Training in progress, step 64, checkpoint

checkpoint-64/1_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-64/added_tokens.json

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

checkpoint-64/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "bobox/DeBERTa-small-ST-v1-test",
+  "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-64/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-64/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-64/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6ed7a258eca45562b95659402afb7d524b81dfba0608e515da7cdf6b733ec73
+size 1130520122

checkpoint-64/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fc9bb51e80e22d9ea518a8cccbacaeef31f4bed0468831e0283249eabc19645
+size 565251810

checkpoint-64/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44cc4b52c010ad43ba8242b60d56bd6509a4909f57792b844091249583eed080
+size 14244

checkpoint-64/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c6d0f9d600d575cc1d8f85a0ff009df751ff8cc8e6ebe018c68228315400d47
+size 1064

checkpoint-64/sentence_bert_config.json

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

checkpoint-64/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
+  }
+}

checkpoint-64/spm.model

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

checkpoint-64/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": 1000000000000000019884624838656,
+  "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"
+}

checkpoint-64/trainer_state.json

@@ -0,0 +1,765 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.2,
+  "eval_steps": 32,
+  "global_step": 64,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003125,
+      "grad_norm": 3.1757984161376953,
+      "learning_rate": 3.125e-07,
+      "loss": 0.7374,
+      "step": 1
+    },
+    {
+      "epoch": 0.00625,
+      "grad_norm": 3.137390375137329,
+      "learning_rate": 6.25e-07,
+      "loss": 0.5723,
+      "step": 2
+    },
+    {
+      "epoch": 0.009375,
+      "grad_norm": 2.765856981277466,
+      "learning_rate": 9.375000000000001e-07,
+      "loss": 0.551,
+      "step": 3
+    },
+    {
+      "epoch": 0.0125,
+      "grad_norm": 3.468062162399292,
+      "learning_rate": 1.25e-06,
+      "loss": 0.7379,
+      "step": 4
+    },
+    {
+      "epoch": 0.015625,
+      "grad_norm": 2.6695668697357178,
+      "learning_rate": 1.5625e-06,
+      "loss": 0.5271,
+      "step": 5
+    },
+    {
+      "epoch": 0.01875,
+      "grad_norm": 2.7720863819122314,
+      "learning_rate": 1.8750000000000003e-06,
+      "loss": 0.5858,
+      "step": 6
+    },
+    {
+      "epoch": 0.021875,
+      "grad_norm": 3.0211267471313477,
+      "learning_rate": 2.1875000000000002e-06,
+      "loss": 0.6562,
+      "step": 7
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 3.641108989715576,
+      "learning_rate": 2.5e-06,
+      "loss": 0.8228,
+      "step": 8
+    },
+    {
+      "epoch": 0.028125,
+      "grad_norm": 3.9061200618743896,
+      "learning_rate": 2.8125e-06,
+      "loss": 0.9988,
+      "step": 9
+    },
+    {
+      "epoch": 0.03125,
+      "grad_norm": 2.642423391342163,
+      "learning_rate": 3.125e-06,
+      "loss": 0.5582,
+      "step": 10
+    },
+    {
+      "epoch": 0.034375,
+      "grad_norm": 3.6546943187713623,
+      "learning_rate": 3.4375e-06,
+      "loss": 0.8546,
+      "step": 11
+    },
+    {
+      "epoch": 0.0375,
+      "grad_norm": 2.5504300594329834,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.4235,
+      "step": 12
+    },
+    {
+      "epoch": 0.040625,
+      "grad_norm": 2.845123529434204,
+      "learning_rate": 4.0625000000000005e-06,
+      "loss": 0.6418,
+      "step": 13
+    },
+    {
+      "epoch": 0.04375,
+      "grad_norm": 2.8562164306640625,
+      "learning_rate": 4.3750000000000005e-06,
+      "loss": 0.6577,
+      "step": 14
+    },
+    {
+      "epoch": 0.046875,
+      "grad_norm": 3.4033620357513428,
+      "learning_rate": 4.6875000000000004e-06,
+      "loss": 0.8333,
+      "step": 15
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.148242473602295,
+      "learning_rate": 5e-06,
+      "loss": 0.4082,
+      "step": 16
+    },
+    {
+      "epoch": 0.053125,
+      "grad_norm": 3.685960292816162,
+      "learning_rate": 5.3125e-06,
+      "loss": 0.8101,
+      "step": 17
+    },
+    {
+      "epoch": 0.05625,
+      "grad_norm": 2.7071452140808105,
+      "learning_rate": 5.625e-06,
+      "loss": 0.5259,
+      "step": 18
+    },
+    {
+      "epoch": 0.059375,
+      "grad_norm": 3.508561611175537,
+      "learning_rate": 5.9375e-06,
+      "loss": 0.9015,
+      "step": 19
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 4.140976428985596,
+      "learning_rate": 6.25e-06,
+      "loss": 1.3915,
+      "step": 20
+    },
+    {
+      "epoch": 0.065625,
+      "grad_norm": 1.5563820600509644,
+      "learning_rate": 6.5625e-06,
+      "loss": 0.26,
+      "step": 21
+    },
+    {
+      "epoch": 0.06875,
+      "grad_norm": 3.1467344760894775,
+      "learning_rate": 6.875e-06,
+      "loss": 0.6885,
+      "step": 22
+    },
+    {
+      "epoch": 0.071875,
+      "grad_norm": 3.539327383041382,
+      "learning_rate": 7.1875e-06,
+      "loss": 0.9357,
+      "step": 23
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 3.1691510677337646,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.7168,
+      "step": 24
+    },
+    {
+      "epoch": 0.078125,
+      "grad_norm": 3.9020121097564697,
+      "learning_rate": 7.8125e-06,
+      "loss": 0.8678,
+      "step": 25
+    },
+    {
+      "epoch": 0.08125,
+      "grad_norm": 2.3635435104370117,
+      "learning_rate": 8.125000000000001e-06,
+      "loss": 0.4922,
+      "step": 26
+    },
+    {
+      "epoch": 0.084375,
+      "grad_norm": 2.5170037746429443,
+      "learning_rate": 8.4375e-06,
+      "loss": 0.4937,
+      "step": 27
+    },
+    {
+      "epoch": 0.0875,
+      "grad_norm": 2.7988407611846924,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 0.5891,
+      "step": 28
+    },
+    {
+      "epoch": 0.090625,
+      "grad_norm": 2.99135160446167,
+      "learning_rate": 9.0625e-06,
+      "loss": 0.6921,
+      "step": 29
+    },
+    {
+      "epoch": 0.09375,
+      "grad_norm": 3.098013162612915,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 0.8087,
+      "step": 30
+    },
+    {
+      "epoch": 0.096875,
+      "grad_norm": 3.358091115951538,
+      "learning_rate": 9.6875e-06,
+      "loss": 0.805,
+      "step": 31
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.0206046104431152,
+      "learning_rate": 1e-05,
+      "loss": 0.6141,
+      "step": 32
+    },
+    {
+      "epoch": 0.1,
+      "eval_VitaminC_cosine_accuracy": 0.5546875,
+      "eval_VitaminC_cosine_accuracy_threshold": 0.8487042188644409,
+      "eval_VitaminC_cosine_ap": 0.5467207830251657,
+      "eval_VitaminC_cosine_f1": 0.6657824933687002,
+      "eval_VitaminC_cosine_f1_threshold": 0.2510407269001007,
+      "eval_VitaminC_cosine_precision": 0.4990059642147117,
+      "eval_VitaminC_cosine_recall": 1.0,
+      "eval_VitaminC_dot_accuracy": 0.55078125,
+      "eval_VitaminC_dot_accuracy_threshold": 318.7947082519531,
+      "eval_VitaminC_dot_ap": 0.5360598625078122,
+      "eval_VitaminC_dot_f1": 0.6657824933687002,
+      "eval_VitaminC_dot_f1_threshold": 98.82717895507812,
+      "eval_VitaminC_dot_precision": 0.4990059642147117,
+      "eval_VitaminC_dot_recall": 1.0,
+      "eval_VitaminC_euclidean_accuracy": 0.552734375,
+      "eval_VitaminC_euclidean_accuracy_threshold": 15.370981216430664,
+      "eval_VitaminC_euclidean_ap": 0.54465834495355,
+      "eval_VitaminC_euclidean_f1": 0.6657824933687002,
+      "eval_VitaminC_euclidean_f1_threshold": 24.364877700805664,
+      "eval_VitaminC_euclidean_precision": 0.4990059642147117,
+      "eval_VitaminC_euclidean_recall": 1.0,
+      "eval_VitaminC_manhattan_accuracy": 0.5546875,
+      "eval_VitaminC_manhattan_accuracy_threshold": 273.6689758300781,
+      "eval_VitaminC_manhattan_ap": 0.5450408710915566,
+      "eval_VitaminC_manhattan_f1": 0.6675531914893617,
+      "eval_VitaminC_manhattan_f1_threshold": 502.82244873046875,
+      "eval_VitaminC_manhattan_precision": 0.500998003992016,
+      "eval_VitaminC_manhattan_recall": 1.0,
+      "eval_VitaminC_max_accuracy": 0.5546875,
+      "eval_VitaminC_max_accuracy_threshold": 318.7947082519531,
+      "eval_VitaminC_max_ap": 0.5467207830251657,
+      "eval_VitaminC_max_f1": 0.6675531914893617,
+      "eval_VitaminC_max_f1_threshold": 502.82244873046875,
+      "eval_VitaminC_max_precision": 0.500998003992016,
+      "eval_VitaminC_max_recall": 1.0,
+      "eval_sequential_score": 0.5467207830251657,
+      "eval_sts-test_pearson_cosine": 0.8677868917853514,
+      "eval_sts-test_pearson_dot": 0.8601917125112223,
+      "eval_sts-test_pearson_euclidean": 0.889472619726378,
+      "eval_sts-test_pearson_manhattan": 0.890143281884324,
+      "eval_sts-test_pearson_max": 0.890143281884324,
+      "eval_sts-test_spearman_cosine": 0.8954519734959775,
+      "eval_sts-test_spearman_dot": 0.8621348855070287,
+      "eval_sts-test_spearman_euclidean": 0.8880001748147683,
+      "eval_sts-test_spearman_manhattan": 0.8870461226731652,
+      "eval_sts-test_spearman_max": 0.8954519734959775,
+      "eval_vitaminc-pairs_loss": 2.332582473754883,
+      "eval_vitaminc-pairs_runtime": 2.2432,
+      "eval_vitaminc-pairs_samples_per_second": 48.146,
+      "eval_vitaminc-pairs_steps_per_second": 0.892,
+      "step": 32
+    },
+    {
+      "epoch": 0.1,
+      "eval_negation-triplets_loss": 0.8681236505508423,
+      "eval_negation-triplets_runtime": 0.2927,
+      "eval_negation-triplets_samples_per_second": 218.641,
+      "eval_negation-triplets_steps_per_second": 3.416,
+      "step": 32
+    },
+    {
+      "epoch": 0.1,
+      "eval_scitail-pairs-pos_loss": 0.07759770005941391,
+      "eval_scitail-pairs-pos_runtime": 0.3708,
+      "eval_scitail-pairs-pos_samples_per_second": 145.613,
+      "eval_scitail-pairs-pos_steps_per_second": 2.697,
+      "step": 32
+    },
+    {
+      "epoch": 0.1,
+      "eval_xsum-pairs_loss": 0.09131219983100891,
+      "eval_xsum-pairs_runtime": 2.8486,
+      "eval_xsum-pairs_samples_per_second": 44.934,
+      "eval_xsum-pairs_steps_per_second": 0.702,
+      "step": 32
+    },
+    {
+      "epoch": 0.1,
+      "eval_sciq_pairs_loss": 0.01965576782822609,
+      "eval_sciq_pairs_runtime": 3.6062,
+      "eval_sciq_pairs_samples_per_second": 35.494,
+      "eval_sciq_pairs_steps_per_second": 0.555,
+      "step": 32
+    },
+    {
+      "epoch": 0.1,
+      "eval_qasc_pairs_loss": 0.10996829718351364,
+      "eval_qasc_pairs_runtime": 0.5975,
+      "eval_qasc_pairs_samples_per_second": 214.235,
+      "eval_qasc_pairs_steps_per_second": 3.347,
+      "step": 32
+    },
+    {
+      "epoch": 0.1,
+      "eval_openbookqa_pairs_loss": 0.6932356953620911,
+      "eval_openbookqa_pairs_runtime": 0.5729,
+      "eval_openbookqa_pairs_samples_per_second": 223.415,
+      "eval_openbookqa_pairs_steps_per_second": 3.491,
+      "step": 32
+    },
+    {
+      "epoch": 0.1,
+      "eval_msmarco_pairs_loss": 0.32686129212379456,
+      "eval_msmarco_pairs_runtime": 1.4637,
+      "eval_msmarco_pairs_samples_per_second": 87.448,
+      "eval_msmarco_pairs_steps_per_second": 1.366,
+      "step": 32
+    },
+    {
+      "epoch": 0.1,
+      "eval_nq_pairs_loss": 0.1978442668914795,
+      "eval_nq_pairs_runtime": 2.8588,
+      "eval_nq_pairs_samples_per_second": 44.774,
+      "eval_nq_pairs_steps_per_second": 0.7,
+      "step": 32
+    },
+    {
+      "epoch": 0.1,
+      "eval_trivia_pairs_loss": 0.7432661652565002,
+      "eval_trivia_pairs_runtime": 4.3895,
+      "eval_trivia_pairs_samples_per_second": 29.16,
+      "eval_trivia_pairs_steps_per_second": 0.456,
+      "step": 32
+    },
+    {
+      "epoch": 0.1,
+      "eval_gooaq_pairs_loss": 0.3761173486709595,
+      "eval_gooaq_pairs_runtime": 1.0043,
+      "eval_gooaq_pairs_samples_per_second": 127.452,
+      "eval_gooaq_pairs_steps_per_second": 1.991,
+      "step": 32
+    },
+    {
+      "epoch": 0.1,
+      "eval_paws-pos_loss": 0.02476382441818714,
+      "eval_paws-pos_runtime": 0.6858,
+      "eval_paws-pos_samples_per_second": 186.635,
+      "eval_paws-pos_steps_per_second": 2.916,
+      "step": 32
+    },
+    {
+      "epoch": 0.103125,
+      "grad_norm": 3.51029109954834,
+      "learning_rate": 1.0312500000000002e-05,
+      "loss": 0.7783,
+      "step": 33
+    },
+    {
+      "epoch": 0.10625,
+      "grad_norm": 3.376455783843994,
+      "learning_rate": 1.0625e-05,
+      "loss": 0.8746,
+      "step": 34
+    },
+    {
+      "epoch": 0.109375,
+      "grad_norm": 2.7385308742523193,
+      "learning_rate": 1.0937500000000002e-05,
+      "loss": 0.5085,
+      "step": 35
+    },
+    {
+      "epoch": 0.1125,
+      "grad_norm": 2.782606840133667,
+      "learning_rate": 1.125e-05,
+      "loss": 0.4842,
+      "step": 36
+    },
+    {
+      "epoch": 0.115625,
+      "grad_norm": 3.4377782344818115,
+      "learning_rate": 1.1562500000000002e-05,
+      "loss": 0.8097,
+      "step": 37
+    },
+    {
+      "epoch": 0.11875,
+      "grad_norm": 2.6202378273010254,
+      "learning_rate": 1.1875e-05,
+      "loss": 0.5325,
+      "step": 38
+    },
+    {
+      "epoch": 0.121875,
+      "grad_norm": 3.0869128704071045,
+      "learning_rate": 1.2187500000000001e-05,
+      "loss": 0.7221,
+      "step": 39
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 3.131516456604004,
+      "learning_rate": 1.25e-05,
+      "loss": 0.708,
+      "step": 40
+    },
+    {
+      "epoch": 0.128125,
+      "grad_norm": 2.0318033695220947,
+      "learning_rate": 1.2812500000000001e-05,
+      "loss": 0.2789,
+      "step": 41
+    },
+    {
+      "epoch": 0.13125,
+      "grad_norm": 3.2574217319488525,
+      "learning_rate": 1.3125e-05,
+      "loss": 0.7986,
+      "step": 42
+    },
+    {
+      "epoch": 0.134375,
+      "grad_norm": 3.6287729740142822,
+      "learning_rate": 1.3437500000000001e-05,
+      "loss": 0.9653,
+      "step": 43
+    },
+    {
+      "epoch": 0.1375,
+      "grad_norm": 3.1281752586364746,
+      "learning_rate": 1.375e-05,
+      "loss": 0.7857,
+      "step": 44
+    },
+    {
+      "epoch": 0.140625,
+      "grad_norm": 2.201566219329834,
+      "learning_rate": 1.4062500000000001e-05,
+      "loss": 0.2726,
+      "step": 45
+    },
+    {
+      "epoch": 0.14375,
+      "grad_norm": 1.8727688789367676,
+      "learning_rate": 1.4375e-05,
+      "loss": 0.2458,
+      "step": 46
+    },
+    {
+      "epoch": 0.146875,
+      "grad_norm": 3.156454086303711,
+      "learning_rate": 1.4687500000000001e-05,
+      "loss": 0.6988,
+      "step": 47
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 3.0224971771240234,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.6328,
+      "step": 48
+    },
+    {
+      "epoch": 0.153125,
+      "grad_norm": 3.4717319011688232,
+      "learning_rate": 1.5312500000000003e-05,
+      "loss": 0.795,
+      "step": 49
+    },
+    {
+      "epoch": 0.15625,
+      "grad_norm": 2.8961374759674072,
+      "learning_rate": 1.5625e-05,
+      "loss": 0.6163,
+      "step": 50
+    },
+    {
+      "epoch": 0.159375,
+      "grad_norm": 3.667778491973877,
+      "learning_rate": 1.59375e-05,
+      "loss": 0.8269,
+      "step": 51
+    },
+    {
+      "epoch": 0.1625,
+      "grad_norm": 2.350587844848633,
+      "learning_rate": 1.6250000000000002e-05,
+      "loss": 0.52,
+      "step": 52
+    },
+    {
+      "epoch": 0.165625,
+      "grad_norm": 3.312248468399048,
+      "learning_rate": 1.6562500000000003e-05,
+      "loss": 0.7523,
+      "step": 53
+    },
+    {
+      "epoch": 0.16875,
+      "grad_norm": 2.8101534843444824,
+      "learning_rate": 1.6875e-05,
+      "loss": 0.6979,
+      "step": 54
+    },
+    {
+      "epoch": 0.171875,
+      "grad_norm": 3.144334077835083,
+      "learning_rate": 1.71875e-05,
+      "loss": 0.7845,
+      "step": 55
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 3.671412229537964,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 0.9325,
+      "step": 56
+    },
+    {
+      "epoch": 0.178125,
+      "grad_norm": 3.204644203186035,
+      "learning_rate": 1.7812500000000003e-05,
+      "loss": 0.8546,
+      "step": 57
+    },
+    {
+      "epoch": 0.18125,
+      "grad_norm": 2.9951093196868896,
+      "learning_rate": 1.8125e-05,
+      "loss": 0.6392,
+      "step": 58
+    },
+    {
+      "epoch": 0.184375,
+      "grad_norm": 3.036386013031006,
+      "learning_rate": 1.84375e-05,
+      "loss": 0.5827,
+      "step": 59
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 3.0899698734283447,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 0.5961,
+      "step": 60
+    },
+    {
+      "epoch": 0.190625,
+      "grad_norm": 2.3574728965759277,
+      "learning_rate": 1.9062500000000003e-05,
+      "loss": 0.3625,
+      "step": 61
+    },
+    {
+      "epoch": 0.19375,
+      "grad_norm": 2.4232304096221924,
+      "learning_rate": 1.9375e-05,
+      "loss": 0.2584,
+      "step": 62
+    },
+    {
+      "epoch": 0.196875,
+      "grad_norm": 1.9016233682632446,
+      "learning_rate": 1.96875e-05,
+      "loss": 0.4047,
+      "step": 63
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 3.193114995956421,
+      "learning_rate": 2e-05,
+      "loss": 0.9429,
+      "step": 64
+    },
+    {
+      "epoch": 0.2,
+      "eval_VitaminC_cosine_accuracy": 0.560546875,
+      "eval_VitaminC_cosine_accuracy_threshold": 0.8192525506019592,
+      "eval_VitaminC_cosine_ap": 0.5485465805560719,
+      "eval_VitaminC_cosine_f1": 0.6675531914893617,
+      "eval_VitaminC_cosine_f1_threshold": 0.30620089173316956,
+      "eval_VitaminC_cosine_precision": 0.500998003992016,
+      "eval_VitaminC_cosine_recall": 1.0,
+      "eval_VitaminC_dot_accuracy": 0.5546875,
+      "eval_VitaminC_dot_accuracy_threshold": 308.60137939453125,
+      "eval_VitaminC_dot_ap": 0.5375184580780159,
+      "eval_VitaminC_dot_f1": 0.6657824933687002,
+      "eval_VitaminC_dot_f1_threshold": 97.275634765625,
+      "eval_VitaminC_dot_precision": 0.4990059642147117,
+      "eval_VitaminC_dot_recall": 1.0,
+      "eval_VitaminC_euclidean_accuracy": 0.552734375,
+      "eval_VitaminC_euclidean_accuracy_threshold": 11.976862907409668,
+      "eval_VitaminC_euclidean_ap": 0.5494925067012235,
+      "eval_VitaminC_euclidean_f1": 0.6666666666666666,
+      "eval_VitaminC_euclidean_f1_threshold": 23.21343994140625,
+      "eval_VitaminC_euclidean_precision": 0.5,
+      "eval_VitaminC_euclidean_recall": 1.0,
+      "eval_VitaminC_manhattan_accuracy": 0.552734375,
+      "eval_VitaminC_manhattan_accuracy_threshold": 313.34185791015625,
+      "eval_VitaminC_manhattan_ap": 0.5475158315491966,
+      "eval_VitaminC_manhattan_f1": 0.6666666666666666,
+      "eval_VitaminC_manhattan_f1_threshold": 495.06231689453125,
+      "eval_VitaminC_manhattan_precision": 0.5,
+      "eval_VitaminC_manhattan_recall": 1.0,
+      "eval_VitaminC_max_accuracy": 0.560546875,
+      "eval_VitaminC_max_accuracy_threshold": 313.34185791015625,
+      "eval_VitaminC_max_ap": 0.5494925067012235,
+      "eval_VitaminC_max_f1": 0.6675531914893617,
+      "eval_VitaminC_max_f1_threshold": 495.06231689453125,
+      "eval_VitaminC_max_precision": 0.500998003992016,
+      "eval_VitaminC_max_recall": 1.0,
+      "eval_sequential_score": 0.5494925067012235,
+      "eval_sts-test_pearson_cosine": 0.8681028367252808,
+      "eval_sts-test_pearson_dot": 0.8578643818026934,
+      "eval_sts-test_pearson_euclidean": 0.8913506886125709,
+      "eval_sts-test_pearson_manhattan": 0.8922209656727235,
+      "eval_sts-test_pearson_max": 0.8922209656727235,
+      "eval_sts-test_spearman_cosine": 0.8960442588011338,
+      "eval_sts-test_spearman_dot": 0.8606696844578128,
+      "eval_sts-test_spearman_euclidean": 0.8895474944286376,
+      "eval_sts-test_spearman_manhattan": 0.8895341585527426,
+      "eval_sts-test_spearman_max": 0.8960442588011338,
+      "eval_vitaminc-pairs_loss": 2.260099411010742,
+      "eval_vitaminc-pairs_runtime": 1.8392,
+      "eval_vitaminc-pairs_samples_per_second": 58.723,
+      "eval_vitaminc-pairs_steps_per_second": 1.087,
+      "step": 64
+    },
+    {
+      "epoch": 0.2,
+      "eval_negation-triplets_loss": 0.836820662021637,
+      "eval_negation-triplets_runtime": 0.294,
+      "eval_negation-triplets_samples_per_second": 217.7,
+      "eval_negation-triplets_steps_per_second": 3.402,
+      "step": 64
+    },
+    {
+      "epoch": 0.2,
+      "eval_scitail-pairs-pos_loss": 0.08362159878015518,
+      "eval_scitail-pairs-pos_runtime": 0.3686,
+      "eval_scitail-pairs-pos_samples_per_second": 146.509,
+      "eval_scitail-pairs-pos_steps_per_second": 2.713,
+      "step": 64
+    },
+    {
+      "epoch": 0.2,
+      "eval_xsum-pairs_loss": 0.08567425608634949,
+      "eval_xsum-pairs_runtime": 2.8489,
+      "eval_xsum-pairs_samples_per_second": 44.93,
+      "eval_xsum-pairs_steps_per_second": 0.702,
+      "step": 64
+    },
+    {
+      "epoch": 0.2,
+      "eval_sciq_pairs_loss": 0.019713517278432846,
+      "eval_sciq_pairs_runtime": 3.616,
+      "eval_sciq_pairs_samples_per_second": 35.399,
+      "eval_sciq_pairs_steps_per_second": 0.553,
+      "step": 64
+    },
+    {
+      "epoch": 0.2,
+      "eval_qasc_pairs_loss": 0.11403815448284149,
+      "eval_qasc_pairs_runtime": 0.6024,
+      "eval_qasc_pairs_samples_per_second": 212.48,
+      "eval_qasc_pairs_steps_per_second": 3.32,
+      "step": 64
+    },
+    {
+      "epoch": 0.2,
+      "eval_openbookqa_pairs_loss": 0.6793034076690674,
+      "eval_openbookqa_pairs_runtime": 0.5864,
+      "eval_openbookqa_pairs_samples_per_second": 218.266,
+      "eval_openbookqa_pairs_steps_per_second": 3.41,
+      "step": 64
+    },
+    {
+      "epoch": 0.2,
+      "eval_msmarco_pairs_loss": 0.34600257873535156,
+      "eval_msmarco_pairs_runtime": 1.4668,
+      "eval_msmarco_pairs_samples_per_second": 87.263,
+      "eval_msmarco_pairs_steps_per_second": 1.363,
+      "step": 64
+    },
+    {
+      "epoch": 0.2,
+      "eval_nq_pairs_loss": 0.22141708433628082,
+      "eval_nq_pairs_runtime": 2.8596,
+      "eval_nq_pairs_samples_per_second": 44.761,
+      "eval_nq_pairs_steps_per_second": 0.699,
+      "step": 64
+    },
+    {
+      "epoch": 0.2,
+      "eval_trivia_pairs_loss": 0.7303681969642639,
+      "eval_trivia_pairs_runtime": 4.3864,
+      "eval_trivia_pairs_samples_per_second": 29.181,
+      "eval_trivia_pairs_steps_per_second": 0.456,
+      "step": 64
+    },
+    {
+      "epoch": 0.2,
+      "eval_gooaq_pairs_loss": 0.38013964891433716,
+      "eval_gooaq_pairs_runtime": 1.0052,
+      "eval_gooaq_pairs_samples_per_second": 127.34,
+      "eval_gooaq_pairs_steps_per_second": 1.99,
+      "step": 64
+    },
+    {
+      "epoch": 0.2,
+      "eval_paws-pos_loss": 0.024541139602661133,
+      "eval_paws-pos_runtime": 0.6851,
+      "eval_paws-pos_samples_per_second": 186.844,
+      "eval_paws-pos_steps_per_second": 2.919,
+      "step": 64
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 640,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 64,
+  "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": 320,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-64/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffe6f56833ae1db889da47aa19784a25c77bb02e655bcfee55cb3e0df77d35b1
+size 5688