Training in progress, step 1550, checkpoint

checkpoint-1550/1_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-1550/added_tokens.json

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

checkpoint-1550/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-1550/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-1550/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-1550/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dea49b97664b4f37bef41d1afa7ba1fe87e670488b75ed9b91715cf809de2a01
+size 1130520122

checkpoint-1550/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcb28730a02ebbf86a976cd2713d6e3d9fa77058e98ad3986c1d27b8e53cd25c
+size 565251810

checkpoint-1550/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ec481d67ec60355e0885c47cacc177f727ff8be6e5ee2df10cf3d34d47f7188
+size 14180

checkpoint-1550/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3c402abf68663356660c7ded14fc0f45e5bbe7fe16e19c7cd262e269aefff62
+size 1064

checkpoint-1550/sentence_bert_config.json

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

checkpoint-1550/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-1550/spm.model

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

checkpoint-1550/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-1550/trainer_state.json

@@ -0,0 +1,740 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.30003871467286103,
+  "eval_steps": 775,
+  "global_step": 1550,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007549361207897794,
+      "grad_norm": 1.0711718797683716,
+      "learning_rate": 5.03225806451613e-07,
+      "loss": 0.1034,
+      "step": 39
+    },
+    {
+      "epoch": 0.015098722415795587,
+      "grad_norm": 2.8229963779449463,
+      "learning_rate": 1.006451612903226e-06,
+      "loss": 0.139,
+      "step": 78
+    },
+    {
+      "epoch": 0.02264808362369338,
+      "grad_norm": 0.3261104226112366,
+      "learning_rate": 1.5096774193548389e-06,
+      "loss": 0.084,
+      "step": 117
+    },
+    {
+      "epoch": 0.030197444831591175,
+      "grad_norm": 8.717601776123047,
+      "learning_rate": 2.012903225806452e-06,
+      "loss": 0.1074,
+      "step": 156
+    },
+    {
+      "epoch": 0.03774680603948897,
+      "grad_norm": 0.08064748346805573,
+      "learning_rate": 2.503225806451613e-06,
+      "loss": 0.1525,
+      "step": 195
+    },
+    {
+      "epoch": 0.04529616724738676,
+      "grad_norm": 3.0626015663146973,
+      "learning_rate": 3.006451612903226e-06,
+      "loss": 0.1627,
+      "step": 234
+    },
+    {
+      "epoch": 0.052845528455284556,
+      "grad_norm": 0.07878410816192627,
+      "learning_rate": 3.509677419354839e-06,
+      "loss": 0.0982,
+      "step": 273
+    },
+    {
+      "epoch": 0.06039488966318235,
+      "grad_norm": 0.5001585483551025,
+      "learning_rate": 4.012903225806452e-06,
+      "loss": 0.1806,
+      "step": 312
+    },
+    {
+      "epoch": 0.06794425087108014,
+      "grad_norm": 0.8794911503791809,
+      "learning_rate": 4.516129032258065e-06,
+      "loss": 0.1339,
+      "step": 351
+    },
+    {
+      "epoch": 0.07549361207897794,
+      "grad_norm": 0.5939064025878906,
+      "learning_rate": 5.019354838709678e-06,
+      "loss": 0.1606,
+      "step": 390
+    },
+    {
+      "epoch": 0.08304297328687572,
+      "grad_norm": 0.08480428904294968,
+      "learning_rate": 5.522580645161291e-06,
+      "loss": 0.2116,
+      "step": 429
+    },
+    {
+      "epoch": 0.09059233449477352,
+      "grad_norm": 0.1998225599527359,
+      "learning_rate": 6.0258064516129035e-06,
+      "loss": 0.1388,
+      "step": 468
+    },
+    {
+      "epoch": 0.09814169570267131,
+      "grad_norm": 11.921182632446289,
+      "learning_rate": 6.529032258064517e-06,
+      "loss": 0.1341,
+      "step": 507
+    },
+    {
+      "epoch": 0.10569105691056911,
+      "grad_norm": 13.058198928833008,
+      "learning_rate": 7.03225806451613e-06,
+      "loss": 0.1414,
+      "step": 546
+    },
+    {
+      "epoch": 0.1132404181184669,
+      "grad_norm": 5.592000484466553,
+      "learning_rate": 7.535483870967742e-06,
+      "loss": 0.1683,
+      "step": 585
+    },
+    {
+      "epoch": 0.1207897793263647,
+      "grad_norm": 4.383182048797607,
+      "learning_rate": 8.038709677419356e-06,
+      "loss": 0.1387,
+      "step": 624
+    },
+    {
+      "epoch": 0.12833914053426249,
+      "grad_norm": 0.30313506722450256,
+      "learning_rate": 8.541935483870969e-06,
+      "loss": 0.1114,
+      "step": 663
+    },
+    {
+      "epoch": 0.13588850174216027,
+      "grad_norm": 2.676938772201538,
+      "learning_rate": 9.045161290322582e-06,
+      "loss": 0.109,
+      "step": 702
+    },
+    {
+      "epoch": 0.14343786295005806,
+      "grad_norm": 7.334486961364746,
+      "learning_rate": 9.548387096774195e-06,
+      "loss": 0.1842,
+      "step": 741
+    },
+    {
+      "epoch": 0.15001935733643051,
+      "eval_StS-test_pearson_cosine": 0.8802888791327717,
+      "eval_StS-test_pearson_dot": 0.764956894146423,
+      "eval_StS-test_pearson_euclidean": 0.8598764090016476,
+      "eval_StS-test_pearson_manhattan": 0.8578515302861167,
+      "eval_StS-test_pearson_max": 0.8802888791327717,
+      "eval_StS-test_spearman_cosine": 0.8942594550471006,
+      "eval_StS-test_spearman_dot": 0.7622342053691785,
+      "eval_StS-test_spearman_euclidean": 0.8630131008926252,
+      "eval_StS-test_spearman_manhattan": 0.8617745701855535,
+      "eval_StS-test_spearman_max": 0.8942594550471006,
+      "eval_Vitaminc-test_cosine_accuracy": 0.5763157894736842,
+      "eval_Vitaminc-test_cosine_accuracy_threshold": 0.7017868757247925,
+      "eval_Vitaminc-test_cosine_ap": 0.5602670608787189,
+      "eval_Vitaminc-test_cosine_f1": 0.6728971962616821,
+      "eval_Vitaminc-test_cosine_f1_threshold": 0.4250669479370117,
+      "eval_Vitaminc-test_cosine_precision": 0.5142857142857142,
+      "eval_Vitaminc-test_cosine_recall": 0.972972972972973,
+      "eval_Vitaminc-test_dot_accuracy": 0.5657894736842105,
+      "eval_Vitaminc-test_dot_accuracy_threshold": 10.199991226196289,
+      "eval_Vitaminc-test_dot_ap": 0.5533537794640732,
+      "eval_Vitaminc-test_dot_f1": 0.6703499079189686,
+      "eval_Vitaminc-test_dot_f1_threshold": 6.7232666015625,
+      "eval_Vitaminc-test_dot_precision": 0.5083798882681564,
+      "eval_Vitaminc-test_dot_recall": 0.9837837837837838,
+      "eval_Vitaminc-test_euclidean_accuracy": 0.5789473684210527,
+      "eval_Vitaminc-test_euclidean_accuracy_threshold": 2.9913148880004883,
+      "eval_Vitaminc-test_euclidean_ap": 0.5561230019069514,
+      "eval_Vitaminc-test_euclidean_f1": 0.6654611211573237,
+      "eval_Vitaminc-test_euclidean_f1_threshold": 5.274639129638672,
+      "eval_Vitaminc-test_euclidean_precision": 0.5,
+      "eval_Vitaminc-test_euclidean_recall": 0.9945945945945946,
+      "eval_Vitaminc-test_manhattan_accuracy": 0.5736842105263158,
+      "eval_Vitaminc-test_manhattan_accuracy_threshold": 59.83754348754883,
+      "eval_Vitaminc-test_manhattan_ap": 0.5571804547666452,
+      "eval_Vitaminc-test_manhattan_f1": 0.6666666666666666,
+      "eval_Vitaminc-test_manhattan_f1_threshold": 108.11463928222656,
+      "eval_Vitaminc-test_manhattan_precision": 0.5013623978201635,
+      "eval_Vitaminc-test_manhattan_recall": 0.9945945945945946,
+      "eval_Vitaminc-test_max_accuracy": 0.5789473684210527,
+      "eval_Vitaminc-test_max_accuracy_threshold": 59.83754348754883,
+      "eval_Vitaminc-test_max_ap": 0.5602670608787189,
+      "eval_Vitaminc-test_max_f1": 0.6728971962616821,
+      "eval_Vitaminc-test_max_f1_threshold": 108.11463928222656,
+      "eval_Vitaminc-test_max_precision": 0.5142857142857142,
+      "eval_Vitaminc-test_max_recall": 0.9945945945945946,
+      "eval_mrpc-test_cosine_accuracy": 0.7342105263157894,
+      "eval_mrpc-test_cosine_accuracy_threshold": 0.7406734228134155,
+      "eval_mrpc-test_cosine_ap": 0.8425118223704731,
+      "eval_mrpc-test_cosine_f1": 0.8197879858657243,
+      "eval_mrpc-test_cosine_f1_threshold": 0.706486701965332,
+      "eval_mrpc-test_cosine_precision": 0.7295597484276729,
+      "eval_mrpc-test_cosine_recall": 0.9354838709677419,
+      "eval_mrpc-test_dot_accuracy": 0.6921052631578948,
+      "eval_mrpc-test_dot_accuracy_threshold": 6.86049747467041,
+      "eval_mrpc-test_dot_ap": 0.7548679970556984,
+      "eval_mrpc-test_dot_f1": 0.803921568627451,
+      "eval_mrpc-test_dot_f1_threshold": 5.707286834716797,
+      "eval_mrpc-test_dot_precision": 0.6758241758241759,
+      "eval_mrpc-test_dot_recall": 0.9919354838709677,
+      "eval_mrpc-test_euclidean_accuracy": 0.7315789473684211,
+      "eval_mrpc-test_euclidean_accuracy_threshold": 2.678755044937134,
+      "eval_mrpc-test_euclidean_ap": 0.8249777785839534,
+      "eval_mrpc-test_euclidean_f1": 0.8175438596491229,
+      "eval_mrpc-test_euclidean_f1_threshold": 2.9142637252807617,
+      "eval_mrpc-test_euclidean_precision": 0.7236024844720497,
+      "eval_mrpc-test_euclidean_recall": 0.9395161290322581,
+      "eval_mrpc-test_manhattan_accuracy": 0.7289473684210527,
+      "eval_mrpc-test_manhattan_accuracy_threshold": 54.35257339477539,
+      "eval_mrpc-test_manhattan_ap": 0.8241886593955292,
+      "eval_mrpc-test_manhattan_f1": 0.8167539267015707,
+      "eval_mrpc-test_manhattan_f1_threshold": 58.74644470214844,
+      "eval_mrpc-test_manhattan_precision": 0.72,
+      "eval_mrpc-test_manhattan_recall": 0.9435483870967742,
+      "eval_mrpc-test_max_accuracy": 0.7342105263157894,
+      "eval_mrpc-test_max_accuracy_threshold": 54.35257339477539,
+      "eval_mrpc-test_max_ap": 0.8425118223704731,
+      "eval_mrpc-test_max_f1": 0.8197879858657243,
+      "eval_mrpc-test_max_f1_threshold": 58.74644470214844,
+      "eval_mrpc-test_max_precision": 0.7295597484276729,
+      "eval_mrpc-test_max_recall": 0.9919354838709677,
+      "eval_nli-pairs_loss": 0.8303536772727966,
+      "eval_nli-pairs_runtime": 3.0052,
+      "eval_nli-pairs_samples_per_second": 53.242,
+      "eval_nli-pairs_steps_per_second": 1.664,
+      "eval_sequential_score": 0.5602670608787189,
+      "step": 775
+    },
+    {
+      "epoch": 0.15001935733643051,
+      "eval_vitaminc-pairs_loss": 6.683011054992676,
+      "eval_vitaminc-pairs_runtime": 1.5541,
+      "eval_vitaminc-pairs_samples_per_second": 85.578,
+      "eval_vitaminc-pairs_steps_per_second": 3.217,
+      "step": 775
+    },
+    {
+      "epoch": 0.15001935733643051,
+      "eval_qnli-contrastive_loss": 0.14666679501533508,
+      "eval_qnli-contrastive_runtime": 0.5182,
+      "eval_qnli-contrastive_samples_per_second": 308.782,
+      "eval_qnli-contrastive_steps_per_second": 9.649,
+      "step": 775
+    },
+    {
+      "epoch": 0.15001935733643051,
+      "eval_scitail-pairs-qa_loss": 0.029243946075439453,
+      "eval_scitail-pairs-qa_runtime": 1.205,
+      "eval_scitail-pairs-qa_samples_per_second": 132.779,
+      "eval_scitail-pairs-qa_steps_per_second": 4.149,
+      "step": 775
+    },
+    {
+      "epoch": 0.15001935733643051,
+      "eval_scitail-pairs-pos_loss": 0.27491405606269836,
+      "eval_scitail-pairs-pos_runtime": 2.408,
+      "eval_scitail-pairs-pos_samples_per_second": 66.446,
+      "eval_scitail-pairs-pos_steps_per_second": 2.076,
+      "step": 775
+    },
+    {
+      "epoch": 0.15001935733643051,
+      "eval_xsum-pairs_loss": 0.26869887113571167,
+      "eval_xsum-pairs_runtime": 1.4329,
+      "eval_xsum-pairs_samples_per_second": 111.665,
+      "eval_xsum-pairs_steps_per_second": 3.49,
+      "step": 775
+    },
+    {
+      "epoch": 0.15001935733643051,
+      "eval_compression-pairs_loss": 0.04634805768728256,
+      "eval_compression-pairs_runtime": 0.3969,
+      "eval_compression-pairs_samples_per_second": 403.145,
+      "eval_compression-pairs_steps_per_second": 12.598,
+      "step": 775
+    },
+    {
+      "epoch": 0.15001935733643051,
+      "eval_sciq_pairs_loss": 0.23269198834896088,
+      "eval_sciq_pairs_runtime": 7.9878,
+      "eval_sciq_pairs_samples_per_second": 20.031,
+      "eval_sciq_pairs_steps_per_second": 0.626,
+      "step": 775
+    },
+    {
+      "epoch": 0.15001935733643051,
+      "eval_qasc_pairs_loss": 0.12053151428699493,
+      "eval_qasc_pairs_runtime": 1.4583,
+      "eval_qasc_pairs_samples_per_second": 109.72,
+      "eval_qasc_pairs_steps_per_second": 3.429,
+      "step": 775
+    },
+    {
+      "epoch": 0.15001935733643051,
+      "eval_qasc_facts_sym_loss": 0.1144954189658165,
+      "eval_qasc_facts_sym_runtime": 0.3218,
+      "eval_qasc_facts_sym_samples_per_second": 497.171,
+      "eval_qasc_facts_sym_steps_per_second": 15.537,
+      "step": 775
+    },
+    {
+      "epoch": 0.15001935733643051,
+      "eval_openbookqa_pairs_loss": 1.7202316522598267,
+      "eval_openbookqa_pairs_runtime": 1.2341,
+      "eval_openbookqa_pairs_samples_per_second": 129.652,
+      "eval_openbookqa_pairs_steps_per_second": 4.052,
+      "step": 775
+    },
+    {
+      "epoch": 0.15001935733643051,
+      "eval_msmarco_pairs_loss": 0.5212310552597046,
+      "eval_msmarco_pairs_runtime": 3.1195,
+      "eval_msmarco_pairs_samples_per_second": 51.291,
+      "eval_msmarco_pairs_steps_per_second": 1.603,
+      "step": 775
+    },
+    {
+      "epoch": 0.15001935733643051,
+      "eval_nq_pairs_loss": 0.39821678400039673,
+      "eval_nq_pairs_runtime": 7.7241,
+      "eval_nq_pairs_samples_per_second": 20.714,
+      "eval_nq_pairs_steps_per_second": 0.647,
+      "step": 775
+    },
+    {
+      "epoch": 0.15001935733643051,
+      "eval_trivia_pairs_loss": 0.6368125081062317,
+      "eval_trivia_pairs_runtime": 10.2427,
+      "eval_trivia_pairs_samples_per_second": 15.621,
+      "eval_trivia_pairs_steps_per_second": 0.488,
+      "step": 775
+    },
+    {
+      "epoch": 0.15001935733643051,
+      "eval_quora_pairs_loss": 0.16319230198860168,
+      "eval_quora_pairs_runtime": 4.5921,
+      "eval_quora_pairs_samples_per_second": 146.992,
+      "eval_quora_pairs_steps_per_second": 4.791,
+      "step": 775
+    },
+    {
+      "epoch": 0.15001935733643051,
+      "eval_gooaq_pairs_loss": 0.4080866873264313,
+      "eval_gooaq_pairs_runtime": 2.3151,
+      "eval_gooaq_pairs_samples_per_second": 69.111,
+      "eval_gooaq_pairs_steps_per_second": 2.16,
+      "step": 775
+    },
+    {
+      "epoch": 0.15001935733643051,
+      "eval_mrpc_pairs_loss": 0.020639527589082718,
+      "eval_mrpc_pairs_runtime": 0.3773,
+      "eval_mrpc_pairs_samples_per_second": 424.103,
+      "eval_mrpc_pairs_steps_per_second": 13.253,
+      "step": 775
+    },
+    {
+      "epoch": 0.15098722415795587,
+      "grad_norm": 1.3743501901626587,
+      "learning_rate": 1.0051612903225807e-05,
+      "loss": 0.1977,
+      "step": 780
+    },
+    {
+      "epoch": 0.15853658536585366,
+      "grad_norm": 0.4715043008327484,
+      "learning_rate": 1.055483870967742e-05,
+      "loss": 0.1869,
+      "step": 819
+    },
+    {
+      "epoch": 0.16608594657375145,
+      "grad_norm": 4.3643646240234375,
+      "learning_rate": 1.1058064516129032e-05,
+      "loss": 0.1175,
+      "step": 858
+    },
+    {
+      "epoch": 0.17363530778164923,
+      "grad_norm": 2.12259840965271,
+      "learning_rate": 1.1561290322580648e-05,
+      "loss": 0.1599,
+      "step": 897
+    },
+    {
+      "epoch": 0.18118466898954705,
+      "grad_norm": 2.2424590587615967,
+      "learning_rate": 1.2064516129032259e-05,
+      "loss": 0.1727,
+      "step": 936
+    },
+    {
+      "epoch": 0.18873403019744484,
+      "grad_norm": 5.78494930267334,
+      "learning_rate": 1.2567741935483872e-05,
+      "loss": 0.1227,
+      "step": 975
+    },
+    {
+      "epoch": 0.19628339140534262,
+      "grad_norm": 0.27822694182395935,
+      "learning_rate": 1.3070967741935485e-05,
+      "loss": 0.1384,
+      "step": 1014
+    },
+    {
+      "epoch": 0.2038327526132404,
+      "grad_norm": 4.893210411071777,
+      "learning_rate": 1.3574193548387098e-05,
+      "loss": 0.1924,
+      "step": 1053
+    },
+    {
+      "epoch": 0.21138211382113822,
+      "grad_norm": 2.539022207260132,
+      "learning_rate": 1.407741935483871e-05,
+      "loss": 0.1477,
+      "step": 1092
+    },
+    {
+      "epoch": 0.218931475029036,
+      "grad_norm": 11.830439567565918,
+      "learning_rate": 1.4580645161290324e-05,
+      "loss": 0.2048,
+      "step": 1131
+    },
+    {
+      "epoch": 0.2264808362369338,
+      "grad_norm": 0.17901472747325897,
+      "learning_rate": 1.5083870967741936e-05,
+      "loss": 0.169,
+      "step": 1170
+    },
+    {
+      "epoch": 0.23403019744483158,
+      "grad_norm": 2.696475028991699,
+      "learning_rate": 1.558709677419355e-05,
+      "loss": 0.1339,
+      "step": 1209
+    },
+    {
+      "epoch": 0.2415795586527294,
+      "grad_norm": 0.13523121178150177,
+      "learning_rate": 1.6090322580645162e-05,
+      "loss": 0.1757,
+      "step": 1248
+    },
+    {
+      "epoch": 0.24912891986062718,
+      "grad_norm": 8.184245109558105,
+      "learning_rate": 1.6593548387096775e-05,
+      "loss": 0.2076,
+      "step": 1287
+    },
+    {
+      "epoch": 0.25667828106852497,
+      "grad_norm": 2.106351852416992,
+      "learning_rate": 1.7096774193548388e-05,
+      "loss": 0.1906,
+      "step": 1326
+    },
+    {
+      "epoch": 0.26422764227642276,
+      "grad_norm": 0.3403491675853729,
+      "learning_rate": 1.76e-05,
+      "loss": 0.1519,
+      "step": 1365
+    },
+    {
+      "epoch": 0.27177700348432055,
+      "grad_norm": 5.393270969390869,
+      "learning_rate": 1.8103225806451614e-05,
+      "loss": 0.2287,
+      "step": 1404
+    },
+    {
+      "epoch": 0.27932636469221833,
+      "grad_norm": 7.627374649047852,
+      "learning_rate": 1.8606451612903227e-05,
+      "loss": 0.1687,
+      "step": 1443
+    },
+    {
+      "epoch": 0.2868757259001161,
+      "grad_norm": 0.3724862039089203,
+      "learning_rate": 1.910967741935484e-05,
+      "loss": 0.1746,
+      "step": 1482
+    },
+    {
+      "epoch": 0.29442508710801396,
+      "grad_norm": 3.9233756065368652,
+      "learning_rate": 1.9612903225806452e-05,
+      "loss": 0.193,
+      "step": 1521
+    },
+    {
+      "epoch": 0.30003871467286103,
+      "eval_StS-test_pearson_cosine": 0.8783503283778296,
+      "eval_StS-test_pearson_dot": 0.7519743076230905,
+      "eval_StS-test_pearson_euclidean": 0.8526648759032491,
+      "eval_StS-test_pearson_manhattan": 0.8500463267925812,
+      "eval_StS-test_pearson_max": 0.8783503283778296,
+      "eval_StS-test_spearman_cosine": 0.8916895640378009,
+      "eval_StS-test_spearman_dot": 0.7526563367387616,
+      "eval_StS-test_spearman_euclidean": 0.8577392195178156,
+      "eval_StS-test_spearman_manhattan": 0.856421980698813,
+      "eval_StS-test_spearman_max": 0.8916895640378009,
+      "eval_Vitaminc-test_cosine_accuracy": 0.5815789473684211,
+      "eval_Vitaminc-test_cosine_accuracy_threshold": 0.6885078549385071,
+      "eval_Vitaminc-test_cosine_ap": 0.5594671162074226,
+      "eval_Vitaminc-test_cosine_f1": 0.6666666666666666,
+      "eval_Vitaminc-test_cosine_f1_threshold": 0.3584425151348114,
+      "eval_Vitaminc-test_cosine_precision": 0.5041551246537396,
+      "eval_Vitaminc-test_cosine_recall": 0.9837837837837838,
+      "eval_Vitaminc-test_dot_accuracy": 0.5552631578947368,
+      "eval_Vitaminc-test_dot_accuracy_threshold": 10.157585144042969,
+      "eval_Vitaminc-test_dot_ap": 0.5474432520808579,
+      "eval_Vitaminc-test_dot_f1": 0.6691449814126395,
+      "eval_Vitaminc-test_dot_f1_threshold": 6.706892013549805,
+      "eval_Vitaminc-test_dot_precision": 0.509915014164306,
+      "eval_Vitaminc-test_dot_recall": 0.972972972972973,
+      "eval_Vitaminc-test_euclidean_accuracy": 0.5710526315789474,
+      "eval_Vitaminc-test_euclidean_accuracy_threshold": 3.079951763153076,
+      "eval_Vitaminc-test_euclidean_ap": 0.5563773196498328,
+      "eval_Vitaminc-test_euclidean_f1": 0.6642599277978339,
+      "eval_Vitaminc-test_euclidean_f1_threshold": 5.1627936363220215,
+      "eval_Vitaminc-test_euclidean_precision": 0.4986449864498645,
+      "eval_Vitaminc-test_euclidean_recall": 0.9945945945945946,
+      "eval_Vitaminc-test_manhattan_accuracy": 0.5710526315789474,
+      "eval_Vitaminc-test_manhattan_accuracy_threshold": 56.85852813720703,
+      "eval_Vitaminc-test_manhattan_ap": 0.5539226989698821,
+      "eval_Vitaminc-test_manhattan_f1": 0.6642599277978339,
+      "eval_Vitaminc-test_manhattan_f1_threshold": 106.36761474609375,
+      "eval_Vitaminc-test_manhattan_precision": 0.4986449864498645,
+      "eval_Vitaminc-test_manhattan_recall": 0.9945945945945946,
+      "eval_Vitaminc-test_max_accuracy": 0.5815789473684211,
+      "eval_Vitaminc-test_max_accuracy_threshold": 56.85852813720703,
+      "eval_Vitaminc-test_max_ap": 0.5594671162074226,
+      "eval_Vitaminc-test_max_f1": 0.6691449814126395,
+      "eval_Vitaminc-test_max_f1_threshold": 106.36761474609375,
+      "eval_Vitaminc-test_max_precision": 0.509915014164306,
+      "eval_Vitaminc-test_max_recall": 0.9945945945945946,
+      "eval_mrpc-test_cosine_accuracy": 0.7368421052631579,
+      "eval_mrpc-test_cosine_accuracy_threshold": 0.7056469917297363,
+      "eval_mrpc-test_cosine_ap": 0.8451082765959403,
+      "eval_mrpc-test_cosine_f1": 0.8214285714285715,
+      "eval_mrpc-test_cosine_f1_threshold": 0.7056469917297363,
+      "eval_mrpc-test_cosine_precision": 0.7371794871794872,
+      "eval_mrpc-test_cosine_recall": 0.9274193548387096,
+      "eval_mrpc-test_dot_accuracy": 0.6815789473684211,
+      "eval_mrpc-test_dot_accuracy_threshold": 6.941728591918945,
+      "eval_mrpc-test_dot_ap": 0.7538592350728381,
+      "eval_mrpc-test_dot_f1": 0.8032520325203252,
+      "eval_mrpc-test_dot_f1_threshold": 5.031067848205566,
+      "eval_mrpc-test_dot_precision": 0.6730245231607629,
+      "eval_mrpc-test_dot_recall": 0.9959677419354839,
+      "eval_mrpc-test_euclidean_accuracy": 0.7342105263157894,
+      "eval_mrpc-test_euclidean_accuracy_threshold": 2.7893333435058594,
+      "eval_mrpc-test_euclidean_ap": 0.827420775276135,
+      "eval_mrpc-test_euclidean_f1": 0.8212389380530973,
+      "eval_mrpc-test_euclidean_f1_threshold": 2.7893333435058594,
+      "eval_mrpc-test_euclidean_precision": 0.7318611987381703,
+      "eval_mrpc-test_euclidean_recall": 0.9354838709677419,
+      "eval_mrpc-test_manhattan_accuracy": 0.7421052631578947,
+      "eval_mrpc-test_manhattan_accuracy_threshold": 55.37153625488281,
+      "eval_mrpc-test_manhattan_ap": 0.8283672556404068,
+      "eval_mrpc-test_manhattan_f1": 0.8268551236749118,
+      "eval_mrpc-test_manhattan_f1_threshold": 55.37153625488281,
+      "eval_mrpc-test_manhattan_precision": 0.7358490566037735,
+      "eval_mrpc-test_manhattan_recall": 0.9435483870967742,
+      "eval_mrpc-test_max_accuracy": 0.7421052631578947,
+      "eval_mrpc-test_max_accuracy_threshold": 55.37153625488281,
+      "eval_mrpc-test_max_ap": 0.8451082765959403,
+      "eval_mrpc-test_max_f1": 0.8268551236749118,
+      "eval_mrpc-test_max_f1_threshold": 55.37153625488281,
+      "eval_mrpc-test_max_precision": 0.7371794871794872,
+      "eval_mrpc-test_max_recall": 0.9959677419354839,
+      "eval_nli-pairs_loss": 0.9141222834587097,
+      "eval_nli-pairs_runtime": 3.0201,
+      "eval_nli-pairs_samples_per_second": 52.978,
+      "eval_nli-pairs_steps_per_second": 1.656,
+      "eval_sequential_score": 0.5594671162074226,
+      "step": 1550
+    },
+    {
+      "epoch": 0.30003871467286103,
+      "eval_vitaminc-pairs_loss": 6.753823280334473,
+      "eval_vitaminc-pairs_runtime": 1.5657,
+      "eval_vitaminc-pairs_samples_per_second": 84.948,
+      "eval_vitaminc-pairs_steps_per_second": 3.194,
+      "step": 1550
+    },
+    {
+      "epoch": 0.30003871467286103,
+      "eval_qnli-contrastive_loss": 0.12271632999181747,
+      "eval_qnli-contrastive_runtime": 0.5165,
+      "eval_qnli-contrastive_samples_per_second": 309.771,
+      "eval_qnli-contrastive_steps_per_second": 9.68,
+      "step": 1550
+    },
+    {
+      "epoch": 0.30003871467286103,
+      "eval_scitail-pairs-qa_loss": 0.029196780174970627,
+      "eval_scitail-pairs-qa_runtime": 1.2115,
+      "eval_scitail-pairs-qa_samples_per_second": 132.064,
+      "eval_scitail-pairs-qa_steps_per_second": 4.127,
+      "step": 1550
+    },
+    {
+      "epoch": 0.30003871467286103,
+      "eval_scitail-pairs-pos_loss": 0.289101779460907,
+      "eval_scitail-pairs-pos_runtime": 2.3804,
+      "eval_scitail-pairs-pos_samples_per_second": 67.216,
+      "eval_scitail-pairs-pos_steps_per_second": 2.101,
+      "step": 1550
+    },
+    {
+      "epoch": 0.30003871467286103,
+      "eval_xsum-pairs_loss": 0.2750719487667084,
+      "eval_xsum-pairs_runtime": 1.4001,
+      "eval_xsum-pairs_samples_per_second": 114.278,
+      "eval_xsum-pairs_steps_per_second": 3.571,
+      "step": 1550
+    },
+    {
+      "epoch": 0.30003871467286103,
+      "eval_compression-pairs_loss": 0.044591814279556274,
+      "eval_compression-pairs_runtime": 0.3981,
+      "eval_compression-pairs_samples_per_second": 401.899,
+      "eval_compression-pairs_steps_per_second": 12.559,
+      "step": 1550
+    },
+    {
+      "epoch": 0.30003871467286103,
+      "eval_sciq_pairs_loss": 0.23492515087127686,
+      "eval_sciq_pairs_runtime": 8.0302,
+      "eval_sciq_pairs_samples_per_second": 19.925,
+      "eval_sciq_pairs_steps_per_second": 0.623,
+      "step": 1550
+    },
+    {
+      "epoch": 0.30003871467286103,
+      "eval_qasc_pairs_loss": 0.12543106079101562,
+      "eval_qasc_pairs_runtime": 1.4545,
+      "eval_qasc_pairs_samples_per_second": 110.005,
+      "eval_qasc_pairs_steps_per_second": 3.438,
+      "step": 1550
+    },
+    {
+      "epoch": 0.30003871467286103,
+      "eval_qasc_facts_sym_loss": 0.11363373696804047,
+      "eval_qasc_facts_sym_runtime": 0.3227,
+      "eval_qasc_facts_sym_samples_per_second": 495.815,
+      "eval_qasc_facts_sym_steps_per_second": 15.494,
+      "step": 1550
+    },
+    {
+      "epoch": 0.30003871467286103,
+      "eval_openbookqa_pairs_loss": 1.7581151723861694,
+      "eval_openbookqa_pairs_runtime": 1.2329,
+      "eval_openbookqa_pairs_samples_per_second": 129.773,
+      "eval_openbookqa_pairs_steps_per_second": 4.055,
+      "step": 1550
+    },
+    {
+      "epoch": 0.30003871467286103,
+      "eval_msmarco_pairs_loss": 0.6149172782897949,
+      "eval_msmarco_pairs_runtime": 3.1361,
+      "eval_msmarco_pairs_samples_per_second": 51.019,
+      "eval_msmarco_pairs_steps_per_second": 1.594,
+      "step": 1550
+    },
+    {
+      "epoch": 0.30003871467286103,
+      "eval_nq_pairs_loss": 0.4025111198425293,
+      "eval_nq_pairs_runtime": 7.7112,
+      "eval_nq_pairs_samples_per_second": 20.749,
+      "eval_nq_pairs_steps_per_second": 0.648,
+      "step": 1550
+    },
+    {
+      "epoch": 0.30003871467286103,
+      "eval_trivia_pairs_loss": 0.680270791053772,
+      "eval_trivia_pairs_runtime": 10.1952,
+      "eval_trivia_pairs_samples_per_second": 15.694,
+      "eval_trivia_pairs_steps_per_second": 0.49,
+      "step": 1550
+    },
+    {
+      "epoch": 0.30003871467286103,
+      "eval_quora_pairs_loss": 0.16780488193035126,
+      "eval_quora_pairs_runtime": 4.7091,
+      "eval_quora_pairs_samples_per_second": 143.341,
+      "eval_quora_pairs_steps_per_second": 4.672,
+      "step": 1550
+    },
+    {
+      "epoch": 0.30003871467286103,
+      "eval_gooaq_pairs_loss": 0.3964831233024597,
+      "eval_gooaq_pairs_runtime": 2.2968,
+      "eval_gooaq_pairs_samples_per_second": 69.663,
+      "eval_gooaq_pairs_steps_per_second": 2.177,
+      "step": 1550
+    },
+    {
+      "epoch": 0.30003871467286103,
+      "eval_mrpc_pairs_loss": 0.02026505209505558,
+      "eval_mrpc_pairs_runtime": 0.3783,
+      "eval_mrpc_pairs_samples_per_second": 422.927,
+      "eval_mrpc_pairs_steps_per_second": 13.216,
+      "step": 1550
+    }
+  ],
+  "logging_steps": 39,
+  "max_steps": 15498,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1550,
+  "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-1550/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da474a1df6d19af1e75ba94920eb0b6de75b2ffff73e12974949411043dbe7e8
+size 5688