Upload folder using huggingface_hub

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "../result/valentwin-cihr-n-100-hn-10-selective-neg-lr-3e5-bs-512-20240421",
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.txt

@@ -0,0 +1,2 @@
+epoch = 3.0
+eval_accuracy = 0.9842582394306533

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccfe8b0653131d6b9cf1c76ab007c8afd651738f1c9206587d72742e6873333b
+size 498604904

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78479e41c479945636a7f210017b26e898a78e18dd818be99122f8dea3ffcf1e
+size 997331514

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b3ca595c50840eaa4c7865bc854327c27fbe92babb00e080b735dcc644bb575
+size 1064

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "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>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

train_results.txt

@@ -0,0 +1,3 @@
+epoch = 3.0
+train_runtime = 1970.7768
+train_samples_per_second = 0.592

trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": 0.9854150282405091,
+  "best_model_checkpoint": "../result/valentwin-cihr-n-100-hn-10-selective-neg-lr-3e5-bs-512-20240421",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1167,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.9999999999999998e-05,
+      "loss": 0.2774,
+      "step": 389
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9854150282405091,
+      "step": 389
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 9.999999999999999e-06,
+      "loss": 0.0806,
+      "step": 778
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9845928362050476,
+      "step": 778
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.0458,
+      "step": 1167
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9829484521341245,
+      "step": 1167
+    },
+    {
+      "epoch": 3.0,
+      "step": 1167,
+      "total_flos": 0,
+      "train_runtime": 1970.7768,
+      "train_samples_per_second": 0.592
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1167,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": null,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adaa1d8aad9ad884cd7235f2b290c3bacd9b12e8aee28dbf9debc9aaf2cfe347
+size 4920