Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05fe06169dbaa744f5d41938724b2ee4787a338b283e95233ba3da4c88c19345
+oid sha256:a440a4f9cfd036bb6b0def9457b6e506188504c0d067b5fdf912cb98e0c2e006
 size 1421491284

run-8/checkpoint-1500/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-8/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a440a4f9cfd036bb6b0def9457b6e506188504c0d067b5fdf912cb98e0c2e006
+size 1421491284

run-8/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2cbb97709e7144b3d0ab0e358ccb04aeb9cf148723bb47616bb8695ab9c1588
+size 2843215085

run-8/checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f48dc2f5362fb223b487a26aed5961225e681be7dd0c9dcd202d693a285b27e
+size 14244

run-8/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bde3caf35cf8c1e0a71c93a438689c402acf594cb95fffb3af47e38206608b14
+size 1064

run-8/checkpoint-1500/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-8/checkpoint-1500/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-8/checkpoint-1500/trainer_state.json

@@ -0,0 +1,117 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.02139037433155,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.748240053653717,
+      "eval_loss": 0.4897768199443817,
+      "eval_runtime": 9.3572,
+      "eval_samples_per_second": 318.792,
+      "eval_steps_per_second": 19.985,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7867918014526367,
+      "eval_loss": 0.4351676404476166,
+      "eval_runtime": 9.48,
+      "eval_samples_per_second": 314.662,
+      "eval_steps_per_second": 19.726,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 15.95652961730957,
+      "learning_rate": 4.723376230943584e-06,
+      "loss": 0.4992,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8079115152359009,
+      "eval_loss": 0.413047730922699,
+      "eval_runtime": 9.447,
+      "eval_samples_per_second": 315.76,
+      "eval_steps_per_second": 19.795,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.805229663848877,
+      "eval_loss": 0.4279593527317047,
+      "eval_runtime": 9.494,
+      "eval_samples_per_second": 314.198,
+      "eval_steps_per_second": 19.697,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8109285831451416,
+      "eval_loss": 0.46117427945137024,
+      "eval_runtime": 9.4914,
+      "eval_samples_per_second": 314.286,
+      "eval_steps_per_second": 19.702,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 18.722320556640625,
+      "learning_rate": 2.9995162926430056e-06,
+      "loss": 0.258,
+      "step": 1000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8129400014877319,
+      "eval_loss": 0.5127686262130737,
+      "eval_runtime": 9.3459,
+      "eval_samples_per_second": 319.179,
+      "eval_steps_per_second": 20.009,
+      "step": 1122
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8069058060646057,
+      "eval_loss": 0.5462248921394348,
+      "eval_runtime": 9.4811,
+      "eval_samples_per_second": 314.625,
+      "eval_steps_per_second": 19.723,
+      "step": 1309
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8112637996673584,
+      "eval_loss": 0.5747013688087463,
+      "eval_runtime": 9.4581,
+      "eval_samples_per_second": 315.392,
+      "eval_steps_per_second": 19.771,
+      "step": 1496
+    },
+    {
+      "epoch": 8.02139037433155,
+      "grad_norm": 17.311113357543945,
+      "learning_rate": 1.2756563543424279e-06,
+      "loss": 0.1447,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1870,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 2.010272908557654e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.447236169244162e-06,
+    "per_device_train_batch_size": 64
+  }
+}

run-8/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e40e8cef35b8bcc1ef26293c9bc0d35e5378a8e1a03af177be080cc43a98fabb
+size 5048