Training in progress, step 1241, checkpoint

checkpoint-1241/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

checkpoint-1241/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

checkpoint-1241/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "bobox/DeBERTa-ST-AllLayers-v3-checkpoints-tmp",
+  "architectures": [
+    "DebertaV2Model"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

checkpoint-1241/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.42.3",
+    "pytorch": "2.1.2"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

checkpoint-1241/modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

checkpoint-1241/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0ff2cd8ecc837c2516e4333e31f51035b7455cc437f2d386c0646b9e223a578
+size 1130520122

checkpoint-1241/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33169bfc4fb33b478b37557bcdb295cc2d8f9cfcb905ee0f584f62cdf7dd51fd
+size 565251810

checkpoint-1241/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40e97f79da6325b751c8ee5407b7016a582fc6ac35888a8eda527ce949cfd836
+size 14244

checkpoint-1241/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e28a7160077359c606fad355eda04141b1184e99d8e30f2f2dde1040e5eecd9b
+size 1064

checkpoint-1241/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

checkpoint-1241/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1241/spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

checkpoint-1241/tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "stride": 0,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

checkpoint-1241/trainer_state.json

@@ -0,0 +1,713 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.20012901144976616,
+  "eval_steps": 311,
+  "global_step": 1241,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00516045799064667,
+      "grad_norm": 9.933993339538574,
+      "learning_rate": 1.1231884057971015e-06,
+      "loss": 0.6816,
+      "step": 32
+    },
+    {
+      "epoch": 0.01032091598129334,
+      "grad_norm": 14.133739471435547,
+      "learning_rate": 2.282608695652174e-06,
+      "loss": 0.6581,
+      "step": 64
+    },
+    {
+      "epoch": 0.015481373971940009,
+      "grad_norm": 0.4211793839931488,
+      "learning_rate": 3.4420289855072468e-06,
+      "loss": 0.5162,
+      "step": 96
+    },
+    {
+      "epoch": 0.02064183196258668,
+      "grad_norm": 23.16193962097168,
+      "learning_rate": 4.601449275362319e-06,
+      "loss": 0.772,
+      "step": 128
+    },
+    {
+      "epoch": 0.02580228995323335,
+      "grad_norm": 21.05358123779297,
+      "learning_rate": 5.7608695652173925e-06,
+      "loss": 0.6174,
+      "step": 160
+    },
+    {
+      "epoch": 0.030962747943880018,
+      "grad_norm": 3.430863618850708,
+      "learning_rate": 6.9202898550724634e-06,
+      "loss": 0.6038,
+      "step": 192
+    },
+    {
+      "epoch": 0.03612320593452669,
+      "grad_norm": 9.02695083618164,
+      "learning_rate": 8.079710144927536e-06,
+      "loss": 0.5998,
+      "step": 224
+    },
+    {
+      "epoch": 0.04128366392517336,
+      "grad_norm": 0.43893784284591675,
+      "learning_rate": 9.23913043478261e-06,
+      "loss": 0.5668,
+      "step": 256
+    },
+    {
+      "epoch": 0.04644412191582003,
+      "grad_norm": 0.7273858189582825,
+      "learning_rate": 1.0398550724637681e-05,
+      "loss": 0.4217,
+      "step": 288
+    },
+    {
+      "epoch": 0.05015320109659732,
+      "eval_nli-pairs_loss": 1.0159435272216797,
+      "eval_nli-pairs_runtime": 3.6212,
+      "eval_nli-pairs_samples_per_second": 27.615,
+      "eval_nli-pairs_steps_per_second": 1.105,
+      "eval_sts-test_pearson_cosine": 0.7924171549391827,
+      "eval_sts-test_pearson_dot": 0.5125723700327796,
+      "eval_sts-test_pearson_euclidean": 0.7225664519214365,
+      "eval_sts-test_pearson_manhattan": 0.7159071827826674,
+      "eval_sts-test_pearson_max": 0.7924171549391827,
+      "eval_sts-test_spearman_cosine": 0.8098639737290916,
+      "eval_sts-test_spearman_dot": 0.4941393316149358,
+      "eval_sts-test_spearman_euclidean": 0.7149410740639525,
+      "eval_sts-test_spearman_manhattan": 0.7103052060124385,
+      "eval_sts-test_spearman_max": 0.8098639737290916,
+      "step": 311
+    },
+    {
+      "epoch": 0.05015320109659732,
+      "eval_vitaminc-pairs_loss": 5.266397953033447,
+      "eval_vitaminc-pairs_runtime": 1.1302,
+      "eval_vitaminc-pairs_samples_per_second": 75.205,
+      "eval_vitaminc-pairs_steps_per_second": 2.654,
+      "step": 311
+    },
+    {
+      "epoch": 0.05015320109659732,
+      "eval_qnli-contrastive_loss": 0.16530731320381165,
+      "eval_qnli-contrastive_runtime": 0.3536,
+      "eval_qnli-contrastive_samples_per_second": 282.811,
+      "eval_qnli-contrastive_steps_per_second": 11.312,
+      "step": 311
+    },
+    {
+      "epoch": 0.05015320109659732,
+      "eval_scitail-pairs-qa_loss": 0.038222018629312515,
+      "eval_scitail-pairs-qa_runtime": 0.8751,
+      "eval_scitail-pairs-qa_samples_per_second": 114.268,
+      "eval_scitail-pairs-qa_steps_per_second": 4.571,
+      "step": 311
+    },
+    {
+      "epoch": 0.05015320109659732,
+      "eval_scitail-pairs-pos_loss": 0.4047476053237915,
+      "eval_scitail-pairs-pos_runtime": 1.3804,
+      "eval_scitail-pairs-pos_samples_per_second": 72.443,
+      "eval_scitail-pairs-pos_steps_per_second": 2.898,
+      "step": 311
+    },
+    {
+      "epoch": 0.05015320109659732,
+      "eval_xsum-pairs_loss": 0.24429777264595032,
+      "eval_xsum-pairs_runtime": 0.9313,
+      "eval_xsum-pairs_samples_per_second": 107.376,
+      "eval_xsum-pairs_steps_per_second": 4.295,
+      "step": 311
+    },
+    {
+      "epoch": 0.05015320109659732,
+      "eval_compression-pairs_loss": 0.07131721824407578,
+      "eval_compression-pairs_runtime": 0.2765,
+      "eval_compression-pairs_samples_per_second": 361.678,
+      "eval_compression-pairs_steps_per_second": 14.467,
+      "step": 311
+    },
+    {
+      "epoch": 0.05015320109659732,
+      "eval_sciq_pairs_loss": 0.23269836604595184,
+      "eval_sciq_pairs_runtime": 4.0686,
+      "eval_sciq_pairs_samples_per_second": 24.578,
+      "eval_sciq_pairs_steps_per_second": 0.983,
+      "step": 311
+    },
+    {
+      "epoch": 0.05015320109659732,
+      "eval_qasc_pairs_loss": 0.168828547000885,
+      "eval_qasc_pairs_runtime": 1.0568,
+      "eval_qasc_pairs_samples_per_second": 94.628,
+      "eval_qasc_pairs_steps_per_second": 3.785,
+      "step": 311
+    },
+    {
+      "epoch": 0.05015320109659732,
+      "eval_openbookqa_pairs_loss": 1.8080159425735474,
+      "eval_openbookqa_pairs_runtime": 0.9003,
+      "eval_openbookqa_pairs_samples_per_second": 111.071,
+      "eval_openbookqa_pairs_steps_per_second": 4.443,
+      "step": 311
+    },
+    {
+      "epoch": 0.05015320109659732,
+      "eval_msmarco_pairs_loss": 0.5308343172073364,
+      "eval_msmarco_pairs_runtime": 2.1107,
+      "eval_msmarco_pairs_samples_per_second": 47.377,
+      "eval_msmarco_pairs_steps_per_second": 1.895,
+      "step": 311
+    },
+    {
+      "epoch": 0.05015320109659732,
+      "eval_nq_pairs_loss": 0.26344215869903564,
+      "eval_nq_pairs_runtime": 4.508,
+      "eval_nq_pairs_samples_per_second": 22.183,
+      "eval_nq_pairs_steps_per_second": 0.887,
+      "step": 311
+    },
+    {
+      "epoch": 0.05015320109659732,
+      "eval_trivia_pairs_loss": 0.8994726538658142,
+      "eval_trivia_pairs_runtime": 6.4793,
+      "eval_trivia_pairs_samples_per_second": 15.434,
+      "eval_trivia_pairs_steps_per_second": 0.617,
+      "step": 311
+    },
+    {
+      "epoch": 0.05015320109659732,
+      "eval_quora_pairs_loss": 0.019602684304118156,
+      "eval_quora_pairs_runtime": 0.6891,
+      "eval_quora_pairs_samples_per_second": 145.126,
+      "eval_quora_pairs_steps_per_second": 5.805,
+      "step": 311
+    },
+    {
+      "epoch": 0.05015320109659732,
+      "eval_gooaq_pairs_loss": 0.5839698910713196,
+      "eval_gooaq_pairs_runtime": 1.4072,
+      "eval_gooaq_pairs_samples_per_second": 71.062,
+      "eval_gooaq_pairs_steps_per_second": 2.842,
+      "step": 311
+    },
+    {
+      "epoch": 0.05015320109659732,
+      "eval_mrpc_pairs_loss": 0.03139862045645714,
+      "eval_mrpc_pairs_runtime": 0.2596,
+      "eval_mrpc_pairs_samples_per_second": 385.156,
+      "eval_mrpc_pairs_steps_per_second": 15.406,
+      "step": 311
+    },
+    {
+      "epoch": 0.0516045799064667,
+      "grad_norm": 0.20445337891578674,
+      "learning_rate": 1.1557971014492753e-05,
+      "loss": 0.385,
+      "step": 320
+    },
+    {
+      "epoch": 0.05676503789711337,
+      "grad_norm": 28.880046844482422,
+      "learning_rate": 1.2717391304347827e-05,
+      "loss": 0.5309,
+      "step": 352
+    },
+    {
+      "epoch": 0.061925495887760036,
+      "grad_norm": 5.474071502685547,
+      "learning_rate": 1.3876811594202898e-05,
+      "loss": 0.7088,
+      "step": 384
+    },
+    {
+      "epoch": 0.06708595387840671,
+      "grad_norm": 5.415467739105225,
+      "learning_rate": 1.5036231884057972e-05,
+      "loss": 0.437,
+      "step": 416
+    },
+    {
+      "epoch": 0.07224641186905338,
+      "grad_norm": 16.55014991760254,
+      "learning_rate": 1.6195652173913045e-05,
+      "loss": 0.3989,
+      "step": 448
+    },
+    {
+      "epoch": 0.07740686985970005,
+      "grad_norm": 3.071091651916504,
+      "learning_rate": 1.7355072463768116e-05,
+      "loss": 0.4707,
+      "step": 480
+    },
+    {
+      "epoch": 0.08256732785034672,
+      "grad_norm": 0.14953163266181946,
+      "learning_rate": 1.851449275362319e-05,
+      "loss": 0.3066,
+      "step": 512
+    },
+    {
+      "epoch": 0.08772778584099339,
+      "grad_norm": 15.234663963317871,
+      "learning_rate": 1.9673913043478263e-05,
+      "loss": 0.3541,
+      "step": 544
+    },
+    {
+      "epoch": 0.09288824383164006,
+      "grad_norm": 0.17410986125469208,
+      "learning_rate": 2.0833333333333336e-05,
+      "loss": 0.3891,
+      "step": 576
+    },
+    {
+      "epoch": 0.09804870182228673,
+      "grad_norm": 0.1499205231666565,
+      "learning_rate": 2.1992753623188406e-05,
+      "loss": 0.3785,
+      "step": 608
+    },
+    {
+      "epoch": 0.10030640219319464,
+      "eval_nli-pairs_loss": 1.0188440084457397,
+      "eval_nli-pairs_runtime": 3.6596,
+      "eval_nli-pairs_samples_per_second": 27.325,
+      "eval_nli-pairs_steps_per_second": 1.093,
+      "eval_sts-test_pearson_cosine": 0.7916799006663855,
+      "eval_sts-test_pearson_dot": 0.5045869753412373,
+      "eval_sts-test_pearson_euclidean": 0.7207643323198801,
+      "eval_sts-test_pearson_manhattan": 0.7137156351145015,
+      "eval_sts-test_pearson_max": 0.7916799006663855,
+      "eval_sts-test_spearman_cosine": 0.8085135407766834,
+      "eval_sts-test_spearman_dot": 0.49054820661704757,
+      "eval_sts-test_spearman_euclidean": 0.7142796374223352,
+      "eval_sts-test_spearman_manhattan": 0.7087974417327754,
+      "eval_sts-test_spearman_max": 0.8085135407766834,
+      "step": 622
+    },
+    {
+      "epoch": 0.10030640219319464,
+      "eval_vitaminc-pairs_loss": 5.289845943450928,
+      "eval_vitaminc-pairs_runtime": 1.1325,
+      "eval_vitaminc-pairs_samples_per_second": 75.057,
+      "eval_vitaminc-pairs_steps_per_second": 2.649,
+      "step": 622
+    },
+    {
+      "epoch": 0.10030640219319464,
+      "eval_qnli-contrastive_loss": 0.1695801019668579,
+      "eval_qnli-contrastive_runtime": 0.3582,
+      "eval_qnli-contrastive_samples_per_second": 279.158,
+      "eval_qnli-contrastive_steps_per_second": 11.166,
+      "step": 622
+    },
+    {
+      "epoch": 0.10030640219319464,
+      "eval_scitail-pairs-qa_loss": 0.038966864347457886,
+      "eval_scitail-pairs-qa_runtime": 0.88,
+      "eval_scitail-pairs-qa_samples_per_second": 113.635,
+      "eval_scitail-pairs-qa_steps_per_second": 4.545,
+      "step": 622
+    },
+    {
+      "epoch": 0.10030640219319464,
+      "eval_scitail-pairs-pos_loss": 0.4368051588535309,
+      "eval_scitail-pairs-pos_runtime": 1.3332,
+      "eval_scitail-pairs-pos_samples_per_second": 75.005,
+      "eval_scitail-pairs-pos_steps_per_second": 3.0,
+      "step": 622
+    },
+    {
+      "epoch": 0.10030640219319464,
+      "eval_xsum-pairs_loss": 0.2461192011833191,
+      "eval_xsum-pairs_runtime": 0.9354,
+      "eval_xsum-pairs_samples_per_second": 106.909,
+      "eval_xsum-pairs_steps_per_second": 4.276,
+      "step": 622
+    },
+    {
+      "epoch": 0.10030640219319464,
+      "eval_compression-pairs_loss": 0.07092336565256119,
+      "eval_compression-pairs_runtime": 0.2741,
+      "eval_compression-pairs_samples_per_second": 364.809,
+      "eval_compression-pairs_steps_per_second": 14.592,
+      "step": 622
+    },
+    {
+      "epoch": 0.10030640219319464,
+      "eval_sciq_pairs_loss": 0.24137285351753235,
+      "eval_sciq_pairs_runtime": 4.1172,
+      "eval_sciq_pairs_samples_per_second": 24.288,
+      "eval_sciq_pairs_steps_per_second": 0.972,
+      "step": 622
+    },
+    {
+      "epoch": 0.10030640219319464,
+      "eval_qasc_pairs_loss": 0.1700724959373474,
+      "eval_qasc_pairs_runtime": 1.0602,
+      "eval_qasc_pairs_samples_per_second": 94.325,
+      "eval_qasc_pairs_steps_per_second": 3.773,
+      "step": 622
+    },
+    {
+      "epoch": 0.10030640219319464,
+      "eval_openbookqa_pairs_loss": 1.8052237033843994,
+      "eval_openbookqa_pairs_runtime": 0.8871,
+      "eval_openbookqa_pairs_samples_per_second": 112.721,
+      "eval_openbookqa_pairs_steps_per_second": 4.509,
+      "step": 622
+    },
+    {
+      "epoch": 0.10030640219319464,
+      "eval_msmarco_pairs_loss": 0.5037128329277039,
+      "eval_msmarco_pairs_runtime": 2.0568,
+      "eval_msmarco_pairs_samples_per_second": 48.619,
+      "eval_msmarco_pairs_steps_per_second": 1.945,
+      "step": 622
+    },
+    {
+      "epoch": 0.10030640219319464,
+      "eval_nq_pairs_loss": 0.2771645188331604,
+      "eval_nq_pairs_runtime": 4.5138,
+      "eval_nq_pairs_samples_per_second": 22.154,
+      "eval_nq_pairs_steps_per_second": 0.886,
+      "step": 622
+    },
+    {
+      "epoch": 0.10030640219319464,
+      "eval_trivia_pairs_loss": 0.9114018082618713,
+      "eval_trivia_pairs_runtime": 6.5422,
+      "eval_trivia_pairs_samples_per_second": 15.285,
+      "eval_trivia_pairs_steps_per_second": 0.611,
+      "step": 622
+    },
+    {
+      "epoch": 0.10030640219319464,
+      "eval_quora_pairs_loss": 0.023751432076096535,
+      "eval_quora_pairs_runtime": 0.676,
+      "eval_quora_pairs_samples_per_second": 147.94,
+      "eval_quora_pairs_steps_per_second": 5.918,
+      "step": 622
+    },
+    {
+      "epoch": 0.10030640219319464,
+      "eval_gooaq_pairs_loss": 0.5844606161117554,
+      "eval_gooaq_pairs_runtime": 1.4001,
+      "eval_gooaq_pairs_samples_per_second": 71.422,
+      "eval_gooaq_pairs_steps_per_second": 2.857,
+      "step": 622
+    },
+    {
+      "epoch": 0.10030640219319464,
+      "eval_mrpc_pairs_loss": 0.03143290430307388,
+      "eval_mrpc_pairs_runtime": 0.2623,
+      "eval_mrpc_pairs_samples_per_second": 381.299,
+      "eval_mrpc_pairs_steps_per_second": 15.252,
+      "step": 622
+    },
+    {
+      "epoch": 0.1032091598129334,
+      "grad_norm": 1.3653217554092407,
+      "learning_rate": 2.249708415360171e-05,
+      "loss": 0.331,
+      "step": 640
+    },
+    {
+      "epoch": 0.10836961780358007,
+      "grad_norm": 0.5018106698989868,
+      "learning_rate": 2.247750843725014e-05,
+      "loss": 0.3123,
+      "step": 672
+    },
+    {
+      "epoch": 0.11353007579422673,
+      "grad_norm": 11.877176284790039,
+      "learning_rate": 2.243954454134712e-05,
+      "loss": 0.3477,
+      "step": 704
+    },
+    {
+      "epoch": 0.1186905337848734,
+      "grad_norm": 1.803855061531067,
+      "learning_rate": 2.2383261566249135e-05,
+      "loss": 0.2304,
+      "step": 736
+    },
+    {
+      "epoch": 0.12385099177552007,
+      "grad_norm": 1.3398637771606445,
+      "learning_rate": 2.2308761955963843e-05,
+      "loss": 0.3731,
+      "step": 768
+    },
+    {
+      "epoch": 0.12901144976616674,
+      "grad_norm": 1.6008487939834595,
+      "learning_rate": 2.2216181311685635e-05,
+      "loss": 0.2475,
+      "step": 800
+    },
+    {
+      "epoch": 0.13417190775681342,
+      "grad_norm": 1.6338393688201904,
+      "learning_rate": 2.2105688144979794e-05,
+      "loss": 0.4628,
+      "step": 832
+    },
+    {
+      "epoch": 0.13933236574746008,
+      "grad_norm": 7.390059947967529,
+      "learning_rate": 2.19774835710645e-05,
+      "loss": 0.3959,
+      "step": 864
+    },
+    {
+      "epoch": 0.14449282373810676,
+      "grad_norm": 4.810283184051514,
+      "learning_rate": 2.1831800942749025e-05,
+      "loss": 0.4319,
+      "step": 896
+    },
+    {
+      "epoch": 0.14965328172875342,
+      "grad_norm": 1.4031744003295898,
+      "learning_rate": 2.1668905425694316e-05,
+      "loss": 0.3313,
+      "step": 928
+    },
+    {
+      "epoch": 0.15045960328979197,
+      "eval_nli-pairs_loss": 1.1211928129196167,
+      "eval_nli-pairs_runtime": 3.6242,
+      "eval_nli-pairs_samples_per_second": 27.593,
+      "eval_nli-pairs_steps_per_second": 1.104,
+      "eval_sts-test_pearson_cosine": 0.7900142106272904,
+      "eval_sts-test_pearson_dot": 0.5204997048111483,
+      "eval_sts-test_pearson_euclidean": 0.7197544423606174,
+      "eval_sts-test_pearson_manhattan": 0.7129138118200246,
+      "eval_sts-test_pearson_max": 0.7900142106272904,
+      "eval_sts-test_spearman_cosine": 0.8070129991415972,
+      "eval_sts-test_spearman_dot": 0.5041327961468517,
+      "eval_sts-test_spearman_euclidean": 0.7107914253741027,
+      "eval_sts-test_spearman_manhattan": 0.7054678713044391,
+      "eval_sts-test_spearman_max": 0.8070129991415972,
+      "step": 933
+    },
+    {
+      "epoch": 0.15045960328979197,
+      "eval_vitaminc-pairs_loss": 5.291687965393066,
+      "eval_vitaminc-pairs_runtime": 1.1371,
+      "eval_vitaminc-pairs_samples_per_second": 74.751,
+      "eval_vitaminc-pairs_steps_per_second": 2.638,
+      "step": 933
+    },
+    {
+      "epoch": 0.15045960328979197,
+      "eval_qnli-contrastive_loss": 0.2255122810602188,
+      "eval_qnli-contrastive_runtime": 0.3581,
+      "eval_qnli-contrastive_samples_per_second": 279.26,
+      "eval_qnli-contrastive_steps_per_second": 11.17,
+      "step": 933
+    },
+    {
+      "epoch": 0.15045960328979197,
+      "eval_scitail-pairs-qa_loss": 0.03855748474597931,
+      "eval_scitail-pairs-qa_runtime": 0.9087,
+      "eval_scitail-pairs-qa_samples_per_second": 110.053,
+      "eval_scitail-pairs-qa_steps_per_second": 4.402,
+      "step": 933
+    },
+    {
+      "epoch": 0.15045960328979197,
+      "eval_scitail-pairs-pos_loss": 0.4346088171005249,
+      "eval_scitail-pairs-pos_runtime": 1.3407,
+      "eval_scitail-pairs-pos_samples_per_second": 74.588,
+      "eval_scitail-pairs-pos_steps_per_second": 2.984,
+      "step": 933
+    },
+    {
+      "epoch": 0.15045960328979197,
+      "eval_xsum-pairs_loss": 0.24305100739002228,
+      "eval_xsum-pairs_runtime": 0.934,
+      "eval_xsum-pairs_samples_per_second": 107.065,
+      "eval_xsum-pairs_steps_per_second": 4.283,
+      "step": 933
+    },
+    {
+      "epoch": 0.15045960328979197,
+      "eval_compression-pairs_loss": 0.07631812989711761,
+      "eval_compression-pairs_runtime": 0.2754,
+      "eval_compression-pairs_samples_per_second": 363.066,
+      "eval_compression-pairs_steps_per_second": 14.523,
+      "step": 933
+    },
+    {
+      "epoch": 0.15045960328979197,
+      "eval_sciq_pairs_loss": 0.23677608370780945,
+      "eval_sciq_pairs_runtime": 4.0696,
+      "eval_sciq_pairs_samples_per_second": 24.572,
+      "eval_sciq_pairs_steps_per_second": 0.983,
+      "step": 933
+    },
+    {
+      "epoch": 0.15045960328979197,
+      "eval_qasc_pairs_loss": 0.16437365114688873,
+      "eval_qasc_pairs_runtime": 1.0525,
+      "eval_qasc_pairs_samples_per_second": 95.011,
+      "eval_qasc_pairs_steps_per_second": 3.8,
+      "step": 933
+    },
+    {
+      "epoch": 0.15045960328979197,
+      "eval_openbookqa_pairs_loss": 1.8445327281951904,
+      "eval_openbookqa_pairs_runtime": 0.8949,
+      "eval_openbookqa_pairs_samples_per_second": 111.746,
+      "eval_openbookqa_pairs_steps_per_second": 4.47,
+      "step": 933
+    },
+    {
+      "epoch": 0.15045960328979197,
+      "eval_msmarco_pairs_loss": 0.5443564057350159,
+      "eval_msmarco_pairs_runtime": 2.0587,
+      "eval_msmarco_pairs_samples_per_second": 48.574,
+      "eval_msmarco_pairs_steps_per_second": 1.943,
+      "step": 933
+    },
+    {
+      "epoch": 0.15045960328979197,
+      "eval_nq_pairs_loss": 0.284332811832428,
+      "eval_nq_pairs_runtime": 4.5062,
+      "eval_nq_pairs_samples_per_second": 22.192,
+      "eval_nq_pairs_steps_per_second": 0.888,
+      "step": 933
+    },
+    {
+      "epoch": 0.15045960328979197,
+      "eval_trivia_pairs_loss": 0.9098919630050659,
+      "eval_trivia_pairs_runtime": 6.4944,
+      "eval_trivia_pairs_samples_per_second": 15.398,
+      "eval_trivia_pairs_steps_per_second": 0.616,
+      "step": 933
+    },
+    {
+      "epoch": 0.15045960328979197,
+      "eval_quora_pairs_loss": 0.04041712358593941,
+      "eval_quora_pairs_runtime": 0.6789,
+      "eval_quora_pairs_samples_per_second": 147.304,
+      "eval_quora_pairs_steps_per_second": 5.892,
+      "step": 933
+    },
+    {
+      "epoch": 0.15045960328979197,
+      "eval_gooaq_pairs_loss": 0.5749976634979248,
+      "eval_gooaq_pairs_runtime": 1.4231,
+      "eval_gooaq_pairs_samples_per_second": 70.269,
+      "eval_gooaq_pairs_steps_per_second": 2.811,
+      "step": 933
+    },
+    {
+      "epoch": 0.15045960328979197,
+      "eval_mrpc_pairs_loss": 0.031527042388916016,
+      "eval_mrpc_pairs_runtime": 0.2631,
+      "eval_mrpc_pairs_samples_per_second": 380.026,
+      "eval_mrpc_pairs_steps_per_second": 15.201,
+      "step": 933
+    },
+    {
+      "epoch": 0.1548137397194001,
+      "grad_norm": 16.21021270751953,
+      "learning_rate": 2.1489093515769124e-05,
+      "loss": 0.3114,
+      "step": 960
+    },
+    {
+      "epoch": 0.15997419771004676,
+      "grad_norm": 7.069672584533691,
+      "learning_rate": 2.1292692499380168e-05,
+      "loss": 0.3443,
+      "step": 992
+    },
+    {
+      "epoch": 0.16513465570069344,
+      "grad_norm": 0.17181938886642456,
+      "learning_rate": 2.1080059857758552e-05,
+      "loss": 0.3194,
+      "step": 1024
+    },
+    {
+      "epoch": 0.1702951136913401,
+      "grad_norm": 2.400918483734131,
+      "learning_rate": 2.085158261628683e-05,
+      "loss": 0.42,
+      "step": 1056
+    },
+    {
+      "epoch": 0.17545557168198678,
+      "grad_norm": 2.035386323928833,
+      "learning_rate": 2.060767664005095e-05,
+      "loss": 0.3576,
+      "step": 1088
+    },
+    {
+      "epoch": 0.18061602967263343,
+      "grad_norm": 3.427015542984009,
+      "learning_rate": 2.034878587689937e-05,
+      "loss": 0.3015,
+      "step": 1120
+    },
+    {
+      "epoch": 0.18577648766328012,
+      "grad_norm": 8.173876762390137,
+      "learning_rate": 2.0075381549387025e-05,
+      "loss": 0.318,
+      "step": 1152
+    },
+    {
+      "epoch": 0.1909369456539268,
+      "grad_norm": 7.757373332977295,
+      "learning_rate": 1.978796129707498e-05,
+      "loss": 0.3592,
+      "step": 1184
+    },
+    {
+      "epoch": 0.19609740364457345,
+      "grad_norm": 2.753797769546509,
+      "learning_rate": 1.9487048270746936e-05,
+      "loss": 0.2671,
+      "step": 1216
+    }
+  ],
+  "logging_steps": 32,
+  "max_steps": 12402,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1241,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1241/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ddaab2c5398d0449d2887f8fc99299c7dfe2e9af12ad3d71fa69aafe944f2f4
+size 5688