Training in progress, step 3500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce1272b2082c074f0396519cd808a4c8119978b44e5383f2cbfd6d144af45eb4
+oid sha256:4f7d25481e681f44ba27d8739c8e323e06580f610b8d3af37a2d8c34237721c9
 size 1421491284

run-4/checkpoint-3000/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-4/checkpoint-3000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a4ade2943d946a6d71dba6fe2b47738ed94311a0d8886d6af14a53dea3ff71e
+size 1421491284

run-4/checkpoint-3000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f74c14c100b5319487b15924161b31dbe6af2835763d98549df3cd1b4ba500a
+size 2843215085

run-4/checkpoint-3000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39d877b28a8cd06c07aabb601fbd8f6ea1d4177967208aba352cb58683f5b319
+size 14244

run-4/checkpoint-3000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:392812e78d7d500c6b36e07a2042cf14ebc2132ecad0d73592464a51b325c06d
+size 1064

run-4/checkpoint-3000/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-4/checkpoint-3000/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-4/checkpoint-3000/trainer_state.json

@@ -0,0 +1,138 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.04289544235925,
+  "eval_steps": 500,
+  "global_step": 3000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7321488261222839,
+      "eval_loss": 0.5215846300125122,
+      "eval_runtime": 9.3633,
+      "eval_samples_per_second": 318.585,
+      "eval_steps_per_second": 19.972,
+      "step": 373
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 13.217938423156738,
+      "learning_rate": 2.418286940875578e-06,
+      "loss": 0.5967,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7723767757415771,
+      "eval_loss": 0.45723703503608704,
+      "eval_runtime": 9.2866,
+      "eval_samples_per_second": 321.216,
+      "eval_steps_per_second": 20.137,
+      "step": 746
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 15.163392066955566,
+      "learning_rate": 2.043939117210628e-06,
+      "loss": 0.4683,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.796513557434082,
+      "eval_loss": 0.4389999508857727,
+      "eval_runtime": 9.2689,
+      "eval_samples_per_second": 321.829,
+      "eval_steps_per_second": 20.175,
+      "step": 1119
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8055648803710938,
+      "eval_loss": 0.45021912455558777,
+      "eval_runtime": 9.4524,
+      "eval_samples_per_second": 315.58,
+      "eval_steps_per_second": 19.783,
+      "step": 1492
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 33.55284118652344,
+      "learning_rate": 1.6695912935456774e-06,
+      "loss": 0.3783,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8079115152359009,
+      "eval_loss": 0.4486864507198334,
+      "eval_runtime": 9.329,
+      "eval_samples_per_second": 319.756,
+      "eval_steps_per_second": 20.045,
+      "step": 1865
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 17.95193862915039,
+      "learning_rate": 1.2952434698807272e-06,
+      "loss": 0.3049,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8139457106590271,
+      "eval_loss": 0.44699645042419434,
+      "eval_runtime": 9.3232,
+      "eval_samples_per_second": 319.955,
+      "eval_steps_per_second": 20.058,
+      "step": 2238
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 19.94598388671875,
+      "learning_rate": 9.208956462157772e-07,
+      "loss": 0.2663,
+      "step": 2500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8162923455238342,
+      "eval_loss": 0.4586087167263031,
+      "eval_runtime": 9.3905,
+      "eval_samples_per_second": 317.661,
+      "eval_steps_per_second": 19.914,
+      "step": 2611
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8169627785682678,
+      "eval_loss": 0.46715453267097473,
+      "eval_runtime": 9.458,
+      "eval_samples_per_second": 315.395,
+      "eval_steps_per_second": 19.772,
+      "step": 2984
+    },
+    {
+      "epoch": 8.04289544235925,
+      "grad_norm": 21.875141143798828,
+      "learning_rate": 5.465478225508271e-07,
+      "loss": 0.2394,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.6826244219836316e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.7926347645405278e-06,
+    "per_device_train_batch_size": 32
+  }
+}

run-4/checkpoint-3000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7db8a7a0dfed6f985d34492a77fc54ac5788fe514ba2cde45d3b63947da0c296
+size 5048

run-4/checkpoint-3500/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-4/checkpoint-3500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f7d25481e681f44ba27d8739c8e323e06580f610b8d3af37a2d8c34237721c9
+size 1421491284

run-4/checkpoint-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f05dc77f0e86a22e4e4c336bc492006ea90ba165f24bc269d1da22bb8ca4b9c5
+size 2843215085

run-4/checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89fcfe9c1b5080b260fd4f680dbc672465e21ae3377576806ff2322f72cb0630
+size 14244

run-4/checkpoint-3500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24b707ef72de5b8d53eeae53cb7eb60b47e56ba3da28baa61c94cbfe7a768fb8
+size 1064

run-4/checkpoint-3500/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-4/checkpoint-3500/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-4/checkpoint-3500/trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.383378016085791,
+  "eval_steps": 500,
+  "global_step": 3500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7321488261222839,
+      "eval_loss": 0.5215846300125122,
+      "eval_runtime": 9.3633,
+      "eval_samples_per_second": 318.585,
+      "eval_steps_per_second": 19.972,
+      "step": 373
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 13.217938423156738,
+      "learning_rate": 2.418286940875578e-06,
+      "loss": 0.5967,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7723767757415771,
+      "eval_loss": 0.45723703503608704,
+      "eval_runtime": 9.2866,
+      "eval_samples_per_second": 321.216,
+      "eval_steps_per_second": 20.137,
+      "step": 746
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 15.163392066955566,
+      "learning_rate": 2.043939117210628e-06,
+      "loss": 0.4683,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.796513557434082,
+      "eval_loss": 0.4389999508857727,
+      "eval_runtime": 9.2689,
+      "eval_samples_per_second": 321.829,
+      "eval_steps_per_second": 20.175,
+      "step": 1119
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8055648803710938,
+      "eval_loss": 0.45021912455558777,
+      "eval_runtime": 9.4524,
+      "eval_samples_per_second": 315.58,
+      "eval_steps_per_second": 19.783,
+      "step": 1492
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 33.55284118652344,
+      "learning_rate": 1.6695912935456774e-06,
+      "loss": 0.3783,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8079115152359009,
+      "eval_loss": 0.4486864507198334,
+      "eval_runtime": 9.329,
+      "eval_samples_per_second": 319.756,
+      "eval_steps_per_second": 20.045,
+      "step": 1865
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 17.95193862915039,
+      "learning_rate": 1.2952434698807272e-06,
+      "loss": 0.3049,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8139457106590271,
+      "eval_loss": 0.44699645042419434,
+      "eval_runtime": 9.3232,
+      "eval_samples_per_second": 319.955,
+      "eval_steps_per_second": 20.058,
+      "step": 2238
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 19.94598388671875,
+      "learning_rate": 9.208956462157772e-07,
+      "loss": 0.2663,
+      "step": 2500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8162923455238342,
+      "eval_loss": 0.4586087167263031,
+      "eval_runtime": 9.3905,
+      "eval_samples_per_second": 317.661,
+      "eval_steps_per_second": 19.914,
+      "step": 2611
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8169627785682678,
+      "eval_loss": 0.46715453267097473,
+      "eval_runtime": 9.458,
+      "eval_samples_per_second": 315.395,
+      "eval_steps_per_second": 19.772,
+      "step": 2984
+    },
+    {
+      "epoch": 8.04289544235925,
+      "grad_norm": 21.875141143798828,
+      "learning_rate": 5.465478225508271e-07,
+      "loss": 0.2394,
+      "step": 3000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8183037042617798,
+      "eval_loss": 0.4889311194419861,
+      "eval_runtime": 9.4511,
+      "eval_samples_per_second": 315.626,
+      "eval_steps_per_second": 19.786,
+      "step": 3357
+    },
+    {
+      "epoch": 9.383378016085791,
+      "grad_norm": 31.631711959838867,
+      "learning_rate": 1.7219999888587704e-07,
+      "loss": 0.2114,
+      "step": 3500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.9626746750006364e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.7926347645405278e-06,
+    "per_device_train_batch_size": 32
+  }
+}

run-4/checkpoint-3500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7db8a7a0dfed6f985d34492a77fc54ac5788fe514ba2cde45d3b63947da0c296
+size 5048