Upload folder using huggingface_hub

README.md

@@ -1,3 +1,58 @@
 ---
-license: other
+base_model: core4
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: core5
+  results: []
 ---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# core5
+
+This model is a fine-tuned version of [core4](https://huggingface.co/core4) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7270
+- Accuracy: 0.8177
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.34.0.dev0
+- Pytorch 2.0.1+cu117
+- Datasets 2.14.5
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.8177498068763019,
+    "eval_loss": 0.7270267605781555,
+    "eval_runtime": 3.2848,
+    "eval_samples": 267,
+    "eval_samples_per_second": 81.283,
+    "eval_steps_per_second": 10.351,
+    "perplexity": 2.0689200591391117,
+    "train_loss": 0.9312247221089841,
+    "train_runtime": 1289.1473,
+    "train_samples": 44772,
+    "train_samples_per_second": 34.73,
+    "train_steps_per_second": 1.085
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "core4",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "n_ctx": 2048,
+  "n_positions": 2048,
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.8177498068763019,
+    "eval_loss": 0.7270267605781555,
+    "eval_runtime": 3.2848,
+    "eval_samples": 267,
+    "eval_samples_per_second": 81.283,
+    "eval_steps_per_second": 10.351,
+    "perplexity": 2.0689200591391117
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.34.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ef5ea88802bb8af9c8e7a12a7686a722b06afd1720e6d392ad01adf1a3133a9
+size 1294082185

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 2048,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.9312247221089841,
+    "train_runtime": 1289.1473,
+    "train_samples": 44772,
+    "train_samples_per_second": 34.73,
+    "train_steps_per_second": 1.085
+}

trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9998213328568876,
+  "eval_steps": 500,
+  "global_step": 1399,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.000642601858470336,
+      "loss": 0.9263,
+      "step": 500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002852037169406719,
+      "loss": 0.9004,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "step": 1399,
+      "total_flos": 7.997027865801523e+16,
+      "train_loss": 0.9312247221089841,
+      "train_runtime": 1289.1473,
+      "train_samples_per_second": 34.73,
+      "train_steps_per_second": 1.085
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1399,
+  "num_train_epochs": 1,
+  "save_steps": -1399,
+  "total_flos": 7.997027865801523e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d117c74e1b20f888e6fb49e47881986e372a1f7f5bf40c080453491bf01fae34
+size 4027