v1

README.md

@@ -1 +1,55 @@
-Pygmalion-350m
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: pygmalion-training
+  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. -->
+
+# pygmalion-training
+
+This model is a fine-tuned version of [/notebooks/pygmalion/pygmalion-350m/](https://huggingface.co//notebooks/pygmalion/pygmalion-350m/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.2731
+- Accuracy: 0.5187
+
+## 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: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.27.0.dev0
+- Pytorch 1.13.1+cu117
+- Datasets 2.10.0
+- Tokenizers 0.13.2

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.5187400890626697,
+    "eval_loss": 2.2730870246887207,
+    "eval_runtime": 13.6348,
+    "eval_samples": 225,
+    "eval_samples_per_second": 16.502,
+    "eval_steps_per_second": 2.127,
+    "perplexity": 9.70932753185012,
+    "train_loss": 2.059293716672867,
+    "train_runtime": 354.2246,
+    "train_samples": 672,
+    "train_samples_per_second": 5.691,
+    "train_steps_per_second": 0.711
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "/notebooks/pygmalion/pygmalion-350m/",
+  "_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": false,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 4096,
+  "hidden_size": 1024,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 512
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.5187400890626697,
+    "eval_loss": 2.2730870246887207,
+    "eval_runtime": 13.6348,
+    "eval_samples": 225,
+    "eval_samples_per_second": 16.502,
+    "eval_steps_per_second": 2.127,
+    "perplexity": 9.70932753185012
+}

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": "4.27.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b53bcd933c0711721230c64cf51b54a4f01fcb55f680cce1076be082b9877f35
+size 1324917277

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
+  },
+  "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
+  },
+  "special_tokens_map_file": null,
+  "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": 3.0,
+    "train_loss": 2.059293716672867,
+    "train_runtime": 354.2246,
+    "train_samples": 672,
+    "train_samples_per_second": 5.691,
+    "train_steps_per_second": 0.711
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 252,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.0,
+      "step": 252,
+      "total_flos": 3757483814289408.0,
+      "train_loss": 2.059293716672867,
+      "train_runtime": 354.2246,
+      "train_samples_per_second": 5.691,
+      "train_steps_per_second": 0.711
+    }
+  ],
+  "max_steps": 252,
+  "num_train_epochs": 3,
+  "total_flos": 3757483814289408.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b77dcf54b398b1cd2d53775de718856975e65595345377ab4e08e28512855b36
+size 3579