Training in progress, epoch 1

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+vocab.json filter=lfs diff=lfs merge=lfs -text

.gitignore

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

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "xlm-mlm-en-2048",
+  "architectures": [
+    "XLMForSequenceClassification"
+  ],
+  "asm": false,
+  "attention_dropout": 0.1,
+  "bos_index": 0,
+  "bos_token_id": 0,
+  "causal": false,
+  "dropout": 0.1,
+  "emb_dim": 2048,
+  "embed_init_std": 0.02209708691207961,
+  "end_n_top": 5,
+  "eos_index": 1,
+  "gelu_activation": true,
+  "init_std": 0.02,
+  "is_encoder": true,
+  "lang_id": 0,
+  "layer_norm_eps": 1e-12,
+  "mask_index": 5,
+  "mask_token_id": 0,
+  "max_position_embeddings": 512,
+  "model_type": "xlm",
+  "n_heads": 16,
+  "n_langs": 1,
+  "n_layers": 12,
+  "pad_index": 2,
+  "pad_token_id": 2,
+  "problem_type": "single_label_classification",
+  "sinusoidal_embeddings": false,
+  "start_n_top": 5,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "unk_index": 3,
+  "use_lang_emb": true,
+  "vocab_size": 30145
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7afbbdaa9e2ef8a8d3b0fc8b08678ad45c908b28470fccde5fb49fd2394917b
+size 2668441385

runs/May31_17-24-54_8053ae486478/1685553901.1365833/events.out.tfevents.1685553901.8053ae486478.412.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41874b676addc0ca343e05b16c510d64f4c0d1eab87c9a919b2edb4b95a10b0a
+size 5918

runs/May31_17-24-54_8053ae486478/events.out.tfevents.1685553901.8053ae486478.412.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beab83aef93a2b36ddde06a4cdb71b4100d53c2096d4637f0c32aa5caf7aed79
+size 5569

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<special0>",
+    "<special1>",
+    "<special2>",
+    "<special3>",
+    "<special4>",
+    "<special5>",
+    "<special6>",
+    "<special7>",
+    "<special8>",
+    "<special9>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "</s>",
+  "mask_token": "<special1>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,26 @@
+{
+  "additional_special_tokens": [
+    "<special0>",
+    "<special1>",
+    "<special2>",
+    "<special3>",
+    "<special4>",
+    "<special5>",
+    "<special6>",
+    "<special7>",
+    "<special8>",
+    "<special9>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "</s>",
+  "do_lowercase_and_remove_accent": true,
+  "id2lang": null,
+  "lang2id": null,
+  "mask_token": "<special1>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67104d4ea2654e74b7c5204c231ac6ec0565533d748b8165a3cb31d6b8283453
+size 3707

vocab.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eb700423b2604e555abf45cf9912bc16015c7f3f9d9d25fcff95c19cd9e15cf
+size 646176