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 sha256:2ffdc419c0955c5b768dcbbe88faad4bf22cea53605c9fe4074ca9d083adb05c
+size 1130520122

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbe2fc34c5e1d1cc3880d11fddb3b85a8a35ab6f560ccd6126456a313344d43b
+size 565251810

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f687a4ba9f684d4913c83ab55045603e2534ca8151cfefbdd3db16a5515199a5
+size 14180

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": 17.846229553222656,
+      "learning_rate": 3.004181408813123e-06,
+      "loss": 4.4848,
+      "step": 471
+    },
+    {
+      "epoch": 0.1,
+      "eval_nli-pairs_loss": 3.227689504623413,
+      "eval_nli-pairs_runtime": 23.5758,
+      "eval_nli-pairs_samples_per_second": 288.77,
+      "eval_nli-pairs_steps_per_second": 18.069,
+      "step": 471
+    },
+    {
+      "epoch": 0.1,
+      "eval_scitail-pairs-pos_loss": 2.469686508178711,
+      "eval_scitail-pairs-pos_runtime": 5.4679,
+      "eval_scitail-pairs-pos_samples_per_second": 238.485,
+      "eval_scitail-pairs-pos_steps_per_second": 14.997,
+      "step": 471
+    },
+    {
+      "epoch": 0.1,
+      "eval_qnli-contrastive_loss": 3.3142430782318115,
+      "eval_qnli-contrastive_runtime": 15.7426,
+      "eval_qnli-contrastive_samples_per_second": 347.019,
+      "eval_qnli-contrastive_steps_per_second": 21.724,
+      "step": 471
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 29.59261703491211,
+      "learning_rate": 6.027661627532969e-06,
+      "loss": 2.6358,
+      "step": 942
+    },
+    {
+      "epoch": 0.2,
+      "eval_nli-pairs_loss": 1.5920209884643555,
+      "eval_nli-pairs_runtime": 23.3765,
+      "eval_nli-pairs_samples_per_second": 291.232,
+      "eval_nli-pairs_steps_per_second": 18.223,
+      "step": 942
+    },
+    {
+      "epoch": 0.2,
+      "eval_scitail-pairs-pos_loss": 0.9157330989837646,
+      "eval_scitail-pairs-pos_runtime": 5.4478,
+      "eval_scitail-pairs-pos_samples_per_second": 239.363,
+      "eval_scitail-pairs-pos_steps_per_second": 15.052,
+      "step": 942
+    },
+    {
+      "epoch": 0.2,
+      "eval_qnli-contrastive_loss": 2.663238763809204,
+      "eval_qnli-contrastive_runtime": 15.751,
+      "eval_qnli-contrastive_samples_per_second": 346.836,
+      "eval_qnli-contrastive_steps_per_second": 21.713,
+      "step": 942
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 24.539047241210938,
+      "learning_rate": 9.057574782888389e-06,
+      "loss": 1.7183,
+      "step": 1413
+    },
+    {
+      "epoch": 0.3,
+      "eval_nli-pairs_loss": 1.1536647081375122,
+      "eval_nli-pairs_runtime": 23.6115,
+      "eval_nli-pairs_samples_per_second": 288.335,
+      "eval_nli-pairs_steps_per_second": 18.042,
+      "step": 1413
+    },
+    {
+      "epoch": 0.3,
+      "eval_scitail-pairs-pos_loss": 0.7445429563522339,
+      "eval_scitail-pairs-pos_runtime": 5.3966,
+      "eval_scitail-pairs-pos_samples_per_second": 241.635,
+      "eval_scitail-pairs-pos_steps_per_second": 15.195,
+      "step": 1413
+    },
+    {
+      "epoch": 0.3,
+      "eval_qnli-contrastive_loss": 2.130812406539917,
+      "eval_qnli-contrastive_runtime": 15.7293,
+      "eval_qnli-contrastive_samples_per_second": 347.313,
+      "eval_qnli-contrastive_steps_per_second": 21.743,
+      "step": 1413
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 139.8046875,
+      "learning_rate": 1.208748793824381e-05,
+      "loss": 1.6114,
+      "step": 1884
+    },
+    {
+      "epoch": 0.4,
+      "eval_nli-pairs_loss": 0.8992123007774353,
+      "eval_nli-pairs_runtime": 23.6196,
+      "eval_nli-pairs_samples_per_second": 288.236,
+      "eval_nli-pairs_steps_per_second": 18.036,
+      "step": 1884
+    },
+    {
+      "epoch": 0.4,
+      "eval_scitail-pairs-pos_loss": 0.6193641424179077,
+      "eval_scitail-pairs-pos_runtime": 5.4024,
+      "eval_scitail-pairs-pos_samples_per_second": 241.376,
+      "eval_scitail-pairs-pos_steps_per_second": 15.179,
+      "step": 1884
+    },
+    {
+      "epoch": 0.4,
+      "eval_qnli-contrastive_loss": 1.6952241659164429,
+      "eval_qnli-contrastive_runtime": 15.7392,
+      "eval_qnli-contrastive_samples_per_second": 347.095,
+      "eval_qnli-contrastive_steps_per_second": 21.729,
+      "step": 1884
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.1193487644195557,
+      "learning_rate": 1.511740109359923e-05,
+      "loss": 1.5367,
+      "step": 2355
+    },
+    {
+      "epoch": 0.5,
+      "eval_nli-pairs_loss": 0.8112400770187378,
+      "eval_nli-pairs_runtime": 23.4573,
+      "eval_nli-pairs_samples_per_second": 290.23,
+      "eval_nli-pairs_steps_per_second": 18.161,
+      "step": 2355
+    },
+    {
+      "epoch": 0.5,
+      "eval_scitail-pairs-pos_loss": 0.6661093831062317,
+      "eval_scitail-pairs-pos_runtime": 5.3621,
+      "eval_scitail-pairs-pos_samples_per_second": 243.189,
+      "eval_scitail-pairs-pos_steps_per_second": 15.293,
+      "step": 2355
+    },
+    {
+      "epoch": 0.5,
+      "eval_qnli-contrastive_loss": 0.8697724938392639,
+      "eval_qnli-contrastive_runtime": 15.7092,
+      "eval_qnli-contrastive_samples_per_second": 347.759,
+      "eval_qnli-contrastive_steps_per_second": 21.771,
+      "step": 2355
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 8.693464279174805,
+      "learning_rate": 1.814731424895465e-05,
+      "loss": 1.1657,
+      "step": 2826
+    },
+    {
+      "epoch": 0.6,
+      "eval_nli-pairs_loss": 0.7330080270767212,
+      "eval_nli-pairs_runtime": 23.359,
+      "eval_nli-pairs_samples_per_second": 291.451,
+      "eval_nli-pairs_steps_per_second": 18.237,
+      "step": 2826
+    },
+    {
+      "epoch": 0.6,
+      "eval_scitail-pairs-pos_loss": 0.558278501033783,
+      "eval_scitail-pairs-pos_runtime": 5.3162,
+      "eval_scitail-pairs-pos_samples_per_second": 245.289,
+      "eval_scitail-pairs-pos_steps_per_second": 15.425,
+      "step": 2826
+    },
+    {
+      "epoch": 0.6,
+      "eval_qnli-contrastive_loss": 0.8414629101753235,
+      "eval_qnli-contrastive_runtime": 15.5773,
+      "eval_qnli-contrastive_samples_per_second": 350.703,
+      "eval_qnli-contrastive_steps_per_second": 21.955,
+      "step": 2826
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 20.00510025024414,
+      "learning_rate": 1.995853561663268e-05,
+      "loss": 1.2926,
+      "step": 3297
+    },
+    {
+      "epoch": 0.7,
+      "eval_nli-pairs_loss": 0.688292384147644,
+      "eval_nli-pairs_runtime": 23.1585,
+      "eval_nli-pairs_samples_per_second": 293.974,
+      "eval_nli-pairs_steps_per_second": 18.395,
+      "step": 3297
+    },
+    {
+      "epoch": 0.7,
+      "eval_scitail-pairs-pos_loss": 0.5283708572387695,
+      "eval_scitail-pairs-pos_runtime": 5.3322,
+      "eval_scitail-pairs-pos_samples_per_second": 244.552,
+      "eval_scitail-pairs-pos_steps_per_second": 15.378,
+      "step": 3297
+    },
+    {
+      "epoch": 0.7,
+      "eval_qnli-contrastive_loss": 0.5239661335945129,
+      "eval_qnli-contrastive_runtime": 15.5222,
+      "eval_qnli-contrastive_samples_per_second": 351.947,
+      "eval_qnli-contrastive_steps_per_second": 22.033,
+      "step": 3297
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 20.681690216064453,
+      "learning_rate": 1.9476312452068522e-05,
+      "loss": 1.1523,
+      "step": 3768
+    },
+    {
+      "epoch": 0.8,
+      "eval_nli-pairs_loss": 0.6775749325752258,
+      "eval_nli-pairs_runtime": 23.2425,
+      "eval_nli-pairs_samples_per_second": 292.912,
+      "eval_nli-pairs_steps_per_second": 18.328,
+      "step": 3768
+    },
+    {
+      "epoch": 0.8,
+      "eval_scitail-pairs-pos_loss": 0.4816366732120514,
+      "eval_scitail-pairs-pos_runtime": 5.2694,
+      "eval_scitail-pairs-pos_samples_per_second": 247.467,
+      "eval_scitail-pairs-pos_steps_per_second": 15.562,
+      "step": 3768
+    },
+    {
+      "epoch": 0.8,
+      "eval_qnli-contrastive_loss": 0.4342482388019562,
+      "eval_qnli-contrastive_runtime": 15.5335,
+      "eval_qnli-contrastive_samples_per_second": 351.691,
+      "eval_qnli-contrastive_steps_per_second": 22.017,
+      "step": 3768
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 12.640650749206543,
+      "learning_rate": 1.8475083492522773e-05,
+      "loss": 1.0387,
+      "step": 4239
+    },
+    {
+      "epoch": 0.9,
+      "eval_nli-pairs_loss": 0.6213383674621582,
+      "eval_nli-pairs_runtime": 23.1579,
+      "eval_nli-pairs_samples_per_second": 293.981,
+      "eval_nli-pairs_steps_per_second": 18.395,
+      "step": 4239
+    },
+    {
+      "epoch": 0.9,
+      "eval_scitail-pairs-pos_loss": 0.4603377878665924,
+      "eval_scitail-pairs-pos_runtime": 5.3009,
+      "eval_scitail-pairs-pos_samples_per_second": 245.997,
+      "eval_scitail-pairs-pos_steps_per_second": 15.469,
+      "step": 4239
+    },
+    {
+      "epoch": 0.9,
+      "eval_qnli-contrastive_loss": 0.3022189736366272,
+      "eval_qnli-contrastive_runtime": 15.5459,
+      "eval_qnli-contrastive_samples_per_second": 351.411,
+      "eval_qnli-contrastive_steps_per_second": 21.999,
+      "step": 4239
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 20.227073669433594,
+      "learning_rate": 1.701008869684049e-05,
+      "loss": 1.0356,
+      "step": 4710
+    },
+    {
+      "epoch": 1.0,
+      "eval_nli-pairs_loss": 0.6488831043243408,
+      "eval_nli-pairs_runtime": 23.1759,
+      "eval_nli-pairs_samples_per_second": 293.753,
+      "eval_nli-pairs_steps_per_second": 18.381,
+      "step": 4710
+    },
+    {
+      "epoch": 1.0,
+      "eval_scitail-pairs-pos_loss": 0.5449082255363464,
+      "eval_scitail-pairs-pos_runtime": 5.3602,
+      "eval_scitail-pairs-pos_samples_per_second": 243.276,
+      "eval_scitail-pairs-pos_steps_per_second": 15.298,
+      "step": 4710
+    },
+    {
+      "epoch": 1.0,
+      "eval_qnli-contrastive_loss": 0.1294127106666565,
+      "eval_qnli-contrastive_runtime": 15.5044,
+      "eval_qnli-contrastive_samples_per_second": 352.352,
+      "eval_qnli-contrastive_steps_per_second": 22.058,
+      "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:f77cf769359ac9f8d174c1dacb0dddd22a816e2ab9373ddf22d72bd785967730
+size 5624