Training in progress, epoch 1

.gitignore

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

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endofpiece|>": 50266,
+  "<|startofpiece|>": 50265,
+  "[MASK]": 50267
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "BAAI/glm-roberta-large",
+  "architectures": [
+    "GLMForConditionalGeneration"
+  ],
+  "attention_dropout_prob": 0.1,
+  "attention_scale": 1.0,
+  "auto_map": {
+    "AutoConfig": "configuration_glm.GLMConfig",
+    "AutoModel": "modeling_glm.GLMModel",
+    "AutoModelForMultipleChoice": "modeling_glm.GLMForMultipleChoice",
+    "AutoModelForSeq2SeqLM": "modeling_glm.GLMForConditionalGeneration"
+  },
+  "block_position_encoding": true,
+  "checkpoint_activations": false,
+  "checkpoint_num_layers": 1,
+  "embedding_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "max_sequence_length": 512,
+  "model_type": "glm",
+  "num_attention_heads": 16,
+  "num_layers": 24,
+  "output_dropout_prob": 0.1,
+  "output_predict": true,
+  "parallel_output": true,
+  "pool_token": "cls",
+  "relative_encoding": false,
+  "spell_func": "lstm",
+  "spell_length": null,
+  "torch_dtype": "float16",
+  "transformers_version": "4.24.0",
+  "vocab_size": 50304
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8f92746e5cb090ffef4d65d831110764d3a37e7f4ee31c1eb0c97dbe4081725
+size 709847841

runs/Jan07_13-12-10_821e18845ca1/1673097138.5737278/events.out.tfevents.1673097138.821e18845ca1.1305.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f36d9739200763c41d5c1822b04f38f66d158214f47079259264511007103d94
+size 5751

runs/Jan07_13-12-10_821e18845ca1/events.out.tfevents.1673097138.821e18845ca1.1305.16

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac9f6189e11d91ea8e5f23cfd93431cb8347b2ed816e7e86c2da7829e5bc78e1
+size 5088

special_tokens_map.json

@@ -0,0 +1,55 @@
+{
+  "additional_special_tokens": [
+    "<|startofpiece|>",
+    "<|endofpiece|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,68 @@
+{
+  "add_prefix_space": false,
+  "additional_special_tokens": [
+    "<|startofpiece|>",
+    "<|endofpiece|>"
+  ],
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "name_or_path": "BAAI/glm-roberta-large",
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GLMRobertaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_fast": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7562a5d356d51244c5354d5a46111b87dbfe26fca52408c11f4f3d3dcf35435
+size 3579