fine tuning

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "output/content/models/tweetGPTfi/weights/checkpoint-140000",
+  "_name_or_path": "/home/juno/repos/gitlab.com/remotejob/gcloudscripts/gptfimodel/models/tweetGPT2fi/checkpoint-5000",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -25,8 +25,13 @@
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
   "transformers_version": "4.7.0.dev0",
   "use_cache": true,
-  "vocab_size": 50001,
-  "<|endoftext|>": 50000
+  "vocab_size": 50257
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ea3c14ad944e135422b3c074016cef60d1403e23e6657d845e305e159414d50
-size 509619451
+oid sha256:8e2df387b5b90bb51f03fe55642ddcc3a5c014feb6ce94ac939ac43ca0e61a06
+size 510405883

rust_model.ot

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65bb155d528a29e09bc8ac6fe6d474b173686e4dca2c3b2456ee734170de6686
-size 547354662
+oid sha256:2e7a37c1e4f7dbdeb486de2b2ae22ab1ababb6443f29cdbafa443c3e48d0e254
+size 548141094

special_tokens_map.json

@@ -1 +1 @@
-{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "special_tokens_map_file": null, "name_or_path": "output/content/models/tweetGPTfi/weights/checkpoint-140000", "errors": "replace"}
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "/home/juno/repos/gitlab.com/remotejob/gcloudscripts/gptfimodel/models/tweetGPT2fi/checkpoint-5000"}

usrful.bash

@@ -1,3 +0,0 @@
-huggingface-cli repo create tweetsGPT2fi_v1
-
-git clone https://huggingface.co/remotejob/tweetsGPT2fi_v1