"f1-score": 1.0,
"precision": 1.0,
"recall": 1.0,
"support": 12536.0
},
"eval_accuracy": 0.9107717781252874,
"eval_loss": 0.6661651134490967,
"eval_macro avg": {
"f1-score": 0.8543742972869109,
"precision": 0.8558548321816474,
"recall": 0.8529756183933175,
"support": 32613.0
},
"eval_runtime": 4.9645,
"eval_samples_per_second": 16.316,
"eval_steps_per_second": 2.216,
"eval_weighted avg": {
"f1-score": 0.9103873346045664,
"precision": 0.9100412278575488,
"recall": 0.9107717781252874,
"support": 32613.0
},
"step": 1539
},
{
"epoch": 20.0,
"eval_B-Claim": {
"f1-score": 0.697278911564626,
"precision": 0.6996587030716723,
"recall": 0.6949152542372882,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.9072847682119205,
"precision": 0.9383561643835616,
"recall": 0.8782051282051282,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8958475153165418,
"precision": 0.8867924528301887,
"recall": 0.9050894085281981,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6639919759277834,
"precision": 0.6908426819723454,
"recall": 0.6391503741250302,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.9188432835820896,
"precision": 0.9403341288782816,
"recall": 0.898312813497492,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.9079586401378662,
"precision": 0.8937466265710541,
"recall": 0.9226299450768128,
"support": 12563.0
},
"eval_O": {
"f1-score": 0.9999601132782897,
"precision": 1.0,
"recall": 0.9999202297383536,
"support": 12536.0
},
"eval_accuracy": 0.9120289455125257,
"eval_loss": 0.6076620817184448,
"eval_macro avg": {
"f1-score": 0.8558807440027308,
"precision": 0.8642472511010147,
"recall": 0.8483175933440433,
"support": 32613.0
},
"eval_runtime": 4.9557,
"eval_samples_per_second": 16.345,
"eval_steps_per_second": 2.22,
"eval_weighted avg": {
"f1-score": 0.910883429910181,
"precision": 0.9102484848959365,
"recall": 0.9120289455125257,
"support": 32613.0
},
"step": 1620
},
{
"epoch": 21.0,
"eval_B-Claim": {
"f1-score": 0.6752767527675276,
"precision": 0.7408906882591093,
"recall": 0.6203389830508474,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.9120521172638437,
"precision": 0.9271523178807947,
"recall": 0.8974358974358975,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8992042440318302,
"precision": 0.8681177976952625,
"recall": 0.9325997248968363,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6303986710963455,
"precision": 0.73904576436222,
"recall": 0.5496017378711079,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.9182505152278452,
"precision": 0.922263109475621,
"recall": 0.9142726858185134,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.909555793008701,
"precision": 0.8736163037900447,
"recall": 0.9485791610284168,
"support": 12563.0
},
"eval_O": {
"f1-score": 0.9999202361011406,
"precision": 0.9998404849258254,
"recall": 1.0,
"support": 12536.0
},
"eval_accuracy": 0.9117836445589182,
"eval_loss": 0.685625433921814,
"eval_macro avg": {
"f1-score": 0.8492369042138906,
"precision": 0.8672752094841254,
"recall": 0.8375468843002313,
"support": 32613.0
},
"eval_runtime": 4.9777,
"eval_samples_per_second": 16.273,
"eval_steps_per_second": 2.21,
"eval_weighted avg": {
"f1-score": 0.9070745665639394,
"precision": 0.9072440958491244,
"recall": 0.9117836445589182,
"support": 32613.0
},
"step": 1701
},
{
"epoch": 22.0,
"eval_B-Claim": {
"f1-score": 0.7060653188180404,
"precision": 0.6522988505747126,
"recall": 0.7694915254237288,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.9032258064516129,
"precision": 0.9090909090909091,
"recall": 0.8974358974358975,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8852459016393444,
"precision": 0.9186390532544378,
"recall": 0.8541953232462174,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6783193277310924,
"precision": 0.6329987452948557,
"recall": 0.7306299782766111,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.9076923076923077,
"precision": 0.9007633587786259,
"recall": 0.9147286821705426,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.8980493191019507,
"precision": 0.9234650967199327,
"recall": 0.8739950648730399,
"support": 12563.0
},
"eval_O": {
"f1-score": 1.0,
"precision": 1.0,
"recall": 1.0,
"support": 12536.0
},
"eval_accuracy": 0.9056817833379327,
"eval_loss": 0.714400589466095,
"eval_macro avg": {
"f1-score": 0.8540854259191927,
"precision": 0.8481794305304963,
"recall": 0.8629252102037197,
"support": 32613.0
},
"eval_runtime": 5.1631,
"eval_samples_per_second": 15.688,
"eval_steps_per_second": 2.13,
"eval_weighted avg": {
"f1-score": 0.9079755332777275,
"precision": 0.911828926872852,
"recall": 0.9056817833379327,
"support": 32613.0
},
"step": 1782
},
{
"epoch": 23.0,
"eval_B-Claim": {
"f1-score": 0.6942148760330579,
"precision": 0.6774193548387096,
"recall": 0.711864406779661,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.88659793814433,
"precision": 0.9555555555555556,
"recall": 0.8269230769230769,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8945205479452054,
"precision": 0.8908594815825375,
"recall": 0.8982118294360385,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6700834326579261,
"precision": 0.6618789733929833,
"recall": 0.6784938450398262,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.8958790538892953,
"precision": 0.9627882599580713,
"recall": 0.8376652986776105,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.9067846840795036,
"precision": 0.900345260514752,
"recall": 0.9133168829101329,
"support": 12563.0
},
"eval_O": {
"f1-score": 1.0,
"precision": 1.0,
"recall": 1.0,
"support": 12536.0
},
"eval_accuracy": 0.909146659307638,
"eval_loss": 0.6947330236434937,
"eval_macro avg": {
"f1-score": 0.8497257903927597,
"precision": 0.8641209836918013,
"recall": 0.8380679056809066,
"support": 32613.0
},
"eval_runtime": 4.9764,
"eval_samples_per_second": 16.277,
"eval_steps_per_second": 2.21,
"eval_weighted avg": {
"f1-score": 0.9095199312515945,
"precision": 0.9105926154648943,
"recall": 0.909146659307638,
"support": 32613.0
},
"step": 1863
},
{
"epoch": 24.0,
"eval_B-Claim": {
"f1-score": 0.7096774193548386,
"precision": 0.676923076923077,
"recall": 0.7457627118644068,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.9130434782608695,
"precision": 0.8855421686746988,
"recall": 0.9423076923076923,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8896746817538898,
"precision": 0.9155749636098981,
"recall": 0.8651994497936726,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6777306967984934,
"precision": 0.6613829542844015,
"recall": 0.6949070721699252,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.9096057503811806,
"precision": 0.8707256046705588,
"recall": 0.9521203830369357,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.9036461494880823,
"precision": 0.9190813302601252,
"recall": 0.8887208469314655,
"support": 12563.0
},
"eval_O": {
"f1-score": 1.0,
"precision": 1.0,
"recall": 1.0,
"support": 12536.0
},
"eval_accuracy": 0.9095759359764511,
"eval_loss": 0.7040016055107117,
"eval_macro avg": {
"f1-score": 0.8576254537196221,
"precision": 0.8470328712032513,
"recall": 0.8698597365862997,
"support": 32613.0
},
"eval_runtime": 4.987,
"eval_samples_per_second": 16.242,
"eval_steps_per_second": 2.206,
"eval_weighted avg": {
"f1-score": 0.9103637622541415,
"precision": 0.9117679902876374,
"recall": 0.9095759359764511,
"support": 32613.0
},
"step": 1944
},
{
"epoch": 24.69,
"grad_norm": 0.0041221510618925095,
"learning_rate": 1.0123456790123458e-05,
"loss": 0.0061,
"step": 2000
},
{
"epoch": 25.0,
"eval_B-Claim": {
"f1-score": 0.6870748299319729,
"precision": 0.689419795221843,
"recall": 0.6847457627118644,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.898360655737705,
"precision": 0.9194630872483222,
"recall": 0.8782051282051282,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8940533151059467,
"precision": 0.8885869565217391,
"recall": 0.8995873452544704,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6645924082140635,
"precision": 0.6860226104830421,
"recall": 0.6444605358435916,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.9111880046136103,
"precision": 0.9220354808590103,
"recall": 0.9005927952576379,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.9084473808400189,
"precision": 0.8977846871356393,
"recall": 0.919366393377378,
"support": 12563.0
},
"eval_O": {
"f1-score": 1.0,
"precision": 1.0,
"recall": 1.0,
"support": 12536.0
},
"eval_accuracy": 0.911415693128507,
"eval_loss": 0.6578116416931152,
"eval_macro avg": {
"f1-score": 0.8519595134919024,
"precision": 0.8576160882099424,
"recall": 0.8467082800928672,
"support": 32613.0
},
"eval_runtime": 4.9806,
"eval_samples_per_second": 16.263,
"eval_steps_per_second": 2.209,
"eval_weighted avg": {
"f1-score": 0.9104735591343546,
"precision": 0.9098182414323299,
"recall": 0.911415693128507,
"support": 32613.0
},
"step": 2025
},
{
"epoch": 26.0,
"eval_B-Claim": {
"f1-score": 0.7008264462809918,
"precision": 0.6838709677419355,
"recall": 0.7186440677966102,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.8947368421052632,
"precision": 0.918918918918919,
"recall": 0.8717948717948718,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8964088397790055,
"precision": 0.9001386962552012,
"recall": 0.8927097661623109,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6849380362249762,
"precision": 0.6763944457519416,
"recall": 0.6937002172338885,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.9123211813567144,
"precision": 0.9234002802428771,
"recall": 0.9015047879616963,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.9089821314613912,
"precision": 0.910944120233432,
"recall": 0.9070285759770755,
"support": 12563.0
},
"eval_O": {
"f1-score": 0.9999601132782897,
"precision": 1.0,
"recall": 0.9999202297383536,
"support": 12536.0
},
"eval_accuracy": 0.9130714745653574,
"eval_loss": 0.7021818161010742,
"eval_macro avg": {
"f1-score": 0.8568819414980903,
"precision": 0.8590953470206152,
"recall": 0.8550432166664008,
"support": 32613.0
},
"eval_runtime": 4.965,
"eval_samples_per_second": 16.314,
"eval_steps_per_second": 2.215,
"eval_weighted avg": {
"f1-score": 0.913484595343639,
"precision": 0.9139608163869709,
"recall": 0.9130714745653574,
"support": 32613.0
},
"step": 2106
},
{
"epoch": 27.0,
"eval_B-Claim": {
"f1-score": 0.692967409948542,
"precision": 0.7013888888888888,
"recall": 0.6847457627118644,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.9073482428115015,
"precision": 0.9044585987261147,
"recall": 0.9102564102564102,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8958904109589041,
"precision": 0.8922237380627558,
"recall": 0.8995873452544704,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6764050507551375,
"precision": 0.69428208386277,
"recall": 0.6594255370504465,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.9191374663072776,
"precision": 0.9057104913678619,
"recall": 0.93296853625171,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.9100839005857211,
"precision": 0.9049980322707596,
"recall": 0.9152272546366313,
"support": 12563.0
},
"eval_O": {
"f1-score": 1.0,
"precision": 1.0,
"recall": 1.0,
"support": 12536.0
},
"eval_accuracy": 0.9140526783797872,
"eval_loss": 0.7241345643997192,
"eval_macro avg": {
"f1-score": 0.8574046401952976,
"precision": 0.8575802618827357,
"recall": 0.8574586923087905,
"support": 32613.0
},
"eval_runtime": 4.9786,
"eval_samples_per_second": 16.27,
"eval_steps_per_second": 2.209,
"eval_weighted avg": {
"f1-score": 0.9132763828083692,
"precision": 0.9126659915256446,
"recall": 0.9140526783797872,
"support": 32613.0
},
"step": 2187
},
{
"epoch": 28.0,
"eval_B-Claim": {
"f1-score": 0.702791461412151,
"precision": 0.6815286624203821,
"recall": 0.7254237288135593,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.8970099667774087,
"precision": 0.9310344827586207,
"recall": 0.8653846153846154,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8956461644782308,
"precision": 0.9,
"recall": 0.8913342503438789,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6791507633587787,
"precision": 0.6713039377505305,
"recall": 0.6871832005792904,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.9076923076923077,
"precision": 0.9284692417739628,
"recall": 0.8878248974008208,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.9079402985074626,
"precision": 0.9079764368731094,
"recall": 0.9079041630183873,
"support": 12563.0
},
"eval_O": {
"f1-score": 0.9999202233745512,
"precision": 1.0,
"recall": 0.9998404594767071,
"support": 12536.0
},
"eval_accuracy": 0.9116303314629136,
"eval_loss": 0.7758038640022278,
"eval_macro avg": {
"f1-score": 0.85573588365727,
"precision": 0.8600446802252293,
"recall": 0.8521279021453229,
"support": 32613.0
},
"eval_runtime": 4.9782,
"eval_samples_per_second": 16.271,
"eval_steps_per_second": 2.21,
"eval_weighted avg": {
"f1-score": 0.9120331319181557,
"precision": 0.9125454748864557,
"recall": 0.9116303314629136,
"support": 32613.0
},
"step": 2268
},
{
"epoch": 29.0,
"eval_B-Claim": {
"f1-score": 0.7140495867768595,
"precision": 0.6967741935483871,
"recall": 0.7322033898305085,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.9155844155844156,
"precision": 0.9276315789473685,
"recall": 0.9038461538461539,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8975069252077562,
"precision": 0.9037656903765691,
"recall": 0.8913342503438789,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6932471264367815,
"precision": 0.6878118317890235,
"recall": 0.6987690079652426,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.9248,
"precision": 0.9271310724106324,
"recall": 0.9224806201550387,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.9102149894300187,
"precision": 0.912216181643748,
"recall": 0.9082225583061371,
"support": 12563.0
},
"eval_O": {
"f1-score": 0.9999601132782897,
"precision": 1.0,
"recall": 0.9999202297383536,
"support": 12536.0
},
"eval_accuracy": 0.9158311102934412,
"eval_loss": 0.7231832146644592,
"eval_macro avg": {
"f1-score": 0.8650518795305887,
"precision": 0.865047221245104,
"recall": 0.8652537443121877,
"support": 32613.0
},
"eval_runtime": 4.968,
"eval_samples_per_second": 16.304,
"eval_steps_per_second": 2.214,
"eval_weighted avg": {
"f1-score": 0.9160979814383814,
"precision": 0.9163913568578534,
"recall": 0.9158311102934412,
"support": 32613.0
},
"step": 2349
},
{
"epoch": 30.0,
"eval_B-Claim": {
"f1-score": 0.6937394247038917,
"precision": 0.6925675675675675,
"recall": 0.6949152542372882,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.9061488673139159,
"precision": 0.9150326797385621,
"recall": 0.8974358974358975,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8942307692307693,
"precision": 0.8930041152263375,
"recall": 0.8954607977991746,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6808769792935445,
"precision": 0.6872387509220556,
"recall": 0.6746319092445088,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.9230070406540993,
"precision": 0.9194570135746606,
"recall": 0.9265845873233014,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.908715505261068,
"precision": 0.9065916653462209,
"recall": 0.9108493194300724,
"support": 12563.0
},
"eval_O": {
"f1-score": 1.0,
"precision": 1.0,
"recall": 1.0,
"support": 12536.0
},
"eval_accuracy": 0.9138073774261798,
"eval_loss": 0.7184767127037048,
"eval_macro avg": {
"f1-score": 0.8581026552081842,
"precision": 0.8591273989107719,
"recall": 0.8571253950671774,
"support": 32613.0
},
"eval_runtime": 4.9612,
"eval_samples_per_second": 16.327,
"eval_steps_per_second": 2.217,
"eval_weighted avg": {
"f1-score": 0.9135418017594757,
"precision": 0.9132976723952129,
"recall": 0.9138073774261798,
"support": 32613.0
},
"step": 2430
},
{
"epoch": 30.86,
"grad_norm": 0.002683656057342887,
"learning_rate": 7.654320987654322e-06,
"loss": 0.0024,
"step": 2500
},
{
"epoch": 31.0,
"eval_B-Claim": {
"f1-score": 0.6986754966887417,
"precision": 0.6828478964401294,
"recall": 0.7152542372881356,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.9206349206349206,
"precision": 0.9119496855345912,
"recall": 0.9294871794871795,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.890125173852573,
"precision": 0.90014064697609,
"recall": 0.8803301237964236,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6821539194662855,
"precision": 0.6734885909197835,
"recall": 0.6910451363746077,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.9271943751417554,
"precision": 0.9223826714801444,
"recall": 0.9320565435476517,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.905381076215243,
"precision": 0.9101512226512226,
"recall": 0.9006606702220807,
"support": 12563.0
},
"eval_O": {
"f1-score": 0.9999601132782897,
"precision": 1.0,
"recall": 0.9999202297383536,
"support": 12536.0
},
"eval_accuracy": 0.912304909085334,
"eval_loss": 0.73140949010849,
"eval_macro avg": {
"f1-score": 0.8605892964682583,
"precision": 0.8572801020002803,
"recall": 0.8641077314934904,
"support": 32613.0
},
"eval_runtime": 4.9803,
"eval_samples_per_second": 16.264,
"eval_steps_per_second": 2.209,
"eval_weighted avg": {
"f1-score": 0.9127082057497462,
"precision": 0.913175260529506,
"recall": 0.912304909085334,
"support": 32613.0
},
"step": 2511
},
{
"epoch": 32.0,
"eval_B-Claim": {
"f1-score": 0.6913996627318718,
"precision": 0.6879194630872483,
"recall": 0.6949152542372882,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.9240506329113924,
"precision": 0.9125,
"recall": 0.9358974358974359,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8895027624309392,
"precision": 0.8932038834951457,
"recall": 0.8858321870701513,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6711132670385641,
"precision": 0.6743845966366073,
"recall": 0.6678735216027033,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.928603302097278,
"precision": 0.909130624726955,
"recall": 0.9489284085727314,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.9038691663342641,
"precision": 0.9058927000879508,
"recall": 0.9018546525511423,
"support": 12563.0
},
"eval_O": {
"f1-score": 0.9999601132782897,
"precision": 1.0,
"recall": 0.9999202297383536,
"support": 12536.0
},
"eval_accuracy": 0.9109250912212922,
"eval_loss": 0.7511080503463745,
"eval_macro avg": {
"f1-score": 0.8583569866889427,
"precision": 0.8547187525762724,
"recall": 0.8621745270956865,
"support": 32613.0
},
"eval_runtime": 5.0707,
"eval_samples_per_second": 15.974,
"eval_steps_per_second": 2.169,
"eval_weighted avg": {
"f1-score": 0.9107546356079316,
"precision": 0.9106514058813452,
"recall": 0.9109250912212922,
"support": 32613.0
},
"step": 2592
},
{
"epoch": 33.0,
"eval_B-Claim": {
"f1-score": 0.7094594594594594,
"precision": 0.7070707070707071,
"recall": 0.711864406779661,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.9185667752442997,
"precision": 0.9337748344370861,
"recall": 0.9038461538461539,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8984910836762688,
"precision": 0.896032831737346,
"recall": 0.9009628610729024,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6867204695524578,
"precision": 0.695910780669145,
"recall": 0.6777697320782042,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.9270425776754891,
"precision": 0.9358736059479554,
"recall": 0.9183766529867761,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.9104648862512364,
"precision": 0.9051290119572057,
"recall": 0.9158640452121308,
"support": 12563.0
},
"eval_O": {
"f1-score": 0.9999601132782897,
"precision": 1.0,
"recall": 0.9999202297383536,
"support": 12536.0
},
"eval_accuracy": 0.9158617729126421,
"eval_loss": 0.7425341010093689,
"eval_macro avg": {
"f1-score": 0.8643864807339287,
"precision": 0.8676845388313493,
"recall": 0.8612291545305973,
"support": 32613.0
},
"eval_runtime": 4.9731,
"eval_samples_per_second": 16.288,
"eval_steps_per_second": 2.212,
"eval_weighted avg": {
"f1-score": 0.9155106123184129,
"precision": 0.9152281470826237,
"recall": 0.9158617729126421,
"support": 32613.0
},
"step": 2673
},
{
"epoch": 34.0,
"eval_B-Claim": {
"f1-score": 0.6989247311827957,
"precision": 0.7414448669201521,
"recall": 0.6610169491525424,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.9022082018927445,
"precision": 0.8881987577639752,
"recall": 0.9166666666666666,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.9055330634278002,
"precision": 0.8887417218543047,
"recall": 0.922971114167813,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6595328200443691,
"precision": 0.7178977272727273,
"recall": 0.6099444846729423,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.8977876106194691,
"precision": 0.8719381177481736,
"recall": 0.9252165982672138,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.9145199063231851,
"precision": 0.8972198820556023,
"recall": 0.9325001989970548,
"support": 12563.0
},
"eval_O": {
"f1-score": 0.9997606319317004,
"precision": 1.0,
"recall": 0.9995213784301212,
"support": 12536.0
},
"eval_accuracy": 0.9140526783797872,
"eval_loss": 0.7677819728851318,
"eval_macro avg": {
"f1-score": 0.8540381379174375,
"precision": 0.8579201533735622,
"recall": 0.8525481986220506,
"support": 32613.0
},
"eval_runtime": 5.0132,
"eval_samples_per_second": 16.157,
"eval_steps_per_second": 2.194,
"eval_weighted avg": {
"f1-score": 0.9115584392994356,
"precision": 0.9106057225130435,
"recall": 0.9140526783797872,
"support": 32613.0
},
"step": 2754
},
{
"epoch": 35.0,
"eval_B-Claim": {
"f1-score": 0.7009966777408638,
"precision": 0.6872964169381107,
"recall": 0.7152542372881356,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.9042904290429044,
"precision": 0.9319727891156463,
"recall": 0.8782051282051282,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8945554789800138,
"precision": 0.8964088397790055,
"recall": 0.8927097661623109,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.690017931858936,
"precision": 0.6835622927522501,
"recall": 0.6965966690803765,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.9171501508470644,
"precision": 0.9338374291115312,
"recall": 0.9010487916096671,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.910284986467123,
"precision": 0.910357455616591,
"recall": 0.9102125288545729,
"support": 12563.0
},
"eval_O": {
"f1-score": 1.0,
"precision": 1.0,
"recall": 1.0,
"support": 12536.0
},
"eval_accuracy": 0.9146659307638059,
"eval_loss": 0.808364987373352,
"eval_macro avg": {
"f1-score": 0.8596136649909865,
"precision": 0.8633478890447337,
"recall": 0.8562895887428844,
"support": 32613.0
},
"eval_runtime": 4.9841,
"eval_samples_per_second": 16.252,
"eval_steps_per_second": 2.207,
"eval_weighted avg": {
"f1-score": 0.9149777701397716,
"precision": 0.9153575016233867,
"recall": 0.9146659307638059,
"support": 32613.0
},
"step": 2835
},
{
"epoch": 36.0,
"eval_B-Claim": {
"f1-score": 0.6881720430107526,
"precision": 0.7300380228136882,
"recall": 0.6508474576271186,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.9050632911392406,
"precision": 0.89375,
"recall": 0.9166666666666666,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.9001349527665317,
"precision": 0.8834437086092716,
"recall": 0.9174690508940853,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6585080067699518,
"precision": 0.7148106274731487,
"recall": 0.6104272266473569,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.9073909171861086,
"precision": 0.8864723792953458,
"recall": 0.9293205654354765,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.9130146341463415,
"precision": 0.8955749502373297,
"recall": 0.9311470190241184,
"support": 12563.0
},
"eval_O": {
"f1-score": 1.0,
"precision": 1.0,
"recall": 1.0,
"support": 12536.0
},
"eval_accuracy": 0.9138380400453807,
"eval_loss": 0.8094782829284668,
"eval_macro avg": {
"f1-score": 0.8531834064312752,
"precision": 0.8577270983469691,
"recall": 0.8508397123278317,
"support": 32613.0
},
"eval_runtime": 4.948,
"eval_samples_per_second": 16.37,
"eval_steps_per_second": 2.223,
"eval_weighted avg": {
"f1-score": 0.9113822260750222,
"precision": 0.9103625011540336,
"recall": 0.9138380400453807,
"support": 32613.0
},
"step": 2916
},
{
"epoch": 37.0,
"eval_B-Claim": {
"f1-score": 0.6933333333333332,
"precision": 0.6819672131147541,
"recall": 0.7050847457627119,
"support": 295.0
},
"eval_B-MajorClaim": {
"f1-score": 0.9135802469135802,
"precision": 0.8809523809523809,
"recall": 0.9487179487179487,
"support": 156.0
},
"eval_B-Premise": {
"f1-score": 0.8896648044692737,
"precision": 0.9035460992907801,
"recall": 0.8762035763411279,
"support": 727.0
},
"eval_I-Claim": {
"f1-score": 0.6752997601918465,
"precision": 0.6709554443650226,
"recall": 0.6797006999758629,
"support": 4143.0
},
"eval_I-MajorClaim": {
"f1-score": 0.9153129737925059,
"precision": 0.8716996699669967,
"recall": 0.9635202918376653,
"support": 2193.0
},
"eval_I-Premise": {
"f1-score": 0.9059946052578606,
"precision": 0.9165852069077876,
"recall": 0.8956459444400223,
"support": 12563.0
},
"eval_O": {
"f1-score": 0.9999202361011406,
"precision": 0.9998404849258254,
"recall": 1.0,
"support": 12536.0
},
"eval_accuracy": 0.910986416459694,
"eval_loss": 0.8418905735015869,
"eval_macro avg": {
"f1-score": 0.8561579942942201,
"precision": 0.8465066427890783,
"recall": 0.8669818867250484,
"support": 32613.0
},
"eval_runtime": 4.9617,
"eval_samples_per_second": 16.325,
"eval_steps_per_second": 2.217,
"eval_weighted avg": {
"f1-score": 0.9111672255947384,
"precision": 0.9117822024694574,
"recall": 0.910986416459694,
"support": 32613.0
},
"step": 2997
}
],
"logging_steps": 500,
"max_steps": 4050,
"num_input_tokens_seen": 0,
"num_train_epochs": 50,
"save_steps": 500,
"total_flos": 5303737523763000.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}