Training in progress, step 10

27_10_23_results_real_3.csv

@@ -13,3 +13,4 @@ run_number,items_per_minute,changed_settings,total_time_taken,rouge_scores_unnes
 12,0.0,0,0.0,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0
 13,0.0,0,0.0,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0
 14,0.0,0,0.0,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0
+15,0.0,0,0.0,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0

README.md

@@ -1156,6 +1156,18 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_use_double_quant: True
 - bnb_4bit_compute_dtype: bfloat16
 
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
 The following `bitsandbytes` quantization config was used during training:
 - quant_method: bitsandbytes
 - load_in_8bit: False
@@ -1265,5 +1277,6 @@ The following `bitsandbytes` quantization config was used during training:
 - PEFT 0.5.0
 - PEFT 0.5.0
 - PEFT 0.5.0
+- PEFT 0.5.0
 
 - PEFT 0.5.0

adapter_config.json

@@ -1,6 +1,6 @@
 {
   "auto_mapping": null,
-  "base_model_name_or_path": "tiiuae/falcon-7b",
+  "base_model_name_or_path": "tiiuae/falcon-rw-1b",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0daadbfd3ec5857d4975058971366fbd1bd98ae31ce05a3fc424d3ad5c8521e5
-size 261189453
+oid sha256:1fff1f0690d150b98f4ba51bfeb4749ab6e770535b0224a717d8284cb63ba9bd
+size 100733709

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:322b64c08c2c7395ebf7005f59d72b96ed1565ad762c8c8c6bbe4ee941b9b292
+oid sha256:c01fefcf4063adf1445ac76b8283325a24110fc4bdab20203a549556c076c7cd
 size 261131840

special_tokens_map.json

@@ -1,17 +1,6 @@
 {
-  "additional_special_tokens": [
-    ">>TITLE<<",
-    ">>ABSTRACT<<",
-    ">>INTRODUCTION<<",
-    ">>SUMMARY<<",
-    ">>COMMENT<<",
-    ">>ANSWER<<",
-    ">>QUESTION<<",
-    ">>DOMAIN<<",
-    ">>PREFIX<<",
-    ">>SUFFIX<<",
-    ">>MIDDLE<<"
-  ],
+  "bos_token": "<|endoftext|>",
   "eos_token": "<|endoftext|>",
-  "pad_token": "<|endoftext|>"
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
 }

tokenizer_config.json

@@ -1,95 +1,7 @@
 {
   "add_prefix_space": false,
   "added_tokens_decoder": {
-    "0": {
-      "content": ">>TITLE<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": ">>ABSTRACT<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": ">>INTRODUCTION<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "3": {
-      "content": ">>SUMMARY<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "4": {
-      "content": ">>COMMENT<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "5": {
-      "content": ">>ANSWER<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "6": {
-      "content": ">>QUESTION<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "7": {
-      "content": ">>DOMAIN<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "8": {
-      "content": ">>PREFIX<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "9": {
-      "content": ">>SUFFIX<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "10": {
-      "content": ">>MIDDLE<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "11": {
+    "50256": {
       "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
@@ -98,26 +10,11 @@
       "special": true
     }
   },
-  "additional_special_tokens": [
-    ">>TITLE<<",
-    ">>ABSTRACT<<",
-    ">>INTRODUCTION<<",
-    ">>SUMMARY<<",
-    ">>COMMENT<<",
-    ">>ANSWER<<",
-    ">>QUESTION<<",
-    ">>DOMAIN<<",
-    ">>PREFIX<<",
-    ">>SUFFIX<<",
-    ">>MIDDLE<<"
-  ],
+  "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
-  "model_input_names": [
-    "input_ids",
-    "attention_mask"
-  ],
-  "model_max_length": 2048,
+  "model_max_length": 1024,
   "pad_token": "<|endoftext|>",
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1225629652dbc6b51413e67206b008bd6e70729acc98876020e76cfe737d290f
+oid sha256:0da88285b0dd9d0d5dd6e92a0091778dec625cd0fb75308860f064592231c197
 size 4283