Training in progress, step 100, checkpoint

checkpoint-100/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "EleutherAI/polyglot-ko-1.3b",
+  "architectures": [
+    "GPTNeoXForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 2048,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 2,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.5,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 30080
+}

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:226e1482b525f689cadc8a62f482bc048143f2463c79b91213c14e97d30f5c5c
+size 10161845574

checkpoint-100/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c0d1925947b7fe77391129177beff41d2af37af9d3f286a39e5418d16d53622
+size 5080945162

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c8c1979a903366056f816dfa903e1707fbe02269ee67fd5bd4bb542c4208efb
+size 14308

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eacb31fcf858f3c52820cf56e2807df974ab6dc863e79e5b8b4fd6d46688a586
+size 1064

checkpoint-100/special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|sep|>",
+    "<|acc|>",
+    "<|tel|>",
+    "<|rrn|>"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,72 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|unused0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|unused1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<|sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30000": {
+      "content": "<|acc|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30001": {
+      "content": "<|tel|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30002": {
+      "content": "<|rrn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|sep|>",
+    "<|acc|>",
+    "<|tel|>",
+    "<|rrn|>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,88 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.1625685836212152,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 8.994130006901536e-06,
+      "loss": 0.3053,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.976535341747906e-06,
+      "loss": 0.1363,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.947261907011569e-06,
+      "loss": 0.1087,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8.906386073741352e-06,
+      "loss": 0.106,
+      "step": 40
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 8.85401448231912e-06,
+      "loss": 0.0791,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 8.790283764247187e-06,
+      "loss": 0.0702,
+      "step": 60
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 8.715360185692326e-06,
+      "loss": 0.0773,
+      "step": 70
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 8.629439213716327e-06,
+      "loss": 0.0583,
+      "step": 80
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 8.532745006324751e-06,
+      "loss": 0.0637,
+      "step": 90
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 8.425529827664287e-06,
+      "loss": 0.0554,
+      "step": 100
+    },
+    {
+      "epoch": 0.16,
+      "eval_accuracy": 0.5,
+      "eval_loss": 7.870811641330633e-11,
+      "eval_runtime": 51.3409,
+      "eval_samples_per_second": 85.195,
+      "eval_steps_per_second": 10.654,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 615,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 0.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f83b04586007121ba3ee6bfcd4a06860c6098884f4f89ada67554e532440c28
+size 4600