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 sha256:4770037dab759e530db510172a4cd51db6a290126f848169cab57ebeb0ce58d5
+size 7077084396

checkpoint-157/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41c595a8caddad41035b435344d810959bb555186ba2819712849430331965c4
+size 3538506546

checkpoint-157/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a256f954d26eba151c11db3176e9c845b8a8ebbb18d898ee8878228a68fe02fa
+size 14244

checkpoint-157/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef5d11f4933a5b5fecf70dea7f3b6ded1296075809fa15e950301093e326189e
+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": 200.60667419433594,
+      "learning_rate": 2.129925452609159e-07,
+      "loss": 7.1882,
+      "step": 16
+    },
+    {
+      "epoch": 0.020460358056265986,
+      "grad_norm": 174.4742889404297,
+      "learning_rate": 5.324813631522898e-07,
+      "loss": 9.1489,
+      "step": 32
+    },
+    {
+      "epoch": 0.030690537084398978,
+      "grad_norm": 193.9903106689453,
+      "learning_rate": 8.732694355697552e-07,
+      "loss": 8.805,
+      "step": 48
+    },
+    {
+      "epoch": 0.04092071611253197,
+      "grad_norm": 3077.94775390625,
+      "learning_rate": 1.192758253461129e-06,
+      "loss": 5.7489,
+      "step": 64
+    },
+    {
+      "epoch": 0.05115089514066496,
+      "grad_norm": 80.12879943847656,
+      "learning_rate": 1.5335463258785943e-06,
+      "loss": 4.7163,
+      "step": 80
+    },
+    {
+      "epoch": 0.061381074168797956,
+      "grad_norm": 99.18599700927734,
+      "learning_rate": 1.8743343982960599e-06,
+      "loss": 3.176,
+      "step": 96
+    },
+    {
+      "epoch": 0.07161125319693094,
+      "grad_norm": 23.476715087890625,
+      "learning_rate": 2.1938232161874336e-06,
+      "loss": 2.034,
+      "step": 112
+    },
+    {
+      "epoch": 0.08184143222506395,
+      "grad_norm": 39.820777893066406,
+      "learning_rate": 2.534611288604899e-06,
+      "loss": 1.1278,
+      "step": 128
+    },
+    {
+      "epoch": 0.09207161125319693,
+      "grad_norm": 12.513270378112793,
+      "learning_rate": 2.8753993610223648e-06,
+      "loss": 0.7996,
+      "step": 144
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_Qnli-dev_cosine_accuracy": 0.662109375,
+      "eval_Qnli-dev_cosine_accuracy_threshold": 0.8656402826309204,
+      "eval_Qnli-dev_cosine_ap": 0.6654869266843996,
+      "eval_Qnli-dev_cosine_f1": 0.6504559270516718,
+      "eval_Qnli-dev_cosine_f1_threshold": 0.6888570785522461,
+      "eval_Qnli-dev_cosine_precision": 0.5071090047393365,
+      "eval_Qnli-dev_cosine_recall": 0.9067796610169492,
+      "eval_Qnli-dev_dot_accuracy": 0.654296875,
+      "eval_Qnli-dev_dot_accuracy_threshold": 905.306640625,
+      "eval_Qnli-dev_dot_ap": 0.6262830221036416,
+      "eval_Qnli-dev_dot_f1": 0.65625,
+      "eval_Qnli-dev_dot_f1_threshold": 810.4493408203125,
+      "eval_Qnli-dev_dot_precision": 0.5558823529411765,
+      "eval_Qnli-dev_dot_recall": 0.8008474576271186,
+      "eval_Qnli-dev_euclidean_accuracy": 0.662109375,
+      "eval_Qnli-dev_euclidean_accuracy_threshold": 17.05492401123047,
+      "eval_Qnli-dev_euclidean_ap": 0.6671756125841228,
+      "eval_Qnli-dev_euclidean_f1": 0.6495176848874598,
+      "eval_Qnli-dev_euclidean_f1_threshold": 23.73143768310547,
+      "eval_Qnli-dev_euclidean_precision": 0.5233160621761658,
+      "eval_Qnli-dev_euclidean_recall": 0.8559322033898306,
+      "eval_Qnli-dev_manhattan_accuracy": 0.65625,
+      "eval_Qnli-dev_manhattan_accuracy_threshold": 526.1962890625,
+      "eval_Qnli-dev_manhattan_ap": 0.6662986170174698,
+      "eval_Qnli-dev_manhattan_f1": 0.6487341772151899,
+      "eval_Qnli-dev_manhattan_f1_threshold": 748.320068359375,
+      "eval_Qnli-dev_manhattan_precision": 0.5176767676767676,
+      "eval_Qnli-dev_manhattan_recall": 0.8686440677966102,
+      "eval_Qnli-dev_max_accuracy": 0.662109375,
+      "eval_Qnli-dev_max_accuracy_threshold": 905.306640625,
+      "eval_Qnli-dev_max_ap": 0.6671756125841228,
+      "eval_Qnli-dev_max_f1": 0.65625,
+      "eval_Qnli-dev_max_f1_threshold": 810.4493408203125,
+      "eval_Qnli-dev_max_precision": 0.5558823529411765,
+      "eval_Qnli-dev_max_recall": 0.9067796610169492,
+      "eval_allNLI-dev_cosine_accuracy": 0.6875,
+      "eval_allNLI-dev_cosine_accuracy_threshold": 0.9388645887374878,
+      "eval_allNLI-dev_cosine_ap": 0.5213973850248246,
+      "eval_allNLI-dev_cosine_f1": 0.5590361445783132,
+      "eval_allNLI-dev_cosine_f1_threshold": 0.7874077558517456,
+      "eval_allNLI-dev_cosine_precision": 0.4793388429752066,
+      "eval_allNLI-dev_cosine_recall": 0.6705202312138728,
+      "eval_allNLI-dev_dot_accuracy": 0.6953125,
+      "eval_allNLI-dev_dot_accuracy_threshold": 942.6085205078125,
+      "eval_allNLI-dev_dot_ap": 0.520777376545363,
+      "eval_allNLI-dev_dot_f1": 0.5538461538461539,
+      "eval_allNLI-dev_dot_f1_threshold": 817.1332397460938,
+      "eval_allNLI-dev_dot_precision": 0.44680851063829785,
+      "eval_allNLI-dev_dot_recall": 0.7283236994219653,
+      "eval_allNLI-dev_euclidean_accuracy": 0.6875,
+      "eval_allNLI-dev_euclidean_accuracy_threshold": 12.643478393554688,
+      "eval_allNLI-dev_euclidean_ap": 0.518083458930424,
+      "eval_allNLI-dev_euclidean_f1": 0.5605381165919282,
+      "eval_allNLI-dev_euclidean_f1_threshold": 22.352760314941406,
+      "eval_allNLI-dev_euclidean_precision": 0.45787545787545786,
+      "eval_allNLI-dev_euclidean_recall": 0.7225433526011561,
+      "eval_allNLI-dev_manhattan_accuracy": 0.6875,
+      "eval_allNLI-dev_manhattan_accuracy_threshold": 392.8375549316406,
+      "eval_allNLI-dev_manhattan_ap": 0.5229585168795372,
+      "eval_allNLI-dev_manhattan_f1": 0.5590909090909091,
+      "eval_allNLI-dev_manhattan_f1_threshold": 690.5735473632812,
+      "eval_allNLI-dev_manhattan_precision": 0.4606741573033708,
+      "eval_allNLI-dev_manhattan_recall": 0.7109826589595376,
+      "eval_allNLI-dev_max_accuracy": 0.6953125,
+      "eval_allNLI-dev_max_accuracy_threshold": 942.6085205078125,
+      "eval_allNLI-dev_max_ap": 0.5229585168795372,
+      "eval_allNLI-dev_max_f1": 0.5605381165919282,
+      "eval_allNLI-dev_max_f1_threshold": 817.1332397460938,
+      "eval_allNLI-dev_max_precision": 0.4793388429752066,
+      "eval_allNLI-dev_max_recall": 0.7283236994219653,
+      "eval_sequential_score": 0.6671756125841228,
+      "eval_sts-test_pearson_cosine": 0.8718645025760672,
+      "eval_sts-test_pearson_dot": 0.8442027854618407,
+      "eval_sts-test_pearson_euclidean": 0.8902978035400368,
+      "eval_sts-test_pearson_manhattan": 0.8909390707647828,
+      "eval_sts-test_pearson_max": 0.8909390707647828,
+      "eval_sts-test_spearman_cosine": 0.8775905391512535,
+      "eval_sts-test_spearman_dot": 0.8282565695883292,
+      "eval_sts-test_spearman_euclidean": 0.8785767674497972,
+      "eval_sts-test_spearman_manhattan": 0.8796654313856657,
+      "eval_sts-test_spearman_max": 0.8796654313856657,
+      "eval_vitaminc-pairs_loss": 3.82141375541687,
+      "eval_vitaminc-pairs_runtime": 4.6321,
+      "eval_vitaminc-pairs_samples_per_second": 27.633,
+      "eval_vitaminc-pairs_steps_per_second": 0.216,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_negation-triplets_loss": 1.2526816129684448,
+      "eval_negation-triplets_runtime": 3.4008,
+      "eval_negation-triplets_samples_per_second": 37.638,
+      "eval_negation-triplets_steps_per_second": 0.294,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_scitail-pairs-pos_loss": 0.07802588492631912,
+      "eval_scitail-pairs-pos_runtime": 2.7191,
+      "eval_scitail-pairs-pos_samples_per_second": 47.075,
+      "eval_scitail-pairs-pos_steps_per_second": 0.368,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_scitail-pairs-qa_loss": 0.11051780730485916,
+      "eval_scitail-pairs-qa_runtime": 2.1249,
+      "eval_scitail-pairs-qa_samples_per_second": 60.237,
+      "eval_scitail-pairs-qa_steps_per_second": 0.471,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_xsum-pairs_loss": 0.1444225311279297,
+      "eval_xsum-pairs_runtime": 3.075,
+      "eval_xsum-pairs_samples_per_second": 41.626,
+      "eval_xsum-pairs_steps_per_second": 0.325,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_sciq_pairs_loss": 0.10900198668241501,
+      "eval_sciq_pairs_runtime": 4.6201,
+      "eval_sciq_pairs_samples_per_second": 27.705,
+      "eval_sciq_pairs_steps_per_second": 0.216,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_qasc_pairs_loss": 0.8441975116729736,
+      "eval_qasc_pairs_runtime": 2.0926,
+      "eval_qasc_pairs_samples_per_second": 61.168,
+      "eval_qasc_pairs_steps_per_second": 0.478,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_openbookqa_pairs_loss": 0.7852775454521179,
+      "eval_openbookqa_pairs_runtime": 2.2378,
+      "eval_openbookqa_pairs_samples_per_second": 57.198,
+      "eval_openbookqa_pairs_steps_per_second": 0.447,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_msmarco_pairs_loss": 0.7973570823669434,
+      "eval_msmarco_pairs_runtime": 2.2477,
+      "eval_msmarco_pairs_samples_per_second": 56.948,
+      "eval_msmarco_pairs_steps_per_second": 0.445,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_nq_pairs_loss": 1.149829387664795,
+      "eval_nq_pairs_runtime": 3.1982,
+      "eval_nq_pairs_samples_per_second": 40.023,
+      "eval_nq_pairs_steps_per_second": 0.313,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_trivia_pairs_loss": 0.46642398834228516,
+      "eval_trivia_pairs_runtime": 3.2778,
+      "eval_trivia_pairs_samples_per_second": 39.05,
+      "eval_trivia_pairs_steps_per_second": 0.305,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_gooaq_pairs_loss": 0.7757962346076965,
+      "eval_gooaq_pairs_runtime": 2.1385,
+      "eval_gooaq_pairs_samples_per_second": 59.856,
+      "eval_gooaq_pairs_steps_per_second": 0.468,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_paws-pos_loss": 0.03750575706362724,
+      "eval_paws-pos_runtime": 2.2521,
+      "eval_paws-pos_samples_per_second": 56.836,
+      "eval_paws-pos_steps_per_second": 0.444,
+      "step": 157
+    },
+    {
+      "epoch": 0.100383631713555,
+      "eval_global_dataset_loss": 0.48674729466438293,
+      "eval_global_dataset_runtime": 8.6002,
+      "eval_global_dataset_samples_per_second": 37.79,
+      "eval_global_dataset_steps_per_second": 0.349,
+      "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:ae5d47b05b44fe0990966324c4a681d83a347e47ed07c3ca3b6e4479e0e161a9
+size 5560