Training in progress, step 1000

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/Study/rus_gpt2_2_epoch",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "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": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 54848
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b95b3096fa5d9e1ae72ca1930fca2f58377a6ee2c93dcd1b24ec575824ec91c
+size 511877760

runs/Sep19_02-23-31_d8ed5db1b60a/events.out.tfevents.1726712612.d8ed5db1b60a.2184.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f071db10d95ce6e41ea8a4e99202c3aec6b88f838ef3f404278c24e2d555ca69
+size 6265

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d27b73c8c895952bbf0cb2aeb6c457479915d8dbea2f13b8fa516df4e0b15814
+size 5240