Training in progress, step 16, checkpoint

checkpoint-16/1_WeightedPooling/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-16/added_tokens.json

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

checkpoint-16/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "bobox/DeBERTa-small-ST-v1-test-step3",
+  "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": "4.44.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

checkpoint-16/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.44.0",
+    "pytorch": "2.4.0"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

checkpoint-16/modules.json

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

checkpoint-16/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0228fcfe6bd17ac2e3d96fa8d77027b57317e1f6b01900264495260ab456fb78
+size 9475334

checkpoint-16/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1886a286545822d70cd17732b6025a52902e7429a8ab7eec28bf9c1a4f143b6c
+size 565251810

checkpoint-16/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16a5d40a52c77f32b888879c57abab15e00b792547e1b742b08bc549b488afdc
+size 14244

checkpoint-16/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ce25298e4ba9c66fbb9b17ad0654fa9bed5e59f0a04e77e53fb8ac523b4a69c
+size 1064

checkpoint-16/sentence_bert_config.json

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

checkpoint-16/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-16/spm.model

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

checkpoint-16/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": 512,
+  "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-16/trainer_state.json

@@ -0,0 +1,531 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.1553398058252427,
+  "eval_steps": 8,
+  "global_step": 16,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009708737864077669,
+      "grad_norm": 0.38736554980278015,
+      "learning_rate": 4.411764705882353e-07,
+      "loss": 0.1607,
+      "step": 1
+    },
+    {
+      "epoch": 0.019417475728155338,
+      "grad_norm": 0.38099536299705505,
+      "learning_rate": 8.823529411764706e-07,
+      "loss": 0.1664,
+      "step": 2
+    },
+    {
+      "epoch": 0.02912621359223301,
+      "grad_norm": 0.2045232504606247,
+      "learning_rate": 1.323529411764706e-06,
+      "loss": 0.2686,
+      "step": 3
+    },
+    {
+      "epoch": 0.038834951456310676,
+      "grad_norm": 0.370655357837677,
+      "learning_rate": 1.7647058823529412e-06,
+      "loss": 0.1656,
+      "step": 4
+    },
+    {
+      "epoch": 0.04854368932038835,
+      "grad_norm": 0.35929468274116516,
+      "learning_rate": 2.2058823529411767e-06,
+      "loss": 0.1269,
+      "step": 5
+    },
+    {
+      "epoch": 0.05825242718446602,
+      "grad_norm": 0.2196977585554123,
+      "learning_rate": 2.647058823529412e-06,
+      "loss": 0.1066,
+      "step": 6
+    },
+    {
+      "epoch": 0.06796116504854369,
+      "grad_norm": 0.6120501756668091,
+      "learning_rate": 3.0882352941176476e-06,
+      "loss": 0.1936,
+      "step": 7
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "grad_norm": 0.7004581689834595,
+      "learning_rate": 3.5294117647058825e-06,
+      "loss": 0.087,
+      "step": 8
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "eval_Qnli-dev_cosine_accuracy": 0.6953125,
+      "eval_Qnli-dev_cosine_accuracy_threshold": 0.6691694855690002,
+      "eval_Qnli-dev_cosine_ap": 0.7181099755520133,
+      "eval_Qnli-dev_cosine_f1": 0.6764705882352942,
+      "eval_Qnli-dev_cosine_f1_threshold": 0.49676012992858887,
+      "eval_Qnli-dev_cosine_precision": 0.550531914893617,
+      "eval_Qnli-dev_cosine_recall": 0.8771186440677966,
+      "eval_Qnli-dev_dot_accuracy": 0.669921875,
+      "eval_Qnli-dev_dot_accuracy_threshold": 308.413330078125,
+      "eval_Qnli-dev_dot_ap": 0.678634155184842,
+      "eval_Qnli-dev_dot_f1": 0.6698872785829306,
+      "eval_Qnli-dev_dot_f1_threshold": 208.48468017578125,
+      "eval_Qnli-dev_dot_precision": 0.5402597402597402,
+      "eval_Qnli-dev_dot_recall": 0.8813559322033898,
+      "eval_Qnli-dev_euclidean_accuracy": 0.708984375,
+      "eval_Qnli-dev_euclidean_accuracy_threshold": 17.320636749267578,
+      "eval_Qnli-dev_euclidean_ap": 0.7302104938839877,
+      "eval_Qnli-dev_euclidean_f1": 0.6845637583892616,
+      "eval_Qnli-dev_euclidean_f1_threshold": 20.530838012695312,
+      "eval_Qnli-dev_euclidean_precision": 0.5666666666666667,
+      "eval_Qnli-dev_euclidean_recall": 0.864406779661017,
+      "eval_Qnli-dev_manhattan_accuracy": 0.7109375,
+      "eval_Qnli-dev_manhattan_accuracy_threshold": 369.90869140625,
+      "eval_Qnli-dev_manhattan_ap": 0.732538057005555,
+      "eval_Qnli-dev_manhattan_f1": 0.6836518046709129,
+      "eval_Qnli-dev_manhattan_f1_threshold": 372.4708251953125,
+      "eval_Qnli-dev_manhattan_precision": 0.6851063829787234,
+      "eval_Qnli-dev_manhattan_recall": 0.6822033898305084,
+      "eval_Qnli-dev_max_accuracy": 0.7109375,
+      "eval_Qnli-dev_max_accuracy_threshold": 369.90869140625,
+      "eval_Qnli-dev_max_ap": 0.732538057005555,
+      "eval_Qnli-dev_max_f1": 0.6845637583892616,
+      "eval_Qnli-dev_max_f1_threshold": 372.4708251953125,
+      "eval_Qnli-dev_max_precision": 0.6851063829787234,
+      "eval_Qnli-dev_max_recall": 0.8813559322033898,
+      "eval_allNLI-dev_cosine_accuracy": 0.740234375,
+      "eval_allNLI-dev_cosine_accuracy_threshold": 0.7844594717025757,
+      "eval_allNLI-dev_cosine_ap": 0.6356383940181094,
+      "eval_allNLI-dev_cosine_f1": 0.6369710467706012,
+      "eval_allNLI-dev_cosine_f1_threshold": 0.5889398455619812,
+      "eval_allNLI-dev_cosine_precision": 0.5181159420289855,
+      "eval_allNLI-dev_cosine_recall": 0.8265895953757225,
+      "eval_allNLI-dev_dot_accuracy": 0.72265625,
+      "eval_allNLI-dev_dot_accuracy_threshold": 294.92120361328125,
+      "eval_allNLI-dev_dot_ap": 0.5914839688879726,
+      "eval_allNLI-dev_dot_f1": 0.6099290780141845,
+      "eval_allNLI-dev_dot_f1_threshold": 246.92991638183594,
+      "eval_allNLI-dev_dot_precision": 0.516,
+      "eval_allNLI-dev_dot_recall": 0.7456647398843931,
+      "eval_allNLI-dev_euclidean_accuracy": 0.744140625,
+      "eval_allNLI-dev_euclidean_accuracy_threshold": 13.74991226196289,
+      "eval_allNLI-dev_euclidean_ap": 0.6412989964435845,
+      "eval_allNLI-dev_euclidean_f1": 0.6464208242950108,
+      "eval_allNLI-dev_euclidean_f1_threshold": 18.407054901123047,
+      "eval_allNLI-dev_euclidean_precision": 0.5173611111111112,
+      "eval_allNLI-dev_euclidean_recall": 0.861271676300578,
+      "eval_allNLI-dev_manhattan_accuracy": 0.744140625,
+      "eval_allNLI-dev_manhattan_accuracy_threshold": 313.8516540527344,
+      "eval_allNLI-dev_manhattan_ap": 0.6416934437743762,
+      "eval_allNLI-dev_manhattan_f1": 0.655,
+      "eval_allNLI-dev_manhattan_f1_threshold": 361.0255126953125,
+      "eval_allNLI-dev_manhattan_precision": 0.5770925110132159,
+      "eval_allNLI-dev_manhattan_recall": 0.7572254335260116,
+      "eval_allNLI-dev_max_accuracy": 0.744140625,
+      "eval_allNLI-dev_max_accuracy_threshold": 313.8516540527344,
+      "eval_allNLI-dev_max_ap": 0.6416934437743762,
+      "eval_allNLI-dev_max_f1": 0.655,
+      "eval_allNLI-dev_max_f1_threshold": 361.0255126953125,
+      "eval_allNLI-dev_max_precision": 0.5770925110132159,
+      "eval_allNLI-dev_max_recall": 0.861271676300578,
+      "eval_sequential_score": 0.732538057005555,
+      "eval_sts-test_pearson_cosine": 0.8858982884210256,
+      "eval_sts-test_pearson_dot": 0.8750202743648935,
+      "eval_sts-test_pearson_euclidean": 0.9073481145616336,
+      "eval_sts-test_pearson_manhattan": 0.908032029485236,
+      "eval_sts-test_pearson_max": 0.908032029485236,
+      "eval_sts-test_spearman_cosine": 0.9075027297778789,
+      "eval_sts-test_spearman_dot": 0.8759972599919353,
+      "eval_sts-test_spearman_euclidean": 0.9040041656648221,
+      "eval_sts-test_spearman_manhattan": 0.9045863348242628,
+      "eval_sts-test_spearman_max": 0.9075027297778789,
+      "eval_vitaminc-pairs_loss": 2.801919460296631,
+      "eval_vitaminc-pairs_runtime": 3.8986,
+      "eval_vitaminc-pairs_samples_per_second": 32.832,
+      "eval_vitaminc-pairs_steps_per_second": 0.257,
+      "step": 8
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "eval_negation-triplets_loss": 1.355710744857788,
+      "eval_negation-triplets_runtime": 0.639,
+      "eval_negation-triplets_samples_per_second": 200.304,
+      "eval_negation-triplets_steps_per_second": 1.565,
+      "step": 8
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "eval_scitail-pairs-pos_loss": 0.06071745231747627,
+      "eval_scitail-pairs-pos_runtime": 0.9322,
+      "eval_scitail-pairs-pos_samples_per_second": 137.311,
+      "eval_scitail-pairs-pos_steps_per_second": 1.073,
+      "step": 8
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "eval_scitail-pairs-qa_loss": 1.0544098927312007e-07,
+      "eval_scitail-pairs-qa_runtime": 0.5629,
+      "eval_scitail-pairs-qa_samples_per_second": 227.378,
+      "eval_scitail-pairs-qa_steps_per_second": 1.776,
+      "step": 8
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "eval_xsum-pairs_loss": 0.00016850717656780034,
+      "eval_xsum-pairs_runtime": 2.9256,
+      "eval_xsum-pairs_samples_per_second": 43.751,
+      "eval_xsum-pairs_steps_per_second": 0.342,
+      "step": 8
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "eval_sciq_pairs_loss": 0.0582379512488842,
+      "eval_sciq_pairs_runtime": 2.5278,
+      "eval_sciq_pairs_samples_per_second": 34.418,
+      "eval_sciq_pairs_steps_per_second": 0.396,
+      "step": 8
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "eval_qasc_pairs_loss": 0.07362987846136093,
+      "eval_qasc_pairs_runtime": 0.3723,
+      "eval_qasc_pairs_samples_per_second": 233.691,
+      "eval_qasc_pairs_steps_per_second": 2.686,
+      "step": 8
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "eval_openbookqa_pairs_loss": 1.3787189722061157,
+      "eval_openbookqa_pairs_runtime": 0.5744,
+      "eval_openbookqa_pairs_samples_per_second": 222.849,
+      "eval_openbookqa_pairs_steps_per_second": 1.741,
+      "step": 8
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "eval_msmarco_pairs_loss": 0.1278172731399536,
+      "eval_msmarco_pairs_runtime": 1.0983,
+      "eval_msmarco_pairs_samples_per_second": 79.215,
+      "eval_msmarco_pairs_steps_per_second": 0.911,
+      "step": 8
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "eval_nq_pairs_loss": 0.0051126074977219105,
+      "eval_nq_pairs_runtime": 2.2469,
+      "eval_nq_pairs_samples_per_second": 38.719,
+      "eval_nq_pairs_steps_per_second": 0.445,
+      "step": 8
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "eval_trivia_pairs_loss": 0.26755890250205994,
+      "eval_trivia_pairs_runtime": 2.4342,
+      "eval_trivia_pairs_samples_per_second": 41.081,
+      "eval_trivia_pairs_steps_per_second": 0.411,
+      "step": 8
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "eval_gooaq_pairs_loss": 0.05755230411887169,
+      "eval_gooaq_pairs_runtime": 0.5805,
+      "eval_gooaq_pairs_samples_per_second": 149.876,
+      "eval_gooaq_pairs_steps_per_second": 1.723,
+      "step": 8
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "eval_paws-pos_loss": 0.04592936113476753,
+      "eval_paws-pos_runtime": 0.6903,
+      "eval_paws-pos_samples_per_second": 185.415,
+      "eval_paws-pos_steps_per_second": 1.449,
+      "step": 8
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "eval_global_dataset_loss": 0.4901905357837677,
+      "eval_global_dataset_runtime": 25.0307,
+      "eval_global_dataset_samples_per_second": 26.487,
+      "eval_global_dataset_steps_per_second": 0.24,
+      "step": 8
+    },
+    {
+      "epoch": 0.08737864077669903,
+      "grad_norm": 1.2741845846176147,
+      "learning_rate": 3.970588235294118e-06,
+      "loss": 0.1952,
+      "step": 9
+    },
+    {
+      "epoch": 0.0970873786407767,
+      "grad_norm": 0.46481379866600037,
+      "learning_rate": 4.411764705882353e-06,
+      "loss": 0.4167,
+      "step": 10
+    },
+    {
+      "epoch": 0.10679611650485436,
+      "grad_norm": 0.7963629961013794,
+      "learning_rate": 4.852941176470589e-06,
+      "loss": 0.7876,
+      "step": 11
+    },
+    {
+      "epoch": 0.11650485436893204,
+      "grad_norm": 0.6939969658851624,
+      "learning_rate": 5.294117647058824e-06,
+      "loss": 0.3714,
+      "step": 12
+    },
+    {
+      "epoch": 0.1262135922330097,
+      "grad_norm": 0.44538313150405884,
+      "learning_rate": 5.735294117647059e-06,
+      "loss": 0.1852,
+      "step": 13
+    },
+    {
+      "epoch": 0.13592233009708737,
+      "grad_norm": 0.3318534791469574,
+      "learning_rate": 6.176470588235295e-06,
+      "loss": 0.1144,
+      "step": 14
+    },
+    {
+      "epoch": 0.14563106796116504,
+      "grad_norm": 0.4242781698703766,
+      "learning_rate": 6.61764705882353e-06,
+      "loss": 0.1234,
+      "step": 15
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "grad_norm": 0.2060050666332245,
+      "learning_rate": 7.058823529411765e-06,
+      "loss": 0.0569,
+      "step": 16
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "eval_Qnli-dev_cosine_accuracy": 0.6953125,
+      "eval_Qnli-dev_cosine_accuracy_threshold": 0.6684989929199219,
+      "eval_Qnli-dev_cosine_ap": 0.7189160511154118,
+      "eval_Qnli-dev_cosine_f1": 0.6764705882352942,
+      "eval_Qnli-dev_cosine_f1_threshold": 0.49889329075813293,
+      "eval_Qnli-dev_cosine_precision": 0.550531914893617,
+      "eval_Qnli-dev_cosine_recall": 0.8771186440677966,
+      "eval_Qnli-dev_dot_accuracy": 0.66796875,
+      "eval_Qnli-dev_dot_accuracy_threshold": 303.81427001953125,
+      "eval_Qnli-dev_dot_ap": 0.6791091476516111,
+      "eval_Qnli-dev_dot_f1": 0.6697247706422018,
+      "eval_Qnli-dev_dot_f1_threshold": 184.08914184570312,
+      "eval_Qnli-dev_dot_precision": 0.5239234449760766,
+      "eval_Qnli-dev_dot_recall": 0.9279661016949152,
+      "eval_Qnli-dev_euclidean_accuracy": 0.7109375,
+      "eval_Qnli-dev_euclidean_accuracy_threshold": 17.21223258972168,
+      "eval_Qnli-dev_euclidean_ap": 0.7305713530476123,
+      "eval_Qnli-dev_euclidean_f1": 0.6848739495798319,
+      "eval_Qnli-dev_euclidean_f1_threshold": 17.62983512878418,
+      "eval_Qnli-dev_euclidean_precision": 0.6791666666666667,
+      "eval_Qnli-dev_euclidean_recall": 0.690677966101695,
+      "eval_Qnli-dev_manhattan_accuracy": 0.712890625,
+      "eval_Qnli-dev_manhattan_accuracy_threshold": 367.2698974609375,
+      "eval_Qnli-dev_manhattan_ap": 0.7327153618467641,
+      "eval_Qnli-dev_manhattan_f1": 0.6824034334763949,
+      "eval_Qnli-dev_manhattan_f1_threshold": 368.1672058105469,
+      "eval_Qnli-dev_manhattan_precision": 0.691304347826087,
+      "eval_Qnli-dev_manhattan_recall": 0.673728813559322,
+      "eval_Qnli-dev_max_accuracy": 0.712890625,
+      "eval_Qnli-dev_max_accuracy_threshold": 367.2698974609375,
+      "eval_Qnli-dev_max_ap": 0.7327153618467641,
+      "eval_Qnli-dev_max_f1": 0.6848739495798319,
+      "eval_Qnli-dev_max_f1_threshold": 368.1672058105469,
+      "eval_Qnli-dev_max_precision": 0.691304347826087,
+      "eval_Qnli-dev_max_recall": 0.9279661016949152,
+      "eval_allNLI-dev_cosine_accuracy": 0.7421875,
+      "eval_allNLI-dev_cosine_accuracy_threshold": 0.7840416431427002,
+      "eval_allNLI-dev_cosine_ap": 0.6349487371750362,
+      "eval_allNLI-dev_cosine_f1": 0.6367713004484306,
+      "eval_allNLI-dev_cosine_f1_threshold": 0.5954304337501526,
+      "eval_allNLI-dev_cosine_precision": 0.5201465201465202,
+      "eval_allNLI-dev_cosine_recall": 0.8208092485549133,
+      "eval_allNLI-dev_dot_accuracy": 0.724609375,
+      "eval_allNLI-dev_dot_accuracy_threshold": 291.18670654296875,
+      "eval_allNLI-dev_dot_ap": 0.5913303711668598,
+      "eval_allNLI-dev_dot_f1": 0.6070588235294118,
+      "eval_allNLI-dev_dot_f1_threshold": 242.49884033203125,
+      "eval_allNLI-dev_dot_precision": 0.5119047619047619,
+      "eval_allNLI-dev_dot_recall": 0.7456647398843931,
+      "eval_allNLI-dev_euclidean_accuracy": 0.744140625,
+      "eval_allNLI-dev_euclidean_accuracy_threshold": 13.559854507446289,
+      "eval_allNLI-dev_euclidean_ap": 0.6408865358113234,
+      "eval_allNLI-dev_euclidean_f1": 0.6450116009280741,
+      "eval_allNLI-dev_euclidean_f1_threshold": 17.65105628967285,
+      "eval_allNLI-dev_euclidean_precision": 0.5387596899224806,
+      "eval_allNLI-dev_euclidean_recall": 0.8034682080924855,
+      "eval_allNLI-dev_manhattan_accuracy": 0.7421875,
+      "eval_allNLI-dev_manhattan_accuracy_threshold": 307.83563232421875,
+      "eval_allNLI-dev_manhattan_ap": 0.6414745653251337,
+      "eval_allNLI-dev_manhattan_f1": 0.6533665835411472,
+      "eval_allNLI-dev_manhattan_f1_threshold": 357.5172119140625,
+      "eval_allNLI-dev_manhattan_precision": 0.5745614035087719,
+      "eval_allNLI-dev_manhattan_recall": 0.7572254335260116,
+      "eval_allNLI-dev_max_accuracy": 0.744140625,
+      "eval_allNLI-dev_max_accuracy_threshold": 307.83563232421875,
+      "eval_allNLI-dev_max_ap": 0.6414745653251337,
+      "eval_allNLI-dev_max_f1": 0.6533665835411472,
+      "eval_allNLI-dev_max_f1_threshold": 357.5172119140625,
+      "eval_allNLI-dev_max_precision": 0.5745614035087719,
+      "eval_allNLI-dev_max_recall": 0.8208092485549133,
+      "eval_sequential_score": 0.7327153618467641,
+      "eval_sts-test_pearson_cosine": 0.8857317653883374,
+      "eval_sts-test_pearson_dot": 0.8740754819923455,
+      "eval_sts-test_pearson_euclidean": 0.9064480556463691,
+      "eval_sts-test_pearson_manhattan": 0.9071116458208927,
+      "eval_sts-test_pearson_max": 0.9071116458208927,
+      "eval_sts-test_spearman_cosine": 0.9078527293932209,
+      "eval_sts-test_spearman_dot": 0.8744967501974819,
+      "eval_sts-test_spearman_euclidean": 0.9030452803869885,
+      "eval_sts-test_spearman_manhattan": 0.903667904686727,
+      "eval_sts-test_spearman_max": 0.9078527293932209,
+      "eval_vitaminc-pairs_loss": 2.799455165863037,
+      "eval_vitaminc-pairs_runtime": 3.8555,
+      "eval_vitaminc-pairs_samples_per_second": 33.2,
+      "eval_vitaminc-pairs_steps_per_second": 0.259,
+      "step": 16
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "eval_negation-triplets_loss": 1.3501245975494385,
+      "eval_negation-triplets_runtime": 0.6331,
+      "eval_negation-triplets_samples_per_second": 202.181,
+      "eval_negation-triplets_steps_per_second": 1.58,
+      "step": 16
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "eval_scitail-pairs-pos_loss": 0.060843899846076965,
+      "eval_scitail-pairs-pos_runtime": 0.9131,
+      "eval_scitail-pairs-pos_samples_per_second": 140.183,
+      "eval_scitail-pairs-pos_steps_per_second": 1.095,
+      "step": 16
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "eval_scitail-pairs-qa_loss": 1.1229322893768767e-07,
+      "eval_scitail-pairs-qa_runtime": 0.5691,
+      "eval_scitail-pairs-qa_samples_per_second": 224.9,
+      "eval_scitail-pairs-qa_steps_per_second": 1.757,
+      "step": 16
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "eval_xsum-pairs_loss": 0.0001665251620579511,
+      "eval_xsum-pairs_runtime": 2.9369,
+      "eval_xsum-pairs_samples_per_second": 43.584,
+      "eval_xsum-pairs_steps_per_second": 0.34,
+      "step": 16
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "eval_sciq_pairs_loss": 0.05696266517043114,
+      "eval_sciq_pairs_runtime": 2.5397,
+      "eval_sciq_pairs_samples_per_second": 34.256,
+      "eval_sciq_pairs_steps_per_second": 0.394,
+      "step": 16
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "eval_qasc_pairs_loss": 0.07378190755844116,
+      "eval_qasc_pairs_runtime": 0.3731,
+      "eval_qasc_pairs_samples_per_second": 233.155,
+      "eval_qasc_pairs_steps_per_second": 2.68,
+      "step": 16
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "eval_openbookqa_pairs_loss": 1.3709176778793335,
+      "eval_openbookqa_pairs_runtime": 0.5704,
+      "eval_openbookqa_pairs_samples_per_second": 224.402,
+      "eval_openbookqa_pairs_steps_per_second": 1.753,
+      "step": 16
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "eval_msmarco_pairs_loss": 0.13161690533161163,
+      "eval_msmarco_pairs_runtime": 1.0994,
+      "eval_msmarco_pairs_samples_per_second": 79.136,
+      "eval_msmarco_pairs_steps_per_second": 0.91,
+      "step": 16
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "eval_nq_pairs_loss": 0.005713976453989744,
+      "eval_nq_pairs_runtime": 2.2521,
+      "eval_nq_pairs_samples_per_second": 38.631,
+      "eval_nq_pairs_steps_per_second": 0.444,
+      "step": 16
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "eval_trivia_pairs_loss": 0.2678990364074707,
+      "eval_trivia_pairs_runtime": 2.4403,
+      "eval_trivia_pairs_samples_per_second": 40.979,
+      "eval_trivia_pairs_steps_per_second": 0.41,
+      "step": 16
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "eval_gooaq_pairs_loss": 0.05776378884911537,
+      "eval_gooaq_pairs_runtime": 0.5822,
+      "eval_gooaq_pairs_samples_per_second": 149.421,
+      "eval_gooaq_pairs_steps_per_second": 1.717,
+      "step": 16
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "eval_paws-pos_loss": 0.04598955065011978,
+      "eval_paws-pos_runtime": 0.6747,
+      "eval_paws-pos_samples_per_second": 189.727,
+      "eval_paws-pos_steps_per_second": 1.482,
+      "step": 16
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "eval_global_dataset_loss": 0.48036298155784607,
+      "eval_global_dataset_runtime": 25.0731,
+      "eval_global_dataset_samples_per_second": 26.443,
+      "eval_global_dataset_steps_per_second": 0.239,
+      "step": 16
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 309,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 16,
+  "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": 96,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-16/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00d891109b3776bbe6fe5299eaca62fc99db8369e44011108f84f516eaa2f0e0
+size 5624