Training in progress, epoch 0

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "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": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

last-checkpoint/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "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": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06284b62dce971663287bfa2d1906918b8eeee0aa31e8257861ec7412360ed37
+size 997697669

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74c5995a0f458881960ac0313c862d0baafb8d7a1a7d3325fe6c7713017466a5
+size 498863417

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f0386d83a4a01d2a9fd4b30963f980513336fa914937081320b5958faea1195
+size 14575

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab797403e04ca23f395c92d39729cd1361fd4154a0f1a35d906b47914ec01b18
+size 627

last-checkpoint/trainer_state.json

@@ -0,0 +1,30 @@
+{
+  "best_metric": 1.452467679977417,
+  "best_model_checkpoint": "tapt_helpfulness_base_pretraining_no_condencing/checkpoint-112",
+  "epoch": 0.9950027762354248,
+  "global_step": 112,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9e-05,
+      "loss": 1.6371,
+      "step": 112
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.452467679977417,
+      "eval_runtime": 46.8888,
+      "eval_samples_per_second": 106.635,
+      "eval_steps_per_second": 1.685,
+      "step": 112
+    }
+  ],
+  "max_steps": 1120,
+  "num_train_epochs": 10,
+  "total_flos": 2.996775449835552e+16,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e68e31b6e9813aef601c84ffd8496ba478311588e44554ea64e47f9c8057dd40
+size 3963

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74c5995a0f458881960ac0313c862d0baafb8d7a1a7d3325fe6c7713017466a5
+size 498863417

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e68e31b6e9813aef601c84ffd8496ba478311588e44554ea64e47f9c8057dd40
+size 3963