Training in progress, step 2500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f995d6218f764cb5cce5e11fcc237f352d05fa1ac82d230340eebccf1cc3325
+oid sha256:ce1272b2082c074f0396519cd808a4c8119978b44e5383f2cbfd6d144af45eb4
 size 1421491284

run-4/checkpoint-2000/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-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:982a37ad76bbee4f9a5c83948939d06021d5f4d87d572ea6e5c785afe2fb26d8
+size 1421491284

run-4/checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddf94da8004b8d0d28346808808e2d159f5a8c0531fb6eaffec375b65be8069b
+size 2843215085

run-4/checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbb381a449d36d9eafe0476c182c2075cfdd8fa3b10ccea6591a7dde531518da
+size 14244

run-4/checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14a2a2febc3aff3c0b48b89f916c802be075c5870039d3b116eaf14a301ef952
+size 1064

run-4/checkpoint-2000/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-2000/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-2000/trainer_state.json

@@ -0,0 +1,97 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.361930294906166,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "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
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.1222931181027428e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.7926347645405278e-06,
+    "per_device_train_batch_size": 32
+  }
+}

run-4/checkpoint-2000/training_args.bin

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

run-4/checkpoint-2500/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-2500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce1272b2082c074f0396519cd808a4c8119978b44e5383f2cbfd6d144af45eb4
+size 1421491284

run-4/checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d929ad837c2580eddff79d16607a0a53cb988c341a5e0335fe5096da54a50be
+size 2843215085

run-4/checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b5a7ca7ed33ad4adea3ef03b53fcfdcc68615f1d5a661797fd26a1d64e5bb70
+size 14244

run-4/checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b320c212de7f1be88e20149159d6e12bcab4b28fd42acba21b3d5a8322e74fc
+size 1064

run-4/checkpoint-2500/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-2500/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-2500/trainer_state.json

@@ -0,0 +1,113 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.702412868632708,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "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
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.4022192353692968e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.7926347645405278e-06,
+    "per_device_train_batch_size": 32
+  }
+}

run-4/checkpoint-2500/training_args.bin

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