Training in progress, step 736, 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": "bobox/DeBERTaV3-small-GeneralSentenceTransformer-v3-step1",
+  "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:af5733a12078cfeb88604ef7c20830be60ed202d924e9c8893b3696692b3fa50
+size 1130520122

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68a5bd0246f8098e26752dc46d3cc477b289ce80315455cf656b63715d896724
+size 565251810

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd8a0882b79afadd021e37536e5b7065791a67a9fa12445cafcef383cd2a9b33
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d1c1c27bc93bacf4e1419c974b071b27781e1938ed4d320f10ff0009505f3ba
+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 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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 +1,65 @@
+{
+  "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]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "stride": 0,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5,
+  "eval_steps": 295,
+  "global_step": 736,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.050271739130434784,
+      "grad_norm": 28.786767959594727,
+      "learning_rate": 3.60082304526749e-07,
+      "loss": 1.047,
+      "step": 74
+    },
+    {
+      "epoch": 0.10054347826086957,
+      "grad_norm": 13.373394966125488,
+      "learning_rate": 7.407407407407407e-07,
+      "loss": 1.0717,
+      "step": 148
+    },
+    {
+      "epoch": 0.15081521739130435,
+      "grad_norm": 24.112974166870117,
+      "learning_rate": 1.1213991769547327e-06,
+      "loss": 0.9934,
+      "step": 222
+    },
+    {
+      "epoch": 0.20040760869565216,
+      "eval_nli-pairs_loss": 0.27089595794677734,
+      "eval_nli-pairs_runtime": 34.1789,
+      "eval_nli-pairs_samples_per_second": 199.187,
+      "eval_nli-pairs_steps_per_second": 7.139,
+      "step": 295
+    },
+    {
+      "epoch": 0.20040760869565216,
+      "eval_scitail-pairs-pos_loss": 0.3903529644012451,
+      "eval_scitail-pairs-pos_runtime": 7.34,
+      "eval_scitail-pairs-pos_samples_per_second": 177.657,
+      "eval_scitail-pairs-pos_steps_per_second": 6.403,
+      "step": 295
+    },
+    {
+      "epoch": 0.20040760869565216,
+      "eval_qnli-contrastive_loss": 1.3032768964767456,
+      "eval_qnli-contrastive_runtime": 15.8804,
+      "eval_qnli-contrastive_samples_per_second": 344.008,
+      "eval_qnli-contrastive_steps_per_second": 12.342,
+      "step": 295
+    },
+    {
+      "epoch": 0.20040760869565216,
+      "eval_sts-label_loss": 8.962252616882324,
+      "eval_sts-label_runtime": 2.678,
+      "eval_sts-label_samples_per_second": 560.117,
+      "eval_sts-label_steps_per_second": 20.164,
+      "step": 295
+    },
+    {
+      "epoch": 0.20108695652173914,
+      "grad_norm": 0.6236209869384766,
+      "learning_rate": 1.5020576131687246e-06,
+      "loss": 1.1575,
+      "step": 296
+    },
+    {
+      "epoch": 0.2513586956521739,
+      "grad_norm": 165.3773956298828,
+      "learning_rate": 1.8827160493827162e-06,
+      "loss": 1.1961,
+      "step": 370
+    },
+    {
+      "epoch": 0.3016304347826087,
+      "grad_norm": 17.5723819732666,
+      "learning_rate": 2.263374485596708e-06,
+      "loss": 1.0785,
+      "step": 444
+    },
+    {
+      "epoch": 0.35190217391304346,
+      "grad_norm": 4.6810455322265625,
+      "learning_rate": 2.6388888888888893e-06,
+      "loss": 1.0578,
+      "step": 518
+    },
+    {
+      "epoch": 0.4008152173913043,
+      "eval_nli-pairs_loss": 0.26986387372016907,
+      "eval_nli-pairs_runtime": 34.415,
+      "eval_nli-pairs_samples_per_second": 197.821,
+      "eval_nli-pairs_steps_per_second": 7.09,
+      "step": 590
+    },
+    {
+      "epoch": 0.4008152173913043,
+      "eval_scitail-pairs-pos_loss": 0.3808487355709076,
+      "eval_scitail-pairs-pos_runtime": 7.4034,
+      "eval_scitail-pairs-pos_samples_per_second": 176.135,
+      "eval_scitail-pairs-pos_steps_per_second": 6.348,
+      "step": 590
+    },
+    {
+      "epoch": 0.4008152173913043,
+      "eval_qnli-contrastive_loss": 1.2296193838119507,
+      "eval_qnli-contrastive_runtime": 15.8379,
+      "eval_qnli-contrastive_samples_per_second": 344.931,
+      "eval_qnli-contrastive_steps_per_second": 12.375,
+      "step": 590
+    },
+    {
+      "epoch": 0.4008152173913043,
+      "eval_sts-label_loss": 8.84292984008789,
+      "eval_sts-label_runtime": 2.671,
+      "eval_sts-label_samples_per_second": 561.59,
+      "eval_sts-label_steps_per_second": 20.217,
+      "step": 590
+    },
+    {
+      "epoch": 0.40217391304347827,
+      "grad_norm": 12.041239738464355,
+      "learning_rate": 3.019547325102881e-06,
+      "loss": 1.0735,
+      "step": 592
+    },
+    {
+      "epoch": 0.452445652173913,
+      "grad_norm": 55.57080841064453,
+      "learning_rate": 3.4002057613168726e-06,
+      "loss": 1.0379,
+      "step": 666
+    }
+  ],
+  "logging_steps": 74,
+  "max_steps": 2944,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 736,
+  "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": 30,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f996f379647107e3a716cc68df4db697fdcc7d8d4af6e487504122a6cbf1de2
+size 5624