Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5469907e6049aa7f762ee36fc642a97e48233fa0bf3001e9e70008683ab69264
+oid sha256:c194fa572fc8c37531705b1f7a84d3c6dffbc34089014fe059a206ddd4dcbe85
 size 1421491284

run-5/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-5/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c194fa572fc8c37531705b1f7a84d3c6dffbc34089014fe059a206ddd4dcbe85
+size 1421491284

run-5/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4e3e3dddebdc21ea2cdc6892ebed831f7c977178c2e442723052fd1d32f07de
+size 2843215085

run-5/checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337d994df14d2464b8db4f75ed5528cb65ff69cc995770db5a502206a6a568df
+size 14244

run-5/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b5a762f82f83e795fe61e6c1e6bb75845b11f78730b02d6c88a4084e41ee603
+size 1064

run-5/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-5/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-5/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": 0.7180690765380859,
+      "eval_loss": 0.5168977379798889,
+      "eval_runtime": 8.9988,
+      "eval_samples_per_second": 331.49,
+      "eval_steps_per_second": 20.781,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7489104866981506,
+      "eval_loss": 0.4839635193347931,
+      "eval_runtime": 9.0276,
+      "eval_samples_per_second": 330.431,
+      "eval_steps_per_second": 20.714,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 11.86405086517334,
+      "learning_rate": 2.657717114424308e-06,
+      "loss": 0.5459,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7710358500480652,
+      "eval_loss": 0.45898401737213135,
+      "eval_runtime": 8.9655,
+      "eval_samples_per_second": 332.719,
+      "eval_steps_per_second": 20.858,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7814280986785889,
+      "eval_loss": 0.452875018119812,
+      "eval_runtime": 9.0244,
+      "eval_samples_per_second": 330.549,
+      "eval_steps_per_second": 20.722,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7918202877044678,
+      "eval_loss": 0.439310222864151,
+      "eval_runtime": 9.0184,
+      "eval_samples_per_second": 330.768,
+      "eval_steps_per_second": 20.735,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 13.807589530944824,
+      "learning_rate": 1.6877473646344146e-06,
+      "loss": 0.3888,
+      "step": 1000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8002011179924011,
+      "eval_loss": 0.45794954895973206,
+      "eval_runtime": 9.0045,
+      "eval_samples_per_second": 331.28,
+      "eval_steps_per_second": 20.767,
+      "step": 1122
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8008716106414795,
+      "eval_loss": 0.47091251611709595,
+      "eval_runtime": 9.035,
+      "eval_samples_per_second": 330.161,
+      "eval_steps_per_second": 20.697,
+      "step": 1309
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7991954684257507,
+      "eval_loss": 0.4877369999885559,
+      "eval_runtime": 9.0082,
+      "eval_samples_per_second": 331.141,
+      "eval_steps_per_second": 20.759,
+      "step": 1496
+    },
+    {
+      "epoch": 8.02139037433155,
+      "grad_norm": 17.31001853942871,
+      "learning_rate": 7.177776148445211e-07,
+      "loss": 0.2962,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1870,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.643409902012778e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.6276868642142013e-06,
+    "per_device_train_batch_size": 64
+  }
+}

run-5/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1f5a8f4338857cbef25f978b916b2b96d715df58cda996e714ae3406bfce470
+size 5048