Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7045c3589ce9f9adf3b04c9c52f68d6bd9430169e9051381a9451bd44d19baec
+oid sha256:e62177dad61f4f8e5884148f8c706d8bfcd68da8169443c956861208ec9f542e
 size 1421491284

run-6/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-6/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e62177dad61f4f8e5884148f8c706d8bfcd68da8169443c956861208ec9f542e
+size 1421491284

run-6/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2637828d2a20da2a66f0931c9493abc86dd41afdf02dbad4b61cc556d1996c66
+size 2843215085

run-6/checkpoint-1500/rng_state.pth

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

run-6/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68036ab6a3c767a022a9248716ad50ed8de3b633dc914d8b2b8f8c679e3086fc
+size 1064

run-6/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-6/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-6/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": 0.7683539986610413,
+      "eval_loss": 0.4618770182132721,
+      "eval_runtime": 9.2947,
+      "eval_samples_per_second": 320.936,
+      "eval_steps_per_second": 20.119,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7971840500831604,
+      "eval_loss": 0.42974236607551575,
+      "eval_runtime": 9.3349,
+      "eval_samples_per_second": 319.554,
+      "eval_steps_per_second": 20.032,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 16.69818115234375,
+      "learning_rate": 8.87708337266305e-06,
+      "loss": 0.4407,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8159570693969727,
+      "eval_loss": 0.4164794683456421,
+      "eval_runtime": 9.288,
+      "eval_samples_per_second": 321.167,
+      "eval_steps_per_second": 20.134,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8129400014877319,
+      "eval_loss": 0.5053750276565552,
+      "eval_runtime": 9.4534,
+      "eval_samples_per_second": 315.549,
+      "eval_steps_per_second": 19.781,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8099228739738464,
+      "eval_loss": 0.590611457824707,
+      "eval_runtime": 9.4637,
+      "eval_samples_per_second": 315.205,
+      "eval_steps_per_second": 19.76,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 18.07274627685547,
+      "learning_rate": 5.637271922786024e-06,
+      "loss": 0.1629,
+      "step": 1000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8132752180099487,
+      "eval_loss": 0.6388338804244995,
+      "eval_runtime": 9.4591,
+      "eval_samples_per_second": 315.357,
+      "eval_steps_per_second": 19.769,
+      "step": 1122
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8105933666229248,
+      "eval_loss": 0.7334861159324646,
+      "eval_runtime": 9.4671,
+      "eval_samples_per_second": 315.09,
+      "eval_steps_per_second": 19.753,
+      "step": 1309
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8162923455238342,
+      "eval_loss": 0.7645613551139832,
+      "eval_runtime": 9.4764,
+      "eval_samples_per_second": 314.781,
+      "eval_steps_per_second": 19.733,
+      "step": 1496
+    },
+    {
+      "epoch": 8.02139037433155,
+      "grad_norm": 7.866405963897705,
+      "learning_rate": 2.3974604729089986e-06,
+      "loss": 0.0626,
+      "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": 1.2116894822540074e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-6/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09c4c94249778096fc61b375be2707ad177ad76c4fc968601193ba10d84538e5
+size 5048