Training in progress, step 871, 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 sha256:839951a3b458c681d39df9cfbf4fb7e62a90ce63309b1ee342bf3eb505abfa77
+size 1130520122

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80497c471d66cac6dd87976e0401d86234ba52917f323c73fec20815ae2f5803
+size 565251810

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2d8681747f3a889afbeb55310a23e4914bfed074d6b3f1c0962b05b54813ee1
+size 14180

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6ae73bfc00f33c333c3cce2cc75ab33f53fec40d952a5013f435bd0955b417a
+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 +1,240 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.25021545532892847,
+  "eval_steps": 88,
+  "global_step": 871,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02528009192760701,
+      "grad_norm": 8.922952651977539,
+      "learning_rate": 1.5143603133159272e-06,
+      "loss": 7.5831,
+      "step": 88
+    },
+    {
+      "epoch": 0.02528009192760701,
+      "eval_nli-pairs_loss": 6.087147235870361,
+      "eval_nli-pairs_runtime": 38.8312,
+      "eval_nli-pairs_samples_per_second": 175.323,
+      "eval_nli-pairs_steps_per_second": 10.971,
+      "step": 88
+    },
+    {
+      "epoch": 0.02528009192760701,
+      "eval_scitail-pairs-pos_loss": 3.7706263065338135,
+      "eval_scitail-pairs-pos_runtime": 8.0579,
+      "eval_scitail-pairs-pos_samples_per_second": 161.829,
+      "eval_scitail-pairs-pos_steps_per_second": 10.176,
+      "step": 88
+    },
+    {
+      "epoch": 0.05056018385521402,
+      "grad_norm": 4.343107223510742,
+      "learning_rate": 3.046127067014796e-06,
+      "loss": 6.7273,
+      "step": 176
+    },
+    {
+      "epoch": 0.05056018385521402,
+      "eval_nli-pairs_loss": 5.9269890785217285,
+      "eval_nli-pairs_runtime": 38.115,
+      "eval_nli-pairs_samples_per_second": 178.618,
+      "eval_nli-pairs_steps_per_second": 11.177,
+      "step": 176
+    },
+    {
+      "epoch": 0.05056018385521402,
+      "eval_scitail-pairs-pos_loss": 3.7313730716705322,
+      "eval_scitail-pairs-pos_runtime": 7.805,
+      "eval_scitail-pairs-pos_samples_per_second": 167.071,
+      "eval_scitail-pairs-pos_steps_per_second": 10.506,
+      "step": 176
+    },
+    {
+      "epoch": 0.07584027578282103,
+      "grad_norm": 16.866355895996094,
+      "learning_rate": 4.577893820713664e-06,
+      "loss": 5.9091,
+      "step": 264
+    },
+    {
+      "epoch": 0.07584027578282103,
+      "eval_nli-pairs_loss": 4.598970890045166,
+      "eval_nli-pairs_runtime": 38.0313,
+      "eval_nli-pairs_samples_per_second": 179.01,
+      "eval_nli-pairs_steps_per_second": 11.201,
+      "step": 264
+    },
+    {
+      "epoch": 0.07584027578282103,
+      "eval_scitail-pairs-pos_loss": 2.8227546215057373,
+      "eval_scitail-pairs-pos_runtime": 7.7737,
+      "eval_scitail-pairs-pos_samples_per_second": 167.746,
+      "eval_scitail-pairs-pos_steps_per_second": 10.548,
+      "step": 264
+    },
+    {
+      "epoch": 0.10112036771042804,
+      "grad_norm": 13.346307754516602,
+      "learning_rate": 6.1096605744125335e-06,
+      "loss": 4.2126,
+      "step": 352
+    },
+    {
+      "epoch": 0.10112036771042804,
+      "eval_nli-pairs_loss": 3.062242269515991,
+      "eval_nli-pairs_runtime": 38.0333,
+      "eval_nli-pairs_samples_per_second": 179.001,
+      "eval_nli-pairs_steps_per_second": 11.201,
+      "step": 352
+    },
+    {
+      "epoch": 0.10112036771042804,
+      "eval_scitail-pairs-pos_loss": 1.792738437652588,
+      "eval_scitail-pairs-pos_runtime": 7.7584,
+      "eval_scitail-pairs-pos_samples_per_second": 168.075,
+      "eval_scitail-pairs-pos_steps_per_second": 10.569,
+      "step": 352
+    },
+    {
+      "epoch": 0.12640045963803503,
+      "grad_norm": 54.115352630615234,
+      "learning_rate": 7.641427328111402e-06,
+      "loss": 3.0055,
+      "step": 440
+    },
+    {
+      "epoch": 0.12640045963803503,
+      "eval_nli-pairs_loss": 2.324322462081909,
+      "eval_nli-pairs_runtime": 38.4568,
+      "eval_nli-pairs_samples_per_second": 177.03,
+      "eval_nli-pairs_steps_per_second": 11.077,
+      "step": 440
+    },
+    {
+      "epoch": 0.12640045963803503,
+      "eval_scitail-pairs-pos_loss": 1.1716609001159668,
+      "eval_scitail-pairs-pos_runtime": 7.7757,
+      "eval_scitail-pairs-pos_samples_per_second": 167.701,
+      "eval_scitail-pairs-pos_steps_per_second": 10.546,
+      "step": 440
+    },
+    {
+      "epoch": 0.15168055156564206,
+      "grad_norm": 11.725848197937012,
+      "learning_rate": 9.155787641427328e-06,
+      "loss": 2.4462,
+      "step": 528
+    },
+    {
+      "epoch": 0.15168055156564206,
+      "eval_nli-pairs_loss": 1.9132238626480103,
+      "eval_nli-pairs_runtime": 38.209,
+      "eval_nli-pairs_samples_per_second": 178.178,
+      "eval_nli-pairs_steps_per_second": 11.149,
+      "step": 528
+    },
+    {
+      "epoch": 0.15168055156564206,
+      "eval_scitail-pairs-pos_loss": 1.1093688011169434,
+      "eval_scitail-pairs-pos_runtime": 7.8235,
+      "eval_scitail-pairs-pos_samples_per_second": 166.678,
+      "eval_scitail-pairs-pos_steps_per_second": 10.481,
+      "step": 528
+    },
+    {
+      "epoch": 0.17696064349324905,
+      "grad_norm": 11.779143333435059,
+      "learning_rate": 1.06875543951262e-05,
+      "loss": 2.0925,
+      "step": 616
+    },
+    {
+      "epoch": 0.17696064349324905,
+      "eval_nli-pairs_loss": 1.6520535945892334,
+      "eval_nli-pairs_runtime": 38.3278,
+      "eval_nli-pairs_samples_per_second": 177.626,
+      "eval_nli-pairs_steps_per_second": 11.115,
+      "step": 616
+    },
+    {
+      "epoch": 0.17696064349324905,
+      "eval_scitail-pairs-pos_loss": 0.9030593037605286,
+      "eval_scitail-pairs-pos_runtime": 7.8736,
+      "eval_scitail-pairs-pos_samples_per_second": 165.617,
+      "eval_scitail-pairs-pos_steps_per_second": 10.415,
+      "step": 616
+    },
+    {
+      "epoch": 0.20224073542085608,
+      "grad_norm": 12.419939994812012,
+      "learning_rate": 1.2219321148825067e-05,
+      "loss": 2.0016,
+      "step": 704
+    },
+    {
+      "epoch": 0.20224073542085608,
+      "eval_nli-pairs_loss": 1.4989789724349976,
+      "eval_nli-pairs_runtime": 38.1814,
+      "eval_nli-pairs_samples_per_second": 178.307,
+      "eval_nli-pairs_steps_per_second": 11.157,
+      "step": 704
+    },
+    {
+      "epoch": 0.20224073542085608,
+      "eval_scitail-pairs-pos_loss": 0.8707832098007202,
+      "eval_scitail-pairs-pos_runtime": 7.8875,
+      "eval_scitail-pairs-pos_samples_per_second": 165.324,
+      "eval_scitail-pairs-pos_steps_per_second": 10.396,
+      "step": 704
+    },
+    {
+      "epoch": 0.22752082734846307,
+      "grad_norm": 9.998259544372559,
+      "learning_rate": 1.3751087902523935e-05,
+      "loss": 1.7607,
+      "step": 792
+    },
+    {
+      "epoch": 0.22752082734846307,
+      "eval_nli-pairs_loss": 1.410436749458313,
+      "eval_nli-pairs_runtime": 38.5476,
+      "eval_nli-pairs_samples_per_second": 176.613,
+      "eval_nli-pairs_steps_per_second": 11.051,
+      "step": 792
+    },
+    {
+      "epoch": 0.22752082734846307,
+      "eval_scitail-pairs-pos_loss": 0.8443933129310608,
+      "eval_scitail-pairs-pos_runtime": 8.0485,
+      "eval_scitail-pairs-pos_samples_per_second": 162.017,
+      "eval_scitail-pairs-pos_steps_per_second": 10.188,
+      "step": 792
+    }
+  ],
+  "logging_steps": 88,
+  "max_steps": 3481,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 871,
+  "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": 250,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:716b7538183913799600e309b33191e368abe08cd990c4f2df8173b2af1c7a74
+size 5624