Upload 11 files

roberta_pro_6_epochs/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "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": "4.50.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

roberta_pro_6_epochs/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6bca9009a7a308fb6686e813e8bed1828239df266450caa650189e167890bc8
+size 498813948

roberta_pro_6_epochs/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:309f06c5d7358e461b23bd4603cb3f6a3c7e37555e24a6afe6992e8413a8b949
+size 997748346

roberta_pro_6_epochs/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f01ee45f805a52e27a6e40e5506e3f247d8704126cba94cd92713dfa2c51df0
+size 14244

roberta_pro_6_epochs/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2257a5ce27b10f76821d98bf77c9a61af0947872c23605a0ec3d95e2c8478dd7
+size 1064

roberta_pro_6_epochs/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
+  }
+}

roberta_pro_6_epochs/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": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "unk_token": "<unk>"
+}

roberta_pro_6_epochs/trainer_state.json

@@ -0,0 +1,218 @@
+{
+  "best_global_step": 8750,
+  "best_metric": 1.504846453666687,
+  "best_model_checkpoint": "roberta_output/checkpoint-8750",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 8750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.627317428588867,
+      "learning_rate": 4.9800000000000004e-05,
+      "loss": 1.6833,
+      "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 6.079954147338867,
+      "learning_rate": 4.96e-05,
+      "loss": 1.6763,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.5534604787826538,
+      "eval_runtime": 85.6159,
+      "eval_samples_per_second": 116.801,
+      "eval_steps_per_second": 3.656,
+      "step": 1250
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 6.229701995849609,
+      "learning_rate": 4.94e-05,
+      "loss": 1.659,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 16.463504791259766,
+      "learning_rate": 4.92e-05,
+      "loss": 1.6454,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 6.997915267944336,
+      "learning_rate": 4.9e-05,
+      "loss": 1.6356,
+      "step": 2500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.5359652042388916,
+      "eval_runtime": 85.6758,
+      "eval_samples_per_second": 116.719,
+      "eval_steps_per_second": 3.653,
+      "step": 2500
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 5.758323669433594,
+      "learning_rate": 4.88e-05,
+      "loss": 1.6198,
+      "step": 3000
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 5.444720268249512,
+      "learning_rate": 4.86e-05,
+      "loss": 1.6139,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.5359666347503662,
+      "eval_runtime": 85.6435,
+      "eval_samples_per_second": 116.763,
+      "eval_steps_per_second": 3.655,
+      "step": 3750
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 5.747928619384766,
+      "learning_rate": 4.8400000000000004e-05,
+      "loss": 1.6095,
+      "step": 4000
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 5.788783073425293,
+      "learning_rate": 4.82e-05,
+      "loss": 1.6008,
+      "step": 4500
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 5.839107990264893,
+      "learning_rate": 4.8e-05,
+      "loss": 1.5959,
+      "step": 5000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.5295963287353516,
+      "eval_runtime": 85.601,
+      "eval_samples_per_second": 116.821,
+      "eval_steps_per_second": 3.657,
+      "step": 5000
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 5.5150909423828125,
+      "learning_rate": 4.78e-05,
+      "loss": 1.5863,
+      "step": 5500
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 5.19484806060791,
+      "learning_rate": 4.76e-05,
+      "loss": 1.5783,
+      "step": 6000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.521041750907898,
+      "eval_runtime": 85.5504,
+      "eval_samples_per_second": 116.89,
+      "eval_steps_per_second": 3.659,
+      "step": 6250
+    },
+    {
+      "epoch": 5.2,
+      "grad_norm": 4.922593116760254,
+      "learning_rate": 4.74e-05,
+      "loss": 1.5757,
+      "step": 6500
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 5.198918342590332,
+      "learning_rate": 4.72e-05,
+      "loss": 1.5669,
+      "step": 7000
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 5.508838176727295,
+      "learning_rate": 4.7e-05,
+      "loss": 1.5638,
+      "step": 7500
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.51933753490448,
+      "eval_runtime": 85.5798,
+      "eval_samples_per_second": 116.85,
+      "eval_steps_per_second": 3.657,
+      "step": 7500
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 4.876735210418701,
+      "learning_rate": 4.6800000000000006e-05,
+      "loss": 1.5493,
+      "step": 8000
+    },
+    {
+      "epoch": 6.8,
+      "grad_norm": 5.403846740722656,
+      "learning_rate": 4.660000000000001e-05,
+      "loss": 1.5492,
+      "step": 8500
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.504846453666687,
+      "eval_runtime": 85.5416,
+      "eval_samples_per_second": 116.902,
+      "eval_steps_per_second": 3.659,
+      "step": 8750
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 125000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 100,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.371432972288e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

roberta_pro_6_epochs/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d3ac66c23bc07aa4108bd6fcee5766e2f79743d3afda86626f1ba2d0948341a
+size 5368