Training in progress, step 17745

checkpoint-17745/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-17745/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:756ea72d8eb88a618006fb9f9828bd7f157891b1b2c192515b7f6cd470bae871
+size 995604017

checkpoint-17745/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:262cd113c6e13fea327aca49aca10eaa13dbd2b60e86bfb576e19914439fa42f
+size 510396521

checkpoint-17745/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b49884a0d73c6d5d43c5352b7c4329fb7cb6986b2277a700d8372b4d2724c2a6
+size 14503

checkpoint-17745/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0fb3a04a317adbbe379d7102dd7d00c0bd3b2ac2618f789b9c0f96af4ccfc0a
+size 559

checkpoint-17745/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fa6b251bf9d2185c3deceb1e92b0b5f651760f47654d2619370578dfcf0489f
+size 623

checkpoint-17745/special_tokens_map.json

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

checkpoint-17745/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-17745/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 sha256:9d768ce4b78ffdc7723e5b2fcc3eda6ff6904572796263a4e01756be82b117c5
+oid sha256:262cd113c6e13fea327aca49aca10eaa13dbd2b60e86bfb576e19914439fa42f
 size 510396521