Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:988c7f02e10fb5c0f8dc8467a0a05e594eeead23b80caa57c9e4ad284e498db0
+oid sha256:09c11377595ffb7def7db63d6e6908975043853016051eb142a174acf5b0b2a2
 size 1421491284

run-4/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-4/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09c11377595ffb7def7db63d6e6908975043853016051eb142a174acf5b0b2a2
+size 1421491284

run-4/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:500e562a1b8076e0125b0b6a6e5133829b0a495a0b1ad2d8690246f6a3a356e9
+size 2843215085

run-4/checkpoint-1500/rng_state.pth

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

run-4/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85b57885e3dd57ab9169f950688940c00ff66b6d42695643e9fb13bd1d93c93e
+size 1064

run-4/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-4/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-4/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": 0.7254441976547241,
+      "eval_loss": 0.515117347240448,
+      "eval_runtime": 9.0075,
+      "eval_samples_per_second": 331.167,
+      "eval_steps_per_second": 20.76,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7492457032203674,
+      "eval_loss": 0.4793011546134949,
+      "eval_runtime": 9.1228,
+      "eval_samples_per_second": 326.983,
+      "eval_steps_per_second": 20.498,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 12.898003578186035,
+      "learning_rate": 2.66142701656233e-06,
+      "loss": 0.5477,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7670130729675293,
+      "eval_loss": 0.4651851952075958,
+      "eval_runtime": 8.9403,
+      "eval_samples_per_second": 333.657,
+      "eval_steps_per_second": 20.916,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7847804427146912,
+      "eval_loss": 0.46247026324272156,
+      "eval_runtime": 9.0,
+      "eval_samples_per_second": 331.443,
+      "eval_steps_per_second": 20.778,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7918202877044678,
+      "eval_loss": 0.44435548782348633,
+      "eval_runtime": 9.003,
+      "eval_samples_per_second": 331.336,
+      "eval_steps_per_second": 20.771,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 14.104453086853027,
+      "learning_rate": 1.690103287889947e-06,
+      "loss": 0.398,
+      "step": 1000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7961783409118652,
+      "eval_loss": 0.4577687382698059,
+      "eval_runtime": 8.9982,
+      "eval_samples_per_second": 331.512,
+      "eval_steps_per_second": 20.782,
+      "step": 1122
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7985249757766724,
+      "eval_loss": 0.47194474935531616,
+      "eval_runtime": 8.9787,
+      "eval_samples_per_second": 332.233,
+      "eval_steps_per_second": 20.827,
+      "step": 1309
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.797854483127594,
+      "eval_loss": 0.4951905310153961,
+      "eval_runtime": 9.0065,
+      "eval_samples_per_second": 331.204,
+      "eval_steps_per_second": 20.763,
+      "step": 1496
+    },
+    {
+      "epoch": 8.02139037433155,
+      "grad_norm": 19.72330665588379,
+      "learning_rate": 7.187795592175637e-07,
+      "loss": 0.3037,
+      "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": 3.6327507452347134e-06,
+    "per_device_train_batch_size": 64
+  }
+}

run-4/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f13ce7f3e21ba47d51870a7b8fdab14095997596acbf90c0c730c82502c290
+size 5048