Training in progress, step 5070

checkpoint-5070/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "tomekkorbak/goofy_pasteur",
+  "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": "4.24.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-5070/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d2229430b4315979798c14426493f75fdea796144cda8a61a5080200cae9fa4
+size 995604017

checkpoint-5070/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09aae1dbd4b372c71c47e4f7efc4c58262801540fb83a974f4e173298606760a
+size 510396521

checkpoint-5070/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:276816c69313e6d8f76e049f9d5e32abf27569cc4e9df3954071a392a5d950d5
+size 14503

checkpoint-5070/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00169e579ace8743c9d53a4a5bc6fab9efeccc1d79bdbd19a6585d6919f2bbd5
+size 559

checkpoint-5070/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f77331510c5572e6896b9c443e263f614a3e7ebda62d22d7f3f9a627de22dc65
+size 623

checkpoint-5070/special_tokens_map.json

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

checkpoint-5070/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-5070/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:649cbe06417b4b4953cfd56d7bcaa4072eac7b14eb7a2e865e69720b8fe6cf36
+size 3375

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38ac2d98540367741c35a12f5df0b019c11f5757f91359dd87641ffdf94fb9df
+oid sha256:09aae1dbd4b372c71c47e4f7efc4c58262801540fb83a974f4e173298606760a
 size 510396521