Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa4a7c45b17bd175157f573c38eadfc85825213ef00eeb92414b720e0ba0b8e5
+oid sha256:aa2c4867b791233e273ad41a894139b1fbab0de56a8d71eae6ee5802f2bc1084
 size 1421491284

run-5/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-5/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa2c4867b791233e273ad41a894139b1fbab0de56a8d71eae6ee5802f2bc1084
+size 1421491284

run-5/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:778fa9d337847c4a95d3d3f3aaac9f4a254bd53a4dd54330a979f5a083d94b73
+size 2843215085

run-5/checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f48dc2f5362fb223b487a26aed5961225e681be7dd0c9dcd202d693a285b27e
+size 14244

run-5/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d23968bd288e1c35074f7b4f911654d2547272764747c6b0483c6e0e1c4be946
+size 1064

run-5/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-5/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-5/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": 0.7019778490066528,
+      "eval_loss": 0.5544637441635132,
+      "eval_runtime": 9.2773,
+      "eval_samples_per_second": 321.539,
+      "eval_steps_per_second": 20.157,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.744552493095398,
+      "eval_loss": 0.49814581871032715,
+      "eval_runtime": 9.3471,
+      "eval_samples_per_second": 319.136,
+      "eval_steps_per_second": 20.006,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 11.23240852355957,
+      "learning_rate": 1.7634576095057786e-06,
+      "loss": 0.5749,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.763660728931427,
+      "eval_loss": 0.4700300395488739,
+      "eval_runtime": 9.4418,
+      "eval_samples_per_second": 315.936,
+      "eval_steps_per_second": 19.806,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7747234106063843,
+      "eval_loss": 0.4598151743412018,
+      "eval_runtime": 9.504,
+      "eval_samples_per_second": 313.868,
+      "eval_steps_per_second": 19.676,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7864565849304199,
+      "eval_loss": 0.4558647572994232,
+      "eval_runtime": 9.4827,
+      "eval_samples_per_second": 314.573,
+      "eval_steps_per_second": 19.72,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 16.31344985961914,
+      "learning_rate": 1.1198599418029397e-06,
+      "loss": 0.4329,
+      "step": 1000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7921555638313293,
+      "eval_loss": 0.44776955246925354,
+      "eval_runtime": 9.3414,
+      "eval_samples_per_second": 319.33,
+      "eval_steps_per_second": 20.018,
+      "step": 1122
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.797854483127594,
+      "eval_loss": 0.44390732049942017,
+      "eval_runtime": 9.3593,
+      "eval_samples_per_second": 318.719,
+      "eval_steps_per_second": 19.98,
+      "step": 1309
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.797854483127594,
+      "eval_loss": 0.4467073380947113,
+      "eval_runtime": 9.3887,
+      "eval_samples_per_second": 317.723,
+      "eval_steps_per_second": 19.918,
+      "step": 1496
+    },
+    {
+      "epoch": 8.02139037433155,
+      "grad_norm": 18.439756393432617,
+      "learning_rate": 4.762622741001008e-07,
+      "loss": 0.3675,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1870,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.7876643808636188e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.4070552772086175e-06,
+    "per_device_train_batch_size": 64
+  }
+}

run-5/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6433f0c0ad099ec3bf4145fcc86507c8490c2f642ce9a6a75665bc6009566568
+size 5048