Training in progress, step 1, checkpoint

checkpoint-1/1_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
+}

checkpoint-1/added_tokens.json

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

checkpoint-1/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": "4.42.3",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

checkpoint-1/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.42.3",
+    "pytorch": "2.1.2"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

checkpoint-1/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-1/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aabe9a3d980e783926dd69a89875e5beb9cc987ee70c92c26e2fb87a94434131
+size 1130520122

checkpoint-1/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:746e90be4f1fd2037efed931baab61aec80c17d7b250b7618290bcd8ec2c09fb
+size 565251810

checkpoint-1/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39e31a009a68f800d7116d7dc544c153ec26170c60d13a9695fe05d2a6366f41
+size 14244

checkpoint-1/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58132b50b14a0cd97d50b2aebc6944d2ffa90c1aa2465f18c20bbc44dd31f547
+size 1064

checkpoint-1/sentence_bert_config.json

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

checkpoint-1/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-1/spm.model

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

checkpoint-1/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-1/trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0547945205479452,
+  "eval_steps": 1,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0547945205479452,
+      "grad_norm": 17.049646377563477,
+      "learning_rate": 4e-05,
+      "loss": 6.851,
+      "step": 1
+    },
+    {
+      "epoch": 0.0547945205479452,
+      "eval_NLI-v2_cosine_accuracy": 1.0,
+      "eval_NLI-v2_dot_accuracy": 0.125,
+      "eval_NLI-v2_euclidean_accuracy": 1.0,
+      "eval_NLI-v2_manhattan_accuracy": 1.0,
+      "eval_NLI-v2_max_accuracy": 1.0,
+      "eval_VitaminC_cosine_accuracy": 0.55078125,
+      "eval_VitaminC_cosine_accuracy_threshold": 0.9466925859451294,
+      "eval_VitaminC_cosine_ap": 0.5153192822743842,
+      "eval_VitaminC_cosine_f1": 0.6525198938992042,
+      "eval_VitaminC_cosine_f1_threshold": 0.49584439396858215,
+      "eval_VitaminC_cosine_precision": 0.484251968503937,
+      "eval_VitaminC_cosine_recall": 1.0,
+      "eval_VitaminC_dot_accuracy": 0.55078125,
+      "eval_VitaminC_dot_accuracy_threshold": 417.46221923828125,
+      "eval_VitaminC_dot_ap": 0.5127659553715838,
+      "eval_VitaminC_dot_f1": 0.6525198938992042,
+      "eval_VitaminC_dot_f1_threshold": 199.873291015625,
+      "eval_VitaminC_dot_precision": 0.484251968503937,
+      "eval_VitaminC_dot_recall": 1.0,
+      "eval_VitaminC_euclidean_accuracy": 0.546875,
+      "eval_VitaminC_euclidean_accuracy_threshold": 6.84520149230957,
+      "eval_VitaminC_euclidean_ap": 0.5128797056139347,
+      "eval_VitaminC_euclidean_f1": 0.6525198938992042,
+      "eval_VitaminC_euclidean_f1_threshold": 20.29159164428711,
+      "eval_VitaminC_euclidean_precision": 0.484251968503937,
+      "eval_VitaminC_euclidean_recall": 1.0,
+      "eval_VitaminC_manhattan_accuracy": 0.546875,
+      "eval_VitaminC_manhattan_accuracy_threshold": 117.19680786132812,
+      "eval_VitaminC_manhattan_ap": 0.5178540867523715,
+      "eval_VitaminC_manhattan_f1": 0.6542553191489362,
+      "eval_VitaminC_manhattan_f1_threshold": 292.8346252441406,
+      "eval_VitaminC_manhattan_precision": 0.48616600790513836,
+      "eval_VitaminC_manhattan_recall": 1.0,
+      "eval_VitaminC_max_accuracy": 0.55078125,
+      "eval_VitaminC_max_accuracy_threshold": 417.46221923828125,
+      "eval_VitaminC_max_ap": 0.5178540867523715,
+      "eval_VitaminC_max_f1": 0.6542553191489362,
+      "eval_VitaminC_max_f1_threshold": 292.8346252441406,
+      "eval_VitaminC_max_precision": 0.48616600790513836,
+      "eval_VitaminC_max_recall": 1.0,
+      "eval_sequential_score": 0.5178540867523715,
+      "eval_sts-test_pearson_cosine": 0.01688864747186382,
+      "eval_sts-test_pearson_dot": 0.16020781347065607,
+      "eval_sts-test_pearson_euclidean": 0.02427633810266949,
+      "eval_sts-test_pearson_manhattan": 0.05915868944955206,
+      "eval_sts-test_pearson_max": 0.16020781347065607,
+      "eval_sts-test_spearman_cosine": 0.0704767781934101,
+      "eval_sts-test_spearman_dot": 0.19413812590183685,
+      "eval_sts-test_spearman_euclidean": 0.0506775286593327,
+      "eval_sts-test_spearman_manhattan": 0.07640924890718144,
+      "eval_sts-test_spearman_max": 0.19413812590183685,
+      "eval_vitaminc-pairs_loss": 2.7278947830200195,
+      "eval_vitaminc-pairs_runtime": 1.5228,
+      "eval_vitaminc-pairs_samples_per_second": 70.92,
+      "eval_vitaminc-pairs_steps_per_second": 1.313,
+      "step": 1
+    },
+    {
+      "epoch": 0.0547945205479452,
+      "eval_negation-triplets_loss": 5.259257793426514,
+      "eval_negation-triplets_runtime": 0.3007,
+      "eval_negation-triplets_samples_per_second": 212.85,
+      "eval_negation-triplets_steps_per_second": 3.326,
+      "step": 1
+    },
+    {
+      "epoch": 0.0547945205479452,
+      "eval_scitail-pairs-pos_loss": 1.9180195331573486,
+      "eval_scitail-pairs-pos_runtime": 0.4022,
+      "eval_scitail-pairs-pos_samples_per_second": 134.25,
+      "eval_scitail-pairs-pos_steps_per_second": 2.486,
+      "step": 1
+    },
+    {
+      "epoch": 0.0547945205479452,
+      "eval_xsum-pairs_loss": 6.389987945556641,
+      "eval_xsum-pairs_runtime": 3.3036,
+      "eval_xsum-pairs_samples_per_second": 38.746,
+      "eval_xsum-pairs_steps_per_second": 0.605,
+      "step": 1
+    },
+    {
+      "epoch": 0.0547945205479452,
+      "eval_sciq_pairs_loss": 1.1206029653549194,
+      "eval_sciq_pairs_runtime": 3.3516,
+      "eval_sciq_pairs_samples_per_second": 38.191,
+      "eval_sciq_pairs_steps_per_second": 0.597,
+      "step": 1
+    },
+    {
+      "epoch": 0.0547945205479452,
+      "eval_qasc_pairs_loss": 7.901282787322998,
+      "eval_qasc_pairs_runtime": 0.6747,
+      "eval_qasc_pairs_samples_per_second": 189.709,
+      "eval_qasc_pairs_steps_per_second": 2.964,
+      "step": 1
+    },
+    {
+      "epoch": 0.0547945205479452,
+      "eval_openbookqa_pairs_loss": 4.747707366943359,
+      "eval_openbookqa_pairs_runtime": 0.5849,
+      "eval_openbookqa_pairs_samples_per_second": 218.847,
+      "eval_openbookqa_pairs_steps_per_second": 3.419,
+      "step": 1
+    },
+    {
+      "epoch": 0.0547945205479452,
+      "eval_msmarco_pairs_loss": 10.60707950592041,
+      "eval_msmarco_pairs_runtime": 1.2013,
+      "eval_msmarco_pairs_samples_per_second": 106.551,
+      "eval_msmarco_pairs_steps_per_second": 1.665,
+      "step": 1
+    },
+    {
+      "epoch": 0.0547945205479452,
+      "eval_nq_pairs_loss": 10.446059226989746,
+      "eval_nq_pairs_runtime": 2.7595,
+      "eval_nq_pairs_samples_per_second": 46.385,
+      "eval_nq_pairs_steps_per_second": 0.725,
+      "step": 1
+    },
+    {
+      "epoch": 0.0547945205479452,
+      "eval_trivia_pairs_loss": 7.870224952697754,
+      "eval_trivia_pairs_runtime": 3.9907,
+      "eval_trivia_pairs_samples_per_second": 29.819,
+      "eval_trivia_pairs_steps_per_second": 0.501,
+      "step": 1
+    },
+    {
+      "epoch": 0.0547945205479452,
+      "eval_gooaq_pairs_loss": 8.126296997070312,
+      "eval_gooaq_pairs_runtime": 0.8871,
+      "eval_gooaq_pairs_samples_per_second": 144.296,
+      "eval_gooaq_pairs_steps_per_second": 2.255,
+      "step": 1
+    },
+    {
+      "epoch": 0.0547945205479452,
+      "eval_paws-pos_loss": 2.2177822589874268,
+      "eval_paws-pos_runtime": 0.69,
+      "eval_paws-pos_samples_per_second": 185.509,
+      "eval_paws-pos_steps_per_second": 2.899,
+      "step": 1
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 2,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1,
+  "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": 160,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d8ee34c18a400f97b88a2eac5f9619f6acd81ed3e37e87a781d225dd83c9b5d
+size 5688