Upload folder using huggingface_hub

README.md

@@ -1,3 +1,57 @@
 ---
 license: other
+base_model: facebook/opt-1.3b
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: ss5
+  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. -->
+
+# ss5
+
+This model is a fine-tuned version of [facebook/opt-1.3b](https://huggingface.co/facebook/opt-1.3b) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4784
+- Accuracy: 0.6753
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- 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 4.33.0.dev0
+- Pytorch 2.1.0.dev20230605+cu121
+- Datasets 2.14.4
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.6752705025786228,
+    "eval_loss": 1.4784468412399292,
+    "eval_runtime": 55.0697,
+    "eval_samples": 232,
+    "eval_samples_per_second": 4.213,
+    "eval_steps_per_second": 0.527,
+    "perplexity": 4.3861280346659415,
+    "train_loss": 1.700456760354238,
+    "train_runtime": 3303.7788,
+    "train_samples": 11678,
+    "train_samples_per_second": 3.535,
+    "train_steps_per_second": 0.442
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "facebook/opt-1.3b",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 8192,
+  "hidden_size": 2048,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.33.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 2048
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.6752705025786228,
+    "eval_loss": 1.4784468412399292,
+    "eval_runtime": 55.0697,
+    "eval_samples": 232,
+    "eval_samples_per_second": 4.213,
+    "eval_steps_per_second": 0.527,
+    "perplexity": 4.3861280346659415
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.33.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c82ac35a6d50d4f6668cf6fc2037aece6e394df4a65ef6ff81ad131822fe6e70
+size 2631648218

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.700456760354238,
+    "train_runtime": 3303.7788,
+    "train_samples": 11678,
+    "train_samples_per_second": 3.535,
+    "train_steps_per_second": 0.442
+}

trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1460,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.287671232876712e-05,
+      "loss": 1.776,
+      "step": 500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.5753424657534248e-05,
+      "loss": 1.6672,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "step": 1460,
+      "total_flos": 8.671679350623437e+16,
+      "train_loss": 1.700456760354238,
+      "train_runtime": 3303.7788,
+      "train_samples_per_second": 3.535,
+      "train_steps_per_second": 0.442
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1460,
+  "num_train_epochs": 1,
+  "save_steps": -1460,
+  "total_flos": 8.671679350623437e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68e5b42e7290d1422423b958c1cf982b94ae5db9e379c560d977a8e2c38edab8
+size 4472