Training in progress, epoch 1, 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": "microsoft/deberta-v3-base",
+  "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": 12,
+  "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:c217ec5ed7683232d5d3afb449087bb11e4db849e8b1efff8c729af39b54d5e5
+size 1470818042

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd2f3f68ba49d47cbec07de1aa03058e8d378b613393580878612d075ed121ae
+size 735393442

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc714c88ec391a98111803512f7736018b315d823b10b032755e42e945ba2c0f
+size 14180

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e0999f04ac6f6b7e8411fbfda0087582e9c80162eed3de595c2a89025e9fbdb
+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 +1,15 @@
+{
+  "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
+  }
+}

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 +1,58 @@
+{
+  "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"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,343 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 5269,
+  "global_step": 52690,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 32.186187744140625,
+      "learning_rate": 4.995255266654014e-07,
+      "loss": 2.5594,
+      "step": 5269
+    },
+    {
+      "epoch": 0.1,
+      "eval_nli-pairs_loss": 2.4415905475616455,
+      "eval_nli-pairs_runtime": 54.4725,
+      "eval_nli-pairs_samples_per_second": 124.98,
+      "eval_nli-pairs_steps_per_second": 12.502,
+      "step": 5269
+    },
+    {
+      "epoch": 0.1,
+      "eval_scitail-pairs-pos_loss": 2.6613597869873047,
+      "eval_scitail-pairs-pos_runtime": 10.8398,
+      "eval_scitail-pairs-pos_samples_per_second": 120.297,
+      "eval_scitail-pairs-pos_steps_per_second": 12.085,
+      "step": 5269
+    },
+    {
+      "epoch": 0.1,
+      "eval_qnli-contrastive_loss": 1.159198522567749,
+      "eval_qnli-contrastive_runtime": 35.2131,
+      "eval_qnli-contrastive_samples_per_second": 155.141,
+      "eval_qnli-contrastive_steps_per_second": 15.534,
+      "step": 5269
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 52.057003021240234,
+      "learning_rate": 9.992408426646422e-07,
+      "loss": 1.4137,
+      "step": 10538
+    },
+    {
+      "epoch": 0.2,
+      "eval_nli-pairs_loss": 1.1457639932632446,
+      "eval_nli-pairs_runtime": 54.3904,
+      "eval_nli-pairs_samples_per_second": 125.169,
+      "eval_nli-pairs_steps_per_second": 12.521,
+      "step": 10538
+    },
+    {
+      "epoch": 0.2,
+      "eval_scitail-pairs-pos_loss": 1.2518893480300903,
+      "eval_scitail-pairs-pos_runtime": 11.0182,
+      "eval_scitail-pairs-pos_samples_per_second": 118.349,
+      "eval_scitail-pairs-pos_steps_per_second": 11.889,
+      "step": 10538
+    },
+    {
+      "epoch": 0.2,
+      "eval_qnli-contrastive_loss": 0.7108705639839172,
+      "eval_qnli-contrastive_runtime": 35.5561,
+      "eval_qnli-contrastive_samples_per_second": 153.644,
+      "eval_qnli-contrastive_steps_per_second": 15.384,
+      "step": 10538
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.281833648681641,
+      "learning_rate": 1.4990510533308028e-06,
+      "loss": 0.8171,
+      "step": 15807
+    },
+    {
+      "epoch": 0.3,
+      "eval_nli-pairs_loss": 0.687666654586792,
+      "eval_nli-pairs_runtime": 54.1668,
+      "eval_nli-pairs_samples_per_second": 125.686,
+      "eval_nli-pairs_steps_per_second": 12.572,
+      "step": 15807
+    },
+    {
+      "epoch": 0.3,
+      "eval_scitail-pairs-pos_loss": 0.7561426758766174,
+      "eval_scitail-pairs-pos_runtime": 10.851,
+      "eval_scitail-pairs-pos_samples_per_second": 120.173,
+      "eval_scitail-pairs-pos_steps_per_second": 12.073,
+      "step": 15807
+    },
+    {
+      "epoch": 0.3,
+      "eval_qnli-contrastive_loss": 0.3190048038959503,
+      "eval_qnli-contrastive_runtime": 35.1986,
+      "eval_qnli-contrastive_samples_per_second": 155.205,
+      "eval_qnli-contrastive_steps_per_second": 15.54,
+      "step": 15807
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.00767707824707,
+      "learning_rate": 1.998766369330044e-06,
+      "loss": 0.6407,
+      "step": 21076
+    },
+    {
+      "epoch": 0.4,
+      "eval_nli-pairs_loss": 0.5073979496955872,
+      "eval_nli-pairs_runtime": 55.8366,
+      "eval_nli-pairs_samples_per_second": 121.927,
+      "eval_nli-pairs_steps_per_second": 12.196,
+      "step": 21076
+    },
+    {
+      "epoch": 0.4,
+      "eval_scitail-pairs-pos_loss": 0.6417884826660156,
+      "eval_scitail-pairs-pos_runtime": 11.0871,
+      "eval_scitail-pairs-pos_samples_per_second": 117.614,
+      "eval_scitail-pairs-pos_steps_per_second": 11.816,
+      "step": 21076
+    },
+    {
+      "epoch": 0.4,
+      "eval_qnli-contrastive_loss": 0.09126196801662445,
+      "eval_qnli-contrastive_runtime": 35.8847,
+      "eval_qnli-contrastive_samples_per_second": 152.238,
+      "eval_qnli-contrastive_steps_per_second": 15.243,
+      "step": 21076
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 11.507905006408691,
+      "learning_rate": 2.498766369330044e-06,
+      "loss": 0.5218,
+      "step": 26345
+    },
+    {
+      "epoch": 0.5,
+      "eval_nli-pairs_loss": 0.44188740849494934,
+      "eval_nli-pairs_runtime": 56.6102,
+      "eval_nli-pairs_samples_per_second": 120.261,
+      "eval_nli-pairs_steps_per_second": 12.03,
+      "step": 26345
+    },
+    {
+      "epoch": 0.5,
+      "eval_scitail-pairs-pos_loss": 0.5492118000984192,
+      "eval_scitail-pairs-pos_runtime": 11.3133,
+      "eval_scitail-pairs-pos_samples_per_second": 115.262,
+      "eval_scitail-pairs-pos_steps_per_second": 11.579,
+      "step": 26345
+    },
+    {
+      "epoch": 0.5,
+      "eval_qnli-contrastive_loss": 0.059079792350530624,
+      "eval_qnli-contrastive_runtime": 36.1632,
+      "eval_qnli-contrastive_samples_per_second": 151.065,
+      "eval_qnli-contrastive_steps_per_second": 15.126,
+      "step": 26345
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 26.949726104736328,
+      "learning_rate": 2.9984816853292846e-06,
+      "loss": 0.4179,
+      "step": 31614
+    },
+    {
+      "epoch": 0.6,
+      "eval_nli-pairs_loss": 0.3886905908584595,
+      "eval_nli-pairs_runtime": 54.62,
+      "eval_nli-pairs_samples_per_second": 124.643,
+      "eval_nli-pairs_steps_per_second": 12.468,
+      "step": 31614
+    },
+    {
+      "epoch": 0.6,
+      "eval_scitail-pairs-pos_loss": 0.5096117258071899,
+      "eval_scitail-pairs-pos_runtime": 10.7482,
+      "eval_scitail-pairs-pos_samples_per_second": 121.322,
+      "eval_scitail-pairs-pos_steps_per_second": 12.188,
+      "step": 31614
+    },
+    {
+      "epoch": 0.6,
+      "eval_qnli-contrastive_loss": 0.05674454942345619,
+      "eval_qnli-contrastive_runtime": 35.3006,
+      "eval_qnli-contrastive_samples_per_second": 154.757,
+      "eval_qnli-contrastive_steps_per_second": 15.496,
+      "step": 31614
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 18.11922264099121,
+      "learning_rate": 3.4983867906623653e-06,
+      "loss": 0.367,
+      "step": 36883
+    },
+    {
+      "epoch": 0.7,
+      "eval_nli-pairs_loss": 0.3481854200363159,
+      "eval_nli-pairs_runtime": 55.4291,
+      "eval_nli-pairs_samples_per_second": 122.824,
+      "eval_nli-pairs_steps_per_second": 12.286,
+      "step": 36883
+    },
+    {
+      "epoch": 0.7,
+      "eval_scitail-pairs-pos_loss": 0.4593205451965332,
+      "eval_scitail-pairs-pos_runtime": 11.5988,
+      "eval_scitail-pairs-pos_samples_per_second": 112.425,
+      "eval_scitail-pairs-pos_steps_per_second": 11.294,
+      "step": 36883
+    },
+    {
+      "epoch": 0.7,
+      "eval_qnli-contrastive_loss": 0.04647330939769745,
+      "eval_qnli-contrastive_runtime": 36.5049,
+      "eval_qnli-contrastive_samples_per_second": 149.651,
+      "eval_qnli-contrastive_steps_per_second": 14.984,
+      "step": 36883
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 89.04375457763672,
+      "learning_rate": 3.998197001328526e-06,
+      "loss": 0.3646,
+      "step": 42152
+    },
+    {
+      "epoch": 0.8,
+      "eval_nli-pairs_loss": 0.3271665871143341,
+      "eval_nli-pairs_runtime": 56.627,
+      "eval_nli-pairs_samples_per_second": 120.225,
+      "eval_nli-pairs_steps_per_second": 12.026,
+      "step": 42152
+    },
+    {
+      "epoch": 0.8,
+      "eval_scitail-pairs-pos_loss": 0.4691656827926636,
+      "eval_scitail-pairs-pos_runtime": 11.2939,
+      "eval_scitail-pairs-pos_samples_per_second": 115.46,
+      "eval_scitail-pairs-pos_steps_per_second": 11.599,
+      "step": 42152
+    },
+    {
+      "epoch": 0.8,
+      "eval_qnli-contrastive_loss": 0.0342307947576046,
+      "eval_qnli-contrastive_runtime": 37.0788,
+      "eval_qnli-contrastive_samples_per_second": 147.335,
+      "eval_qnli-contrastive_steps_per_second": 14.752,
+      "step": 42152
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 34.519649505615234,
+      "learning_rate": 4.498007211994686e-06,
+      "loss": 0.3247,
+      "step": 47421
+    },
+    {
+      "epoch": 0.9,
+      "eval_nli-pairs_loss": 0.3092634379863739,
+      "eval_nli-pairs_runtime": 55.8823,
+      "eval_nli-pairs_samples_per_second": 121.827,
+      "eval_nli-pairs_steps_per_second": 12.186,
+      "step": 47421
+    },
+    {
+      "epoch": 0.9,
+      "eval_scitail-pairs-pos_loss": 0.5043854713439941,
+      "eval_scitail-pairs-pos_runtime": 11.0598,
+      "eval_scitail-pairs-pos_samples_per_second": 117.904,
+      "eval_scitail-pairs-pos_steps_per_second": 11.845,
+      "step": 47421
+    },
+    {
+      "epoch": 0.9,
+      "eval_qnli-contrastive_loss": 0.02216612547636032,
+      "eval_qnli-contrastive_runtime": 35.7978,
+      "eval_qnli-contrastive_samples_per_second": 152.607,
+      "eval_qnli-contrastive_steps_per_second": 15.28,
+      "step": 47421
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9374290704727173,
+      "learning_rate": 4.997722527993928e-06,
+      "loss": 0.3045,
+      "step": 52690
+    },
+    {
+      "epoch": 1.0,
+      "eval_nli-pairs_loss": 0.27252256870269775,
+      "eval_nli-pairs_runtime": 55.7637,
+      "eval_nli-pairs_samples_per_second": 122.087,
+      "eval_nli-pairs_steps_per_second": 12.212,
+      "step": 52690
+    },
+    {
+      "epoch": 1.0,
+      "eval_scitail-pairs-pos_loss": 0.469696968793869,
+      "eval_scitail-pairs-pos_runtime": 11.1594,
+      "eval_scitail-pairs-pos_samples_per_second": 116.853,
+      "eval_scitail-pairs-pos_steps_per_second": 11.739,
+      "step": 52690
+    },
+    {
+      "epoch": 1.0,
+      "eval_qnli-contrastive_loss": 0.03896098583936691,
+      "eval_qnli-contrastive_runtime": 35.7023,
+      "eval_qnli-contrastive_samples_per_second": 153.015,
+      "eval_qnli-contrastive_steps_per_second": 15.321,
+      "step": 52690
+    }
+  ],
+  "logging_steps": 5269,
+  "max_steps": 105380,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 52690,
+  "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": 10,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36afad19446fa02ac0a40c7db17592710986db217478b739cb810c41992639a0
+size 5624