Upload model checkpoint

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-large",
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9431444413842ade34a60bc2d3e98d5ac8058a25c71da83ba2246a469405efa4
+size 1421696540

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91c51f6e34a6c1445391b358694102207590ec33479f2a3dc7398fa03d1f7939
+size 2843626160

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24cc77481921af13c8a2bc773303ad06adbb7095f40644235398cf0ec917cbdc
+size 14244

roberta_incl_struct_no_token_training.log

@@ -0,0 +1,22 @@
+2024-08-21 20:57:58,282 - INFO - Step 15000: training loss = 2.7341
+2024-08-21 21:17:17,134 - INFO - Step 15000: validation loss = 2.2858
+2024-08-21 22:01:32,729 - INFO - Step 30000: training loss = 2.3026
+2024-08-21 22:20:44,236 - INFO - Step 30000: validation loss = 2.1000
+2024-08-21 23:05:05,779 - INFO - Step 45000: training loss = 2.1131
+2024-08-21 23:24:02,233 - INFO - Step 45000: validation loss = 1.9409
+2024-08-22 00:08:16,019 - INFO - Step 60000: training loss = 1.9718
+2024-08-22 00:27:15,134 - INFO - Step 60000: validation loss = 1.8382
+2024-08-22 01:11:31,471 - INFO - Step 75000: training loss = 1.8708
+2024-08-22 01:30:36,834 - INFO - Step 75000: validation loss = 1.7578
+2024-08-22 02:14:57,485 - INFO - Step 90000: training loss = 1.8018
+2024-08-22 02:33:58,733 - INFO - Step 90000: validation loss = 1.6910
+2024-08-22 03:18:14,451 - INFO - Step 105000: training loss = 1.7164
+2024-08-22 03:37:19,532 - INFO - Step 105000: validation loss = 1.6318
+2024-08-22 04:21:28,731 - INFO - Step 120000: training loss = 1.6587
+2024-08-22 04:40:35,634 - INFO - Step 120000: validation loss = 1.5805
+2024-08-22 05:24:54,815 - INFO - Step 135000: training loss = 1.6155
+2024-08-22 05:43:59,034 - INFO - Step 135000: validation loss = 1.5369
+2024-08-22 06:28:17,638 - INFO - Step 150000: training loss = 1.5718
+2024-08-22 06:47:22,234 - INFO - Step 150000: validation loss = 1.4997
+2024-08-22 07:31:32,583 - INFO - Step 165000: training loss = 1.5311
+2024-08-22 07:50:39,333 - INFO - Step 165000: validation loss = 1.4691

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35fa84f293213c0ffc806c56c1911ac05f432ca27985b69caf5489c96822978c
+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 +1,56 @@
+{
+  "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",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,138 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 25000,
+  "global_step": 178100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2807411566535654,
+      "grad_norm": 25.670791625976562,
+      "learning_rate": 4.776186911223408e-05,
+      "loss": 2.2509,
+      "step": 25000
+    },
+    {
+      "epoch": 0.2807411566535654,
+      "eval_loss": 1.907800555229187,
+      "eval_runtime": 1183.5578,
+      "eval_samples_per_second": 150.478,
+      "eval_steps_per_second": 1.176,
+      "step": 25000
+    },
+    {
+      "epoch": 0.5614823133071308,
+      "grad_norm": 27.820302963256836,
+      "learning_rate": 3.996599912658307e-05,
+      "loss": 1.9956,
+      "step": 50000
+    },
+    {
+      "epoch": 0.5614823133071308,
+      "eval_loss": 1.7114382982254028,
+      "eval_runtime": 1201.8966,
+      "eval_samples_per_second": 148.182,
+      "eval_steps_per_second": 1.158,
+      "step": 50000
+    },
+    {
+      "epoch": 0.8422234699606962,
+      "grad_norm": 19.808177947998047,
+      "learning_rate": 3.217106494478758e-05,
+      "loss": 1.7858,
+      "step": 75000
+    },
+    {
+      "epoch": 0.8422234699606962,
+      "eval_loss": 1.5567296743392944,
+      "eval_runtime": 1196.901,
+      "eval_samples_per_second": 148.801,
+      "eval_steps_per_second": 1.163,
+      "step": 75000
+    },
+    {
+      "epoch": 1.1229646266142617,
+      "grad_norm": 13.513537406921387,
+      "learning_rate": 2.437550689375507e-05,
+      "loss": 1.6379,
+      "step": 100000
+    },
+    {
+      "epoch": 1.1229646266142617,
+      "eval_loss": 1.4506515264511108,
+      "eval_runtime": 1128.3856,
+      "eval_samples_per_second": 157.836,
+      "eval_steps_per_second": 1.234,
+      "step": 100000
+    },
+    {
+      "epoch": 1.403705783267827,
+      "grad_norm": 13.943450927734375,
+      "learning_rate": 1.657932497348556e-05,
+      "loss": 1.5144,
+      "step": 125000
+    },
+    {
+      "epoch": 1.403705783267827,
+      "eval_loss": 1.35755455493927,
+      "eval_runtime": 1141.3087,
+      "eval_samples_per_second": 156.049,
+      "eval_steps_per_second": 1.22,
+      "step": 125000
+    },
+    {
+      "epoch": 1.6844469399213926,
+      "grad_norm": 18.438793182373047,
+      "learning_rate": 8.784078857071558e-06,
+      "loss": 1.411,
+      "step": 150000
+    },
+    {
+      "epoch": 1.6844469399213926,
+      "eval_loss": 1.28085196018219,
+      "eval_runtime": 1121.6941,
+      "eval_samples_per_second": 158.778,
+      "eval_steps_per_second": 1.241,
+      "step": 150000
+    },
+    {
+      "epoch": 1.9651880965749577,
+      "grad_norm": 7.969166278839111,
+      "learning_rate": 9.878969368020464e-07,
+      "loss": 1.3335,
+      "step": 175000
+    },
+    {
+      "epoch": 1.9651880965749577,
+      "eval_loss": 1.2316101789474487,
+      "eval_runtime": 1133.5552,
+      "eval_samples_per_second": 157.116,
+      "eval_steps_per_second": 1.228,
+      "step": 175000
+    }
+  ],
+  "logging_steps": 25000,
+  "max_steps": 178100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 25000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.328028350210777e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fb161d6fd43588d86af1ecc0380285ffc25f8f4558fdafa22fcaac4fc82d8dc
+size 5112