Training in progress, step 2937, checkpoint

checkpoint-2937/1_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-2937/added_tokens.json

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

checkpoint-2937/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-2937/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-2937/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-2937/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c35ecbff69078ca3a8c8fe80c4ebdbfdba345f2c6ce8f077e68fc07366684351
+size 1130520122

checkpoint-2937/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b313a1aaf154bf2649f9a678eb93455b8cb12d8108ce51fac284dcb8f44928b5
+size 565251810

checkpoint-2937/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c50e40495cd79573a0b77c9fa1fd4c30d3d0083a7e94fc129a6313dac0a44af2
+size 14244

checkpoint-2937/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ca8939dcfc1b49137fb4d6708406937b49b480805806c3066b2fdac8ff053f9
+size 1064

checkpoint-2937/sentence_bert_config.json

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

checkpoint-2937/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-2937/spm.model

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

checkpoint-2937/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-2937/trainer_state.json

@@ -0,0 +1,556 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5,
+  "eval_steps": 735,
+  "global_step": 2937,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02502553626149132,
+      "grad_norm": 65.55949401855469,
+      "learning_rate": 4.834865509022812e-07,
+      "loss": 16.851,
+      "step": 147
+    },
+    {
+      "epoch": 0.05005107252298264,
+      "grad_norm": 23.207971572875977,
+      "learning_rate": 9.805924412665985e-07,
+      "loss": 11.2787,
+      "step": 294
+    },
+    {
+      "epoch": 0.07507660878447395,
+      "grad_norm": 176.1532440185547,
+      "learning_rate": 1.481103166496425e-06,
+      "loss": 8.9166,
+      "step": 441
+    },
+    {
+      "epoch": 0.10010214504596528,
+      "grad_norm": 22.1564998626709,
+      "learning_rate": 1.981613891726251e-06,
+      "loss": 7.9463,
+      "step": 588
+    },
+    {
+      "epoch": 0.12512768130745658,
+      "grad_norm": 20.11876106262207,
+      "learning_rate": 2.4821246169560777e-06,
+      "loss": 7.2108,
+      "step": 735
+    },
+    {
+      "epoch": 0.12512768130745658,
+      "eval_nli-pairs_loss": 6.905651569366455,
+      "eval_nli-pairs_runtime": 4.0844,
+      "eval_nli-pairs_samples_per_second": 36.725,
+      "eval_nli-pairs_steps_per_second": 1.224,
+      "eval_sts-test_pearson_cosine": 0.3740256550072784,
+      "eval_sts-test_pearson_dot": 0.13384893803205677,
+      "eval_sts-test_pearson_euclidean": 0.3912387619869807,
+      "eval_sts-test_pearson_manhattan": 0.4202605137823524,
+      "eval_sts-test_pearson_max": 0.4202605137823524,
+      "eval_sts-test_spearman_cosine": 0.37210107338950205,
+      "eval_sts-test_spearman_dot": 0.12092409843417483,
+      "eval_sts-test_spearman_euclidean": 0.39172287978780546,
+      "eval_sts-test_spearman_manhattan": 0.4169664738563951,
+      "eval_sts-test_spearman_max": 0.4169664738563951,
+      "step": 735
+    },
+    {
+      "epoch": 0.12512768130745658,
+      "eval_vitaminc-pairs_loss": 5.720878601074219,
+      "eval_vitaminc-pairs_runtime": 2.1703,
+      "eval_vitaminc-pairs_samples_per_second": 69.115,
+      "eval_vitaminc-pairs_steps_per_second": 2.304,
+      "step": 735
+    },
+    {
+      "epoch": 0.12512768130745658,
+      "eval_qnli-contrastive_loss": 8.1649751663208,
+      "eval_qnli-contrastive_runtime": 0.4937,
+      "eval_qnli-contrastive_samples_per_second": 303.841,
+      "eval_qnli-contrastive_steps_per_second": 10.128,
+      "step": 735
+    },
+    {
+      "epoch": 0.12512768130745658,
+      "eval_scitail-pairs-qa_loss": 3.7859296798706055,
+      "eval_scitail-pairs-qa_runtime": 1.1509,
+      "eval_scitail-pairs-qa_samples_per_second": 130.329,
+      "eval_scitail-pairs-qa_steps_per_second": 4.344,
+      "step": 735
+    },
+    {
+      "epoch": 0.12512768130745658,
+      "eval_scitail-pairs-pos_loss": 3.9919917583465576,
+      "eval_scitail-pairs-pos_runtime": 2.1442,
+      "eval_scitail-pairs-pos_samples_per_second": 69.956,
+      "eval_scitail-pairs-pos_steps_per_second": 2.332,
+      "step": 735
+    },
+    {
+      "epoch": 0.12512768130745658,
+      "eval_xsum-pairs_loss": 4.600368976593018,
+      "eval_xsum-pairs_runtime": 2.26,
+      "eval_xsum-pairs_samples_per_second": 66.371,
+      "eval_xsum-pairs_steps_per_second": 2.212,
+      "step": 735
+    },
+    {
+      "epoch": 0.12512768130745658,
+      "eval_compression-pairs_loss": 3.3037569522857666,
+      "eval_compression-pairs_runtime": 0.449,
+      "eval_compression-pairs_samples_per_second": 334.078,
+      "eval_compression-pairs_steps_per_second": 11.136,
+      "step": 735
+    },
+    {
+      "epoch": 0.12512768130745658,
+      "eval_sciq_pairs_loss": 10.214456558227539,
+      "eval_sciq_pairs_runtime": 7.1179,
+      "eval_sciq_pairs_samples_per_second": 21.074,
+      "eval_sciq_pairs_steps_per_second": 0.702,
+      "step": 735
+    },
+    {
+      "epoch": 0.12512768130745658,
+      "eval_qasc_pairs_loss": 10.58031940460205,
+      "eval_qasc_pairs_runtime": 2.0175,
+      "eval_qasc_pairs_samples_per_second": 74.348,
+      "eval_qasc_pairs_steps_per_second": 2.478,
+      "step": 735
+    },
+    {
+      "epoch": 0.12512768130745658,
+      "eval_openbookqa_pairs_loss": 7.862658977508545,
+      "eval_openbookqa_pairs_runtime": 0.8571,
+      "eval_openbookqa_pairs_samples_per_second": 120.168,
+      "eval_openbookqa_pairs_steps_per_second": 4.667,
+      "step": 735
+    },
+    {
+      "epoch": 0.12512768130745658,
+      "eval_msmarco_pairs_loss": 8.754273414611816,
+      "eval_msmarco_pairs_runtime": 2.7533,
+      "eval_msmarco_pairs_samples_per_second": 54.481,
+      "eval_msmarco_pairs_steps_per_second": 1.816,
+      "step": 735
+    },
+    {
+      "epoch": 0.12512768130745658,
+      "eval_nq_pairs_loss": 8.415486335754395,
+      "eval_nq_pairs_runtime": 5.0894,
+      "eval_nq_pairs_samples_per_second": 29.473,
+      "eval_nq_pairs_steps_per_second": 0.982,
+      "step": 735
+    },
+    {
+      "epoch": 0.12512768130745658,
+      "eval_trivia_pairs_loss": 9.051105499267578,
+      "eval_trivia_pairs_runtime": 9.5498,
+      "eval_trivia_pairs_samples_per_second": 15.707,
+      "eval_trivia_pairs_steps_per_second": 0.524,
+      "step": 735
+    },
+    {
+      "epoch": 0.12512768130745658,
+      "eval_quora_pairs_loss": 4.5232110023498535,
+      "eval_quora_pairs_runtime": 1.1469,
+      "eval_quora_pairs_samples_per_second": 130.785,
+      "eval_quora_pairs_steps_per_second": 4.36,
+      "step": 735
+    },
+    {
+      "epoch": 0.12512768130745658,
+      "eval_gooaq_pairs_loss": 7.579105854034424,
+      "eval_gooaq_pairs_runtime": 2.0491,
+      "eval_gooaq_pairs_samples_per_second": 73.203,
+      "eval_gooaq_pairs_steps_per_second": 2.44,
+      "step": 735
+    },
+    {
+      "epoch": 0.1501532175689479,
+      "grad_norm": 31.7736759185791,
+      "learning_rate": 2.982635342185904e-06,
+      "loss": 6.7709,
+      "step": 882
+    },
+    {
+      "epoch": 0.1751787538304392,
+      "grad_norm": 31.57339096069336,
+      "learning_rate": 3.4831460674157306e-06,
+      "loss": 6.1746,
+      "step": 1029
+    },
+    {
+      "epoch": 0.20020429009193055,
+      "grad_norm": 25.392702102661133,
+      "learning_rate": 3.9836567926455565e-06,
+      "loss": 5.7706,
+      "step": 1176
+    },
+    {
+      "epoch": 0.22522982635342187,
+      "grad_norm": 32.390472412109375,
+      "learning_rate": 4.484167517875383e-06,
+      "loss": 5.7283,
+      "step": 1323
+    },
+    {
+      "epoch": 0.25025536261491316,
+      "grad_norm": 18.85039520263672,
+      "learning_rate": 4.98467824310521e-06,
+      "loss": 5.1856,
+      "step": 1470
+    },
+    {
+      "epoch": 0.25025536261491316,
+      "eval_nli-pairs_loss": 4.352054119110107,
+      "eval_nli-pairs_runtime": 4.1476,
+      "eval_nli-pairs_samples_per_second": 36.165,
+      "eval_nli-pairs_steps_per_second": 1.206,
+      "eval_sts-test_pearson_cosine": 0.6694155778571752,
+      "eval_sts-test_pearson_dot": 0.5201102118957572,
+      "eval_sts-test_pearson_euclidean": 0.6613028243200022,
+      "eval_sts-test_pearson_manhattan": 0.6670710500315469,
+      "eval_sts-test_pearson_max": 0.6694155778571752,
+      "eval_sts-test_spearman_cosine": 0.6367853204388882,
+      "eval_sts-test_spearman_dot": 0.4940207180607985,
+      "eval_sts-test_spearman_euclidean": 0.6391132775161348,
+      "eval_sts-test_spearman_manhattan": 0.6446159957787251,
+      "eval_sts-test_spearman_max": 0.6446159957787251,
+      "step": 1470
+    },
+    {
+      "epoch": 0.25025536261491316,
+      "eval_vitaminc-pairs_loss": 3.4987735748291016,
+      "eval_vitaminc-pairs_runtime": 2.1678,
+      "eval_vitaminc-pairs_samples_per_second": 69.194,
+      "eval_vitaminc-pairs_steps_per_second": 2.306,
+      "step": 1470
+    },
+    {
+      "epoch": 0.25025536261491316,
+      "eval_qnli-contrastive_loss": 12.915559768676758,
+      "eval_qnli-contrastive_runtime": 0.4918,
+      "eval_qnli-contrastive_samples_per_second": 304.99,
+      "eval_qnli-contrastive_steps_per_second": 10.166,
+      "step": 1470
+    },
+    {
+      "epoch": 0.25025536261491316,
+      "eval_scitail-pairs-qa_loss": 1.3250077962875366,
+      "eval_scitail-pairs-qa_runtime": 1.154,
+      "eval_scitail-pairs-qa_samples_per_second": 129.984,
+      "eval_scitail-pairs-qa_steps_per_second": 4.333,
+      "step": 1470
+    },
+    {
+      "epoch": 0.25025536261491316,
+      "eval_scitail-pairs-pos_loss": 2.457335948944092,
+      "eval_scitail-pairs-pos_runtime": 2.1475,
+      "eval_scitail-pairs-pos_samples_per_second": 69.85,
+      "eval_scitail-pairs-pos_steps_per_second": 2.328,
+      "step": 1470
+    },
+    {
+      "epoch": 0.25025536261491316,
+      "eval_xsum-pairs_loss": 3.071201801300049,
+      "eval_xsum-pairs_runtime": 2.2634,
+      "eval_xsum-pairs_samples_per_second": 66.271,
+      "eval_xsum-pairs_steps_per_second": 2.209,
+      "step": 1470
+    },
+    {
+      "epoch": 0.25025536261491316,
+      "eval_compression-pairs_loss": 2.0629916191101074,
+      "eval_compression-pairs_runtime": 0.4529,
+      "eval_compression-pairs_samples_per_second": 331.23,
+      "eval_compression-pairs_steps_per_second": 11.041,
+      "step": 1470
+    },
+    {
+      "epoch": 0.25025536261491316,
+      "eval_sciq_pairs_loss": 9.06814193725586,
+      "eval_sciq_pairs_runtime": 7.1445,
+      "eval_sciq_pairs_samples_per_second": 20.995,
+      "eval_sciq_pairs_steps_per_second": 0.7,
+      "step": 1470
+    },
+    {
+      "epoch": 0.25025536261491316,
+      "eval_qasc_pairs_loss": 9.245658874511719,
+      "eval_qasc_pairs_runtime": 2.0471,
+      "eval_qasc_pairs_samples_per_second": 73.274,
+      "eval_qasc_pairs_steps_per_second": 2.442,
+      "step": 1470
+    },
+    {
+      "epoch": 0.25025536261491316,
+      "eval_openbookqa_pairs_loss": 5.652446746826172,
+      "eval_openbookqa_pairs_runtime": 0.8946,
+      "eval_openbookqa_pairs_samples_per_second": 115.14,
+      "eval_openbookqa_pairs_steps_per_second": 4.471,
+      "step": 1470
+    },
+    {
+      "epoch": 0.25025536261491316,
+      "eval_msmarco_pairs_loss": 4.844855785369873,
+      "eval_msmarco_pairs_runtime": 2.7887,
+      "eval_msmarco_pairs_samples_per_second": 53.788,
+      "eval_msmarco_pairs_steps_per_second": 1.793,
+      "step": 1470
+    },
+    {
+      "epoch": 0.25025536261491316,
+      "eval_nq_pairs_loss": 5.023958206176758,
+      "eval_nq_pairs_runtime": 5.0823,
+      "eval_nq_pairs_samples_per_second": 29.514,
+      "eval_nq_pairs_steps_per_second": 0.984,
+      "step": 1470
+    },
+    {
+      "epoch": 0.25025536261491316,
+      "eval_trivia_pairs_loss": 5.2907304763793945,
+      "eval_trivia_pairs_runtime": 9.6673,
+      "eval_trivia_pairs_samples_per_second": 15.516,
+      "eval_trivia_pairs_steps_per_second": 0.517,
+      "step": 1470
+    },
+    {
+      "epoch": 0.25025536261491316,
+      "eval_quora_pairs_loss": 1.5572240352630615,
+      "eval_quora_pairs_runtime": 1.1979,
+      "eval_quora_pairs_samples_per_second": 125.218,
+      "eval_quora_pairs_steps_per_second": 4.174,
+      "step": 1470
+    },
+    {
+      "epoch": 0.25025536261491316,
+      "eval_gooaq_pairs_loss": 3.970768928527832,
+      "eval_gooaq_pairs_runtime": 2.117,
+      "eval_gooaq_pairs_samples_per_second": 70.855,
+      "eval_gooaq_pairs_steps_per_second": 2.362,
+      "step": 1470
+    },
+    {
+      "epoch": 0.2752808988764045,
+      "grad_norm": 40.67585754394531,
+      "learning_rate": 5.4851889683350365e-06,
+      "loss": 4.185,
+      "step": 1617
+    },
+    {
+      "epoch": 0.3003064351378958,
+      "grad_norm": 45.92570495605469,
+      "learning_rate": 5.985699693564862e-06,
+      "loss": 4.6367,
+      "step": 1764
+    },
+    {
+      "epoch": 0.32533197139938713,
+      "grad_norm": 13.566838264465332,
+      "learning_rate": 6.486210418794688e-06,
+      "loss": 4.3615,
+      "step": 1911
+    },
+    {
+      "epoch": 0.3503575076608784,
+      "grad_norm": 9.495999336242676,
+      "learning_rate": 6.986721144024515e-06,
+      "loss": 4.1791,
+      "step": 2058
+    },
+    {
+      "epoch": 0.37538304392236976,
+      "grad_norm": 32.735416412353516,
+      "learning_rate": 7.487231869254341e-06,
+      "loss": 4.1051,
+      "step": 2205
+    },
+    {
+      "epoch": 0.37538304392236976,
+      "eval_nli-pairs_loss": 3.2717113494873047,
+      "eval_nli-pairs_runtime": 4.0124,
+      "eval_nli-pairs_samples_per_second": 37.384,
+      "eval_nli-pairs_steps_per_second": 1.246,
+      "eval_sts-test_pearson_cosine": 0.6958570089637609,
+      "eval_sts-test_pearson_dot": 0.5824298957890577,
+      "eval_sts-test_pearson_euclidean": 0.6893962819387462,
+      "eval_sts-test_pearson_manhattan": 0.6993681181979946,
+      "eval_sts-test_pearson_max": 0.6993681181979946,
+      "eval_sts-test_spearman_cosine": 0.6652712160836801,
+      "eval_sts-test_spearman_dot": 0.5536505624407877,
+      "eval_sts-test_spearman_euclidean": 0.6659844314307678,
+      "eval_sts-test_spearman_manhattan": 0.675740852112121,
+      "eval_sts-test_spearman_max": 0.675740852112121,
+      "step": 2205
+    },
+    {
+      "epoch": 0.37538304392236976,
+      "eval_vitaminc-pairs_loss": 2.7197911739349365,
+      "eval_vitaminc-pairs_runtime": 2.1625,
+      "eval_vitaminc-pairs_samples_per_second": 69.365,
+      "eval_vitaminc-pairs_steps_per_second": 2.312,
+      "step": 2205
+    },
+    {
+      "epoch": 0.37538304392236976,
+      "eval_qnli-contrastive_loss": 9.638714790344238,
+      "eval_qnli-contrastive_runtime": 0.4877,
+      "eval_qnli-contrastive_samples_per_second": 307.567,
+      "eval_qnli-contrastive_steps_per_second": 10.252,
+      "step": 2205
+    },
+    {
+      "epoch": 0.37538304392236976,
+      "eval_scitail-pairs-qa_loss": 0.8106752634048462,
+      "eval_scitail-pairs-qa_runtime": 1.1588,
+      "eval_scitail-pairs-qa_samples_per_second": 129.449,
+      "eval_scitail-pairs-qa_steps_per_second": 4.315,
+      "step": 2205
+    },
+    {
+      "epoch": 0.37538304392236976,
+      "eval_scitail-pairs-pos_loss": 1.8894625902175903,
+      "eval_scitail-pairs-pos_runtime": 2.1181,
+      "eval_scitail-pairs-pos_samples_per_second": 70.817,
+      "eval_scitail-pairs-pos_steps_per_second": 2.361,
+      "step": 2205
+    },
+    {
+      "epoch": 0.37538304392236976,
+      "eval_xsum-pairs_loss": 2.262718439102173,
+      "eval_xsum-pairs_runtime": 2.2585,
+      "eval_xsum-pairs_samples_per_second": 66.416,
+      "eval_xsum-pairs_steps_per_second": 2.214,
+      "step": 2205
+    },
+    {
+      "epoch": 0.37538304392236976,
+      "eval_compression-pairs_loss": 1.4910633563995361,
+      "eval_compression-pairs_runtime": 0.4462,
+      "eval_compression-pairs_samples_per_second": 336.204,
+      "eval_compression-pairs_steps_per_second": 11.207,
+      "step": 2205
+    },
+    {
+      "epoch": 0.37538304392236976,
+      "eval_sciq_pairs_loss": 8.59740161895752,
+      "eval_sciq_pairs_runtime": 7.1845,
+      "eval_sciq_pairs_samples_per_second": 20.878,
+      "eval_sciq_pairs_steps_per_second": 0.696,
+      "step": 2205
+    },
+    {
+      "epoch": 0.37538304392236976,
+      "eval_qasc_pairs_loss": 8.103879928588867,
+      "eval_qasc_pairs_runtime": 2.0762,
+      "eval_qasc_pairs_samples_per_second": 72.246,
+      "eval_qasc_pairs_steps_per_second": 2.408,
+      "step": 2205
+    },
+    {
+      "epoch": 0.37538304392236976,
+      "eval_openbookqa_pairs_loss": 5.090969562530518,
+      "eval_openbookqa_pairs_runtime": 0.89,
+      "eval_openbookqa_pairs_samples_per_second": 115.726,
+      "eval_openbookqa_pairs_steps_per_second": 4.494,
+      "step": 2205
+    },
+    {
+      "epoch": 0.37538304392236976,
+      "eval_msmarco_pairs_loss": 3.9566943645477295,
+      "eval_msmarco_pairs_runtime": 2.8183,
+      "eval_msmarco_pairs_samples_per_second": 53.223,
+      "eval_msmarco_pairs_steps_per_second": 1.774,
+      "step": 2205
+    },
+    {
+      "epoch": 0.37538304392236976,
+      "eval_nq_pairs_loss": 4.009054183959961,
+      "eval_nq_pairs_runtime": 5.0219,
+      "eval_nq_pairs_samples_per_second": 29.869,
+      "eval_nq_pairs_steps_per_second": 0.996,
+      "step": 2205
+    },
+    {
+      "epoch": 0.37538304392236976,
+      "eval_trivia_pairs_loss": 4.286431312561035,
+      "eval_trivia_pairs_runtime": 9.4975,
+      "eval_trivia_pairs_samples_per_second": 15.794,
+      "eval_trivia_pairs_steps_per_second": 0.526,
+      "step": 2205
+    },
+    {
+      "epoch": 0.37538304392236976,
+      "eval_quora_pairs_loss": 1.123273491859436,
+      "eval_quora_pairs_runtime": 1.1487,
+      "eval_quora_pairs_samples_per_second": 130.586,
+      "eval_quora_pairs_steps_per_second": 4.353,
+      "step": 2205
+    },
+    {
+      "epoch": 0.37538304392236976,
+      "eval_gooaq_pairs_loss": 3.222414255142212,
+      "eval_gooaq_pairs_runtime": 2.0173,
+      "eval_gooaq_pairs_samples_per_second": 74.357,
+      "eval_gooaq_pairs_steps_per_second": 2.479,
+      "step": 2205
+    },
+    {
+      "epoch": 0.4004085801838611,
+      "grad_norm": 218.56105041503906,
+      "learning_rate": 7.987742594484168e-06,
+      "loss": 3.7674,
+      "step": 2352
+    },
+    {
+      "epoch": 0.4254341164453524,
+      "grad_norm": 27.877609252929688,
+      "learning_rate": 8.488253319713993e-06,
+      "loss": 3.8729,
+      "step": 2499
+    },
+    {
+      "epoch": 0.45045965270684374,
+      "grad_norm": 33.50013732910156,
+      "learning_rate": 8.988764044943822e-06,
+      "loss": 3.4527,
+      "step": 2646
+    },
+    {
+      "epoch": 0.475485188968335,
+      "grad_norm": 14.015911102294922,
+      "learning_rate": 9.489274770173647e-06,
+      "loss": 3.3545,
+      "step": 2793
+    }
+  ],
+  "logging_steps": 147,
+  "max_steps": 29370,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 2937,
+  "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-2937/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:298cfa7a9e669e98ab55937cac47ecfa89fb6a36f2afe18f46ba782a5f5bf5a4
+size 5624