Training in progress, step 5000

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "schreon/gpt2-lhm-large",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "is_decoder": true,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 256,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "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": 40000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b127ae0c2dd78c09f97a31bdca31b44539c57907c35abd3b59f5c2cdfd8952f
+size 478888509

runs/Feb06_07-18-19_tardis/1675664309.0421624/events.out.tfevents.1675664309.tardis.3081706.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10ad966a0d1a1d5c4b758ec9fe426d71ad17d533146e93300d7bdcb6501abfac
+size 5475

runs/Feb06_07-18-19_tardis/events.out.tfevents.1675664309.tardis.3081706.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceca519d9e3a43ec39024777d4f076b8a71abb05408da0b54cb3f2577bc9c181
+size 4021

runs/Feb06_07-24-37_tardis/1675664683.6458158/events.out.tfevents.1675664683.tardis.3085636.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:143f9c963a485e2df3c5de0b872771bdc8353d95c31232b84b500a96dcfe7e35
+size 5475

runs/Feb06_07-24-37_tardis/events.out.tfevents.1675664683.tardis.3085636.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61581e0cd6da8b70c44a26c60336c580817a9a03f10d2ab40afe9dea37c8faa4
+size 4178

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<cls>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "</s>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,5 @@
+{
+  "name_or_path": "/home/ma/s/schroederl/XNEXT/xnext/data/tokenizer_fast",
+  "special_tokens_map_file": "/home/ma/s/schroederl/XNEXT/xnext/data/tokenizer_fast/special_tokens_map.json",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c5ba81770de58012688197c4fc0d384ea9db8389804692eb65366ad164d69f7
+size 3387