Training in progress, step 500

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "TurkuNLP/gpt3-finnish-large",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 16,
+  "n_layer": 24,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 131072
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:269d4fc9359d7c66324aeeeab96123e4f05f39d9dd921e1a4071dda9d228fcaf
+size 3525191088

runs/Oct14_04-23-38_4db90efba5b3/events.out.tfevents.1728879820.4db90efba5b3.1762.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c933dd8f4a00a49d7caf813f05f5160e8f7696a9cdaa8efbd15a177b3d93b2b1
+size 5076

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd4f38ac916ab7acc785ca7de8088a5b5fe7f22730bf1689fd4e9066c8766e7f
+size 5176