Upload 12 files

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/home/lucyl/llm_social_identities/outputs/identity/roberta_10ep",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "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": 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": "4.32.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:260a8abf56b32a4194c20d14d09cf014350f0f2ff73f8f731b65ce5cb369856b
+size 992613498

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:759b590433ec2bb70977c40cc8a6084fb206d8c2699c9bf4c5a0fa8330dab8b6
+size 496292326

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45d42197db00f096790c83e4f1290ab2630a65a1cc92021cf4bc7fff680b36fd
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b717cc593bc1683cdce0779667a9a28aff74570f8aab1b94bce0668f664b90b7
+size 1064

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "add_prefix_space": false,
+  "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
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,63 @@
+{
+  "best_metric": 0.8933177022274327,
+  "best_model_checkpoint": "./roberta_10ep-roles-3e-05/checkpoint-300",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.8915956151035322,
+      "eval_loss": 0.03141865134239197,
+      "eval_precision": 0.9336734693877551,
+      "eval_recall": 0.8531468531468531,
+      "eval_runtime": 7.0392,
+      "eval_samples_per_second": 28.412,
+      "eval_steps_per_second": 3.552,
+      "step": 75
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.878048780487805,
+      "eval_loss": 0.03434527665376663,
+      "eval_precision": 0.8372093023255814,
+      "eval_recall": 0.9230769230769231,
+      "eval_runtime": 7.2469,
+      "eval_samples_per_second": 27.598,
+      "eval_steps_per_second": 3.45,
+      "step": 150
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.8546824542518838,
+      "eval_loss": 0.04272409528493881,
+      "eval_precision": 0.794,
+      "eval_recall": 0.9254079254079254,
+      "eval_runtime": 7.4309,
+      "eval_samples_per_second": 26.914,
+      "eval_steps_per_second": 3.364,
+      "step": 225
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.8933177022274327,
+      "eval_loss": 0.03827732056379318,
+      "eval_precision": 0.8985849056603774,
+      "eval_recall": 0.8881118881118881,
+      "eval_runtime": 7.1978,
+      "eval_samples_per_second": 27.786,
+      "eval_steps_per_second": 3.473,
+      "step": 300
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 750,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 236841013410240.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39711563e9f6654215f8f974c45f9533cbb7107ee6a20418db54426c3fb5c5fd
+size 4536