Training in progress, step 500

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "ytu-ce-cosmos/turkish-gpt2-large",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 36,
+  "n_positions": 1024,
+  "pad_token_id": 0,
+  "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": "float32",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf7a0efbadbf435cb716a99ec9290f63c5af2f94fe09b300d1fbb74ee33094e0
+size 3096165928

runs/Mar17_09-15-51_134106dab9b0/events.out.tfevents.1710666960.134106dab9b0.4051.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:105b87cbf1292c499264306903c27c4d00a8bfe826c48a3588d5432ad1865582
+size 5484

runs/Mar17_09-20-31_134106dab9b0/events.out.tfevents.1710667237.134106dab9b0.4051.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1943708371c575014803a277b077c080ee516a7f180edf0010a6a3cd9993f1d9
+size 5065

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ad401c6e6c4050c77d42933d9df02cbe10803ce1b79617fe32f62ccc69a8823
+size 4856