Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e5aca20ea7fdec01a6eb110cbb06fec5a64774239fd88e89bf80048cdb08f30
+oid sha256:8432a97877e4c8e14f0d8165c07842c1dd502832b4349cffa74d225c46e76e34
 size 1421491284

run-12/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-12/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8432a97877e4c8e14f0d8165c07842c1dd502832b4349cffa74d225c46e76e34
+size 1421491284

run-12/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a434687214d2ea5fd8b5699a3ebbfe3191aaca0df063e2abcd0a633b60c6348d
+size 2843215085

run-12/checkpoint-1500/rng_state.pth

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

run-12/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cd3210df54d5f2b5e5f45a920129cddd305f3e5e969cb8fc67358e85b7f1a62
+size 1064

run-12/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-12/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-12/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": 0.7696949243545532,
+      "eval_loss": 0.4614783227443695,
+      "eval_runtime": 8.9518,
+      "eval_samples_per_second": 333.23,
+      "eval_steps_per_second": 20.89,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8045591711997986,
+      "eval_loss": 0.4153314232826233,
+      "eval_runtime": 9.0157,
+      "eval_samples_per_second": 330.868,
+      "eval_steps_per_second": 20.742,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 13.34338665008545,
+      "learning_rate": 9.020650824026705e-06,
+      "loss": 0.4417,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8132752180099487,
+      "eval_loss": 0.45979902148246765,
+      "eval_runtime": 8.9278,
+      "eval_samples_per_second": 334.124,
+      "eval_steps_per_second": 20.946,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8209855556488037,
+      "eval_loss": 0.49998581409454346,
+      "eval_runtime": 9.0014,
+      "eval_samples_per_second": 331.392,
+      "eval_steps_per_second": 20.775,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8307073712348938,
+      "eval_loss": 0.5820282101631165,
+      "eval_runtime": 9.2967,
+      "eval_samples_per_second": 320.868,
+      "eval_steps_per_second": 20.115,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 13.978471755981445,
+      "learning_rate": 5.728442494089952e-06,
+      "loss": 0.1523,
+      "step": 1000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8276902437210083,
+      "eval_loss": 0.6376816630363464,
+      "eval_runtime": 8.9684,
+      "eval_samples_per_second": 332.614,
+      "eval_steps_per_second": 20.851,
+      "step": 1122
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8213208317756653,
+      "eval_loss": 0.6916866302490234,
+      "eval_runtime": 8.9885,
+      "eval_samples_per_second": 331.869,
+      "eval_steps_per_second": 20.804,
+      "step": 1309
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8260141015052795,
+      "eval_loss": 0.727628767490387,
+      "eval_runtime": 9.0,
+      "eval_samples_per_second": 331.443,
+      "eval_steps_per_second": 20.778,
+      "step": 1496
+    },
+    {
+      "epoch": 8.02139037433155,
+      "grad_norm": 13.351667404174805,
+      "learning_rate": 2.436234164153198e-06,
+      "loss": 0.0598,
+      "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": 1.231285915396346e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-12/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef8fc0cfdc6d1707e8122925de821664dabc1fdcd8070d94bbc5a29f7803d19e
+size 5048