Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:707a99b6f42b6eddadbd3079a45b31fc5c4ae58350cd699dc1880fb083214a5a
+oid sha256:3f4bec8e2c12ec2d7fbf805f5b966b88e645d3a15eddd41b3d6a005d62b87aa6
 size 1421491284

run-1/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-1/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f4bec8e2c12ec2d7fbf805f5b966b88e645d3a15eddd41b3d6a005d62b87aa6
+size 1421491284

run-1/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2387e8072f941842639d98d7884cc101ecb1dde88222f59cdcd854de2d65e0a3
+size 2843215085

run-1/checkpoint-1500/rng_state.pth

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

run-1/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8803ee191cef2083085837b4c2f555b5d95aad247b8ea33cb6e51559b54f2bbb
+size 1064

run-1/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-1/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-1/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": 0.4502179026603699,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 8.8257,
+      "eval_samples_per_second": 337.99,
+      "eval_steps_per_second": 21.188,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.45792827010154724,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 8.9021,
+      "eval_samples_per_second": 335.091,
+      "eval_steps_per_second": 21.006,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 0.7300083637237549,
+      "learning_rate": 2.8984023593195776e-05,
+      "loss": 0.6982,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.48206502199172974,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 8.7746,
+      "eval_samples_per_second": 339.957,
+      "eval_steps_per_second": 21.311,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.47536036372184753,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 8.856,
+      "eval_samples_per_second": 336.832,
+      "eval_steps_per_second": 21.116,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.480388879776001,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 8.8652,
+      "eval_samples_per_second": 336.483,
+      "eval_steps_per_second": 21.094,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 0.6803002953529358,
+      "learning_rate": 1.840591279275936e-05,
+      "loss": 0.6973,
+      "step": 1000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.4961448311805725,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 8.8549,
+      "eval_samples_per_second": 336.875,
+      "eval_steps_per_second": 21.118,
+      "step": 1122
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.4941334128379822,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 8.8415,
+      "eval_samples_per_second": 337.387,
+      "eval_steps_per_second": 21.15,
+      "step": 1309
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5048608779907227,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 8.8507,
+      "eval_samples_per_second": 337.036,
+      "eval_steps_per_second": 21.128,
+      "step": 1496
+    },
+    {
+      "epoch": 8.02139037433155,
+      "grad_norm": 0.6829273700714111,
+      "learning_rate": 7.827801992322946e-06,
+      "loss": 0.6955,
+      "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": 3.956213439363219e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-1/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2835d680dbeef8d1e3a296694a634a8a24707065dbe7f2d86b9e9eb29c1bd00
+size 5048