Training in progress, step 438, checkpoint

checkpoint-438/1_AdvancedWeightedPooling/config.json

@@ -0,0 +1,10 @@
+{
+  "embed_dim": 1024,
+  "num_heads": 8,
+  "dropout": 0.05,
+  "bias": true,
+  "use_layernorm": false,
+  "use_MLP": false,
+  "MLP_h_size": 1024,
+  "use_residual": false
+}

checkpoint-438/1_AdvancedWeightedPooling/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21b456a8c72f1889e87a06cae425b1efd8812bc3f1ee5250ea98bb0a52d9d083
+size 16795776

checkpoint-438/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "BAAI/bge-m3",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-438/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.47.0",
+    "pytorch": "2.5.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

checkpoint-438/modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_AdvancedWeightedPooling",
+    "type": "__main__.AdvancedWeightedPooling"
+  }
+]

checkpoint-438/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a282a7cab76b925a0b1fa9fde5249fcd7fc34b00745c368338e9fe225d1e4ad
+size 33591506

checkpoint-438/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e969b03be79a3f792216f1febef058e86c2b7f27374fb1e044d87938ceea1ba
+size 2271151270

checkpoint-438/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63b4d9d674854b1885bcc0cd458d694df71630ad65a46be2f43987f0d38042b8
+size 14244

checkpoint-438/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1542c13060cbf11d63740168f06810d9c42ab089663f77ceda24a3db37e35a80
+size 1000

checkpoint-438/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 8192,
+  "do_lower_case": false
+}

checkpoint-438/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

checkpoint-438/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-438/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4f7e21bec3fb0044ca0bb2d50eb5d4d8c596273c422baef84466d2c73748b9c
+size 17083053

checkpoint-438/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-438/trainer_state.json

@@ -0,0 +1,669 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6008230452674898,
+  "eval_steps": 110,
+  "global_step": 438,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015089163237311385,
+      "grad_norm": 3.8793580532073975,
+      "learning_rate": 1.8281535648994517e-05,
+      "loss": 0.7558,
+      "step": 11
+    },
+    {
+      "epoch": 0.03017832647462277,
+      "grad_norm": 3.666482448577881,
+      "learning_rate": 3.839122486288849e-05,
+      "loss": 0.7776,
+      "step": 22
+    },
+    {
+      "epoch": 0.04526748971193416,
+      "grad_norm": 3.493319511413574,
+      "learning_rate": 5.850091407678245e-05,
+      "loss": 0.379,
+      "step": 33
+    },
+    {
+      "epoch": 0.06035665294924554,
+      "grad_norm": 2.435302972793579,
+      "learning_rate": 7.861060329067642e-05,
+      "loss": 0.4947,
+      "step": 44
+    },
+    {
+      "epoch": 0.07544581618655692,
+      "grad_norm": 2.2073612213134766,
+      "learning_rate": 9.872029250457039e-05,
+      "loss": 0.3406,
+      "step": 55
+    },
+    {
+      "epoch": 0.09053497942386832,
+      "grad_norm": 0.5107505917549133,
+      "learning_rate": 0.00011882998171846434,
+      "loss": 0.2391,
+      "step": 66
+    },
+    {
+      "epoch": 0.1056241426611797,
+      "grad_norm": 2.4110350608825684,
+      "learning_rate": 0.00013893967093235832,
+      "loss": 0.2154,
+      "step": 77
+    },
+    {
+      "epoch": 0.12071330589849108,
+      "grad_norm": 3.4400408267974854,
+      "learning_rate": 0.00015904936014625229,
+      "loss": 0.2662,
+      "step": 88
+    },
+    {
+      "epoch": 0.13580246913580246,
+      "grad_norm": 3.31318998336792,
+      "learning_rate": 0.00017915904936014626,
+      "loss": 0.283,
+      "step": 99
+    },
+    {
+      "epoch": 0.15089163237311384,
+      "grad_norm": 2.624321699142456,
+      "learning_rate": 0.00019926873857404023,
+      "loss": 0.2391,
+      "step": 110
+    },
+    {
+      "epoch": 0.15089163237311384,
+      "eval_Qnli-dev_cosine_accuracy": 0.7353515625,
+      "eval_Qnli-dev_cosine_accuracy_threshold": 0.641769528388977,
+      "eval_Qnli-dev_cosine_ap": 0.7934694922676566,
+      "eval_Qnli-dev_cosine_f1": 0.7255734919286321,
+      "eval_Qnli-dev_cosine_f1_threshold": 0.533623456954956,
+      "eval_Qnli-dev_cosine_precision": 0.6170520231213873,
+      "eval_Qnli-dev_cosine_recall": 0.8804123711340206,
+      "eval_allNLI-dev_cosine_accuracy": 0.7451171875,
+      "eval_allNLI-dev_cosine_accuracy_threshold": 0.7058684229850769,
+      "eval_allNLI-dev_cosine_ap": 0.6358738534384165,
+      "eval_allNLI-dev_cosine_f1": 0.6633039092055485,
+      "eval_allNLI-dev_cosine_f1_threshold": 0.6644865274429321,
+      "eval_allNLI-dev_cosine_precision": 0.579295154185022,
+      "eval_allNLI-dev_cosine_recall": 0.775811209439528,
+      "eval_sequential_score": 0.7934694922676566,
+      "eval_sts-test_pearson_cosine": 0.8508165029528609,
+      "eval_sts-test_spearman_cosine": 0.8665992028008191,
+      "eval_vitaminc-pairs_loss": 1.550615668296814,
+      "eval_vitaminc-pairs_runtime": 24.2459,
+      "eval_vitaminc-pairs_samples_per_second": 10.558,
+      "eval_vitaminc-pairs_steps_per_second": 0.041,
+      "step": 110
+    },
+    {
+      "epoch": 0.15089163237311384,
+      "eval_negation-triplets_loss": 0.8121126294136047,
+      "eval_negation-triplets_runtime": 4.2821,
+      "eval_negation-triplets_samples_per_second": 59.784,
+      "eval_negation-triplets_steps_per_second": 0.234,
+      "step": 110
+    },
+    {
+      "epoch": 0.15089163237311384,
+      "eval_scitail-pairs-pos_loss": 0.05080736428499222,
+      "eval_scitail-pairs-pos_runtime": 3.0909,
+      "eval_scitail-pairs-pos_samples_per_second": 82.824,
+      "eval_scitail-pairs-pos_steps_per_second": 0.324,
+      "step": 110
+    },
+    {
+      "epoch": 0.15089163237311384,
+      "eval_scitail-pairs-qa_loss": 0.011191274970769882,
+      "eval_scitail-pairs-qa_runtime": 2.3574,
+      "eval_scitail-pairs-qa_samples_per_second": 108.596,
+      "eval_scitail-pairs-qa_steps_per_second": 0.424,
+      "step": 110
+    },
+    {
+      "epoch": 0.15089163237311384,
+      "eval_xsum-pairs_loss": 0.2039160132408142,
+      "eval_xsum-pairs_runtime": 12.8416,
+      "eval_xsum-pairs_samples_per_second": 19.935,
+      "eval_xsum-pairs_steps_per_second": 0.078,
+      "step": 110
+    },
+    {
+      "epoch": 0.15089163237311384,
+      "eval_sciq_pairs_loss": 0.023365184664726257,
+      "eval_sciq_pairs_runtime": 20.6659,
+      "eval_sciq_pairs_samples_per_second": 12.388,
+      "eval_sciq_pairs_steps_per_second": 0.048,
+      "step": 110
+    },
+    {
+      "epoch": 0.15089163237311384,
+      "eval_qasc_pairs_loss": 0.558290421962738,
+      "eval_qasc_pairs_runtime": 3.009,
+      "eval_qasc_pairs_samples_per_second": 85.077,
+      "eval_qasc_pairs_steps_per_second": 0.332,
+      "step": 110
+    },
+    {
+      "epoch": 0.15089163237311384,
+      "eval_openbookqa_pairs_loss": 1.253723382949829,
+      "eval_openbookqa_pairs_runtime": 2.2457,
+      "eval_openbookqa_pairs_samples_per_second": 113.993,
+      "eval_openbookqa_pairs_steps_per_second": 0.445,
+      "step": 110
+    },
+    {
+      "epoch": 0.15089163237311384,
+      "eval_nq_pairs_loss": 0.10213108360767365,
+      "eval_nq_pairs_runtime": 18.094,
+      "eval_nq_pairs_samples_per_second": 14.148,
+      "eval_nq_pairs_steps_per_second": 0.055,
+      "step": 110
+    },
+    {
+      "epoch": 0.15089163237311384,
+      "eval_trivia_pairs_loss": 0.4372706711292267,
+      "eval_trivia_pairs_runtime": 16.9326,
+      "eval_trivia_pairs_samples_per_second": 15.119,
+      "eval_trivia_pairs_steps_per_second": 0.059,
+      "step": 110
+    },
+    {
+      "epoch": 0.15089163237311384,
+      "eval_gooaq_pairs_loss": 0.2727060914039612,
+      "eval_gooaq_pairs_runtime": 3.6277,
+      "eval_gooaq_pairs_samples_per_second": 70.568,
+      "eval_gooaq_pairs_steps_per_second": 0.276,
+      "step": 110
+    },
+    {
+      "epoch": 0.15089163237311384,
+      "eval_paws-pos_loss": 0.040396444499492645,
+      "eval_paws-pos_runtime": 2.9381,
+      "eval_paws-pos_samples_per_second": 87.132,
+      "eval_paws-pos_steps_per_second": 0.34,
+      "step": 110
+    },
+    {
+      "epoch": 0.15089163237311384,
+      "eval_global_dataset_loss": 0.1820984184741974,
+      "eval_global_dataset_runtime": 125.361,
+      "eval_global_dataset_samples_per_second": 9.764,
+      "eval_global_dataset_steps_per_second": 0.04,
+      "step": 110
+    },
+    {
+      "epoch": 0.16598079561042525,
+      "grad_norm": 3.345057725906372,
+      "learning_rate": 0.00021937842778793417,
+      "loss": 0.2456,
+      "step": 121
+    },
+    {
+      "epoch": 0.18106995884773663,
+      "grad_norm": 2.2555935382843018,
+      "learning_rate": 0.00023948811700182814,
+      "loss": 0.4199,
+      "step": 132
+    },
+    {
+      "epoch": 0.19615912208504802,
+      "grad_norm": 2.3139288425445557,
+      "learning_rate": 0.0002595978062157221,
+      "loss": 0.2809,
+      "step": 143
+    },
+    {
+      "epoch": 0.2112482853223594,
+      "grad_norm": 3.585463047027588,
+      "learning_rate": 0.0002797074954296161,
+      "loss": 0.5773,
+      "step": 154
+    },
+    {
+      "epoch": 0.22633744855967078,
+      "grad_norm": 2.4281251430511475,
+      "learning_rate": 0.00029981718464351003,
+      "loss": 0.3734,
+      "step": 165
+    },
+    {
+      "epoch": 0.24142661179698216,
+      "grad_norm": 0.2383209466934204,
+      "learning_rate": 0.000319926873857404,
+      "loss": 0.2348,
+      "step": 176
+    },
+    {
+      "epoch": 0.25651577503429357,
+      "grad_norm": 2.4634456634521484,
+      "learning_rate": 0.00034003656307129797,
+      "loss": 0.4421,
+      "step": 187
+    },
+    {
+      "epoch": 0.2716049382716049,
+      "grad_norm": 3.1270384788513184,
+      "learning_rate": 0.00036014625228519197,
+      "loss": 0.5076,
+      "step": 198
+    },
+    {
+      "epoch": 0.28669410150891633,
+      "grad_norm": 0.7871516346931458,
+      "learning_rate": 0.0003802559414990859,
+      "loss": 0.211,
+      "step": 209
+    },
+    {
+      "epoch": 0.3017832647462277,
+      "grad_norm": 2.159247636795044,
+      "learning_rate": 0.00040036563071297986,
+      "loss": 0.3514,
+      "step": 220
+    },
+    {
+      "epoch": 0.3017832647462277,
+      "eval_Qnli-dev_cosine_accuracy": 0.736328125,
+      "eval_Qnli-dev_cosine_accuracy_threshold": 0.6637322902679443,
+      "eval_Qnli-dev_cosine_ap": 0.7960534826633536,
+      "eval_Qnli-dev_cosine_f1": 0.7298050139275766,
+      "eval_Qnli-dev_cosine_f1_threshold": 0.5937396287918091,
+      "eval_Qnli-dev_cosine_precision": 0.6638513513513513,
+      "eval_Qnli-dev_cosine_recall": 0.8103092783505155,
+      "eval_allNLI-dev_cosine_accuracy": 0.755859375,
+      "eval_allNLI-dev_cosine_accuracy_threshold": 0.728554904460907,
+      "eval_allNLI-dev_cosine_ap": 0.6433680273177467,
+      "eval_allNLI-dev_cosine_f1": 0.661818181818182,
+      "eval_allNLI-dev_cosine_f1_threshold": 0.6872978210449219,
+      "eval_allNLI-dev_cosine_precision": 0.5617283950617284,
+      "eval_allNLI-dev_cosine_recall": 0.8053097345132744,
+      "eval_sequential_score": 0.7960534826633536,
+      "eval_sts-test_pearson_cosine": 0.8381104761555598,
+      "eval_sts-test_spearman_cosine": 0.8624525294470655,
+      "eval_vitaminc-pairs_loss": 1.5675894021987915,
+      "eval_vitaminc-pairs_runtime": 24.2649,
+      "eval_vitaminc-pairs_samples_per_second": 10.55,
+      "eval_vitaminc-pairs_steps_per_second": 0.041,
+      "step": 220
+    },
+    {
+      "epoch": 0.3017832647462277,
+      "eval_negation-triplets_loss": 0.923573911190033,
+      "eval_negation-triplets_runtime": 4.311,
+      "eval_negation-triplets_samples_per_second": 59.384,
+      "eval_negation-triplets_steps_per_second": 0.232,
+      "step": 220
+    },
+    {
+      "epoch": 0.3017832647462277,
+      "eval_scitail-pairs-pos_loss": 0.0530293844640255,
+      "eval_scitail-pairs-pos_runtime": 3.1182,
+      "eval_scitail-pairs-pos_samples_per_second": 82.098,
+      "eval_scitail-pairs-pos_steps_per_second": 0.321,
+      "step": 220
+    },
+    {
+      "epoch": 0.3017832647462277,
+      "eval_scitail-pairs-qa_loss": 0.008582310751080513,
+      "eval_scitail-pairs-qa_runtime": 2.402,
+      "eval_scitail-pairs-qa_samples_per_second": 106.58,
+      "eval_scitail-pairs-qa_steps_per_second": 0.416,
+      "step": 220
+    },
+    {
+      "epoch": 0.3017832647462277,
+      "eval_xsum-pairs_loss": 0.19049452245235443,
+      "eval_xsum-pairs_runtime": 12.8763,
+      "eval_xsum-pairs_samples_per_second": 19.882,
+      "eval_xsum-pairs_steps_per_second": 0.078,
+      "step": 220
+    },
+    {
+      "epoch": 0.3017832647462277,
+      "eval_sciq_pairs_loss": 0.02437273971736431,
+      "eval_sciq_pairs_runtime": 20.6537,
+      "eval_sciq_pairs_samples_per_second": 12.395,
+      "eval_sciq_pairs_steps_per_second": 0.048,
+      "step": 220
+    },
+    {
+      "epoch": 0.3017832647462277,
+      "eval_qasc_pairs_loss": 0.6957117915153503,
+      "eval_qasc_pairs_runtime": 3.0168,
+      "eval_qasc_pairs_samples_per_second": 84.858,
+      "eval_qasc_pairs_steps_per_second": 0.331,
+      "step": 220
+    },
+    {
+      "epoch": 0.3017832647462277,
+      "eval_openbookqa_pairs_loss": 1.2585959434509277,
+      "eval_openbookqa_pairs_runtime": 2.2495,
+      "eval_openbookqa_pairs_samples_per_second": 113.801,
+      "eval_openbookqa_pairs_steps_per_second": 0.445,
+      "step": 220
+    },
+    {
+      "epoch": 0.3017832647462277,
+      "eval_nq_pairs_loss": 0.12953564524650574,
+      "eval_nq_pairs_runtime": 18.127,
+      "eval_nq_pairs_samples_per_second": 14.123,
+      "eval_nq_pairs_steps_per_second": 0.055,
+      "step": 220
+    },
+    {
+      "epoch": 0.3017832647462277,
+      "eval_trivia_pairs_loss": 0.46085307002067566,
+      "eval_trivia_pairs_runtime": 16.9635,
+      "eval_trivia_pairs_samples_per_second": 15.091,
+      "eval_trivia_pairs_steps_per_second": 0.059,
+      "step": 220
+    },
+    {
+      "epoch": 0.3017832647462277,
+      "eval_gooaq_pairs_loss": 0.2918424606323242,
+      "eval_gooaq_pairs_runtime": 3.6275,
+      "eval_gooaq_pairs_samples_per_second": 70.573,
+      "eval_gooaq_pairs_steps_per_second": 0.276,
+      "step": 220
+    },
+    {
+      "epoch": 0.3017832647462277,
+      "eval_paws-pos_loss": 0.041661862283945084,
+      "eval_paws-pos_runtime": 2.9518,
+      "eval_paws-pos_samples_per_second": 86.727,
+      "eval_paws-pos_steps_per_second": 0.339,
+      "step": 220
+    },
+    {
+      "epoch": 0.3017832647462277,
+      "eval_global_dataset_loss": 0.3610426187515259,
+      "eval_global_dataset_runtime": 125.4174,
+      "eval_global_dataset_samples_per_second": 9.759,
+      "eval_global_dataset_steps_per_second": 0.04,
+      "step": 220
+    },
+    {
+      "epoch": 0.3168724279835391,
+      "grad_norm": 2.7020387649536133,
+      "learning_rate": 0.00042047531992687385,
+      "loss": 0.2981,
+      "step": 231
+    },
+    {
+      "epoch": 0.3319615912208505,
+      "grad_norm": 2.0000767707824707,
+      "learning_rate": 0.0004405850091407678,
+      "loss": 0.3045,
+      "step": 242
+    },
+    {
+      "epoch": 0.34705075445816186,
+      "grad_norm": 2.539660692214966,
+      "learning_rate": 0.00046069469835466185,
+      "loss": 0.3126,
+      "step": 253
+    },
+    {
+      "epoch": 0.36213991769547327,
+      "grad_norm": 2.418445348739624,
+      "learning_rate": 0.0004808043875685558,
+      "loss": 0.7813,
+      "step": 264
+    },
+    {
+      "epoch": 0.3772290809327846,
+      "grad_norm": 0.13016735017299652,
+      "learning_rate": 0.0005009140767824497,
+      "loss": 0.547,
+      "step": 275
+    },
+    {
+      "epoch": 0.39231824417009603,
+      "grad_norm": 2.2323102951049805,
+      "learning_rate": 0.0005210237659963437,
+      "loss": 0.4698,
+      "step": 286
+    },
+    {
+      "epoch": 0.4074074074074074,
+      "grad_norm": 3.097975492477417,
+      "learning_rate": 0.0005411334552102377,
+      "loss": 0.5427,
+      "step": 297
+    },
+    {
+      "epoch": 0.4224965706447188,
+      "grad_norm": 0.7084994316101074,
+      "learning_rate": 0.0005612431444241316,
+      "loss": 0.3151,
+      "step": 308
+    },
+    {
+      "epoch": 0.4375857338820302,
+      "grad_norm": 1.7643369436264038,
+      "learning_rate": 0.0005813528336380256,
+      "loss": 0.4687,
+      "step": 319
+    },
+    {
+      "epoch": 0.45267489711934156,
+      "grad_norm": 1.7608978748321533,
+      "learning_rate": 0.0006014625228519196,
+      "loss": 0.3769,
+      "step": 330
+    },
+    {
+      "epoch": 0.45267489711934156,
+      "eval_Qnli-dev_cosine_accuracy": 0.7255859375,
+      "eval_Qnli-dev_cosine_accuracy_threshold": 0.6892818212509155,
+      "eval_Qnli-dev_cosine_ap": 0.7884120709809157,
+      "eval_Qnli-dev_cosine_f1": 0.7228464419475655,
+      "eval_Qnli-dev_cosine_f1_threshold": 0.6395477056503296,
+      "eval_Qnli-dev_cosine_precision": 0.6620926243567753,
+      "eval_Qnli-dev_cosine_recall": 0.7958762886597938,
+      "eval_allNLI-dev_cosine_accuracy": 0.7421875,
+      "eval_allNLI-dev_cosine_accuracy_threshold": 0.7702663540840149,
+      "eval_allNLI-dev_cosine_ap": 0.6347046378974335,
+      "eval_allNLI-dev_cosine_f1": 0.6455542021924483,
+      "eval_allNLI-dev_cosine_f1_threshold": 0.7014378309249878,
+      "eval_allNLI-dev_cosine_precision": 0.549792531120332,
+      "eval_allNLI-dev_cosine_recall": 0.7817109144542773,
+      "eval_sequential_score": 0.7884120709809157,
+      "eval_sts-test_pearson_cosine": 0.8389808770066287,
+      "eval_sts-test_spearman_cosine": 0.861226668384837,
+      "eval_vitaminc-pairs_loss": 1.5675371885299683,
+      "eval_vitaminc-pairs_runtime": 24.2072,
+      "eval_vitaminc-pairs_samples_per_second": 10.575,
+      "eval_vitaminc-pairs_steps_per_second": 0.041,
+      "step": 330
+    },
+    {
+      "epoch": 0.45267489711934156,
+      "eval_negation-triplets_loss": 0.7654371857643127,
+      "eval_negation-triplets_runtime": 4.2588,
+      "eval_negation-triplets_samples_per_second": 60.111,
+      "eval_negation-triplets_steps_per_second": 0.235,
+      "step": 330
+    },
+    {
+      "epoch": 0.45267489711934156,
+      "eval_scitail-pairs-pos_loss": 0.04239173233509064,
+      "eval_scitail-pairs-pos_runtime": 3.0875,
+      "eval_scitail-pairs-pos_samples_per_second": 82.915,
+      "eval_scitail-pairs-pos_steps_per_second": 0.324,
+      "step": 330
+    },
+    {
+      "epoch": 0.45267489711934156,
+      "eval_scitail-pairs-qa_loss": 0.010665436275303364,
+      "eval_scitail-pairs-qa_runtime": 2.3433,
+      "eval_scitail-pairs-qa_samples_per_second": 109.246,
+      "eval_scitail-pairs-qa_steps_per_second": 0.427,
+      "step": 330
+    },
+    {
+      "epoch": 0.45267489711934156,
+      "eval_xsum-pairs_loss": 0.20898626744747162,
+      "eval_xsum-pairs_runtime": 12.8471,
+      "eval_xsum-pairs_samples_per_second": 19.927,
+      "eval_xsum-pairs_steps_per_second": 0.078,
+      "step": 330
+    },
+    {
+      "epoch": 0.45267489711934156,
+      "eval_sciq_pairs_loss": 0.03412973880767822,
+      "eval_sciq_pairs_runtime": 20.7279,
+      "eval_sciq_pairs_samples_per_second": 12.351,
+      "eval_sciq_pairs_steps_per_second": 0.048,
+      "step": 330
+    },
+    {
+      "epoch": 0.45267489711934156,
+      "eval_qasc_pairs_loss": 0.7678776383399963,
+      "eval_qasc_pairs_runtime": 3.0154,
+      "eval_qasc_pairs_samples_per_second": 84.896,
+      "eval_qasc_pairs_steps_per_second": 0.332,
+      "step": 330
+    },
+    {
+      "epoch": 0.45267489711934156,
+      "eval_openbookqa_pairs_loss": 1.3723315000534058,
+      "eval_openbookqa_pairs_runtime": 2.2474,
+      "eval_openbookqa_pairs_samples_per_second": 113.91,
+      "eval_openbookqa_pairs_steps_per_second": 0.445,
+      "step": 330
+    },
+    {
+      "epoch": 0.45267489711934156,
+      "eval_nq_pairs_loss": 0.15752817690372467,
+      "eval_nq_pairs_runtime": 18.1484,
+      "eval_nq_pairs_samples_per_second": 14.106,
+      "eval_nq_pairs_steps_per_second": 0.055,
+      "step": 330
+    },
+    {
+      "epoch": 0.45267489711934156,
+      "eval_trivia_pairs_loss": 0.6312745213508606,
+      "eval_trivia_pairs_runtime": 16.9738,
+      "eval_trivia_pairs_samples_per_second": 15.082,
+      "eval_trivia_pairs_steps_per_second": 0.059,
+      "step": 330
+    },
+    {
+      "epoch": 0.45267489711934156,
+      "eval_gooaq_pairs_loss": 0.47655048966407776,
+      "eval_gooaq_pairs_runtime": 3.6272,
+      "eval_gooaq_pairs_samples_per_second": 70.579,
+      "eval_gooaq_pairs_steps_per_second": 0.276,
+      "step": 330
+    },
+    {
+      "epoch": 0.45267489711934156,
+      "eval_paws-pos_loss": 0.04226630926132202,
+      "eval_paws-pos_runtime": 2.9441,
+      "eval_paws-pos_samples_per_second": 86.954,
+      "eval_paws-pos_steps_per_second": 0.34,
+      "step": 330
+    },
+    {
+      "epoch": 0.45267489711934156,
+      "eval_global_dataset_loss": 0.23270446062088013,
+      "eval_global_dataset_runtime": 125.3499,
+      "eval_global_dataset_samples_per_second": 9.765,
+      "eval_global_dataset_steps_per_second": 0.04,
+      "step": 330
+    },
+    {
+      "epoch": 0.46776406035665297,
+      "grad_norm": 0.37502893805503845,
+      "learning_rate": 0.0006215722120658135,
+      "loss": 0.3832,
+      "step": 341
+    },
+    {
+      "epoch": 0.4828532235939643,
+      "grad_norm": 2.488353967666626,
+      "learning_rate": 0.0006416819012797075,
+      "loss": 0.4392,
+      "step": 352
+    },
+    {
+      "epoch": 0.49794238683127573,
+      "grad_norm": 0.0037633629981428385,
+      "learning_rate": 0.0006617915904936015,
+      "loss": 0.3929,
+      "step": 363
+    },
+    {
+      "epoch": 0.5130315500685871,
+      "grad_norm": 0.467970073223114,
+      "learning_rate": 0.0006819012797074955,
+      "loss": 0.2611,
+      "step": 374
+    },
+    {
+      "epoch": 0.5281207133058985,
+      "grad_norm": 2.020796537399292,
+      "learning_rate": 0.0007020109689213894,
+      "loss": 0.3528,
+      "step": 385
+    },
+    {
+      "epoch": 0.5432098765432098,
+      "grad_norm": 2.0242817401885986,
+      "learning_rate": 0.0007221206581352834,
+      "loss": 0.738,
+      "step": 396
+    },
+    {
+      "epoch": 0.5582990397805213,
+      "grad_norm": 2.9996001720428467,
+      "learning_rate": 0.0007422303473491774,
+      "loss": 0.4016,
+      "step": 407
+    },
+    {
+      "epoch": 0.5733882030178327,
+      "grad_norm": 1.8861972093582153,
+      "learning_rate": 0.0007623400365630713,
+      "loss": 0.3589,
+      "step": 418
+    },
+    {
+      "epoch": 0.588477366255144,
+      "grad_norm": 0.24432632327079773,
+      "learning_rate": 0.0007824497257769653,
+      "loss": 0.3057,
+      "step": 429
+    }
+  ],
+  "logging_steps": 11,
+  "max_steps": 2187,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 219,
+  "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": 128,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-438/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc4e2f1b0b6ec0b954c31a7a2d7392e2f2f817d60f3db0f6f0a80bdf431c25bc
+size 5880