Upload 14 files

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 50257
+}

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.4,
+    "learning_rate": 6.002269380684279e-06,
+    "train_loss": 4.83620277834145,
+    "train_runtime": 1683.6936,
+    "train_samples": 2365187,
+    "train_samples_per_second": 561.964,
+    "train_steps_per_second": 1.098
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "../../output_models/clm_gpt2_small_2022_new_wmt_0o6_wiki_0o4",
+  "activation_function": "gelu",
+  "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": "4.29.2",
+  "use_cache": true,
+  "vocab_size": 50258
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.29.2"
+}

ipu_config.json

@@ -0,0 +1,45 @@
+{
+  "auto_loss_scaling": false,
+  "device_iterations": 2,
+  "embedding_serialization_factor": 4,
+  "enable_half_partials": true,
+  "executable_cache_dir": "./exe_cache",
+  "execute_encoder_on_cpu_for_generation": false,
+  "explicit_ir_inference": false,
+  "gradient_accumulation_steps": 64,
+  "inference_device_iterations": 5,
+  "inference_embedding_serialization_factor": 1,
+  "inference_ipus_per_replica": 4,
+  "inference_layers_per_ipu": [
+    0,
+    4,
+    4,
+    4
+  ],
+  "inference_matmul_proportion": 0.25,
+  "inference_parallelize_kwargs": {},
+  "inference_projection_serialization_factor": 1,
+  "inference_replication_factor": 4,
+  "inference_serialized_embedding_splits_per_ipu": null,
+  "inference_serialized_projection_splits_per_ipu": null,
+  "ipus_per_replica": 4,
+  "layers_per_ipu": [
+    0,
+    4,
+    4,
+    4
+  ],
+  "matmul_proportion": 0.25,
+  "optimizer_state_offchip": true,
+  "optimum_version": "1.6.1",
+  "output_mode": "final",
+  "parallelize_kwargs": {},
+  "projection_serialization_factor": 1,
+  "recompute_checkpoint_every_layer": true,
+  "replicated_tensor_sharding": true,
+  "replication_factor": 4,
+  "seed": 42,
+  "serialized_embedding_splits_per_ipu": null,
+  "serialized_projection_splits_per_ipu": null,
+  "transformers_version": "4.29.2"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d4b829e92bd1ee065228e0dafb75d1d6b2db7a1c4690b2471e6489af32e3bcd
+size 261517501

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "[PAD]",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.4,
+    "learning_rate": 6.002269380684279e-06,
+    "train_loss": 4.83620277834145,
+    "train_runtime": 1683.6936,
+    "train_samples": 2365187,
+    "train_samples_per_second": 561.964,
+    "train_steps_per_second": 1.098
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efeb5817a6cf34917943a1a89fad300d42f6c3cac8b3015fccb20003a216fefa
+size 2811