Training in progress, step 50

adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "facebook/xglm-564M",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.0,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "revision": null,
+  "target_modules": [
+    "fc1",
+    "fc2",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "out_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be57012cccc192db39188bf76f0bbe522241141852ba27da51a35f139dfe1e96
+size 226595405

added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "</s>": 2,
+  "<madeupword0>": 256001,
+  "<madeupword1>": 256002,
+  "<madeupword2>": 256003,
+  "<madeupword3>": 256004,
+  "<madeupword4>": 256005,
+  "<madeupword5>": 256006,
+  "<madeupword6>": 256007,
+  "<pad>": 1,
+  "<s>": 0,
+  "<unk>": 3
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "facebook/xglm-564M",
+  "activation_dropout": 0,
+  "activation_function": "gelu",
+  "architectures": [
+    "XGLMForCausalLM"
+  ],
+  "attention_dropout": 0.1,
+  "attention_heads": 16,
+  "bos_token_id": 0,
+  "d_model": 1024,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "eos_token_id": 2,
+  "ffn_dim": 4096,
+  "init_std": 0.02,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "xglm",
+  "num_layers": 24,
+  "pad_token_id": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "scale_embedding": true,
+  "transformers_version": "4.34.0.dev0",
+  "use_cache": false,
+  "vocab_size": 256008
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c49dc7e82c10227af764e518924cf2f9d50c00462750d184fa74697bba65eef8
+size 4920706

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "additional_special_tokens": [
+    "<madeupword0>",
+    "<madeupword1>",
+    "<madeupword2>",
+    "<madeupword3>",
+    "<madeupword4>",
+    "<madeupword5>",
+    "<madeupword6>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,114 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "256001": {
+      "content": "<madeupword0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "256002": {
+      "content": "<madeupword1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "256003": {
+      "content": "<madeupword2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "256004": {
+      "content": "<madeupword3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "256005": {
+      "content": "<madeupword4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "256006": {
+      "content": "<madeupword5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "256007": {
+      "content": "<madeupword6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<madeupword0>",
+    "<madeupword1>",
+    "<madeupword2>",
+    "<madeupword3>",
+    "<madeupword4>",
+    "<madeupword5>",
+    "<madeupword6>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XGLMTokenizer",
+  "tokenizer_file": null,
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_fast": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7141607e68efc87ea108ea395abf98f0a47a86d61166ba2a22e9efaaf5e499b9
+size 4475