Training in progress, step 25000

checkpoint-25000/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMAndValueHeadModel"
+  ],
+  "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": true,
+  "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": "4.23.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-25000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40ca0a90703dbb281492086a82a24e5f095c5837521265b5d8391e6bdbfaebc6
+size 995604017

checkpoint-25000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89f7d59f284ca7190be8de53bc37177759022dbfe051e1c47bab464d9a658d83
+size 510396521

checkpoint-25000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16d85a3ed95a30b90b086cfca2c562931a99480d43c74dc19bba369aad02284f
+size 14503

checkpoint-25000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5401ed21cc807f46332f943dfabe7ae5cac489031f5440c70dff9066e1c654a7
+size 559

checkpoint-25000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23cd3f708eb71c6081c21f0e93288539035d486295da1f793f62d7227b6fa9e5
+size 623

checkpoint-25000/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-25000/tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "gpt2",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-25000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8211ecef9ac43c88699e17e28282d08122d1d6c15a84e77c48c505e754b29eb4
+size 3375

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5059824ff2aac251260b5e2f2f9bf518af2de7b63de73e888c9b48b85d255780
+oid sha256:89f7d59f284ca7190be8de53bc37177759022dbfe051e1c47bab464d9a658d83
 size 510396521

tokenizer.json

@@ -1,14 +1,7 @@
 {
   "version": "1.0",
   "truncation": null,
-  "padding": {
-    "strategy": "BatchLongest",
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 50256,
-    "pad_type_id": 0,
-    "pad_token": "<|endoftext|>"
-  },
+  "padding": null,
   "added_tokens": [
     {
       "id": 50256,