Delete pet-leadership-model-roberta-large-mnli_bs4_gas4_lr3e-05_ep2

pet-leadership-model-roberta-large-mnli_bs4_gas4_lr3e-05_ep2/checkpoint-742/config.json

@@ -1,38 +0,0 @@
-{
-  "_name_or_path": "roberta-large-mnli",
-  "_num_labels": 3,
-  "architectures": [
-    "RobertaForMaskedLM"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
-  "id2label": {
-    "0": "CONTRADICTION",
-    "1": "NEUTRAL",
-    "2": "ENTAILMENT"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "label2id": {
-    "CONTRADICTION": 0,
-    "ENTAILMENT": 2,
-    "NEUTRAL": 1
-  },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
-  "torch_dtype": "float32",
-  "transformers_version": "4.49.0",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 50265
-}

pet-leadership-model-roberta-large-mnli_bs4_gas4_lr3e-05_ep2/checkpoint-742/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0b08c1eba1219d1f37d89d4e14c6dc0adf662e053a1ceb6a4176a9eaca04e825
-size 1421696540

pet-leadership-model-roberta-large-mnli_bs4_gas4_lr3e-05_ep2/checkpoint-742/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d1a8ff3e1f8189a005a6f946827138203b25981cb45232b8c057071899f824c6
-size 2843626160

pet-leadership-model-roberta-large-mnli_bs4_gas4_lr3e-05_ep2/checkpoint-742/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:281c36caf51fbd63c7dd963f257385d59119adc28e964456b6e13c349a56717c
-size 14244

pet-leadership-model-roberta-large-mnli_bs4_gas4_lr3e-05_ep2/checkpoint-742/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d1a1b4b54695e12078e54ca4904d7351c3707eb227b68911ee2e1b413feca070
-size 1064

pet-leadership-model-roberta-large-mnli_bs4_gas4_lr3e-05_ep2/checkpoint-742/trainer_state.json

@@ -1,567 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 2.0,
-  "eval_steps": 500,
-  "global_step": 742,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.026954177897574125,
-      "grad_norm": 29.47423553466797,
-      "learning_rate": 2.959568733153639e-05,
-      "loss": 4.3393,
-      "step": 10
-    },
-    {
-      "epoch": 0.05390835579514825,
-      "grad_norm": 31.8802433013916,
-      "learning_rate": 2.9191374663072775e-05,
-      "loss": 0.9828,
-      "step": 20
-    },
-    {
-      "epoch": 0.08086253369272237,
-      "grad_norm": 22.71839714050293,
-      "learning_rate": 2.8787061994609164e-05,
-      "loss": 0.7336,
-      "step": 30
-    },
-    {
-      "epoch": 0.1078167115902965,
-      "grad_norm": 65.7586669921875,
-      "learning_rate": 2.8382749326145553e-05,
-      "loss": 0.6222,
-      "step": 40
-    },
-    {
-      "epoch": 0.1347708894878706,
-      "grad_norm": 32.97853469848633,
-      "learning_rate": 2.7978436657681942e-05,
-      "loss": 0.633,
-      "step": 50
-    },
-    {
-      "epoch": 0.16172506738544473,
-      "grad_norm": 18.638259887695312,
-      "learning_rate": 2.757412398921833e-05,
-      "loss": 0.517,
-      "step": 60
-    },
-    {
-      "epoch": 0.18867924528301888,
-      "grad_norm": 31.97262954711914,
-      "learning_rate": 2.716981132075472e-05,
-      "loss": 0.3794,
-      "step": 70
-    },
-    {
-      "epoch": 0.215633423180593,
-      "grad_norm": 39.317928314208984,
-      "learning_rate": 2.6765498652291105e-05,
-      "loss": 0.4368,
-      "step": 80
-    },
-    {
-      "epoch": 0.24258760107816713,
-      "grad_norm": 25.218809127807617,
-      "learning_rate": 2.6361185983827494e-05,
-      "loss": 0.4537,
-      "step": 90
-    },
-    {
-      "epoch": 0.2695417789757412,
-      "grad_norm": 19.011188507080078,
-      "learning_rate": 2.5956873315363883e-05,
-      "loss": 0.3985,
-      "step": 100
-    },
-    {
-      "epoch": 0.29649595687331537,
-      "grad_norm": 12.845932006835938,
-      "learning_rate": 2.555256064690027e-05,
-      "loss": 0.3786,
-      "step": 110
-    },
-    {
-      "epoch": 0.32345013477088946,
-      "grad_norm": 29.667890548706055,
-      "learning_rate": 2.5148247978436658e-05,
-      "loss": 0.4118,
-      "step": 120
-    },
-    {
-      "epoch": 0.3504043126684636,
-      "grad_norm": 23.784292221069336,
-      "learning_rate": 2.4743935309973046e-05,
-      "loss": 0.5691,
-      "step": 130
-    },
-    {
-      "epoch": 0.37735849056603776,
-      "grad_norm": 10.289161682128906,
-      "learning_rate": 2.4339622641509435e-05,
-      "loss": 0.4434,
-      "step": 140
-    },
-    {
-      "epoch": 0.40431266846361186,
-      "grad_norm": 19.481176376342773,
-      "learning_rate": 2.3935309973045824e-05,
-      "loss": 0.4913,
-      "step": 150
-    },
-    {
-      "epoch": 0.431266846361186,
-      "grad_norm": 23.314889907836914,
-      "learning_rate": 2.353099730458221e-05,
-      "loss": 0.3104,
-      "step": 160
-    },
-    {
-      "epoch": 0.4582210242587601,
-      "grad_norm": 16.9091796875,
-      "learning_rate": 2.31266846361186e-05,
-      "loss": 0.2901,
-      "step": 170
-    },
-    {
-      "epoch": 0.48517520215633425,
-      "grad_norm": 15.09512710571289,
-      "learning_rate": 2.2722371967654988e-05,
-      "loss": 0.2728,
-      "step": 180
-    },
-    {
-      "epoch": 0.5121293800539084,
-      "grad_norm": 43.94502258300781,
-      "learning_rate": 2.2318059299191373e-05,
-      "loss": 0.51,
-      "step": 190
-    },
-    {
-      "epoch": 0.5390835579514824,
-      "grad_norm": 12.847454071044922,
-      "learning_rate": 2.1913746630727762e-05,
-      "loss": 0.4558,
-      "step": 200
-    },
-    {
-      "epoch": 0.5660377358490566,
-      "grad_norm": 31.876087188720703,
-      "learning_rate": 2.150943396226415e-05,
-      "loss": 0.4355,
-      "step": 210
-    },
-    {
-      "epoch": 0.5929919137466307,
-      "grad_norm": 11.343082427978516,
-      "learning_rate": 2.110512129380054e-05,
-      "loss": 0.4043,
-      "step": 220
-    },
-    {
-      "epoch": 0.6199460916442049,
-      "grad_norm": 22.41591453552246,
-      "learning_rate": 2.070080862533693e-05,
-      "loss": 0.3301,
-      "step": 230
-    },
-    {
-      "epoch": 0.6469002695417789,
-      "grad_norm": 23.612829208374023,
-      "learning_rate": 2.0296495956873318e-05,
-      "loss": 0.2875,
-      "step": 240
-    },
-    {
-      "epoch": 0.6738544474393531,
-      "grad_norm": 9.502119064331055,
-      "learning_rate": 1.9892183288409703e-05,
-      "loss": 0.3458,
-      "step": 250
-    },
-    {
-      "epoch": 0.7008086253369272,
-      "grad_norm": 33.75297927856445,
-      "learning_rate": 1.9487870619946092e-05,
-      "loss": 0.3215,
-      "step": 260
-    },
-    {
-      "epoch": 0.7277628032345014,
-      "grad_norm": 31.682952880859375,
-      "learning_rate": 1.908355795148248e-05,
-      "loss": 0.3333,
-      "step": 270
-    },
-    {
-      "epoch": 0.7547169811320755,
-      "grad_norm": 16.26555633544922,
-      "learning_rate": 1.8679245283018867e-05,
-      "loss": 0.3504,
-      "step": 280
-    },
-    {
-      "epoch": 0.7816711590296496,
-      "grad_norm": 22.693450927734375,
-      "learning_rate": 1.8274932614555256e-05,
-      "loss": 0.4523,
-      "step": 290
-    },
-    {
-      "epoch": 0.8086253369272237,
-      "grad_norm": 17.097888946533203,
-      "learning_rate": 1.7870619946091645e-05,
-      "loss": 0.3542,
-      "step": 300
-    },
-    {
-      "epoch": 0.8355795148247979,
-      "grad_norm": 13.334282875061035,
-      "learning_rate": 1.7466307277628033e-05,
-      "loss": 0.2878,
-      "step": 310
-    },
-    {
-      "epoch": 0.862533692722372,
-      "grad_norm": 9.898679733276367,
-      "learning_rate": 1.7061994609164422e-05,
-      "loss": 0.3661,
-      "step": 320
-    },
-    {
-      "epoch": 0.889487870619946,
-      "grad_norm": 10.888357162475586,
-      "learning_rate": 1.665768194070081e-05,
-      "loss": 0.322,
-      "step": 330
-    },
-    {
-      "epoch": 0.9164420485175202,
-      "grad_norm": 35.20107650756836,
-      "learning_rate": 1.6253369272237197e-05,
-      "loss": 0.3405,
-      "step": 340
-    },
-    {
-      "epoch": 0.9433962264150944,
-      "grad_norm": 4.650808334350586,
-      "learning_rate": 1.5849056603773586e-05,
-      "loss": 0.3893,
-      "step": 350
-    },
-    {
-      "epoch": 0.9703504043126685,
-      "grad_norm": 24.92270851135254,
-      "learning_rate": 1.544474393530997e-05,
-      "loss": 0.3561,
-      "step": 360
-    },
-    {
-      "epoch": 0.9973045822102425,
-      "grad_norm": 14.140254020690918,
-      "learning_rate": 1.504043126684636e-05,
-      "loss": 0.2356,
-      "step": 370
-    },
-    {
-      "epoch": 1.0,
-      "eval_loss": 0.2660793364048004,
-      "eval_runtime": 7.2402,
-      "eval_samples_per_second": 204.829,
-      "eval_steps_per_second": 51.242,
-      "step": 371
-    },
-    {
-      "epoch": 1.0242587601078168,
-      "grad_norm": 10.333748817443848,
-      "learning_rate": 1.463611859838275e-05,
-      "loss": 0.1811,
-      "step": 380
-    },
-    {
-      "epoch": 1.0512129380053907,
-      "grad_norm": 20.75710105895996,
-      "learning_rate": 1.4231805929919138e-05,
-      "loss": 0.2177,
-      "step": 390
-    },
-    {
-      "epoch": 1.0781671159029649,
-      "grad_norm": 22.326885223388672,
-      "learning_rate": 1.3827493261455525e-05,
-      "loss": 0.3734,
-      "step": 400
-    },
-    {
-      "epoch": 1.105121293800539,
-      "grad_norm": 8.389409065246582,
-      "learning_rate": 1.3423180592991914e-05,
-      "loss": 0.2553,
-      "step": 410
-    },
-    {
-      "epoch": 1.1320754716981132,
-      "grad_norm": 19.33669090270996,
-      "learning_rate": 1.3018867924528303e-05,
-      "loss": 0.2771,
-      "step": 420
-    },
-    {
-      "epoch": 1.1590296495956873,
-      "grad_norm": 14.596505165100098,
-      "learning_rate": 1.261455525606469e-05,
-      "loss": 0.2798,
-      "step": 430
-    },
-    {
-      "epoch": 1.1859838274932615,
-      "grad_norm": 32.35258102416992,
-      "learning_rate": 1.2210242587601077e-05,
-      "loss": 0.3396,
-      "step": 440
-    },
-    {
-      "epoch": 1.2129380053908356,
-      "grad_norm": 12.335786819458008,
-      "learning_rate": 1.1805929919137466e-05,
-      "loss": 0.1821,
-      "step": 450
-    },
-    {
-      "epoch": 1.2398921832884098,
-      "grad_norm": 8.339882850646973,
-      "learning_rate": 1.1401617250673855e-05,
-      "loss": 0.2896,
-      "step": 460
-    },
-    {
-      "epoch": 1.266846361185984,
-      "grad_norm": 17.156047821044922,
-      "learning_rate": 1.0997304582210243e-05,
-      "loss": 0.1827,
-      "step": 470
-    },
-    {
-      "epoch": 1.2938005390835579,
-      "grad_norm": 8.71430778503418,
-      "learning_rate": 1.0592991913746631e-05,
-      "loss": 0.3261,
-      "step": 480
-    },
-    {
-      "epoch": 1.320754716981132,
-      "grad_norm": 33.503440856933594,
-      "learning_rate": 1.0188679245283019e-05,
-      "loss": 0.2977,
-      "step": 490
-    },
-    {
-      "epoch": 1.3477088948787062,
-      "grad_norm": 13.175012588500977,
-      "learning_rate": 9.784366576819408e-06,
-      "loss": 0.2304,
-      "step": 500
-    },
-    {
-      "epoch": 1.3746630727762803,
-      "grad_norm": 6.546019554138184,
-      "learning_rate": 9.380053908355796e-06,
-      "loss": 0.1473,
-      "step": 510
-    },
-    {
-      "epoch": 1.4016172506738545,
-      "grad_norm": 24.98724365234375,
-      "learning_rate": 8.975741239892184e-06,
-      "loss": 0.3648,
-      "step": 520
-    },
-    {
-      "epoch": 1.4285714285714286,
-      "grad_norm": 6.695165157318115,
-      "learning_rate": 8.571428571428571e-06,
-      "loss": 0.2416,
-      "step": 530
-    },
-    {
-      "epoch": 1.4555256064690028,
-      "grad_norm": 8.321410179138184,
-      "learning_rate": 8.16711590296496e-06,
-      "loss": 0.2227,
-      "step": 540
-    },
-    {
-      "epoch": 1.482479784366577,
-      "grad_norm": 3.5790646076202393,
-      "learning_rate": 7.762803234501349e-06,
-      "loss": 0.2386,
-      "step": 550
-    },
-    {
-      "epoch": 1.509433962264151,
-      "grad_norm": 7.105038642883301,
-      "learning_rate": 7.358490566037736e-06,
-      "loss": 0.1779,
-      "step": 560
-    },
-    {
-      "epoch": 1.536388140161725,
-      "grad_norm": 48.24789047241211,
-      "learning_rate": 6.954177897574124e-06,
-      "loss": 0.2599,
-      "step": 570
-    },
-    {
-      "epoch": 1.5633423180592994,
-      "grad_norm": 7.495761871337891,
-      "learning_rate": 6.549865229110512e-06,
-      "loss": 0.1809,
-      "step": 580
-    },
-    {
-      "epoch": 1.5902964959568733,
-      "grad_norm": 17.49237823486328,
-      "learning_rate": 6.1455525606469e-06,
-      "loss": 0.1797,
-      "step": 590
-    },
-    {
-      "epoch": 1.6172506738544474,
-      "grad_norm": 13.955606460571289,
-      "learning_rate": 5.741239892183289e-06,
-      "loss": 0.2784,
-      "step": 600
-    },
-    {
-      "epoch": 1.6442048517520216,
-      "grad_norm": 27.44432258605957,
-      "learning_rate": 5.336927223719676e-06,
-      "loss": 0.2583,
-      "step": 610
-    },
-    {
-      "epoch": 1.6711590296495957,
-      "grad_norm": 29.639062881469727,
-      "learning_rate": 4.932614555256065e-06,
-      "loss": 0.2687,
-      "step": 620
-    },
-    {
-      "epoch": 1.6981132075471699,
-      "grad_norm": 10.949997901916504,
-      "learning_rate": 4.5283018867924524e-06,
-      "loss": 0.1988,
-      "step": 630
-    },
-    {
-      "epoch": 1.7250673854447438,
-      "grad_norm": 15.069132804870605,
-      "learning_rate": 4.123989218328841e-06,
-      "loss": 0.1382,
-      "step": 640
-    },
-    {
-      "epoch": 1.7520215633423182,
-      "grad_norm": 17.37251091003418,
-      "learning_rate": 3.719676549865229e-06,
-      "loss": 0.199,
-      "step": 650
-    },
-    {
-      "epoch": 1.778975741239892,
-      "grad_norm": 13.217763900756836,
-      "learning_rate": 3.315363881401617e-06,
-      "loss": 0.1404,
-      "step": 660
-    },
-    {
-      "epoch": 1.8059299191374663,
-      "grad_norm": 26.328725814819336,
-      "learning_rate": 2.9110512129380056e-06,
-      "loss": 0.1185,
-      "step": 670
-    },
-    {
-      "epoch": 1.8328840970350404,
-      "grad_norm": 11.576745986938477,
-      "learning_rate": 2.5067385444743936e-06,
-      "loss": 0.2272,
-      "step": 680
-    },
-    {
-      "epoch": 1.8598382749326146,
-      "grad_norm": 1.781421422958374,
-      "learning_rate": 2.1024258760107817e-06,
-      "loss": 0.1137,
-      "step": 690
-    },
-    {
-      "epoch": 1.8867924528301887,
-      "grad_norm": 23.61797523498535,
-      "learning_rate": 1.69811320754717e-06,
-      "loss": 0.2826,
-      "step": 700
-    },
-    {
-      "epoch": 1.9137466307277629,
-      "grad_norm": 0.7516375184059143,
-      "learning_rate": 1.293800539083558e-06,
-      "loss": 0.2227,
-      "step": 710
-    },
-    {
-      "epoch": 1.940700808625337,
-      "grad_norm": 6.095058441162109,
-      "learning_rate": 8.894878706199461e-07,
-      "loss": 0.258,
-      "step": 720
-    },
-    {
-      "epoch": 1.967654986522911,
-      "grad_norm": 8.179100036621094,
-      "learning_rate": 4.851752021563343e-07,
-      "loss": 0.1808,
-      "step": 730
-    },
-    {
-      "epoch": 1.9946091644204853,
-      "grad_norm": 11.866944313049316,
-      "learning_rate": 8.086253369272238e-08,
-      "loss": 0.1688,
-      "step": 740
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 0.2651370167732239,
-      "eval_runtime": 7.4873,
-      "eval_samples_per_second": 198.07,
-      "eval_steps_per_second": 49.551,
-      "step": 742
-    }
-  ],
-  "logging_steps": 10,
-  "max_steps": 742,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
-  "save_steps": 100,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": true
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 962338508269596.0,
-  "train_batch_size": 4,
-  "trial_name": null,
-  "trial_params": null
-}

pet-leadership-model-roberta-large-mnli_bs4_gas4_lr3e-05_ep2/checkpoint-742/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:11d07387ba23496b1ded4dce787e89460237ef6e9414ab716d72f50b57f5c57e
-size 5432