Training in progress, step 10

.gitignore

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

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "abinayam/gpt-2-tamil",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 128,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "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": "4.27.4",
+  "use_cache": true,
+  "vocab_size": 52000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1de31eb7729de01e438490edbd39f470e97aee49f95caa5b6c0851f33748c4d6
+size 515752509

runs/Apr08_09-56-26_07c4f6762b5d/1680947878.6799984/events.out.tfevents.1680947878.07c4f6762b5d.23.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ae6551684c26b29d40a1b69a0bd7b94e2cac7d7e497ff1e1575c8aca906ab8f
+size 5761

runs/Apr08_09-56-26_07c4f6762b5d/events.out.tfevents.1680947878.07c4f6762b5d.23.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cf97b23da0978d6ad0117c3df711e164a7cccdabdb346ed1fb96da3f04e937f
+size 8594

runs/Apr08_10-21-29_07c4f6762b5d/1680949292.1469293/events.out.tfevents.1680949292.07c4f6762b5d.23.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c26da7952685f1f14db301e46ed95032ea8271466e7691bfa27e97c76f38a19c
+size 5761

runs/Apr08_10-21-29_07c4f6762b5d/events.out.tfevents.1680949292.07c4f6762b5d.23.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2a5d92c1bee94fd331bb3f9d8cce315357fb77587c73b0b432c957febf82b3a
+size 4136

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,8 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a10e2b901e240b9911c843d443723f606253ba2cca043a3d96c81273dd200603
+size 3579