Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

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": "4.24.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

ipu_config.json

@@ -0,0 +1,31 @@
+{
+  "decompose_grad_sum": false,
+  "device_iterations": 2,
+  "embedding_serialization_factor": 4,
+  "enable_half_first_order_momentum": true,
+  "enable_half_partials": true,
+  "executable_cache_dir": "/tmp/exe_cache",
+  "execute_encoder_on_cpu_for_generation": false,
+  "gradient_accumulation_steps": 16,
+  "inference_device_iterations": 5,
+  "inference_replication_factor": 1,
+  "ipus_per_replica": 4,
+  "layers_per_ipu": [
+    0,
+    4,
+    4,
+    4
+  ],
+  "matmul_proportion": 0.25,
+  "optimizer_state_offchip": true,
+  "optimum_version": "1.4.1",
+  "output_mode": "final",
+  "profile_dir": "",
+  "recompute_checkpoint_every_layer": true,
+  "replicated_tensor_sharding": false,
+  "replication_factor": 1,
+  "seed": 42,
+  "sharded_execution_for_inference": false,
+  "transformers_version": "4.24.0",
+  "use_popdist": false
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9567e399ebcb3ca37075b4102465b3d46bf4477a4d4c59f4054d0c0a61f2184
+size 261514473

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:627ab2fdc8e900cf4f670412ca775f2c932734a7e27934460e779633914afa06
+size 2671