Add content

README.md

@@ -0,0 +1,71 @@
+---
+license: other
+tags:
+- generated_from_trainer
+datasets:
+- wikitext
+metrics:
+- accuracy
+model-index:
+- name: ov-opt-350m-fp32-kv-cache
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: wikitext wikitext-2-raw-v1
+      type: wikitext
+      config: wikitext-2-raw-v1
+      split: validation
+      args: wikitext-2-raw-v1
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.1335940045617465
+---
+
+<!-- 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. -->
+
+# ov-opt-350m-fp32-kv-cache
+
+This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the wikitext wikitext-2-raw-v1 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 6.2368
+- Accuracy: 0.1336
+
+## 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: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.30.2
+- Pytorch 2.0.1+cu117
+- Datasets 2.13.1
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 0.0,
+    "eval_accuracy": 0.1335940045617465,
+    "eval_loss": 6.2367634773254395,
+    "eval_runtime": 2.1831,
+    "eval_samples": 3,
+    "eval_samples_per_second": 1.374,
+    "eval_steps_per_second": 1.374,
+    "perplexity": 511.2013159644867,
+    "train_loss": 7.921147346496582,
+    "train_runtime": 26.2971,
+    "train_samples": 2355,
+    "train_samples_per_second": 0.304,
+    "train_steps_per_second": 0.038
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "facebook/opt-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": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 512
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 0.0,
+    "eval_accuracy": 0.1335940045617465,
+    "eval_loss": 6.2367634773254395,
+    "eval_runtime": 2.1831,
+    "eval_samples": 3,
+    "eval_samples_per_second": 1.374,
+    "eval_steps_per_second": 1.374,
+    "perplexity": 511.2013159644867
+}

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": "4.30.2"
+}

nncf_output.log

@@ -0,0 +1,17 @@
+INFO:nncf:
+WARNING:nncf:You are setting `forward` on an NNCF-processed model object.
+NNCF relies on custom-wrapping the `forward` call in order to function properly.
+Arbitrary adjustments to the forward function on an NNCFNetwork object have undefined behaviour.
+If you need to replace the underlying forward function of the original model so that NNCF should be using that instead of the original forward function that NNCF saved during the compressed model creation, you can do this by calling:
+model.nncf.set_original_unbound_forward(fn)
+if `fn` has an unbound 0-th `self` argument, or
+with model.nncf.temporary_bound_original_forward(fn): ...
+if `fn` already had 0-th `self` argument bound or never had it in the first place.
+WARNING:nncf:You are setting `forward` on an NNCF-processed model object.
+NNCF relies on custom-wrapping the `forward` call in order to function properly.
+Arbitrary adjustments to the forward function on an NNCFNetwork object have undefined behaviour.
+If you need to replace the underlying forward function of the original model so that NNCF should be using that instead of the original forward function that NNCF saved during the compressed model creation, you can do this by calling:
+model.nncf.set_original_unbound_forward(fn)
+if `fn` has an unbound 0-th `self` argument, or
+with model.nncf.temporary_bound_original_forward(fn): ...
+if `fn` already had 0-th `self` argument bound or never had it in the first place.

openvino_config.json

@@ -0,0 +1,27 @@
+{
+  "compression": {
+    "algorithm": "NoCompressionAlgorithm"
+  },
+  "input_info": [
+    {
+      "keyword": "input_ids",
+      "sample_size": [
+        8,
+        1024
+      ],
+      "type": "long"
+    },
+    {
+      "keyword": "attention_mask",
+      "sample_size": [
+        8,
+        1024
+      ],
+      "type": "long"
+    }
+  ],
+  "log_dir": "/data1/vchua/temp/ov-opt-350m-fp32-kv-cache",
+  "optimum_version": "1.8.8",
+  "save_onnx_model": false,
+  "transformers_version": "4.30.2"
+}

openvino_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feea529894e04917df213164ccba0e32d06d46c996d9798798e164d5fe5f6380
+size 1427742864

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52a269cf40f695787d1328f0502cb555ba7a3e90e38f46abbab4fd1fbaead581
+size 1324911837

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": 0.0,
+    "train_loss": 7.921147346496582,
+    "train_runtime": 26.2971,
+    "train_samples": 2355,
+    "train_samples_per_second": 0.304,
+    "train_steps_per_second": 0.038
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.003389830508474576,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "step": 1,
+      "total_flos": 14910650056704.0,
+      "train_loss": 7.921147346496582,
+      "train_runtime": 26.2971,
+      "train_samples_per_second": 0.304,
+      "train_steps_per_second": 0.038
+    }
+  ],
+  "max_steps": 1,
+  "num_train_epochs": 1,
+  "total_flos": 14910650056704.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:957b37cdb11b6853cd2b4232530d1f216263f43991786f948426080587b2aabf
+size 3963