Training in progress, step 157, checkpoint

checkpoint-157/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1536,
+  "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-157/added_tokens.json

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

checkpoint-157/config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "microsoft/deberta-v2-xlarge",
+  "architectures": [
+    "DebertaV2Model"
+  ],
+  "attention_head_size": 64,
+  "attention_probs_dropout_prob": 0.1,
+  "conv_act": "gelu",
+  "conv_kernel_size": 3,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "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": 24,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1536,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

checkpoint-157/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.42.4",
+    "pytorch": "2.4.0+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

checkpoint-157/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-157/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:970751869d1e18462d3655673e2b657004623d49ecc451880a95f3b48cbc779f
+size 7077084396

checkpoint-157/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dc2c4834244b6315111c4a019abb0ab1a499d5577bfe2354d2510df39055b5d
+size 3538506546

checkpoint-157/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:217a8eb2e19b6854e318dde48ade4d2c88a0398b46f04ccc02cecd7624d41835
+size 14244

checkpoint-157/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:119bbfa6d18a03fe776b5d27353da696f5212281fe1760948ef33a310ca9b89b
+size 1064

checkpoint-157/sentence_bert_config.json

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

checkpoint-157/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-157/spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5598d5e96f339a8d980c15f9afd405a2e5e1be7db41de3ed13b0f03fac1e8c17
+size 2447305

checkpoint-157/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-157/trainer_state.json

@@ -0,0 +1,289 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.100383631713555,
+  "eval_steps": 157,
+  "global_step": 157,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010230179028132993,
+      "grad_norm": 127.07197570800781,
+      "learning_rate": 2.129925452609159e-07,
+      "loss": 7.0465,
+      "step": 16
+    },
+    {
+      "epoch": 0.020460358056265986,
+      "grad_norm": 193.34689331054688,
+      "learning_rate": 5.537806176783813e-07,
+      "loss": 9.0583,
+      "step": 32
+    },
+    {
+      "epoch": 0.030690537084398978,
+      "grad_norm": 183.065185546875,
+      "learning_rate": 8.732694355697552e-07,
+      "loss": 8.6271,
+      "step": 48
+    },
+    {
+      "epoch": 0.04092071611253197,
+      "grad_norm": 150.517333984375,
+      "learning_rate": 1.2140575079872206e-06,
+      "loss": 5.6026,
+      "step": 64
+    },
+    {
+      "epoch": 0.05115089514066496,
+      "grad_norm": 78.38551330566406,
+      "learning_rate": 1.5335463258785943e-06,
+      "loss": 4.6908,
+      "step": 80
+    },
+    {
+      "epoch": 0.061381074168797956,
+      "grad_norm": 106.0997314453125,
+      "learning_rate": 1.8743343982960599e-06,
+      "loss": 3.1954,
+      "step": 96
+    },
+    {
+      "epoch": 0.07161125319693094,
+      "grad_norm": 47.50294876098633,
+      "learning_rate": 2.215122470713525e-06,
+      "loss": 2.1179,
+      "step": 112
+    },
+    {
+      "epoch": 0.08184143222506395,
+      "grad_norm": 24.581972122192383,
+      "learning_rate": 2.5559105431309904e-06,
+      "loss": 1.2636,
+      "step": 128
+    },
+    {
+      "epoch": 0.09207161125319693,
+      "grad_norm": 219.01101684570312,
+      "learning_rate": 2.8966986155484563e-06,
+      "loss": 0.8325,
+      "step": 144
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_Qnli-dev_cosine_accuracy": 0.65234375,
+      "eval_Qnli-dev_cosine_accuracy_threshold": 0.8284608125686646,
+      "eval_Qnli-dev_cosine_ap": 0.6663718886737695,
+      "eval_Qnli-dev_cosine_f1": 0.6469673405909797,
+      "eval_Qnli-dev_cosine_f1_threshold": 0.702437698841095,
+      "eval_Qnli-dev_cosine_precision": 0.5110565110565111,
+      "eval_Qnli-dev_cosine_recall": 0.8813559322033898,
+      "eval_Qnli-dev_dot_accuracy": 0.654296875,
+      "eval_Qnli-dev_dot_accuracy_threshold": 899.9195556640625,
+      "eval_Qnli-dev_dot_ap": 0.6265727343636489,
+      "eval_Qnli-dev_dot_f1": 0.6462480857580397,
+      "eval_Qnli-dev_dot_f1_threshold": 708.03076171875,
+      "eval_Qnli-dev_dot_precision": 0.5059952038369304,
+      "eval_Qnli-dev_dot_recall": 0.8940677966101694,
+      "eval_Qnli-dev_euclidean_accuracy": 0.654296875,
+      "eval_Qnli-dev_euclidean_accuracy_threshold": 17.465450286865234,
+      "eval_Qnli-dev_euclidean_ap": 0.6678841105609593,
+      "eval_Qnli-dev_euclidean_f1": 0.6485568760611206,
+      "eval_Qnli-dev_euclidean_f1_threshold": 22.50777244567871,
+      "eval_Qnli-dev_euclidean_precision": 0.5410764872521246,
+      "eval_Qnli-dev_euclidean_recall": 0.809322033898305,
+      "eval_Qnli-dev_manhattan_accuracy": 0.654296875,
+      "eval_Qnli-dev_manhattan_accuracy_threshold": 541.6007080078125,
+      "eval_Qnli-dev_manhattan_ap": 0.6671352135215549,
+      "eval_Qnli-dev_manhattan_f1": 0.6472602739726028,
+      "eval_Qnli-dev_manhattan_f1_threshold": 693.766845703125,
+      "eval_Qnli-dev_manhattan_precision": 0.5431034482758621,
+      "eval_Qnli-dev_manhattan_recall": 0.8008474576271186,
+      "eval_Qnli-dev_max_accuracy": 0.654296875,
+      "eval_Qnli-dev_max_accuracy_threshold": 899.9195556640625,
+      "eval_Qnli-dev_max_ap": 0.6678841105609593,
+      "eval_Qnli-dev_max_f1": 0.6485568760611206,
+      "eval_Qnli-dev_max_f1_threshold": 708.03076171875,
+      "eval_Qnli-dev_max_precision": 0.5431034482758621,
+      "eval_Qnli-dev_max_recall": 0.8940677966101694,
+      "eval_allNLI-dev_cosine_accuracy": 0.69140625,
+      "eval_allNLI-dev_cosine_accuracy_threshold": 0.8886671662330627,
+      "eval_allNLI-dev_cosine_ap": 0.5184375875165067,
+      "eval_allNLI-dev_cosine_f1": 0.5584415584415584,
+      "eval_allNLI-dev_cosine_f1_threshold": 0.7475587725639343,
+      "eval_allNLI-dev_cosine_precision": 0.4463667820069204,
+      "eval_allNLI-dev_cosine_recall": 0.7456647398843931,
+      "eval_allNLI-dev_dot_accuracy": 0.689453125,
+      "eval_allNLI-dev_dot_accuracy_threshold": 935.1204223632812,
+      "eval_allNLI-dev_dot_ap": 0.4904119502439996,
+      "eval_allNLI-dev_dot_f1": 0.5509259259259259,
+      "eval_allNLI-dev_dot_f1_threshold": 803.4815673828125,
+      "eval_allNLI-dev_dot_precision": 0.4594594594594595,
+      "eval_allNLI-dev_dot_recall": 0.6878612716763006,
+      "eval_allNLI-dev_euclidean_accuracy": 0.6953125,
+      "eval_allNLI-dev_euclidean_accuracy_threshold": 15.452061653137207,
+      "eval_allNLI-dev_euclidean_ap": 0.5162188247814465,
+      "eval_allNLI-dev_euclidean_f1": 0.5557986870897156,
+      "eval_allNLI-dev_euclidean_f1_threshold": 22.695791244506836,
+      "eval_allNLI-dev_euclidean_precision": 0.4471830985915493,
+      "eval_allNLI-dev_euclidean_recall": 0.7341040462427746,
+      "eval_allNLI-dev_manhattan_accuracy": 0.693359375,
+      "eval_allNLI-dev_manhattan_accuracy_threshold": 484.3291015625,
+      "eval_allNLI-dev_manhattan_ap": 0.5171097761848361,
+      "eval_allNLI-dev_manhattan_f1": 0.5550660792951542,
+      "eval_allNLI-dev_manhattan_f1_threshold": 707.2572631835938,
+      "eval_allNLI-dev_manhattan_precision": 0.4483985765124555,
+      "eval_allNLI-dev_manhattan_recall": 0.7283236994219653,
+      "eval_allNLI-dev_max_accuracy": 0.6953125,
+      "eval_allNLI-dev_max_accuracy_threshold": 935.1204223632812,
+      "eval_allNLI-dev_max_ap": 0.5184375875165067,
+      "eval_allNLI-dev_max_f1": 0.5584415584415584,
+      "eval_allNLI-dev_max_f1_threshold": 803.4815673828125,
+      "eval_allNLI-dev_max_precision": 0.4594594594594595,
+      "eval_allNLI-dev_max_recall": 0.7456647398843931,
+      "eval_sequential_score": 0.6678841105609593,
+      "eval_sts-test_pearson_cosine": 0.8691399425075377,
+      "eval_sts-test_pearson_dot": 0.84633945645717,
+      "eval_sts-test_pearson_euclidean": 0.8863973274037125,
+      "eval_sts-test_pearson_manhattan": 0.887205994467606,
+      "eval_sts-test_pearson_max": 0.887205994467606,
+      "eval_sts-test_spearman_cosine": 0.8753474716765325,
+      "eval_sts-test_spearman_dot": 0.8345210301629428,
+      "eval_sts-test_spearman_euclidean": 0.8755160049269324,
+      "eval_sts-test_spearman_manhattan": 0.8763851191744148,
+      "eval_sts-test_spearman_max": 0.8763851191744148,
+      "eval_vitaminc-pairs_loss": 3.764756917953491,
+      "eval_vitaminc-pairs_runtime": 4.7024,
+      "eval_vitaminc-pairs_samples_per_second": 27.22,
+      "eval_vitaminc-pairs_steps_per_second": 0.213,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_negation-triplets_loss": 1.4374932050704956,
+      "eval_negation-triplets_runtime": 3.2218,
+      "eval_negation-triplets_samples_per_second": 39.73,
+      "eval_negation-triplets_steps_per_second": 0.31,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_scitail-pairs-pos_loss": 0.07158112525939941,
+      "eval_scitail-pairs-pos_runtime": 2.7614,
+      "eval_scitail-pairs-pos_samples_per_second": 46.353,
+      "eval_scitail-pairs-pos_steps_per_second": 0.362,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_scitail-pairs-qa_loss": 0.11121156811714172,
+      "eval_scitail-pairs-qa_runtime": 2.2983,
+      "eval_scitail-pairs-qa_samples_per_second": 55.694,
+      "eval_scitail-pairs-qa_steps_per_second": 0.435,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_xsum-pairs_loss": 0.28410428762435913,
+      "eval_xsum-pairs_runtime": 3.1437,
+      "eval_xsum-pairs_samples_per_second": 40.717,
+      "eval_xsum-pairs_steps_per_second": 0.318,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_sciq_pairs_loss": 0.15557295083999634,
+      "eval_sciq_pairs_runtime": 4.4086,
+      "eval_sciq_pairs_samples_per_second": 29.034,
+      "eval_sciq_pairs_steps_per_second": 0.227,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_qasc_pairs_loss": 0.9191333651542664,
+      "eval_qasc_pairs_runtime": 2.1323,
+      "eval_qasc_pairs_samples_per_second": 60.03,
+      "eval_qasc_pairs_steps_per_second": 0.469,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_openbookqa_pairs_loss": 0.8187942504882812,
+      "eval_openbookqa_pairs_runtime": 2.2771,
+      "eval_openbookqa_pairs_samples_per_second": 56.213,
+      "eval_openbookqa_pairs_steps_per_second": 0.439,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_msmarco_pairs_loss": 0.6015267372131348,
+      "eval_msmarco_pairs_runtime": 2.2879,
+      "eval_msmarco_pairs_samples_per_second": 55.946,
+      "eval_msmarco_pairs_steps_per_second": 0.437,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_nq_pairs_loss": 0.9822638630867004,
+      "eval_nq_pairs_runtime": 3.3732,
+      "eval_nq_pairs_samples_per_second": 37.946,
+      "eval_nq_pairs_steps_per_second": 0.296,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_trivia_pairs_loss": 0.3045535683631897,
+      "eval_trivia_pairs_runtime": 3.3462,
+      "eval_trivia_pairs_samples_per_second": 38.253,
+      "eval_trivia_pairs_steps_per_second": 0.299,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_gooaq_pairs_loss": 0.4534245729446411,
+      "eval_gooaq_pairs_runtime": 2.1775,
+      "eval_gooaq_pairs_samples_per_second": 58.783,
+      "eval_gooaq_pairs_steps_per_second": 0.459,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_paws-pos_loss": 0.03816518932580948,
+      "eval_paws-pos_runtime": 2.3035,
+      "eval_paws-pos_samples_per_second": 55.567,
+      "eval_paws-pos_steps_per_second": 0.434,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_global_dataset_loss": 0.4413764476776123,
+      "eval_global_dataset_runtime": 8.8968,
+      "eval_global_dataset_samples_per_second": 36.53,
+      "eval_global_dataset_steps_per_second": 0.337,
+      "step": 157
+    }
+  ],
+  "logging_steps": 16,
+  "max_steps": 3128,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 157,
+  "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": 64,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-157/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d523e4a0d91ff1db0041a8e72663ad04f154bb6b99fc03ec758da489cf961449
+size 5560