Training in progress, step 1856, checkpoint

checkpoint-1856/1_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-1856/added_tokens.json

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

checkpoint-1856/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-small",
+  "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": "4.41.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

checkpoint-1856/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.41.2",
+    "pytorch": "2.1.2"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

checkpoint-1856/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-1856/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a806119a49d07701b04e1de97629c36d346ef876a4cba642da7498b469178736
+size 1130520122

checkpoint-1856/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83bf7102f9e94273fd9a08a9c4dd078a13430c597c901a76f02b5e555862cbcf
+size 565251810

checkpoint-1856/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3338154e0af567e15d98c29bd583b6d5864e82437a982c2ebffee3eb3ad9ad2f
+size 14180

checkpoint-1856/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a96872ee58edb99fe0edadab84cb70394de44da8a07b26c924a6ee88a88265aa
+size 1064

checkpoint-1856/sentence_bert_config.json

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

checkpoint-1856/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1856/spm.model

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

checkpoint-1856/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

checkpoint-1856/trainer_state.json

@@ -0,0 +1,556 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3000323310701584,
+  "eval_steps": 557,
+  "global_step": 1856,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015033947623666343,
+      "grad_norm": 63.938453674316406,
+      "learning_rate": 4.741379310344828e-07,
+      "loss": 11.7791,
+      "step": 93
+    },
+    {
+      "epoch": 0.030067895247332686,
+      "grad_norm": 28.60324478149414,
+      "learning_rate": 9.752155172413793e-07,
+      "loss": 10.5226,
+      "step": 186
+    },
+    {
+      "epoch": 0.04510184287099903,
+      "grad_norm": 17.869054794311523,
+      "learning_rate": 1.476293103448276e-06,
+      "loss": 9.3586,
+      "step": 279
+    },
+    {
+      "epoch": 0.06013579049466537,
+      "grad_norm": 18.835189819335938,
+      "learning_rate": 1.977370689655172e-06,
+      "loss": 8.4548,
+      "step": 372
+    },
+    {
+      "epoch": 0.07516973811833172,
+      "grad_norm": 55.06333541870117,
+      "learning_rate": 2.4784482758620692e-06,
+      "loss": 8.3449,
+      "step": 465
+    },
+    {
+      "epoch": 0.09004203039120595,
+      "eval_nli-pairs_loss": 7.450161933898926,
+      "eval_nli-pairs_runtime": 14.8176,
+      "eval_nli-pairs_samples_per_second": 101.231,
+      "eval_nli-pairs_steps_per_second": 3.172,
+      "eval_sts-test_pearson_cosine": 0.3696416595298566,
+      "eval_sts-test_pearson_dot": 0.13300273461809956,
+      "eval_sts-test_pearson_euclidean": 0.3836877008752716,
+      "eval_sts-test_pearson_manhattan": 0.41477338080789633,
+      "eval_sts-test_pearson_max": 0.41477338080789633,
+      "eval_sts-test_spearman_cosine": 0.3694134524358256,
+      "eval_sts-test_spearman_dot": 0.12058818576425179,
+      "eval_sts-test_spearman_euclidean": 0.38615620458370276,
+      "eval_sts-test_spearman_manhattan": 0.4121304311152658,
+      "eval_sts-test_spearman_max": 0.4121304311152658,
+      "step": 557
+    },
+    {
+      "epoch": 0.09004203039120595,
+      "eval_vitaminc-pairs_loss": 5.403733730316162,
+      "eval_vitaminc-pairs_runtime": 14.4427,
+      "eval_vitaminc-pairs_samples_per_second": 69.17,
+      "eval_vitaminc-pairs_steps_per_second": 2.216,
+      "step": 557
+    },
+    {
+      "epoch": 0.09004203039120595,
+      "eval_qnli-contrastive_loss": 8.863805770874023,
+      "eval_qnli-contrastive_runtime": 4.835,
+      "eval_qnli-contrastive_samples_per_second": 310.238,
+      "eval_qnli-contrastive_steps_per_second": 9.721,
+      "step": 557
+    },
+    {
+      "epoch": 0.09004203039120595,
+      "eval_scitail-pairs-qa_loss": 4.2781147956848145,
+      "eval_scitail-pairs-qa_runtime": 5.761,
+      "eval_scitail-pairs-qa_samples_per_second": 130.186,
+      "eval_scitail-pairs-qa_steps_per_second": 4.166,
+      "step": 557
+    },
+    {
+      "epoch": 0.09004203039120595,
+      "eval_scitail-pairs-pos_loss": 4.930431365966797,
+      "eval_scitail-pairs-pos_runtime": 15.2161,
+      "eval_scitail-pairs-pos_samples_per_second": 85.699,
+      "eval_scitail-pairs-pos_steps_per_second": 2.695,
+      "step": 557
+    },
+    {
+      "epoch": 0.09004203039120595,
+      "eval_xsum-pairs_loss": 4.778657913208008,
+      "eval_xsum-pairs_runtime": 3.0397,
+      "eval_xsum-pairs_samples_per_second": 65.795,
+      "eval_xsum-pairs_steps_per_second": 2.303,
+      "step": 557
+    },
+    {
+      "epoch": 0.09004203039120595,
+      "eval_compression-pairs_loss": 3.489774465560913,
+      "eval_compression-pairs_runtime": 1.2758,
+      "eval_compression-pairs_samples_per_second": 391.924,
+      "eval_compression-pairs_steps_per_second": 12.542,
+      "step": 557
+    },
+    {
+      "epoch": 0.09004203039120595,
+      "eval_sciq_pairs_loss": 7.707857131958008,
+      "eval_sciq_pairs_runtime": 28.932,
+      "eval_sciq_pairs_samples_per_second": 20.185,
+      "eval_sciq_pairs_steps_per_second": 0.657,
+      "step": 557
+    },
+    {
+      "epoch": 0.09004203039120595,
+      "eval_qasc_pairs_loss": 12.320230484008789,
+      "eval_qasc_pairs_runtime": 5.2561,
+      "eval_qasc_pairs_samples_per_second": 77.434,
+      "eval_qasc_pairs_steps_per_second": 2.473,
+      "step": 557
+    },
+    {
+      "epoch": 0.09004203039120595,
+      "eval_openbookqa_pairs_loss": 7.607065677642822,
+      "eval_openbookqa_pairs_runtime": 1.189,
+      "eval_openbookqa_pairs_samples_per_second": 115.224,
+      "eval_openbookqa_pairs_steps_per_second": 4.205,
+      "step": 557
+    },
+    {
+      "epoch": 0.09004203039120595,
+      "eval_msmarco_pairs_loss": 8.519609451293945,
+      "eval_msmarco_pairs_runtime": 19.7371,
+      "eval_msmarco_pairs_samples_per_second": 50.666,
+      "eval_msmarco_pairs_steps_per_second": 1.621,
+      "step": 557
+    },
+    {
+      "epoch": 0.09004203039120595,
+      "eval_nq_pairs_loss": 8.43966007232666,
+      "eval_nq_pairs_runtime": 37.2943,
+      "eval_nq_pairs_samples_per_second": 26.814,
+      "eval_nq_pairs_steps_per_second": 0.858,
+      "step": 557
+    },
+    {
+      "epoch": 0.09004203039120595,
+      "eval_trivia_pairs_loss": 8.689275741577148,
+      "eval_trivia_pairs_runtime": 64.6902,
+      "eval_trivia_pairs_samples_per_second": 15.458,
+      "eval_trivia_pairs_steps_per_second": 0.495,
+      "step": 557
+    },
+    {
+      "epoch": 0.09004203039120595,
+      "eval_quora_pairs_loss": 4.54755163192749,
+      "eval_quora_pairs_runtime": 3.7394,
+      "eval_quora_pairs_samples_per_second": 133.71,
+      "eval_quora_pairs_steps_per_second": 4.279,
+      "step": 557
+    },
+    {
+      "epoch": 0.09004203039120595,
+      "eval_gooaq_pairs_loss": 7.57412052154541,
+      "eval_gooaq_pairs_runtime": 13.3648,
+      "eval_gooaq_pairs_samples_per_second": 74.824,
+      "eval_gooaq_pairs_steps_per_second": 2.394,
+      "step": 557
+    },
+    {
+      "epoch": 0.09020368574199807,
+      "grad_norm": 21.490495681762695,
+      "learning_rate": 2.9795258620689654e-06,
+      "loss": 7.4107,
+      "step": 558
+    },
+    {
+      "epoch": 0.1052376333656644,
+      "grad_norm": 35.23164367675781,
+      "learning_rate": 3.480603448275862e-06,
+      "loss": 7.0111,
+      "step": 651
+    },
+    {
+      "epoch": 0.12027158098933075,
+      "grad_norm": 28.60922622680664,
+      "learning_rate": 3.981681034482759e-06,
+      "loss": 5.9488,
+      "step": 744
+    },
+    {
+      "epoch": 0.13530552861299708,
+      "grad_norm": 22.0839786529541,
+      "learning_rate": 4.482758620689656e-06,
+      "loss": 6.3051,
+      "step": 837
+    },
+    {
+      "epoch": 0.15033947623666344,
+      "grad_norm": 34.64767837524414,
+      "learning_rate": 4.983836206896552e-06,
+      "loss": 5.2056,
+      "step": 930
+    },
+    {
+      "epoch": 0.16537342386032977,
+      "grad_norm": 13.605194091796875,
+      "learning_rate": 5.484913793103448e-06,
+      "loss": 5.0794,
+      "step": 1023
+    },
+    {
+      "epoch": 0.1800840607824119,
+      "eval_nli-pairs_loss": 4.693160057067871,
+      "eval_nli-pairs_runtime": 14.776,
+      "eval_nli-pairs_samples_per_second": 101.516,
+      "eval_nli-pairs_steps_per_second": 3.181,
+      "eval_sts-test_pearson_cosine": 0.6672572282189017,
+      "eval_sts-test_pearson_dot": 0.5110207654364226,
+      "eval_sts-test_pearson_euclidean": 0.65934512843155,
+      "eval_sts-test_pearson_manhattan": 0.6615633016003417,
+      "eval_sts-test_pearson_max": 0.6672572282189017,
+      "eval_sts-test_spearman_cosine": 0.6364241996636473,
+      "eval_sts-test_spearman_dot": 0.4920702168931027,
+      "eval_sts-test_spearman_euclidean": 0.638848044048013,
+      "eval_sts-test_spearman_manhattan": 0.6407402326117282,
+      "eval_sts-test_spearman_max": 0.6407402326117282,
+      "step": 1114
+    },
+    {
+      "epoch": 0.1800840607824119,
+      "eval_vitaminc-pairs_loss": 3.5585296154022217,
+      "eval_vitaminc-pairs_runtime": 14.3661,
+      "eval_vitaminc-pairs_samples_per_second": 69.538,
+      "eval_vitaminc-pairs_steps_per_second": 2.227,
+      "step": 1114
+    },
+    {
+      "epoch": 0.1800840607824119,
+      "eval_qnli-contrastive_loss": 11.759393692016602,
+      "eval_qnli-contrastive_runtime": 4.7771,
+      "eval_qnli-contrastive_samples_per_second": 313.999,
+      "eval_qnli-contrastive_steps_per_second": 9.839,
+      "step": 1114
+    },
+    {
+      "epoch": 0.1800840607824119,
+      "eval_scitail-pairs-qa_loss": 1.3339837789535522,
+      "eval_scitail-pairs-qa_runtime": 5.8445,
+      "eval_scitail-pairs-qa_samples_per_second": 128.326,
+      "eval_scitail-pairs-qa_steps_per_second": 4.106,
+      "step": 1114
+    },
+    {
+      "epoch": 0.1800840607824119,
+      "eval_scitail-pairs-pos_loss": 2.508178234100342,
+      "eval_scitail-pairs-pos_runtime": 15.12,
+      "eval_scitail-pairs-pos_samples_per_second": 86.244,
+      "eval_scitail-pairs-pos_steps_per_second": 2.712,
+      "step": 1114
+    },
+    {
+      "epoch": 0.1800840607824119,
+      "eval_xsum-pairs_loss": 2.727797508239746,
+      "eval_xsum-pairs_runtime": 3.0382,
+      "eval_xsum-pairs_samples_per_second": 65.828,
+      "eval_xsum-pairs_steps_per_second": 2.304,
+      "step": 1114
+    },
+    {
+      "epoch": 0.1800840607824119,
+      "eval_compression-pairs_loss": 1.769970178604126,
+      "eval_compression-pairs_runtime": 1.3017,
+      "eval_compression-pairs_samples_per_second": 384.105,
+      "eval_compression-pairs_steps_per_second": 12.291,
+      "step": 1114
+    },
+    {
+      "epoch": 0.1800840607824119,
+      "eval_sciq_pairs_loss": 6.772756576538086,
+      "eval_sciq_pairs_runtime": 29.0556,
+      "eval_sciq_pairs_samples_per_second": 20.099,
+      "eval_sciq_pairs_steps_per_second": 0.654,
+      "step": 1114
+    },
+    {
+      "epoch": 0.1800840607824119,
+      "eval_qasc_pairs_loss": 10.429397583007812,
+      "eval_qasc_pairs_runtime": 5.2915,
+      "eval_qasc_pairs_samples_per_second": 76.916,
+      "eval_qasc_pairs_steps_per_second": 2.457,
+      "step": 1114
+    },
+    {
+      "epoch": 0.1800840607824119,
+      "eval_openbookqa_pairs_loss": 5.441987037658691,
+      "eval_openbookqa_pairs_runtime": 1.1725,
+      "eval_openbookqa_pairs_samples_per_second": 116.843,
+      "eval_openbookqa_pairs_steps_per_second": 4.264,
+      "step": 1114
+    },
+    {
+      "epoch": 0.1800840607824119,
+      "eval_msmarco_pairs_loss": 4.586305618286133,
+      "eval_msmarco_pairs_runtime": 19.8051,
+      "eval_msmarco_pairs_samples_per_second": 50.492,
+      "eval_msmarco_pairs_steps_per_second": 1.616,
+      "step": 1114
+    },
+    {
+      "epoch": 0.1800840607824119,
+      "eval_nq_pairs_loss": 5.193580150604248,
+      "eval_nq_pairs_runtime": 37.2293,
+      "eval_nq_pairs_samples_per_second": 26.861,
+      "eval_nq_pairs_steps_per_second": 0.86,
+      "step": 1114
+    },
+    {
+      "epoch": 0.1800840607824119,
+      "eval_trivia_pairs_loss": 5.120319366455078,
+      "eval_trivia_pairs_runtime": 64.3021,
+      "eval_trivia_pairs_samples_per_second": 15.552,
+      "eval_trivia_pairs_steps_per_second": 0.498,
+      "step": 1114
+    },
+    {
+      "epoch": 0.1800840607824119,
+      "eval_quora_pairs_loss": 1.4382946491241455,
+      "eval_quora_pairs_runtime": 3.7168,
+      "eval_quora_pairs_samples_per_second": 134.525,
+      "eval_quora_pairs_steps_per_second": 4.305,
+      "step": 1114
+    },
+    {
+      "epoch": 0.1800840607824119,
+      "eval_gooaq_pairs_loss": 3.7513082027435303,
+      "eval_gooaq_pairs_runtime": 13.2594,
+      "eval_gooaq_pairs_samples_per_second": 75.418,
+      "eval_gooaq_pairs_steps_per_second": 2.413,
+      "step": 1114
+    },
+    {
+      "epoch": 0.18040737148399613,
+      "grad_norm": 39.661067962646484,
+      "learning_rate": 5.9859913793103445e-06,
+      "loss": 4.362,
+      "step": 1116
+    },
+    {
+      "epoch": 0.19544131910766246,
+      "grad_norm": 34.55929946899414,
+      "learning_rate": 6.487068965517242e-06,
+      "loss": 4.3245,
+      "step": 1209
+    },
+    {
+      "epoch": 0.2104752667313288,
+      "grad_norm": 25.775623321533203,
+      "learning_rate": 6.988146551724138e-06,
+      "loss": 4.359,
+      "step": 1302
+    },
+    {
+      "epoch": 0.22550921435499516,
+      "grad_norm": 57.751529693603516,
+      "learning_rate": 7.489224137931035e-06,
+      "loss": 4.0488,
+      "step": 1395
+    },
+    {
+      "epoch": 0.2405431619786615,
+      "grad_norm": 33.448768615722656,
+      "learning_rate": 7.990301724137931e-06,
+      "loss": 4.0499,
+      "step": 1488
+    },
+    {
+      "epoch": 0.2555771096023278,
+      "grad_norm": 29.5295467376709,
+      "learning_rate": 8.491379310344827e-06,
+      "loss": 3.7256,
+      "step": 1581
+    },
+    {
+      "epoch": 0.27012609117361785,
+      "eval_nli-pairs_loss": 3.6348764896392822,
+      "eval_nli-pairs_runtime": 14.761,
+      "eval_nli-pairs_samples_per_second": 101.619,
+      "eval_nli-pairs_steps_per_second": 3.184,
+      "eval_sts-test_pearson_cosine": 0.6972871286019413,
+      "eval_sts-test_pearson_dot": 0.5667394576060958,
+      "eval_sts-test_pearson_euclidean": 0.6946767725059286,
+      "eval_sts-test_pearson_manhattan": 0.7031948219809795,
+      "eval_sts-test_pearson_max": 0.7031948219809795,
+      "eval_sts-test_spearman_cosine": 0.6666257059052387,
+      "eval_sts-test_spearman_dot": 0.5430589355737897,
+      "eval_sts-test_spearman_euclidean": 0.6727104999188346,
+      "eval_sts-test_spearman_manhattan": 0.6812486382298032,
+      "eval_sts-test_spearman_max": 0.6812486382298032,
+      "step": 1671
+    },
+    {
+      "epoch": 0.27012609117361785,
+      "eval_vitaminc-pairs_loss": 2.811436653137207,
+      "eval_vitaminc-pairs_runtime": 14.4779,
+      "eval_vitaminc-pairs_samples_per_second": 69.002,
+      "eval_vitaminc-pairs_steps_per_second": 2.21,
+      "step": 1671
+    },
+    {
+      "epoch": 0.27012609117361785,
+      "eval_qnli-contrastive_loss": 9.688385009765625,
+      "eval_qnli-contrastive_runtime": 4.8234,
+      "eval_qnli-contrastive_samples_per_second": 310.984,
+      "eval_qnli-contrastive_steps_per_second": 9.744,
+      "step": 1671
+    },
+    {
+      "epoch": 0.27012609117361785,
+      "eval_scitail-pairs-qa_loss": 0.8966398239135742,
+      "eval_scitail-pairs-qa_runtime": 5.8274,
+      "eval_scitail-pairs-qa_samples_per_second": 128.702,
+      "eval_scitail-pairs-qa_steps_per_second": 4.118,
+      "step": 1671
+    },
+    {
+      "epoch": 0.27012609117361785,
+      "eval_scitail-pairs-pos_loss": 1.9770935773849487,
+      "eval_scitail-pairs-pos_runtime": 15.5498,
+      "eval_scitail-pairs-pos_samples_per_second": 83.859,
+      "eval_scitail-pairs-pos_steps_per_second": 2.637,
+      "step": 1671
+    },
+    {
+      "epoch": 0.27012609117361785,
+      "eval_xsum-pairs_loss": 2.1290199756622314,
+      "eval_xsum-pairs_runtime": 3.0544,
+      "eval_xsum-pairs_samples_per_second": 65.479,
+      "eval_xsum-pairs_steps_per_second": 2.292,
+      "step": 1671
+    },
+    {
+      "epoch": 0.27012609117361785,
+      "eval_compression-pairs_loss": 1.2427340745925903,
+      "eval_compression-pairs_runtime": 1.3179,
+      "eval_compression-pairs_samples_per_second": 379.389,
+      "eval_compression-pairs_steps_per_second": 12.14,
+      "step": 1671
+    },
+    {
+      "epoch": 0.27012609117361785,
+      "eval_sciq_pairs_loss": 6.424961090087891,
+      "eval_sciq_pairs_runtime": 29.2749,
+      "eval_sciq_pairs_samples_per_second": 19.949,
+      "eval_sciq_pairs_steps_per_second": 0.649,
+      "step": 1671
+    },
+    {
+      "epoch": 0.27012609117361785,
+      "eval_qasc_pairs_loss": 9.239206314086914,
+      "eval_qasc_pairs_runtime": 5.2408,
+      "eval_qasc_pairs_samples_per_second": 77.66,
+      "eval_qasc_pairs_steps_per_second": 2.481,
+      "step": 1671
+    },
+    {
+      "epoch": 0.27012609117361785,
+      "eval_openbookqa_pairs_loss": 4.784058570861816,
+      "eval_openbookqa_pairs_runtime": 1.2088,
+      "eval_openbookqa_pairs_samples_per_second": 113.332,
+      "eval_openbookqa_pairs_steps_per_second": 4.136,
+      "step": 1671
+    },
+    {
+      "epoch": 0.27012609117361785,
+      "eval_msmarco_pairs_loss": 3.655301094055176,
+      "eval_msmarco_pairs_runtime": 19.7273,
+      "eval_msmarco_pairs_samples_per_second": 50.691,
+      "eval_msmarco_pairs_steps_per_second": 1.622,
+      "step": 1671
+    },
+    {
+      "epoch": 0.27012609117361785,
+      "eval_nq_pairs_loss": 4.114762783050537,
+      "eval_nq_pairs_runtime": 37.3924,
+      "eval_nq_pairs_samples_per_second": 26.743,
+      "eval_nq_pairs_steps_per_second": 0.856,
+      "step": 1671
+    },
+    {
+      "epoch": 0.27012609117361785,
+      "eval_trivia_pairs_loss": 4.019989967346191,
+      "eval_trivia_pairs_runtime": 64.3836,
+      "eval_trivia_pairs_samples_per_second": 15.532,
+      "eval_trivia_pairs_steps_per_second": 0.497,
+      "step": 1671
+    },
+    {
+      "epoch": 0.27012609117361785,
+      "eval_quora_pairs_loss": 1.002946138381958,
+      "eval_quora_pairs_runtime": 3.7091,
+      "eval_quora_pairs_samples_per_second": 134.803,
+      "eval_quora_pairs_steps_per_second": 4.314,
+      "step": 1671
+    },
+    {
+      "epoch": 0.27012609117361785,
+      "eval_gooaq_pairs_loss": 2.87351131439209,
+      "eval_gooaq_pairs_runtime": 13.2151,
+      "eval_gooaq_pairs_samples_per_second": 75.671,
+      "eval_gooaq_pairs_steps_per_second": 2.421,
+      "step": 1671
+    },
+    {
+      "epoch": 0.27061105722599416,
+      "grad_norm": 142.8954315185547,
+      "learning_rate": 8.992456896551725e-06,
+      "loss": 3.6978,
+      "step": 1674
+    },
+    {
+      "epoch": 0.28564500484966054,
+      "grad_norm": 35.244972229003906,
+      "learning_rate": 9.493534482758622e-06,
+      "loss": 3.9547,
+      "step": 1767
+    }
+  ],
+  "logging_steps": 93,
+  "max_steps": 18558,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1856,
+  "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-1856/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee8c0e50c0dd4c52a0f05547246281a5456854ea82a3d1989795e12ea957e233
+size 5624