Training in progress, epoch 1, checkpoint

last-checkpoint/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
+}

last-checkpoint/added_tokens.json

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

last-checkpoint/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
+}

last-checkpoint/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
+}

last-checkpoint/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"
+  }
+]

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24a991a022791dbad68bcccfc1a822f0a523b0d0033cb55ebbbb7278fa749813
+size 1130520122

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2ad0a254872f555e16b4825539b2ed51a358095478594397a27f095a144279b
+size 565251810

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c341d87b21e7e32706eb595f0f035e1e0247fe56c8c298f72c6e286fd8ab0e20
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:072f295cd9400d44a23f01cc82ad8c9b8b89be4ef3aba1d3b8e750e9883aec90
+size 1064

last-checkpoint/sentence_bert_config.json

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

last-checkpoint/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
+  }
+}

last-checkpoint/spm.model

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

last-checkpoint/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"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,343 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 471,
+  "global_step": 4710,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 23.178159713745117,
+      "learning_rate": 3.004181408813123e-06,
+      "loss": 3.3296,
+      "step": 471
+    },
+    {
+      "epoch": 0.1,
+      "eval_nli-pairs_loss": 1.8879033327102661,
+      "eval_nli-pairs_runtime": 14.5841,
+      "eval_nli-pairs_samples_per_second": 466.81,
+      "eval_nli-pairs_steps_per_second": 29.21,
+      "step": 471
+    },
+    {
+      "epoch": 0.1,
+      "eval_scitail-pairs-pos_loss": 1.3438984155654907,
+      "eval_scitail-pairs-pos_runtime": 3.3055,
+      "eval_scitail-pairs-pos_samples_per_second": 394.499,
+      "eval_scitail-pairs-pos_steps_per_second": 24.807,
+      "step": 471
+    },
+    {
+      "epoch": 0.1,
+      "eval_qnli-contrastive_loss": 2.2597947120666504,
+      "eval_qnli-contrastive_runtime": 15.4075,
+      "eval_qnli-contrastive_samples_per_second": 354.567,
+      "eval_qnli-contrastive_steps_per_second": 22.197,
+      "step": 471
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 20.00649070739746,
+      "learning_rate": 6.021228690897395e-06,
+      "loss": 1.8704,
+      "step": 942
+    },
+    {
+      "epoch": 0.2,
+      "eval_nli-pairs_loss": 0.9545981884002686,
+      "eval_nli-pairs_runtime": 14.5243,
+      "eval_nli-pairs_samples_per_second": 468.731,
+      "eval_nli-pairs_steps_per_second": 29.33,
+      "step": 942
+    },
+    {
+      "epoch": 0.2,
+      "eval_scitail-pairs-pos_loss": 0.5628724098205566,
+      "eval_scitail-pairs-pos_runtime": 3.3029,
+      "eval_scitail-pairs-pos_samples_per_second": 394.801,
+      "eval_scitail-pairs-pos_steps_per_second": 24.826,
+      "step": 942
+    },
+    {
+      "epoch": 0.2,
+      "eval_qnli-contrastive_loss": 1.840173602104187,
+      "eval_qnli-contrastive_runtime": 15.4134,
+      "eval_qnli-contrastive_samples_per_second": 354.433,
+      "eval_qnli-contrastive_steps_per_second": 22.189,
+      "step": 942
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 14.465508460998535,
+      "learning_rate": 9.051141846252816e-06,
+      "loss": 1.2621,
+      "step": 1413
+    },
+    {
+      "epoch": 0.3,
+      "eval_nli-pairs_loss": 0.715168297290802,
+      "eval_nli-pairs_runtime": 14.4626,
+      "eval_nli-pairs_samples_per_second": 470.731,
+      "eval_nli-pairs_steps_per_second": 29.455,
+      "step": 1413
+    },
+    {
+      "epoch": 0.3,
+      "eval_scitail-pairs-pos_loss": 0.45529162883758545,
+      "eval_scitail-pairs-pos_runtime": 3.3513,
+      "eval_scitail-pairs-pos_samples_per_second": 389.098,
+      "eval_scitail-pairs-pos_steps_per_second": 24.468,
+      "step": 1413
+    },
+    {
+      "epoch": 0.3,
+      "eval_qnli-contrastive_loss": 1.388743281364441,
+      "eval_qnli-contrastive_runtime": 15.4261,
+      "eval_qnli-contrastive_samples_per_second": 354.139,
+      "eval_qnli-contrastive_steps_per_second": 22.17,
+      "step": 1413
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 164.2409210205078,
+      "learning_rate": 1.2081055001608235e-05,
+      "loss": 1.2512,
+      "step": 1884
+    },
+    {
+      "epoch": 0.4,
+      "eval_nli-pairs_loss": 0.5274420976638794,
+      "eval_nli-pairs_runtime": 14.4658,
+      "eval_nli-pairs_samples_per_second": 470.628,
+      "eval_nli-pairs_steps_per_second": 29.449,
+      "step": 1884
+    },
+    {
+      "epoch": 0.4,
+      "eval_scitail-pairs-pos_loss": 0.3621281683444977,
+      "eval_scitail-pairs-pos_runtime": 3.3054,
+      "eval_scitail-pairs-pos_samples_per_second": 394.502,
+      "eval_scitail-pairs-pos_steps_per_second": 24.808,
+      "step": 1884
+    },
+    {
+      "epoch": 0.4,
+      "eval_qnli-contrastive_loss": 0.8418154120445251,
+      "eval_qnli-contrastive_runtime": 15.4336,
+      "eval_qnli-contrastive_samples_per_second": 353.967,
+      "eval_qnli-contrastive_steps_per_second": 22.159,
+      "step": 1884
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.1174694299697876,
+      "learning_rate": 1.5110968156963654e-05,
+      "loss": 1.1724,
+      "step": 2355
+    },
+    {
+      "epoch": 0.5,
+      "eval_nli-pairs_loss": 0.49269717931747437,
+      "eval_nli-pairs_runtime": 14.6969,
+      "eval_nli-pairs_samples_per_second": 463.228,
+      "eval_nli-pairs_steps_per_second": 28.986,
+      "step": 2355
+    },
+    {
+      "epoch": 0.5,
+      "eval_scitail-pairs-pos_loss": 0.39243820309638977,
+      "eval_scitail-pairs-pos_runtime": 3.3462,
+      "eval_scitail-pairs-pos_samples_per_second": 389.699,
+      "eval_scitail-pairs-pos_steps_per_second": 24.506,
+      "step": 2355
+    },
+    {
+      "epoch": 0.5,
+      "eval_qnli-contrastive_loss": 0.14236953854560852,
+      "eval_qnli-contrastive_runtime": 15.7375,
+      "eval_qnli-contrastive_samples_per_second": 347.133,
+      "eval_qnli-contrastive_steps_per_second": 21.732,
+      "step": 2355
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 8.20367431640625,
+      "learning_rate": 1.8140881312319075e-05,
+      "loss": 0.9036,
+      "step": 2826
+    },
+    {
+      "epoch": 0.6,
+      "eval_nli-pairs_loss": 0.46205422282218933,
+      "eval_nli-pairs_runtime": 14.6645,
+      "eval_nli-pairs_samples_per_second": 464.249,
+      "eval_nli-pairs_steps_per_second": 29.05,
+      "step": 2826
+    },
+    {
+      "epoch": 0.6,
+      "eval_scitail-pairs-pos_loss": 0.37769660353660583,
+      "eval_scitail-pairs-pos_runtime": 3.3324,
+      "eval_scitail-pairs-pos_samples_per_second": 391.314,
+      "eval_scitail-pairs-pos_steps_per_second": 24.607,
+      "step": 2826
+    },
+    {
+      "epoch": 0.6,
+      "eval_qnli-contrastive_loss": 0.3408704996109009,
+      "eval_qnli-contrastive_runtime": 15.4886,
+      "eval_qnli-contrastive_samples_per_second": 352.711,
+      "eval_qnli-contrastive_steps_per_second": 22.081,
+      "step": 2826
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 13.231554985046387,
+      "learning_rate": 1.995898723197675e-05,
+      "loss": 1.0374,
+      "step": 3297
+    },
+    {
+      "epoch": 0.7,
+      "eval_nli-pairs_loss": 0.41105732321739197,
+      "eval_nli-pairs_runtime": 14.6153,
+      "eval_nli-pairs_samples_per_second": 465.813,
+      "eval_nli-pairs_steps_per_second": 29.148,
+      "step": 3297
+    },
+    {
+      "epoch": 0.7,
+      "eval_scitail-pairs-pos_loss": 0.3417491614818573,
+      "eval_scitail-pairs-pos_runtime": 3.3206,
+      "eval_scitail-pairs-pos_samples_per_second": 392.697,
+      "eval_scitail-pairs-pos_steps_per_second": 24.694,
+      "step": 3297
+    },
+    {
+      "epoch": 0.7,
+      "eval_qnli-contrastive_loss": 0.21254216134548187,
+      "eval_qnli-contrastive_runtime": 15.5347,
+      "eval_qnli-contrastive_samples_per_second": 351.664,
+      "eval_qnli-contrastive_steps_per_second": 22.015,
+      "step": 3297
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 23.010765075683594,
+      "learning_rate": 1.9476312452068522e-05,
+      "loss": 0.9259,
+      "step": 3768
+    },
+    {
+      "epoch": 0.8,
+      "eval_nli-pairs_loss": 0.3852880597114563,
+      "eval_nli-pairs_runtime": 14.5431,
+      "eval_nli-pairs_samples_per_second": 468.125,
+      "eval_nli-pairs_steps_per_second": 29.292,
+      "step": 3768
+    },
+    {
+      "epoch": 0.8,
+      "eval_scitail-pairs-pos_loss": 0.2818955183029175,
+      "eval_scitail-pairs-pos_runtime": 3.3663,
+      "eval_scitail-pairs-pos_samples_per_second": 387.364,
+      "eval_scitail-pairs-pos_steps_per_second": 24.359,
+      "step": 3768
+    },
+    {
+      "epoch": 0.8,
+      "eval_qnli-contrastive_loss": 0.16461187601089478,
+      "eval_qnli-contrastive_runtime": 15.6023,
+      "eval_qnli-contrastive_samples_per_second": 350.141,
+      "eval_qnli-contrastive_steps_per_second": 21.92,
+      "step": 3768
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 4.332469940185547,
+      "learning_rate": 1.8475083492522773e-05,
+      "loss": 0.8709,
+      "step": 4239
+    },
+    {
+      "epoch": 0.9,
+      "eval_nli-pairs_loss": 0.37486234307289124,
+      "eval_nli-pairs_runtime": 14.7406,
+      "eval_nli-pairs_samples_per_second": 461.852,
+      "eval_nli-pairs_steps_per_second": 28.9,
+      "step": 4239
+    },
+    {
+      "epoch": 0.9,
+      "eval_scitail-pairs-pos_loss": 0.29122474789619446,
+      "eval_scitail-pairs-pos_runtime": 3.5504,
+      "eval_scitail-pairs-pos_samples_per_second": 367.283,
+      "eval_scitail-pairs-pos_steps_per_second": 23.096,
+      "step": 4239
+    },
+    {
+      "epoch": 0.9,
+      "eval_qnli-contrastive_loss": 0.11566311866044998,
+      "eval_qnli-contrastive_runtime": 15.6925,
+      "eval_qnli-contrastive_samples_per_second": 348.129,
+      "eval_qnli-contrastive_steps_per_second": 21.794,
+      "step": 4239
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 26.054088592529297,
+      "learning_rate": 1.701008869684049e-05,
+      "loss": 0.8686,
+      "step": 4710
+    },
+    {
+      "epoch": 1.0,
+      "eval_nli-pairs_loss": 0.36355406045913696,
+      "eval_nli-pairs_runtime": 14.5214,
+      "eval_nli-pairs_samples_per_second": 468.824,
+      "eval_nli-pairs_steps_per_second": 29.336,
+      "step": 4710
+    },
+    {
+      "epoch": 1.0,
+      "eval_scitail-pairs-pos_loss": 0.3108903765678406,
+      "eval_scitail-pairs-pos_runtime": 3.3842,
+      "eval_scitail-pairs-pos_samples_per_second": 385.319,
+      "eval_scitail-pairs-pos_steps_per_second": 24.23,
+      "step": 4710
+    },
+    {
+      "epoch": 1.0,
+      "eval_qnli-contrastive_loss": 0.09614822268486023,
+      "eval_qnli-contrastive_runtime": 15.7192,
+      "eval_qnli-contrastive_samples_per_second": 347.537,
+      "eval_qnli-contrastive_steps_per_second": 21.757,
+      "step": 4710
+    }
+  ],
+  "logging_steps": 471,
+  "max_steps": 9420,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 4710,
+  "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": 28,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:560933d9c6eb8f6d338a68068ece75f7a5e1161e1e11dd62ae04fb4abb096493
+size 5624