Add fine-tuned model

README.md

@@ -0,0 +1,61 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- wikitext
+model-index:
+- name: clm_output
+  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. -->
+
+# clm_output
+
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the wikitext wikitext-103-raw-v1 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.9902
+
+## 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: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: IPU
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 1024
+- total_eval_batch_size: 20
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10.0
+- training precision: Mixed Precision
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.18.0.dev0
+- Pytorch 1.10.0+cpu
+- Datasets 2.0.0
+- Tokenizers 0.11.6

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 2.990234375,
+    "eval_runtime": 125.3791,
+    "eval_samples": 240,
+    "eval_samples_per_second": 1.914,
+    "eval_steps_per_second": 0.096,
+    "perplexity": 19.89034374461794,
+    "train_loss": 3.1787637246621623,
+    "train_runtime": 4372.4031,
+    "train_samples": 114248,
+    "train_samples_per_second": 261.293,
+    "train_steps_per_second": 0.254
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "PoptorchPipelinedGPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.18.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 2.990234375,
+    "eval_runtime": 125.3791,
+    "eval_samples": 240,
+    "eval_samples_per_second": 1.914,
+    "eval_steps_per_second": 0.096,
+    "perplexity": 19.89034374461794
+}

ipu_config.json

@@ -0,0 +1,27 @@
+{
+  "device_iterations": 2,
+  "embedding_serialization_factor": 4,
+  "enable_half_first_order_momentum": true,
+  "enable_half_partials": true,
+  "executable_cache_dir": "./exe_cache",
+  "gradient_accumulation_steps": 128,
+  "inference_device_iterations": 5,
+  "inference_replication_factor": 4,
+  "ipus_per_replica": 4,
+  "layers_per_ipu": [
+    0,
+    4,
+    4,
+    4
+  ],
+  "matmul_proportion": 0.25,
+  "optimizer_state_offchip": true,
+  "optimum_version": "1.0.0",
+  "output_mode": "final",
+  "profile_dir": "",
+  "recompute_checkpoint_every_layer": true,
+  "replicated_tensor_sharding": true,
+  "replication_factor": 4,
+  "seed": 42,
+  "use_popdist": false
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b0f59559a81956e16aaa7d8482c91accb63851288c78a3e89f1f5df87ceac70
+size 261514473

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 3.1787637246621623,
+    "train_runtime": 4372.4031,
+    "train_samples": 114248,
+    "train_samples_per_second": 261.293,
+    "train_steps_per_second": 0.254
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69aa9f555f383d982973dccbc5622239aa013a037a2e266e9451266070d1febd
+size 2799