Training in progress, step 5166, checkpoint

checkpoint-5166/1_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-5166/added_tokens.json

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

checkpoint-5166/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-5166/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-5166/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-5166/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48dce9fac67f527c5cd15330176f1ed9f5d1112b836db760542dcebb4a58fc20
+size 1130520122

checkpoint-5166/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25e1bad878927495b582acce5107edb86e060716f82f8eccb92dc12596e12fbc
+size 565251810

checkpoint-5166/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ab1e41e74ed8f024bb2c6e63aea8eda3721a6d4f4319bb800b079eb34bd1ca
+size 14180

checkpoint-5166/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc253291aff0c40a90ac4c74ab0c743394b67fb8cd847ad95f915bb5a3ae2271
+size 1064

checkpoint-5166/sentence_bert_config.json

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

checkpoint-5166/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-5166/spm.model

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

checkpoint-5166/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-5166/trainer_state.json

@@ -0,0 +1,1237 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 1292,
+  "global_step": 5166,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012582268679829655,
+      "grad_norm": 4.108283996582031,
+      "learning_rate": 3.7166085946573755e-07,
+      "loss": 0.4577,
+      "step": 65
+    },
+    {
+      "epoch": 0.02516453735965931,
+      "grad_norm": 0.5773646831512451,
+      "learning_rate": 7.491289198606272e-07,
+      "loss": 0.4707,
+      "step": 130
+    },
+    {
+      "epoch": 0.03774680603948897,
+      "grad_norm": 0.6127182841300964,
+      "learning_rate": 1.1265969802555168e-06,
+      "loss": 0.5259,
+      "step": 195
+    },
+    {
+      "epoch": 0.05032907471931862,
+      "grad_norm": 1.513021469116211,
+      "learning_rate": 1.5040650406504067e-06,
+      "loss": 0.5501,
+      "step": 260
+    },
+    {
+      "epoch": 0.06291134339914828,
+      "grad_norm": 11.750137329101562,
+      "learning_rate": 1.8815331010452962e-06,
+      "loss": 0.5089,
+      "step": 325
+    },
+    {
+      "epoch": 0.07549361207897794,
+      "grad_norm": 4.16257905960083,
+      "learning_rate": 2.259001161440186e-06,
+      "loss": 0.4816,
+      "step": 390
+    },
+    {
+      "epoch": 0.08807588075880758,
+      "grad_norm": 16.527780532836914,
+      "learning_rate": 2.6306620209059233e-06,
+      "loss": 0.5822,
+      "step": 455
+    },
+    {
+      "epoch": 0.10065814943863724,
+      "grad_norm": 0.1845797300338745,
+      "learning_rate": 3.0081300813008134e-06,
+      "loss": 0.5686,
+      "step": 520
+    },
+    {
+      "epoch": 0.1132404181184669,
+      "grad_norm": 12.172422409057617,
+      "learning_rate": 3.3855981416957026e-06,
+      "loss": 0.5686,
+      "step": 585
+    },
+    {
+      "epoch": 0.12582268679829656,
+      "grad_norm": 0.6270273923873901,
+      "learning_rate": 3.7630662020905923e-06,
+      "loss": 0.517,
+      "step": 650
+    },
+    {
+      "epoch": 0.1384049554781262,
+      "grad_norm": 3.6368539333343506,
+      "learning_rate": 4.140534262485482e-06,
+      "loss": 0.3615,
+      "step": 715
+    },
+    {
+      "epoch": 0.15098722415795587,
+      "grad_norm": 9.541145324707031,
+      "learning_rate": 4.518002322880372e-06,
+      "loss": 0.5978,
+      "step": 780
+    },
+    {
+      "epoch": 0.16356949283778552,
+      "grad_norm": 9.86439323425293,
+      "learning_rate": 4.895470383275261e-06,
+      "loss": 0.5153,
+      "step": 845
+    },
+    {
+      "epoch": 0.17615176151761516,
+      "grad_norm": 4.669048309326172,
+      "learning_rate": 5.272938443670151e-06,
+      "loss": 0.5059,
+      "step": 910
+    },
+    {
+      "epoch": 0.18873403019744484,
+      "grad_norm": 9.666926383972168,
+      "learning_rate": 5.650406504065041e-06,
+      "loss": 0.5624,
+      "step": 975
+    },
+    {
+      "epoch": 0.20131629887727448,
+      "grad_norm": 6.078874588012695,
+      "learning_rate": 6.02787456445993e-06,
+      "loss": 0.5201,
+      "step": 1040
+    },
+    {
+      "epoch": 0.21389856755710415,
+      "grad_norm": 1.1067451238632202,
+      "learning_rate": 6.4053426248548205e-06,
+      "loss": 0.6127,
+      "step": 1105
+    },
+    {
+      "epoch": 0.2264808362369338,
+      "grad_norm": 1.1589373350143433,
+      "learning_rate": 6.78281068524971e-06,
+      "loss": 0.5333,
+      "step": 1170
+    },
+    {
+      "epoch": 0.23906310491676344,
+      "grad_norm": 1.977501630783081,
+      "learning_rate": 7.1602787456446e-06,
+      "loss": 0.494,
+      "step": 1235
+    },
+    {
+      "epoch": 0.2500967866821525,
+      "eval_StS-test_pearson_cosine": 0.8821101738384596,
+      "eval_StS-test_pearson_dot": 0.8032893366124795,
+      "eval_StS-test_pearson_euclidean": 0.8697205121607111,
+      "eval_StS-test_pearson_manhattan": 0.8704995590187196,
+      "eval_StS-test_pearson_max": 0.8821101738384596,
+      "eval_StS-test_spearman_cosine": 0.8943047751560564,
+      "eval_StS-test_spearman_dot": 0.8087424893555902,
+      "eval_StS-test_spearman_euclidean": 0.871583089708652,
+      "eval_StS-test_spearman_manhattan": 0.8737012027236009,
+      "eval_StS-test_spearman_max": 0.8943047751560564,
+      "eval_Vitaminc-test_cosine_accuracy": 0.5684210526315789,
+      "eval_Vitaminc-test_cosine_accuracy_threshold": 0.7028586268424988,
+      "eval_Vitaminc-test_cosine_ap": 0.5651043866206488,
+      "eval_Vitaminc-test_cosine_f1": 0.6755218216318786,
+      "eval_Vitaminc-test_cosine_f1_threshold": 0.5077509880065918,
+      "eval_Vitaminc-test_cosine_precision": 0.52046783625731,
+      "eval_Vitaminc-test_cosine_recall": 0.9621621621621622,
+      "eval_Vitaminc-test_dot_accuracy": 0.5684210526315789,
+      "eval_Vitaminc-test_dot_accuracy_threshold": 19.693286895751953,
+      "eval_Vitaminc-test_dot_ap": 0.5463931769790206,
+      "eval_Vitaminc-test_dot_f1": 0.6691449814126395,
+      "eval_Vitaminc-test_dot_f1_threshold": 13.839346885681152,
+      "eval_Vitaminc-test_dot_precision": 0.509915014164306,
+      "eval_Vitaminc-test_dot_recall": 0.972972972972973,
+      "eval_Vitaminc-test_euclidean_accuracy": 0.5894736842105263,
+      "eval_Vitaminc-test_euclidean_accuracy_threshold": 4.252468585968018,
+      "eval_Vitaminc-test_euclidean_ap": 0.5569049511912931,
+      "eval_Vitaminc-test_euclidean_f1": 0.6666666666666666,
+      "eval_Vitaminc-test_euclidean_f1_threshold": 6.922356128692627,
+      "eval_Vitaminc-test_euclidean_precision": 0.5041551246537396,
+      "eval_Vitaminc-test_euclidean_recall": 0.9837837837837838,
+      "eval_Vitaminc-test_manhattan_accuracy": 0.5815789473684211,
+      "eval_Vitaminc-test_manhattan_accuracy_threshold": 87.21337890625,
+      "eval_Vitaminc-test_manhattan_ap": 0.5572154085134091,
+      "eval_Vitaminc-test_manhattan_f1": 0.6666666666666667,
+      "eval_Vitaminc-test_manhattan_f1_threshold": 141.26380920410156,
+      "eval_Vitaminc-test_manhattan_precision": 0.505586592178771,
+      "eval_Vitaminc-test_manhattan_recall": 0.9783783783783784,
+      "eval_Vitaminc-test_max_accuracy": 0.5894736842105263,
+      "eval_Vitaminc-test_max_accuracy_threshold": 87.21337890625,
+      "eval_Vitaminc-test_max_ap": 0.5651043866206488,
+      "eval_Vitaminc-test_max_f1": 0.6755218216318786,
+      "eval_Vitaminc-test_max_f1_threshold": 141.26380920410156,
+      "eval_Vitaminc-test_max_precision": 0.52046783625731,
+      "eval_Vitaminc-test_max_recall": 0.9837837837837838,
+      "eval_mrpc-test_cosine_accuracy": 0.7473684210526316,
+      "eval_mrpc-test_cosine_accuracy_threshold": 0.7145693302154541,
+      "eval_mrpc-test_cosine_ap": 0.8563235829800693,
+      "eval_mrpc-test_cosine_f1": 0.8327645051194539,
+      "eval_mrpc-test_cosine_f1_threshold": 0.6522408723831177,
+      "eval_mrpc-test_cosine_precision": 0.7218934911242604,
+      "eval_mrpc-test_cosine_recall": 0.9838709677419355,
+      "eval_mrpc-test_dot_accuracy": 0.7026315789473684,
+      "eval_mrpc-test_dot_accuracy_threshold": 14.454626083374023,
+      "eval_mrpc-test_dot_ap": 0.796363256728503,
+      "eval_mrpc-test_dot_f1": 0.8054607508532423,
+      "eval_mrpc-test_dot_f1_threshold": 13.752894401550293,
+      "eval_mrpc-test_dot_precision": 0.6982248520710059,
+      "eval_mrpc-test_dot_recall": 0.9516129032258065,
+      "eval_mrpc-test_euclidean_accuracy": 0.7315789473684211,
+      "eval_mrpc-test_euclidean_accuracy_threshold": 3.890326499938965,
+      "eval_mrpc-test_euclidean_ap": 0.8252367395643119,
+      "eval_mrpc-test_euclidean_f1": 0.8165467625899281,
+      "eval_mrpc-test_euclidean_f1_threshold": 3.890326499938965,
+      "eval_mrpc-test_euclidean_precision": 0.737012987012987,
+      "eval_mrpc-test_euclidean_recall": 0.9153225806451613,
+      "eval_mrpc-test_manhattan_accuracy": 0.7289473684210527,
+      "eval_mrpc-test_manhattan_accuracy_threshold": 77.57926177978516,
+      "eval_mrpc-test_manhattan_ap": 0.8208816982117964,
+      "eval_mrpc-test_manhattan_f1": 0.815742397137746,
+      "eval_mrpc-test_manhattan_f1_threshold": 79.14703369140625,
+      "eval_mrpc-test_manhattan_precision": 0.7331189710610932,
+      "eval_mrpc-test_manhattan_recall": 0.9193548387096774,
+      "eval_mrpc-test_max_accuracy": 0.7473684210526316,
+      "eval_mrpc-test_max_accuracy_threshold": 77.57926177978516,
+      "eval_mrpc-test_max_ap": 0.8563235829800693,
+      "eval_mrpc-test_max_f1": 0.8327645051194539,
+      "eval_mrpc-test_max_f1_threshold": 79.14703369140625,
+      "eval_mrpc-test_max_precision": 0.737012987012987,
+      "eval_mrpc-test_max_recall": 0.9838709677419355,
+      "eval_nli-pairs_loss": 0.8093397617340088,
+      "eval_nli-pairs_runtime": 3.0363,
+      "eval_nli-pairs_samples_per_second": 52.696,
+      "eval_nli-pairs_steps_per_second": 1.647,
+      "eval_sequential_score": 0.5651043866206488,
+      "step": 1292
+    },
+    {
+      "epoch": 0.2500967866821525,
+      "eval_vitaminc-pairs_loss": 5.769770622253418,
+      "eval_vitaminc-pairs_runtime": 1.5488,
+      "eval_vitaminc-pairs_samples_per_second": 85.875,
+      "eval_vitaminc-pairs_steps_per_second": 3.228,
+      "step": 1292
+    },
+    {
+      "epoch": 0.2500967866821525,
+      "eval_qnli-contrastive_loss": 0.12109158933162689,
+      "eval_qnli-contrastive_runtime": 0.5097,
+      "eval_qnli-contrastive_samples_per_second": 313.889,
+      "eval_qnli-contrastive_steps_per_second": 9.809,
+      "step": 1292
+    },
+    {
+      "epoch": 0.2500967866821525,
+      "eval_scitail-pairs-qa_loss": 0.07553695887327194,
+      "eval_scitail-pairs-qa_runtime": 1.2071,
+      "eval_scitail-pairs-qa_samples_per_second": 132.548,
+      "eval_scitail-pairs-qa_steps_per_second": 4.142,
+      "step": 1292
+    },
+    {
+      "epoch": 0.2500967866821525,
+      "eval_scitail-pairs-pos_loss": 0.3979075253009796,
+      "eval_scitail-pairs-pos_runtime": 2.3649,
+      "eval_scitail-pairs-pos_samples_per_second": 67.656,
+      "eval_scitail-pairs-pos_steps_per_second": 2.114,
+      "step": 1292
+    },
+    {
+      "epoch": 0.2500967866821525,
+      "eval_xsum-pairs_loss": 0.313429057598114,
+      "eval_xsum-pairs_runtime": 1.4107,
+      "eval_xsum-pairs_samples_per_second": 113.419,
+      "eval_xsum-pairs_steps_per_second": 3.544,
+      "step": 1292
+    },
+    {
+      "epoch": 0.2500967866821525,
+      "eval_compression-pairs_loss": 0.08316509425640106,
+      "eval_compression-pairs_runtime": 0.3958,
+      "eval_compression-pairs_samples_per_second": 404.289,
+      "eval_compression-pairs_steps_per_second": 12.634,
+      "step": 1292
+    },
+    {
+      "epoch": 0.2500967866821525,
+      "eval_sciq_pairs_loss": 0.2692818343639374,
+      "eval_sciq_pairs_runtime": 7.8991,
+      "eval_sciq_pairs_samples_per_second": 20.255,
+      "eval_sciq_pairs_steps_per_second": 0.633,
+      "step": 1292
+    },
+    {
+      "epoch": 0.2500967866821525,
+      "eval_qasc_pairs_loss": 0.19870159029960632,
+      "eval_qasc_pairs_runtime": 1.4336,
+      "eval_qasc_pairs_samples_per_second": 111.608,
+      "eval_qasc_pairs_steps_per_second": 3.488,
+      "step": 1292
+    },
+    {
+      "epoch": 0.2500967866821525,
+      "eval_qasc_facts_sym_loss": 0.16445104777812958,
+      "eval_qasc_facts_sym_runtime": 0.3196,
+      "eval_qasc_facts_sym_samples_per_second": 500.598,
+      "eval_qasc_facts_sym_steps_per_second": 15.644,
+      "step": 1292
+    },
+    {
+      "epoch": 0.2500967866821525,
+      "eval_openbookqa_pairs_loss": 1.7182375192642212,
+      "eval_openbookqa_pairs_runtime": 1.2252,
+      "eval_openbookqa_pairs_samples_per_second": 130.592,
+      "eval_openbookqa_pairs_steps_per_second": 4.081,
+      "step": 1292
+    },
+    {
+      "epoch": 0.2500967866821525,
+      "eval_msmarco_pairs_loss": 0.4961338937282562,
+      "eval_msmarco_pairs_runtime": 3.1144,
+      "eval_msmarco_pairs_samples_per_second": 51.374,
+      "eval_msmarco_pairs_steps_per_second": 1.605,
+      "step": 1292
+    },
+    {
+      "epoch": 0.2500967866821525,
+      "eval_nq_pairs_loss": 0.4005078673362732,
+      "eval_nq_pairs_runtime": 7.7074,
+      "eval_nq_pairs_samples_per_second": 20.759,
+      "eval_nq_pairs_steps_per_second": 0.649,
+      "step": 1292
+    },
+    {
+      "epoch": 0.2500967866821525,
+      "eval_trivia_pairs_loss": 0.654505729675293,
+      "eval_trivia_pairs_runtime": 10.1383,
+      "eval_trivia_pairs_samples_per_second": 15.782,
+      "eval_trivia_pairs_steps_per_second": 0.493,
+      "step": 1292
+    },
+    {
+      "epoch": 0.2500967866821525,
+      "eval_quora_pairs_loss": 0.22833283245563507,
+      "eval_quora_pairs_runtime": 3.894,
+      "eval_quora_pairs_samples_per_second": 173.342,
+      "eval_quora_pairs_steps_per_second": 5.65,
+      "step": 1292
+    },
+    {
+      "epoch": 0.2500967866821525,
+      "eval_gooaq_pairs_loss": 0.4996432662010193,
+      "eval_gooaq_pairs_runtime": 2.2697,
+      "eval_gooaq_pairs_samples_per_second": 70.494,
+      "eval_gooaq_pairs_steps_per_second": 2.203,
+      "step": 1292
+    },
+    {
+      "epoch": 0.2500967866821525,
+      "eval_mrpc_pairs_loss": 0.04613902047276497,
+      "eval_mrpc_pairs_runtime": 0.3743,
+      "eval_mrpc_pairs_samples_per_second": 427.427,
+      "eval_mrpc_pairs_steps_per_second": 13.357,
+      "step": 1292
+    },
+    {
+      "epoch": 0.2516453735965931,
+      "grad_norm": 12.50217342376709,
+      "learning_rate": 7.53774680603949e-06,
+      "loss": 0.6236,
+      "step": 1300
+    },
+    {
+      "epoch": 0.26422764227642276,
+      "grad_norm": 1.8397300243377686,
+      "learning_rate": 7.91521486643438e-06,
+      "loss": 0.4947,
+      "step": 1365
+    },
+    {
+      "epoch": 0.2768099109562524,
+      "grad_norm": 5.885033130645752,
+      "learning_rate": 8.292682926829268e-06,
+      "loss": 0.5595,
+      "step": 1430
+    },
+    {
+      "epoch": 0.28939217963608205,
+      "grad_norm": 1.7783002853393555,
+      "learning_rate": 8.670150987224158e-06,
+      "loss": 0.641,
+      "step": 1495
+    },
+    {
+      "epoch": 0.30197444831591175,
+      "grad_norm": 5.305712699890137,
+      "learning_rate": 9.047619047619047e-06,
+      "loss": 0.5188,
+      "step": 1560
+    },
+    {
+      "epoch": 0.3145567169957414,
+      "grad_norm": 8.24319839477539,
+      "learning_rate": 9.425087108013936e-06,
+      "loss": 0.4927,
+      "step": 1625
+    },
+    {
+      "epoch": 0.32713898567557104,
+      "grad_norm": 11.07426929473877,
+      "learning_rate": 9.802555168408827e-06,
+      "loss": 0.657,
+      "step": 1690
+    },
+    {
+      "epoch": 0.3397212543554007,
+      "grad_norm": 9.04263687133789,
+      "learning_rate": 1.0180023228803716e-05,
+      "loss": 0.4665,
+      "step": 1755
+    },
+    {
+      "epoch": 0.3523035230352303,
+      "grad_norm": 1.4980370998382568,
+      "learning_rate": 1.0557491289198606e-05,
+      "loss": 0.4645,
+      "step": 1820
+    },
+    {
+      "epoch": 0.36488579171506,
+      "grad_norm": 16.511180877685547,
+      "learning_rate": 1.0934959349593495e-05,
+      "loss": 0.5887,
+      "step": 1885
+    },
+    {
+      "epoch": 0.37746806039488967,
+      "grad_norm": 5.706000804901123,
+      "learning_rate": 1.1312427409988386e-05,
+      "loss": 0.5308,
+      "step": 1950
+    },
+    {
+      "epoch": 0.3900503290747193,
+      "grad_norm": 1.0923340320587158,
+      "learning_rate": 1.1689895470383277e-05,
+      "loss": 0.536,
+      "step": 2015
+    },
+    {
+      "epoch": 0.40263259775454896,
+      "grad_norm": 6.521665573120117,
+      "learning_rate": 1.2067363530778166e-05,
+      "loss": 0.4841,
+      "step": 2080
+    },
+    {
+      "epoch": 0.4152148664343786,
+      "grad_norm": 7.254842758178711,
+      "learning_rate": 1.2444831591173055e-05,
+      "loss": 0.6499,
+      "step": 2145
+    },
+    {
+      "epoch": 0.4277971351142083,
+      "grad_norm": 14.938628196716309,
+      "learning_rate": 1.2822299651567945e-05,
+      "loss": 0.5982,
+      "step": 2210
+    },
+    {
+      "epoch": 0.44037940379403795,
+      "grad_norm": 10.192171096801758,
+      "learning_rate": 1.3199767711962834e-05,
+      "loss": 0.5281,
+      "step": 2275
+    },
+    {
+      "epoch": 0.4529616724738676,
+      "grad_norm": 8.02379035949707,
+      "learning_rate": 1.3577235772357725e-05,
+      "loss": 0.6657,
+      "step": 2340
+    },
+    {
+      "epoch": 0.46554394115369724,
+      "grad_norm": 2.842752695083618,
+      "learning_rate": 1.3954703832752614e-05,
+      "loss": 0.5746,
+      "step": 2405
+    },
+    {
+      "epoch": 0.4781262098335269,
+      "grad_norm": 0.4373825788497925,
+      "learning_rate": 1.432636469221835e-05,
+      "loss": 0.5853,
+      "step": 2470
+    },
+    {
+      "epoch": 0.4907084785133566,
+      "grad_norm": 16.475561141967773,
+      "learning_rate": 1.4703832752613242e-05,
+      "loss": 0.5828,
+      "step": 2535
+    },
+    {
+      "epoch": 0.500193573364305,
+      "eval_StS-test_pearson_cosine": 0.8850112014664042,
+      "eval_StS-test_pearson_dot": 0.8059948281019231,
+      "eval_StS-test_pearson_euclidean": 0.8736480607586303,
+      "eval_StS-test_pearson_manhattan": 0.8746434402751778,
+      "eval_StS-test_pearson_max": 0.8850112014664042,
+      "eval_StS-test_spearman_cosine": 0.8964908683344393,
+      "eval_StS-test_spearman_dot": 0.8112940990649002,
+      "eval_StS-test_spearman_euclidean": 0.8728524906348676,
+      "eval_StS-test_spearman_manhattan": 0.8747700566942432,
+      "eval_StS-test_spearman_max": 0.8964908683344393,
+      "eval_Vitaminc-test_cosine_accuracy": 0.5842105263157895,
+      "eval_Vitaminc-test_cosine_accuracy_threshold": 0.6876633763313293,
+      "eval_Vitaminc-test_cosine_ap": 0.5620310838989798,
+      "eval_Vitaminc-test_cosine_f1": 0.6755725190839694,
+      "eval_Vitaminc-test_cosine_f1_threshold": 0.5227451324462891,
+      "eval_Vitaminc-test_cosine_precision": 0.5221238938053098,
+      "eval_Vitaminc-test_cosine_recall": 0.9567567567567568,
+      "eval_Vitaminc-test_dot_accuracy": 0.5552631578947368,
+      "eval_Vitaminc-test_dot_accuracy_threshold": 19.32275390625,
+      "eval_Vitaminc-test_dot_ap": 0.5459852333889619,
+      "eval_Vitaminc-test_dot_f1": 0.6715596330275228,
+      "eval_Vitaminc-test_dot_f1_threshold": 12.946126937866211,
+      "eval_Vitaminc-test_dot_precision": 0.5083333333333333,
+      "eval_Vitaminc-test_dot_recall": 0.9891891891891892,
+      "eval_Vitaminc-test_euclidean_accuracy": 0.5736842105263158,
+      "eval_Vitaminc-test_euclidean_accuracy_threshold": 3.9492130279541016,
+      "eval_Vitaminc-test_euclidean_ap": 0.5569069466677845,
+      "eval_Vitaminc-test_euclidean_f1": 0.6654343807763402,
+      "eval_Vitaminc-test_euclidean_f1_threshold": 6.641269207000732,
+      "eval_Vitaminc-test_euclidean_precision": 0.5056179775280899,
+      "eval_Vitaminc-test_euclidean_recall": 0.972972972972973,
+      "eval_Vitaminc-test_manhattan_accuracy": 0.5789473684210527,
+      "eval_Vitaminc-test_manhattan_accuracy_threshold": 80.14714050292969,
+      "eval_Vitaminc-test_manhattan_ap": 0.556199495550533,
+      "eval_Vitaminc-test_manhattan_f1": 0.6691312384473197,
+      "eval_Vitaminc-test_manhattan_f1_threshold": 138.50221252441406,
+      "eval_Vitaminc-test_manhattan_precision": 0.5084269662921348,
+      "eval_Vitaminc-test_manhattan_recall": 0.9783783783783784,
+      "eval_Vitaminc-test_max_accuracy": 0.5842105263157895,
+      "eval_Vitaminc-test_max_accuracy_threshold": 80.14714050292969,
+      "eval_Vitaminc-test_max_ap": 0.5620310838989798,
+      "eval_Vitaminc-test_max_f1": 0.6755725190839694,
+      "eval_Vitaminc-test_max_f1_threshold": 138.50221252441406,
+      "eval_Vitaminc-test_max_precision": 0.5221238938053098,
+      "eval_Vitaminc-test_max_recall": 0.9891891891891892,
+      "eval_mrpc-test_cosine_accuracy": 0.7368421052631579,
+      "eval_mrpc-test_cosine_accuracy_threshold": 0.7595815658569336,
+      "eval_mrpc-test_cosine_ap": 0.8489522026016108,
+      "eval_mrpc-test_cosine_f1": 0.8235294117647058,
+      "eval_mrpc-test_cosine_f1_threshold": 0.6731016635894775,
+      "eval_mrpc-test_cosine_precision": 0.7212121212121212,
+      "eval_mrpc-test_cosine_recall": 0.9596774193548387,
+      "eval_mrpc-test_dot_accuracy": 0.6894736842105263,
+      "eval_mrpc-test_dot_accuracy_threshold": 15.645252227783203,
+      "eval_mrpc-test_dot_ap": 0.7828717059557433,
+      "eval_mrpc-test_dot_f1": 0.8071895424836601,
+      "eval_mrpc-test_dot_f1_threshold": 11.141586303710938,
+      "eval_mrpc-test_dot_precision": 0.6785714285714286,
+      "eval_mrpc-test_dot_recall": 0.9959677419354839,
+      "eval_mrpc-test_euclidean_accuracy": 0.7368421052631579,
+      "eval_mrpc-test_euclidean_accuracy_threshold": 3.7453079223632812,
+      "eval_mrpc-test_euclidean_ap": 0.8190549606804299,
+      "eval_mrpc-test_euclidean_f1": 0.8172043010752688,
+      "eval_mrpc-test_euclidean_f1_threshold": 3.905801773071289,
+      "eval_mrpc-test_euclidean_precision": 0.7354838709677419,
+      "eval_mrpc-test_euclidean_recall": 0.9193548387096774,
+      "eval_mrpc-test_manhattan_accuracy": 0.7315789473684211,
+      "eval_mrpc-test_manhattan_accuracy_threshold": 74.24961853027344,
+      "eval_mrpc-test_manhattan_ap": 0.815561648496177,
+      "eval_mrpc-test_manhattan_f1": 0.81508078994614,
+      "eval_mrpc-test_manhattan_f1_threshold": 78.01387023925781,
+      "eval_mrpc-test_manhattan_precision": 0.7346278317152104,
+      "eval_mrpc-test_manhattan_recall": 0.9153225806451613,
+      "eval_mrpc-test_max_accuracy": 0.7368421052631579,
+      "eval_mrpc-test_max_accuracy_threshold": 74.24961853027344,
+      "eval_mrpc-test_max_ap": 0.8489522026016108,
+      "eval_mrpc-test_max_f1": 0.8235294117647058,
+      "eval_mrpc-test_max_f1_threshold": 78.01387023925781,
+      "eval_mrpc-test_max_precision": 0.7354838709677419,
+      "eval_mrpc-test_max_recall": 0.9959677419354839,
+      "eval_nli-pairs_loss": 0.805642306804657,
+      "eval_nli-pairs_runtime": 3.1328,
+      "eval_nli-pairs_samples_per_second": 51.072,
+      "eval_nli-pairs_steps_per_second": 1.596,
+      "eval_sequential_score": 0.5620310838989798,
+      "step": 2584
+    },
+    {
+      "epoch": 0.500193573364305,
+      "eval_vitaminc-pairs_loss": 5.803024768829346,
+      "eval_vitaminc-pairs_runtime": 1.6236,
+      "eval_vitaminc-pairs_samples_per_second": 81.915,
+      "eval_vitaminc-pairs_steps_per_second": 3.08,
+      "step": 2584
+    },
+    {
+      "epoch": 0.500193573364305,
+      "eval_qnli-contrastive_loss": 0.1560516655445099,
+      "eval_qnli-contrastive_runtime": 0.5455,
+      "eval_qnli-contrastive_samples_per_second": 293.295,
+      "eval_qnli-contrastive_steps_per_second": 9.165,
+      "step": 2584
+    },
+    {
+      "epoch": 0.500193573364305,
+      "eval_scitail-pairs-qa_loss": 0.07059809565544128,
+      "eval_scitail-pairs-qa_runtime": 1.3304,
+      "eval_scitail-pairs-qa_samples_per_second": 120.266,
+      "eval_scitail-pairs-qa_steps_per_second": 3.758,
+      "step": 2584
+    },
+    {
+      "epoch": 0.500193573364305,
+      "eval_scitail-pairs-pos_loss": 0.40096405148506165,
+      "eval_scitail-pairs-pos_runtime": 2.6358,
+      "eval_scitail-pairs-pos_samples_per_second": 60.703,
+      "eval_scitail-pairs-pos_steps_per_second": 1.897,
+      "step": 2584
+    },
+    {
+      "epoch": 0.500193573364305,
+      "eval_xsum-pairs_loss": 0.3021017014980316,
+      "eval_xsum-pairs_runtime": 1.474,
+      "eval_xsum-pairs_samples_per_second": 108.547,
+      "eval_xsum-pairs_steps_per_second": 3.392,
+      "step": 2584
+    },
+    {
+      "epoch": 0.500193573364305,
+      "eval_compression-pairs_loss": 0.08080567419528961,
+      "eval_compression-pairs_runtime": 0.4395,
+      "eval_compression-pairs_samples_per_second": 364.011,
+      "eval_compression-pairs_steps_per_second": 11.375,
+      "step": 2584
+    },
+    {
+      "epoch": 0.500193573364305,
+      "eval_sciq_pairs_loss": 0.2838394045829773,
+      "eval_sciq_pairs_runtime": 8.1466,
+      "eval_sciq_pairs_samples_per_second": 19.64,
+      "eval_sciq_pairs_steps_per_second": 0.614,
+      "step": 2584
+    },
+    {
+      "epoch": 0.500193573364305,
+      "eval_qasc_pairs_loss": 0.19900637865066528,
+      "eval_qasc_pairs_runtime": 1.4833,
+      "eval_qasc_pairs_samples_per_second": 107.864,
+      "eval_qasc_pairs_steps_per_second": 3.371,
+      "step": 2584
+    },
+    {
+      "epoch": 0.500193573364305,
+      "eval_qasc_facts_sym_loss": 0.15245158970355988,
+      "eval_qasc_facts_sym_runtime": 0.3292,
+      "eval_qasc_facts_sym_samples_per_second": 485.978,
+      "eval_qasc_facts_sym_steps_per_second": 15.187,
+      "step": 2584
+    },
+    {
+      "epoch": 0.500193573364305,
+      "eval_openbookqa_pairs_loss": 1.7069475650787354,
+      "eval_openbookqa_pairs_runtime": 1.4335,
+      "eval_openbookqa_pairs_samples_per_second": 111.612,
+      "eval_openbookqa_pairs_steps_per_second": 3.488,
+      "step": 2584
+    },
+    {
+      "epoch": 0.500193573364305,
+      "eval_msmarco_pairs_loss": 0.5149500966072083,
+      "eval_msmarco_pairs_runtime": 3.2287,
+      "eval_msmarco_pairs_samples_per_second": 49.555,
+      "eval_msmarco_pairs_steps_per_second": 1.549,
+      "step": 2584
+    },
+    {
+      "epoch": 0.500193573364305,
+      "eval_nq_pairs_loss": 0.4162893295288086,
+      "eval_nq_pairs_runtime": 7.8277,
+      "eval_nq_pairs_samples_per_second": 20.44,
+      "eval_nq_pairs_steps_per_second": 0.639,
+      "step": 2584
+    },
+    {
+      "epoch": 0.500193573364305,
+      "eval_trivia_pairs_loss": 0.623663067817688,
+      "eval_trivia_pairs_runtime": 10.277,
+      "eval_trivia_pairs_samples_per_second": 15.569,
+      "eval_trivia_pairs_steps_per_second": 0.487,
+      "step": 2584
+    },
+    {
+      "epoch": 0.500193573364305,
+      "eval_quora_pairs_loss": 0.22309938073158264,
+      "eval_quora_pairs_runtime": 4.3318,
+      "eval_quora_pairs_samples_per_second": 155.824,
+      "eval_quora_pairs_steps_per_second": 5.079,
+      "step": 2584
+    },
+    {
+      "epoch": 0.500193573364305,
+      "eval_gooaq_pairs_loss": 0.49019113183021545,
+      "eval_gooaq_pairs_runtime": 2.2716,
+      "eval_gooaq_pairs_samples_per_second": 70.434,
+      "eval_gooaq_pairs_steps_per_second": 2.201,
+      "step": 2584
+    },
+    {
+      "epoch": 0.500193573364305,
+      "eval_mrpc_pairs_loss": 0.04494442045688629,
+      "eval_mrpc_pairs_runtime": 0.3756,
+      "eval_mrpc_pairs_samples_per_second": 425.958,
+      "eval_mrpc_pairs_steps_per_second": 13.311,
+      "step": 2584
+    },
+    {
+      "epoch": 0.5032907471931862,
+      "grad_norm": 0.5926259756088257,
+      "learning_rate": 1.5081300813008131e-05,
+      "loss": 0.4889,
+      "step": 2600
+    },
+    {
+      "epoch": 0.5158730158730159,
+      "grad_norm": 12.89693832397461,
+      "learning_rate": 1.545876887340302e-05,
+      "loss": 0.517,
+      "step": 2665
+    },
+    {
+      "epoch": 0.5284552845528455,
+      "grad_norm": 0.3751634359359741,
+      "learning_rate": 1.583623693379791e-05,
+      "loss": 0.5479,
+      "step": 2730
+    },
+    {
+      "epoch": 0.5410375532326752,
+      "grad_norm": 10.321626663208008,
+      "learning_rate": 1.62137049941928e-05,
+      "loss": 0.6409,
+      "step": 2795
+    },
+    {
+      "epoch": 0.5536198219125048,
+      "grad_norm": 0.40425410866737366,
+      "learning_rate": 1.659117305458769e-05,
+      "loss": 0.6137,
+      "step": 2860
+    },
+    {
+      "epoch": 0.5662020905923345,
+      "grad_norm": 0.26469847559928894,
+      "learning_rate": 1.696864111498258e-05,
+      "loss": 0.5947,
+      "step": 2925
+    },
+    {
+      "epoch": 0.5787843592721641,
+      "grad_norm": 0.3376736640930176,
+      "learning_rate": 1.7346109175377468e-05,
+      "loss": 0.514,
+      "step": 2990
+    },
+    {
+      "epoch": 0.5913666279519938,
+      "grad_norm": 11.042977333068848,
+      "learning_rate": 1.7723577235772357e-05,
+      "loss": 0.5256,
+      "step": 3055
+    },
+    {
+      "epoch": 0.6039488966318235,
+      "grad_norm": 28.415281295776367,
+      "learning_rate": 1.810104529616725e-05,
+      "loss": 0.5574,
+      "step": 3120
+    },
+    {
+      "epoch": 0.6165311653116531,
+      "grad_norm": 1.138208270072937,
+      "learning_rate": 1.8478513356562136e-05,
+      "loss": 0.5669,
+      "step": 3185
+    },
+    {
+      "epoch": 0.6291134339914828,
+      "grad_norm": 0.38507771492004395,
+      "learning_rate": 1.885598141695703e-05,
+      "loss": 0.5185,
+      "step": 3250
+    },
+    {
+      "epoch": 0.6416957026713124,
+      "grad_norm": 0.4718106687068939,
+      "learning_rate": 1.9233449477351914e-05,
+      "loss": 0.4875,
+      "step": 3315
+    },
+    {
+      "epoch": 0.6542779713511421,
+      "grad_norm": 0.3544551432132721,
+      "learning_rate": 1.9610917537746807e-05,
+      "loss": 0.5773,
+      "step": 3380
+    },
+    {
+      "epoch": 0.6668602400309718,
+      "grad_norm": 15.193903923034668,
+      "learning_rate": 1.9988385598141696e-05,
+      "loss": 0.6102,
+      "step": 3445
+    },
+    {
+      "epoch": 0.6794425087108014,
+      "grad_norm": 14.930959701538086,
+      "learning_rate": 2.0365853658536586e-05,
+      "loss": 0.5882,
+      "step": 3510
+    },
+    {
+      "epoch": 0.6920247773906311,
+      "grad_norm": 0.7249612212181091,
+      "learning_rate": 2.0743321718931475e-05,
+      "loss": 0.5888,
+      "step": 3575
+    },
+    {
+      "epoch": 0.7046070460704607,
+      "grad_norm": 0.21552956104278564,
+      "learning_rate": 2.1120789779326364e-05,
+      "loss": 0.6088,
+      "step": 3640
+    },
+    {
+      "epoch": 0.7171893147502904,
+      "grad_norm": 3.176356554031372,
+      "learning_rate": 2.1498257839721253e-05,
+      "loss": 0.688,
+      "step": 3705
+    },
+    {
+      "epoch": 0.72977158343012,
+      "grad_norm": 4.0542378425598145,
+      "learning_rate": 2.1875725900116146e-05,
+      "loss": 0.6541,
+      "step": 3770
+    },
+    {
+      "epoch": 0.7423538521099496,
+      "grad_norm": 0.5486993193626404,
+      "learning_rate": 2.2253193960511032e-05,
+      "loss": 0.4526,
+      "step": 3835
+    },
+    {
+      "epoch": 0.7502903600464577,
+      "eval_StS-test_pearson_cosine": 0.8754429584344908,
+      "eval_StS-test_pearson_dot": 0.7812438977199179,
+      "eval_StS-test_pearson_euclidean": 0.863532080020405,
+      "eval_StS-test_pearson_manhattan": 0.8642206125042041,
+      "eval_StS-test_pearson_max": 0.8754429584344908,
+      "eval_StS-test_spearman_cosine": 0.8899322603927042,
+      "eval_StS-test_spearman_dot": 0.7897822634826679,
+      "eval_StS-test_spearman_euclidean": 0.8661349339052001,
+      "eval_StS-test_spearman_manhattan": 0.8677664578276145,
+      "eval_StS-test_spearman_max": 0.8899322603927042,
+      "eval_Vitaminc-test_cosine_accuracy": 0.5815789473684211,
+      "eval_Vitaminc-test_cosine_accuracy_threshold": 0.7150823473930359,
+      "eval_Vitaminc-test_cosine_ap": 0.5695623413042502,
+      "eval_Vitaminc-test_cosine_f1": 0.6690909090909091,
+      "eval_Vitaminc-test_cosine_f1_threshold": 0.4144631028175354,
+      "eval_Vitaminc-test_cosine_precision": 0.5041095890410959,
+      "eval_Vitaminc-test_cosine_recall": 0.9945945945945946,
+      "eval_Vitaminc-test_dot_accuracy": 0.5631578947368421,
+      "eval_Vitaminc-test_dot_accuracy_threshold": 25.451148986816406,
+      "eval_Vitaminc-test_dot_ap": 0.5500277455332443,
+      "eval_Vitaminc-test_dot_f1": 0.6691449814126395,
+      "eval_Vitaminc-test_dot_f1_threshold": 14.098217964172363,
+      "eval_Vitaminc-test_dot_precision": 0.509915014164306,
+      "eval_Vitaminc-test_dot_recall": 0.972972972972973,
+      "eval_Vitaminc-test_euclidean_accuracy": 0.5736842105263158,
+      "eval_Vitaminc-test_euclidean_accuracy_threshold": 3.945739269256592,
+      "eval_Vitaminc-test_euclidean_ap": 0.5590599048028368,
+      "eval_Vitaminc-test_euclidean_f1": 0.6654478976234005,
+      "eval_Vitaminc-test_euclidean_f1_threshold": 6.931303024291992,
+      "eval_Vitaminc-test_euclidean_precision": 0.5027624309392266,
+      "eval_Vitaminc-test_euclidean_recall": 0.9837837837837838,
+      "eval_Vitaminc-test_manhattan_accuracy": 0.5736842105263158,
+      "eval_Vitaminc-test_manhattan_accuracy_threshold": 84.99573516845703,
+      "eval_Vitaminc-test_manhattan_ap": 0.559747734383099,
+      "eval_Vitaminc-test_manhattan_f1": 0.6679035250463822,
+      "eval_Vitaminc-test_manhattan_f1_threshold": 139.30535888671875,
+      "eval_Vitaminc-test_manhattan_precision": 0.5084745762711864,
+      "eval_Vitaminc-test_manhattan_recall": 0.972972972972973,
+      "eval_Vitaminc-test_max_accuracy": 0.5815789473684211,
+      "eval_Vitaminc-test_max_accuracy_threshold": 84.99573516845703,
+      "eval_Vitaminc-test_max_ap": 0.5695623413042502,
+      "eval_Vitaminc-test_max_f1": 0.6691449814126395,
+      "eval_Vitaminc-test_max_f1_threshold": 139.30535888671875,
+      "eval_Vitaminc-test_max_precision": 0.509915014164306,
+      "eval_Vitaminc-test_max_recall": 0.9945945945945946,
+      "eval_mrpc-test_cosine_accuracy": 0.7447368421052631,
+      "eval_mrpc-test_cosine_accuracy_threshold": 0.7351576089859009,
+      "eval_mrpc-test_cosine_ap": 0.8492225227540071,
+      "eval_mrpc-test_cosine_f1": 0.8274647887323944,
+      "eval_mrpc-test_cosine_f1_threshold": 0.7097899913787842,
+      "eval_mrpc-test_cosine_precision": 0.734375,
+      "eval_mrpc-test_cosine_recall": 0.9475806451612904,
+      "eval_mrpc-test_dot_accuracy": 0.6947368421052632,
+      "eval_mrpc-test_dot_accuracy_threshold": 13.770221710205078,
+      "eval_mrpc-test_dot_ap": 0.7664430695917603,
+      "eval_mrpc-test_dot_f1": 0.8060200668896322,
+      "eval_mrpc-test_dot_f1_threshold": 13.664058685302734,
+      "eval_mrpc-test_dot_precision": 0.6885714285714286,
+      "eval_mrpc-test_dot_recall": 0.9717741935483871,
+      "eval_mrpc-test_euclidean_accuracy": 0.7421052631578947,
+      "eval_mrpc-test_euclidean_accuracy_threshold": 3.573061466217041,
+      "eval_mrpc-test_euclidean_ap": 0.8229315066081502,
+      "eval_mrpc-test_euclidean_f1": 0.8216216216216217,
+      "eval_mrpc-test_euclidean_f1_threshold": 3.7641119956970215,
+      "eval_mrpc-test_euclidean_precision": 0.742671009771987,
+      "eval_mrpc-test_euclidean_recall": 0.9193548387096774,
+      "eval_mrpc-test_manhattan_accuracy": 0.7394736842105263,
+      "eval_mrpc-test_manhattan_accuracy_threshold": 75.05320739746094,
+      "eval_mrpc-test_manhattan_ap": 0.8195074272882318,
+      "eval_mrpc-test_manhattan_f1": 0.8228980322003578,
+      "eval_mrpc-test_manhattan_f1_threshold": 76.21920013427734,
+      "eval_mrpc-test_manhattan_precision": 0.7395498392282959,
+      "eval_mrpc-test_manhattan_recall": 0.9274193548387096,
+      "eval_mrpc-test_max_accuracy": 0.7447368421052631,
+      "eval_mrpc-test_max_accuracy_threshold": 75.05320739746094,
+      "eval_mrpc-test_max_ap": 0.8492225227540071,
+      "eval_mrpc-test_max_f1": 0.8274647887323944,
+      "eval_mrpc-test_max_f1_threshold": 76.21920013427734,
+      "eval_mrpc-test_max_precision": 0.742671009771987,
+      "eval_mrpc-test_max_recall": 0.9717741935483871,
+      "eval_nli-pairs_loss": 0.8814637064933777,
+      "eval_nli-pairs_runtime": 2.9865,
+      "eval_nli-pairs_samples_per_second": 53.575,
+      "eval_nli-pairs_steps_per_second": 1.674,
+      "eval_sequential_score": 0.5695623413042502,
+      "step": 3876
+    },
+    {
+      "epoch": 0.7502903600464577,
+      "eval_vitaminc-pairs_loss": 5.706007957458496,
+      "eval_vitaminc-pairs_runtime": 1.5554,
+      "eval_vitaminc-pairs_samples_per_second": 85.507,
+      "eval_vitaminc-pairs_steps_per_second": 3.215,
+      "step": 3876
+    },
+    {
+      "epoch": 0.7502903600464577,
+      "eval_qnli-contrastive_loss": 0.14242754876613617,
+      "eval_qnli-contrastive_runtime": 0.5128,
+      "eval_qnli-contrastive_samples_per_second": 311.993,
+      "eval_qnli-contrastive_steps_per_second": 9.75,
+      "step": 3876
+    },
+    {
+      "epoch": 0.7502903600464577,
+      "eval_scitail-pairs-qa_loss": 0.0674210786819458,
+      "eval_scitail-pairs-qa_runtime": 1.2622,
+      "eval_scitail-pairs-qa_samples_per_second": 126.759,
+      "eval_scitail-pairs-qa_steps_per_second": 3.961,
+      "step": 3876
+    },
+    {
+      "epoch": 0.7502903600464577,
+      "eval_scitail-pairs-pos_loss": 0.36303356289863586,
+      "eval_scitail-pairs-pos_runtime": 2.3597,
+      "eval_scitail-pairs-pos_samples_per_second": 67.806,
+      "eval_scitail-pairs-pos_steps_per_second": 2.119,
+      "step": 3876
+    },
+    {
+      "epoch": 0.7502903600464577,
+      "eval_xsum-pairs_loss": 0.32611021399497986,
+      "eval_xsum-pairs_runtime": 1.4024,
+      "eval_xsum-pairs_samples_per_second": 114.091,
+      "eval_xsum-pairs_steps_per_second": 3.565,
+      "step": 3876
+    },
+    {
+      "epoch": 0.7502903600464577,
+      "eval_compression-pairs_loss": 0.08624111860990524,
+      "eval_compression-pairs_runtime": 0.3948,
+      "eval_compression-pairs_samples_per_second": 405.263,
+      "eval_compression-pairs_steps_per_second": 12.664,
+      "step": 3876
+    },
+    {
+      "epoch": 0.7502903600464577,
+      "eval_sciq_pairs_loss": 0.2929747402667999,
+      "eval_sciq_pairs_runtime": 7.9352,
+      "eval_sciq_pairs_samples_per_second": 20.163,
+      "eval_sciq_pairs_steps_per_second": 0.63,
+      "step": 3876
+    },
+    {
+      "epoch": 0.7502903600464577,
+      "eval_qasc_pairs_loss": 0.20694346725940704,
+      "eval_qasc_pairs_runtime": 1.4441,
+      "eval_qasc_pairs_samples_per_second": 110.798,
+      "eval_qasc_pairs_steps_per_second": 3.462,
+      "step": 3876
+    },
+    {
+      "epoch": 0.7502903600464577,
+      "eval_qasc_facts_sym_loss": 0.14476129412651062,
+      "eval_qasc_facts_sym_runtime": 0.3295,
+      "eval_qasc_facts_sym_samples_per_second": 485.621,
+      "eval_qasc_facts_sym_steps_per_second": 15.176,
+      "step": 3876
+    },
+    {
+      "epoch": 0.7502903600464577,
+      "eval_openbookqa_pairs_loss": 1.7119003534317017,
+      "eval_openbookqa_pairs_runtime": 1.2433,
+      "eval_openbookqa_pairs_samples_per_second": 128.687,
+      "eval_openbookqa_pairs_steps_per_second": 4.021,
+      "step": 3876
+    },
+    {
+      "epoch": 0.7502903600464577,
+      "eval_msmarco_pairs_loss": 0.4974798262119293,
+      "eval_msmarco_pairs_runtime": 3.1059,
+      "eval_msmarco_pairs_samples_per_second": 51.516,
+      "eval_msmarco_pairs_steps_per_second": 1.61,
+      "step": 3876
+    },
+    {
+      "epoch": 0.7502903600464577,
+      "eval_nq_pairs_loss": 0.46937060356140137,
+      "eval_nq_pairs_runtime": 7.6944,
+      "eval_nq_pairs_samples_per_second": 20.794,
+      "eval_nq_pairs_steps_per_second": 0.65,
+      "step": 3876
+    },
+    {
+      "epoch": 0.7502903600464577,
+      "eval_trivia_pairs_loss": 0.6990238428115845,
+      "eval_trivia_pairs_runtime": 10.1876,
+      "eval_trivia_pairs_samples_per_second": 15.705,
+      "eval_trivia_pairs_steps_per_second": 0.491,
+      "step": 3876
+    },
+    {
+      "epoch": 0.7502903600464577,
+      "eval_quora_pairs_loss": 0.21933521330356598,
+      "eval_quora_pairs_runtime": 3.8953,
+      "eval_quora_pairs_samples_per_second": 173.287,
+      "eval_quora_pairs_steps_per_second": 5.648,
+      "step": 3876
+    },
+    {
+      "epoch": 0.7502903600464577,
+      "eval_gooaq_pairs_loss": 0.5000605583190918,
+      "eval_gooaq_pairs_runtime": 2.2758,
+      "eval_gooaq_pairs_samples_per_second": 70.306,
+      "eval_gooaq_pairs_steps_per_second": 2.197,
+      "step": 3876
+    },
+    {
+      "epoch": 0.7502903600464577,
+      "eval_mrpc_pairs_loss": 0.044196613132953644,
+      "eval_mrpc_pairs_runtime": 0.3742,
+      "eval_mrpc_pairs_samples_per_second": 427.588,
+      "eval_mrpc_pairs_steps_per_second": 13.362,
+      "step": 3876
+    },
+    {
+      "epoch": 0.7549361207897793,
+      "grad_norm": 1.587725281715393,
+      "learning_rate": 2.2630662020905924e-05,
+      "loss": 0.4466,
+      "step": 3900
+    },
+    {
+      "epoch": 0.7675183894696089,
+      "grad_norm": 9.404407501220703,
+      "learning_rate": 2.3008130081300814e-05,
+      "loss": 0.6293,
+      "step": 3965
+    },
+    {
+      "epoch": 0.7801006581494386,
+      "grad_norm": 3.672903537750244,
+      "learning_rate": 2.3385598141695703e-05,
+      "loss": 0.5591,
+      "step": 4030
+    },
+    {
+      "epoch": 0.7926829268292683,
+      "grad_norm": 1.3529752492904663,
+      "learning_rate": 2.3763066202090596e-05,
+      "loss": 0.5702,
+      "step": 4095
+    },
+    {
+      "epoch": 0.8052651955090979,
+      "grad_norm": 21.519527435302734,
+      "learning_rate": 2.414053426248548e-05,
+      "loss": 0.4645,
+      "step": 4160
+    },
+    {
+      "epoch": 0.8178474641889276,
+      "grad_norm": 5.5179362297058105,
+      "learning_rate": 2.4518002322880374e-05,
+      "loss": 0.5175,
+      "step": 4225
+    },
+    {
+      "epoch": 0.8304297328687572,
+      "grad_norm": 10.127123832702637,
+      "learning_rate": 2.489547038327526e-05,
+      "loss": 0.5188,
+      "step": 4290
+    },
+    {
+      "epoch": 0.8430120015485869,
+      "grad_norm": 5.518251895904541,
+      "learning_rate": 2.5272938443670153e-05,
+      "loss": 0.4908,
+      "step": 4355
+    },
+    {
+      "epoch": 0.8555942702284166,
+      "grad_norm": 0.7371014356613159,
+      "learning_rate": 2.5650406504065042e-05,
+      "loss": 0.5075,
+      "step": 4420
+    },
+    {
+      "epoch": 0.8681765389082462,
+      "grad_norm": 22.15941619873047,
+      "learning_rate": 2.602206736353078e-05,
+      "loss": 0.5625,
+      "step": 4485
+    },
+    {
+      "epoch": 0.8807588075880759,
+      "grad_norm": 1.0873440504074097,
+      "learning_rate": 2.6399535423925668e-05,
+      "loss": 0.4952,
+      "step": 4550
+    },
+    {
+      "epoch": 0.8933410762679055,
+      "grad_norm": 19.877098083496094,
+      "learning_rate": 2.6777003484320557e-05,
+      "loss": 0.5818,
+      "step": 4615
+    },
+    {
+      "epoch": 0.9059233449477352,
+      "grad_norm": 9.559219360351562,
+      "learning_rate": 2.715447154471545e-05,
+      "loss": 0.6346,
+      "step": 4680
+    },
+    {
+      "epoch": 0.9185056136275649,
+      "grad_norm": 2.896815299987793,
+      "learning_rate": 2.7531939605110336e-05,
+      "loss": 0.4971,
+      "step": 4745
+    },
+    {
+      "epoch": 0.9310878823073945,
+      "grad_norm": 4.5045318603515625,
+      "learning_rate": 2.7909407665505228e-05,
+      "loss": 0.4834,
+      "step": 4810
+    },
+    {
+      "epoch": 0.9436701509872242,
+      "grad_norm": 1.2259025573730469,
+      "learning_rate": 2.8286875725900114e-05,
+      "loss": 0.5992,
+      "step": 4875
+    },
+    {
+      "epoch": 0.9562524196670538,
+      "grad_norm": 9.3356294631958,
+      "learning_rate": 2.8664343786295007e-05,
+      "loss": 0.5244,
+      "step": 4940
+    },
+    {
+      "epoch": 0.9688346883468835,
+      "grad_norm": 2.221039056777954,
+      "learning_rate": 2.9041811846689896e-05,
+      "loss": 0.6051,
+      "step": 5005
+    },
+    {
+      "epoch": 0.9814169570267132,
+      "grad_norm": 1.3200041055679321,
+      "learning_rate": 2.9419279907084785e-05,
+      "loss": 0.4323,
+      "step": 5070
+    },
+    {
+      "epoch": 0.9939992257065428,
+      "grad_norm": 8.689266204833984,
+      "learning_rate": 2.9796747967479674e-05,
+      "loss": 0.5347,
+      "step": 5135
+    }
+  ],
+  "logging_steps": 65,
+  "max_steps": 25830,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 2583,
+  "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-5166/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2519118bce6ce43cd8ca9ca2ad2ad4642dfcfe5f9a3c6dd2eeb5a81e8223693e
+size 5624