Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8432a97877e4c8e14f0d8165c07842c1dd502832b4349cffa74d225c46e76e34
+oid sha256:8e414b0a8452270265f7fdace43bbf900545ff72fd1f45d63d7d9c380723ddba
 size 1421491284

run-13/checkpoint-500/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-large",
+  "architectures": [
+    "RobertaForMultipleChoice"
+  ],
+  "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": "4.40.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-13/checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e414b0a8452270265f7fdace43bbf900545ff72fd1f45d63d7d9c380723ddba
+size 1421491284

run-13/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baefb425d7d5209640a2d0e4a67683b8b557268a505d4a92127f618320aae25e
+size 2843215085

run-13/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e800d34865c69a00523e13179b1522643e92893a41c2f88770f3a867354a978
+size 14244

run-13/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ff3659731ee58ffb7cc604ced73438ea613476b7b62f926dd186be004805043
+size 1064

run-13/checkpoint-500/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>"
+}

run-13/checkpoint-500/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>"
+}

run-13/checkpoint-500/trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.6737967914438503,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7670130729675293,
+      "eval_loss": 0.4646908640861511,
+      "eval_runtime": 8.9608,
+      "eval_samples_per_second": 332.896,
+      "eval_steps_per_second": 20.869,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8015420436859131,
+      "eval_loss": 0.4173341989517212,
+      "eval_runtime": 9.0086,
+      "eval_samples_per_second": 331.129,
+      "eval_steps_per_second": 20.758,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 10.940384864807129,
+      "learning_rate": 1.0504443448574759e-05,
+      "loss": 0.4462,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1870,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 5510487892159476.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.4338181933456057e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-13/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b988bba6140377ea3aedbabac4dbe6fbcbd79e213cfb59de5c40ef32a3e7cd
+size 5048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef8fc0cfdc6d1707e8122925de821664dabc1fdcd8070d94bbc5a29f7803d19e
+oid sha256:27b988bba6140377ea3aedbabac4dbe6fbcbd79e213cfb59de5c40ef32a3e7cd
 size 5048