Training in progress, step 4, checkpoint

checkpoint-4/1_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-4/added_tokens.json

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

checkpoint-4/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-4/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-4/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-4/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c98a4383a0978546a09cde2a9418d4b74e737e7ff11f91ef0313646fbd58bac
+size 1130520122

checkpoint-4/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9495c8a837eb2f6f9cf62cab1242bbca22d2a0599fb3b75390ca77b7e52a5fb2
+size 565251810

checkpoint-4/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae8661e57a0a57581cdb83ab31e278fe0a43a4dff52c4be039a87bdcaa350d68
+size 14244

checkpoint-4/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca89f2d49dfb058abe3623375bc3e28d24254514505830490129c306bafb4c9f
+size 1064

checkpoint-4/sentence_bert_config.json

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

checkpoint-4/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-4/spm.model

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

checkpoint-4/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-4/trainer_state.json

@@ -0,0 +1,355 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.11627906976744186,
+  "eval_steps": 2,
+  "global_step": 4,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.029069767441860465,
+      "grad_norm": 13.73514461517334,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 6.7536,
+      "step": 1
+    },
+    {
+      "epoch": 0.05813953488372093,
+      "grad_norm": 16.892961502075195,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 6.6203,
+      "step": 2
+    },
+    {
+      "epoch": 0.05813953488372093,
+      "eval_NLI-v2_cosine_accuracy": 1.0,
+      "eval_NLI-v2_dot_accuracy": 0.109375,
+      "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": 0.9469717741012573,
+      "eval_VitaminC_cosine_ap": 0.5165514227338435,
+      "eval_VitaminC_cosine_f1": 0.6525198938992042,
+      "eval_VitaminC_cosine_f1_threshold": 0.4987494945526123,
+      "eval_VitaminC_cosine_precision": 0.484251968503937,
+      "eval_VitaminC_cosine_recall": 1.0,
+      "eval_VitaminC_dot_accuracy": 0.55078125,
+      "eval_VitaminC_dot_accuracy_threshold": 417.45166015625,
+      "eval_VitaminC_dot_ap": 0.5125282416460941,
+      "eval_VitaminC_dot_f1": 0.6525198938992042,
+      "eval_VitaminC_dot_f1_threshold": 200.84530639648438,
+      "eval_VitaminC_dot_precision": 0.484251968503937,
+      "eval_VitaminC_dot_recall": 1.0,
+      "eval_VitaminC_euclidean_accuracy": 0.546875,
+      "eval_VitaminC_euclidean_accuracy_threshold": 6.841136932373047,
+      "eval_VitaminC_euclidean_ap": 0.512994913068431,
+      "eval_VitaminC_euclidean_f1": 0.6525198938992042,
+      "eval_VitaminC_euclidean_f1_threshold": 20.22179412841797,
+      "eval_VitaminC_euclidean_precision": 0.484251968503937,
+      "eval_VitaminC_euclidean_recall": 1.0,
+      "eval_VitaminC_manhattan_accuracy": 0.546875,
+      "eval_VitaminC_manhattan_accuracy_threshold": 117.1143569946289,
+      "eval_VitaminC_manhattan_ap": 0.5177961641566705,
+      "eval_VitaminC_manhattan_f1": 0.6542553191489362,
+      "eval_VitaminC_manhattan_f1_threshold": 292.3347473144531,
+      "eval_VitaminC_manhattan_precision": 0.48616600790513836,
+      "eval_VitaminC_manhattan_recall": 1.0,
+      "eval_VitaminC_max_accuracy": 0.55078125,
+      "eval_VitaminC_max_accuracy_threshold": 417.45166015625,
+      "eval_VitaminC_max_ap": 0.5177961641566705,
+      "eval_VitaminC_max_f1": 0.6542553191489362,
+      "eval_VitaminC_max_f1_threshold": 292.3347473144531,
+      "eval_VitaminC_max_precision": 0.48616600790513836,
+      "eval_VitaminC_max_recall": 1.0,
+      "eval_sequential_score": 0.5177961641566705,
+      "eval_sts-test_pearson_cosine": 0.017178505918243114,
+      "eval_sts-test_pearson_dot": 0.16228524441844774,
+      "eval_sts-test_pearson_euclidean": 0.024391561236282323,
+      "eval_sts-test_pearson_manhattan": 0.059272519732015624,
+      "eval_sts-test_pearson_max": 0.16228524441844774,
+      "eval_sts-test_spearman_cosine": 0.07115563415775981,
+      "eval_sts-test_spearman_dot": 0.1967074668301984,
+      "eval_sts-test_spearman_euclidean": 0.05117306486959643,
+      "eval_sts-test_spearman_manhattan": 0.07641354546391785,
+      "eval_sts-test_spearman_max": 0.1967074668301984,
+      "eval_vitaminc-pairs_loss": 2.72658371925354,
+      "eval_vitaminc-pairs_runtime": 1.4719,
+      "eval_vitaminc-pairs_samples_per_second": 73.373,
+      "eval_vitaminc-pairs_steps_per_second": 1.359,
+      "step": 2
+    },
+    {
+      "epoch": 0.05813953488372093,
+      "eval_negation-triplets_loss": 5.094177722930908,
+      "eval_negation-triplets_runtime": 0.3027,
+      "eval_negation-triplets_samples_per_second": 211.46,
+      "eval_negation-triplets_steps_per_second": 3.304,
+      "step": 2
+    },
+    {
+      "epoch": 0.05813953488372093,
+      "eval_scitail-pairs-pos_loss": 1.9183871746063232,
+      "eval_scitail-pairs-pos_runtime": 0.3785,
+      "eval_scitail-pairs-pos_samples_per_second": 142.654,
+      "eval_scitail-pairs-pos_steps_per_second": 2.642,
+      "step": 2
+    },
+    {
+      "epoch": 0.05813953488372093,
+      "eval_xsum-pairs_loss": 6.3277668952941895,
+      "eval_xsum-pairs_runtime": 3.4205,
+      "eval_xsum-pairs_samples_per_second": 37.422,
+      "eval_xsum-pairs_steps_per_second": 0.585,
+      "step": 2
+    },
+    {
+      "epoch": 0.05813953488372093,
+      "eval_sciq_pairs_loss": 0.36539140343666077,
+      "eval_sciq_pairs_runtime": 3.4462,
+      "eval_sciq_pairs_samples_per_second": 37.143,
+      "eval_sciq_pairs_steps_per_second": 0.58,
+      "step": 2
+    },
+    {
+      "epoch": 0.05813953488372093,
+      "eval_qasc_pairs_loss": 3.9689104557037354,
+      "eval_qasc_pairs_runtime": 0.6477,
+      "eval_qasc_pairs_samples_per_second": 197.636,
+      "eval_qasc_pairs_steps_per_second": 3.088,
+      "step": 2
+    },
+    {
+      "epoch": 0.05813953488372093,
+      "eval_openbookqa_pairs_loss": 4.7439374923706055,
+      "eval_openbookqa_pairs_runtime": 0.5759,
+      "eval_openbookqa_pairs_samples_per_second": 222.248,
+      "eval_openbookqa_pairs_steps_per_second": 3.473,
+      "step": 2
+    },
+    {
+      "epoch": 0.05813953488372093,
+      "eval_msmarco_pairs_loss": 10.51363754272461,
+      "eval_msmarco_pairs_runtime": 1.3036,
+      "eval_msmarco_pairs_samples_per_second": 98.189,
+      "eval_msmarco_pairs_steps_per_second": 1.534,
+      "step": 2
+    },
+    {
+      "epoch": 0.05813953488372093,
+      "eval_nq_pairs_loss": 4.969011306762695,
+      "eval_nq_pairs_runtime": 2.5922,
+      "eval_nq_pairs_samples_per_second": 49.378,
+      "eval_nq_pairs_steps_per_second": 0.772,
+      "step": 2
+    },
+    {
+      "epoch": 0.05813953488372093,
+      "eval_trivia_pairs_loss": 3.8609507083892822,
+      "eval_trivia_pairs_runtime": 4.3666,
+      "eval_trivia_pairs_samples_per_second": 29.314,
+      "eval_trivia_pairs_steps_per_second": 0.458,
+      "step": 2
+    },
+    {
+      "epoch": 0.05813953488372093,
+      "eval_gooaq_pairs_loss": 8.041110038757324,
+      "eval_gooaq_pairs_runtime": 0.9119,
+      "eval_gooaq_pairs_samples_per_second": 140.361,
+      "eval_gooaq_pairs_steps_per_second": 2.193,
+      "step": 2
+    },
+    {
+      "epoch": 0.05813953488372093,
+      "eval_paws-pos_loss": 2.21897029876709,
+      "eval_paws-pos_runtime": 0.6905,
+      "eval_paws-pos_samples_per_second": 185.364,
+      "eval_paws-pos_steps_per_second": 2.896,
+      "step": 2
+    },
+    {
+      "epoch": 0.0872093023255814,
+      "grad_norm": 15.801941871643066,
+      "learning_rate": 1e-05,
+      "loss": 6.7963,
+      "step": 3
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "grad_norm": 11.94517993927002,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 6.4488,
+      "step": 4
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "eval_NLI-v2_cosine_accuracy": 1.0,
+      "eval_NLI-v2_dot_accuracy": 0.109375,
+      "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": 0.9437637329101562,
+      "eval_VitaminC_cosine_ap": 0.5161989667198088,
+      "eval_VitaminC_cosine_f1": 0.6525198938992042,
+      "eval_VitaminC_cosine_f1_threshold": 0.56722092628479,
+      "eval_VitaminC_cosine_precision": 0.484251968503937,
+      "eval_VitaminC_cosine_recall": 1.0,
+      "eval_VitaminC_dot_accuracy": 0.546875,
+      "eval_VitaminC_dot_accuracy_threshold": 416.9976806640625,
+      "eval_VitaminC_dot_ap": 0.515337582265173,
+      "eval_VitaminC_dot_f1": 0.6507936507936508,
+      "eval_VitaminC_dot_f1_threshold": 223.1047821044922,
+      "eval_VitaminC_dot_precision": 0.4823529411764706,
+      "eval_VitaminC_dot_recall": 1.0,
+      "eval_VitaminC_euclidean_accuracy": 0.55078125,
+      "eval_VitaminC_euclidean_accuracy_threshold": 6.841610908508301,
+      "eval_VitaminC_euclidean_ap": 0.5167890569390883,
+      "eval_VitaminC_euclidean_f1": 0.6542553191489362,
+      "eval_VitaminC_euclidean_f1_threshold": 18.548978805541992,
+      "eval_VitaminC_euclidean_precision": 0.48616600790513836,
+      "eval_VitaminC_euclidean_recall": 1.0,
+      "eval_VitaminC_manhattan_accuracy": 0.54296875,
+      "eval_VitaminC_manhattan_accuracy_threshold": 110.40855407714844,
+      "eval_VitaminC_manhattan_ap": 0.5219582103185639,
+      "eval_VitaminC_manhattan_f1": 0.6542553191489362,
+      "eval_VitaminC_manhattan_f1_threshold": 282.48602294921875,
+      "eval_VitaminC_manhattan_precision": 0.48616600790513836,
+      "eval_VitaminC_manhattan_recall": 1.0,
+      "eval_VitaminC_max_accuracy": 0.55078125,
+      "eval_VitaminC_max_accuracy_threshold": 416.9976806640625,
+      "eval_VitaminC_max_ap": 0.5219582103185639,
+      "eval_VitaminC_max_f1": 0.6542553191489362,
+      "eval_VitaminC_max_f1_threshold": 282.48602294921875,
+      "eval_VitaminC_max_precision": 0.48616600790513836,
+      "eval_VitaminC_max_recall": 1.0,
+      "eval_sequential_score": 0.5219582103185639,
+      "eval_sts-test_pearson_cosine": 0.025276809579094173,
+      "eval_sts-test_pearson_dot": 0.21470147681711343,
+      "eval_sts-test_pearson_euclidean": 0.027783806662194415,
+      "eval_sts-test_pearson_manhattan": 0.059736177006118926,
+      "eval_sts-test_pearson_max": 0.21470147681711343,
+      "eval_sts-test_spearman_cosine": 0.0776783582433888,
+      "eval_sts-test_spearman_dot": 0.2491347682204262,
+      "eval_sts-test_spearman_euclidean": 0.054640386155863654,
+      "eval_sts-test_spearman_manhattan": 0.07764379287610436,
+      "eval_sts-test_spearman_max": 0.2491347682204262,
+      "eval_vitaminc-pairs_loss": 2.7045021057128906,
+      "eval_vitaminc-pairs_runtime": 1.4394,
+      "eval_vitaminc-pairs_samples_per_second": 75.033,
+      "eval_vitaminc-pairs_steps_per_second": 1.389,
+      "step": 4
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "eval_negation-triplets_loss": 5.081584453582764,
+      "eval_negation-triplets_runtime": 0.2952,
+      "eval_negation-triplets_samples_per_second": 216.79,
+      "eval_negation-triplets_steps_per_second": 3.387,
+      "step": 4
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "eval_scitail-pairs-pos_loss": 1.9186776876449585,
+      "eval_scitail-pairs-pos_runtime": 0.3702,
+      "eval_scitail-pairs-pos_samples_per_second": 145.879,
+      "eval_scitail-pairs-pos_steps_per_second": 2.701,
+      "step": 4
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "eval_xsum-pairs_loss": 6.199001312255859,
+      "eval_xsum-pairs_runtime": 3.4227,
+      "eval_xsum-pairs_samples_per_second": 37.398,
+      "eval_xsum-pairs_steps_per_second": 0.584,
+      "step": 4
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "eval_sciq_pairs_loss": 0.3414052426815033,
+      "eval_sciq_pairs_runtime": 3.4403,
+      "eval_sciq_pairs_samples_per_second": 37.206,
+      "eval_sciq_pairs_steps_per_second": 0.581,
+      "step": 4
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "eval_qasc_pairs_loss": 3.662200927734375,
+      "eval_qasc_pairs_runtime": 0.6486,
+      "eval_qasc_pairs_samples_per_second": 197.349,
+      "eval_qasc_pairs_steps_per_second": 3.084,
+      "step": 4
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "eval_openbookqa_pairs_loss": 4.650759220123291,
+      "eval_openbookqa_pairs_runtime": 0.5722,
+      "eval_openbookqa_pairs_samples_per_second": 223.702,
+      "eval_openbookqa_pairs_steps_per_second": 3.495,
+      "step": 4
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "eval_msmarco_pairs_loss": 9.487885475158691,
+      "eval_msmarco_pairs_runtime": 1.2978,
+      "eval_msmarco_pairs_samples_per_second": 98.63,
+      "eval_msmarco_pairs_steps_per_second": 1.541,
+      "step": 4
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "eval_nq_pairs_loss": 4.4714131355285645,
+      "eval_nq_pairs_runtime": 2.569,
+      "eval_nq_pairs_samples_per_second": 49.824,
+      "eval_nq_pairs_steps_per_second": 0.779,
+      "step": 4
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "eval_trivia_pairs_loss": 3.5246145725250244,
+      "eval_trivia_pairs_runtime": 4.3557,
+      "eval_trivia_pairs_samples_per_second": 29.387,
+      "eval_trivia_pairs_steps_per_second": 0.459,
+      "step": 4
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "eval_gooaq_pairs_loss": 7.395092010498047,
+      "eval_gooaq_pairs_runtime": 0.9109,
+      "eval_gooaq_pairs_samples_per_second": 140.521,
+      "eval_gooaq_pairs_steps_per_second": 2.196,
+      "step": 4
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "eval_paws-pos_loss": 2.233201742172241,
+      "eval_paws-pos_runtime": 0.6853,
+      "eval_paws-pos_samples_per_second": 186.773,
+      "eval_paws-pos_steps_per_second": 2.918,
+      "step": 4
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 34,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 2,
+  "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": 224,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edceb7011ecd574f3e3fa5380c854a14e3b5904426b5550bdb62acd6cda68870
+size 5688