Training in progress, step 5000

.gitignore

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

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "schreon/gpt2large-lhm-03",
+  "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": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 36,
+  "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": "4.25.1",
+  "use_cache": true,
+  "vocab_size": 40000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42de8467efc9ba4c7e4df3b84d8999adfd539cc78281a1ebf7df62dd143f1690
+size 3081519165

runs/Feb19_12-03-55_tardis/1676804648.6517532/events.out.tfevents.1676804648.tardis.1509802.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:434fcac8ce15abe3a39ea584b9bb6683de2e113f3bf94613f2ce66689da26562
+size 5538

runs/Feb19_12-03-55_tardis/events.out.tfevents.1676804648.tardis.1509802.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e7f21c9b42c65fd429af56e07c6706b9641343b9157980a0d648786c70b155b
+size 4228

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 +1,6 @@
+{
+  "model_max_length": 1000000000000000019884624838656,
+  "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 sha256:171f819bbd6ba714c5bc16f4aa774b255e703f5c3a9024bf3c77471a9d177bf9
+size 3451