Training in progress, step 20000

checkpoint-20000/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "tomekkorbak/amazing_mahavira",
+  "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": "4.20.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-20000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61241cbaa3bc0b7f1424d1e76cca3d9151c20e2c1b6a9f6cfc7525caa2fd8754
+size 995604017

checkpoint-20000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6176531f42c79d9fdbd24e0395d0b49673c0b46c07753813b3e3bf860fa2d9bf
+size 510396521

checkpoint-20000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62f81a58489747b668a302d572a4929c84f02d2bab8527b9cecc11244d8e1aeb
+size 14503

checkpoint-20000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b28e1581b16116da348dff78212ed9e4800a73ce516d02ef21e1d41697bd9b6
+size 559

checkpoint-20000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3499a76522cdf14ed982712086922dd5640a92b09d8bd9746d729f31a89aa7a
+size 623

checkpoint-20000/special_tokens_map.json

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

checkpoint-20000/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-20000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a51b62c9ff96e5b4afb861a924338d2db8178a1ac9dbf2982ded905f99e38d6
+size 3311

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f46fc5ef5472cbc89792902f1d0462c108f78cfe93e6b7951f51ae21154ab43
+oid sha256:6176531f42c79d9fdbd24e0395d0b49673c0b46c07753813b3e3bf860fa2d9bf
 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,