Training in progress, step 10

26_10_23_config_test.csv

@@ -11,3 +11,5 @@ run_number,comment,peformed_already,num_train_epochs,max_tokens,temperature,stop
 10,classification_of_valuems set True,False,2,100,0.8,False,True,False,False
 11,classification_of_valuems set True,False,2,100,0.8,False,True,False,False
 12,classification_of_valuems set True,False,2,100,0.8,False,True,False,False
+13,classification_of_valuems set True,False,2,100,0.8,False,True,False,False
+14,classification_of_valuems set True,False,2,100,0.8,False,True,False,False

26_10_23_results_real_3.csv

@@ -5,4 +5,4 @@ run_number,items_per_minute,changed_settings,total_time_taken,rouge_scores_unnes
 4,1525.602524101584,classification_of_valuems set True,17.304638385772705,0,0.3449559795118336,0.3423341666457499,0.3223067218438548,0.3962323417858379,0.3934280156800367,0.3705820791169619,0.4480554100301472,0.4472379094634592,0.4191781582462838,0.1924640322240557,0.1864412220397102,0.1791588870738077,0.2322731554369229,0.2249807377601852,0.2130668974234288,0.275524472174082,0.267281230315844,0.2520826707151871,0.25,0.25,0.25
 5,1526.1514943613795,lemmatization set True    stemming set True    classification_of_valuems set True,17.29841375350952,0,0.2740090800292036,0.3255265414032295,0.2775650458916542,0.3242606066397121,0.382074138505741,0.3267769081728278,0.3772870132781871,0.4458722947774239,0.3791647882107381,0.1589738558026723,0.1948121530040918,0.163589425650448,0.197346401556911,0.2400173323974756,0.2012985648757239,0.2417203208425002,0.291225773302693,0.2448890209857868,0.5,0.5,0.5
 6,1530.684509829563,lemmatization set True    classification_of_valuems set True,17.247185707092285,0,0.2089967577635823,0.2539863482828974,0.2180593819184433,0.2566736342083835,0.3067268601430931,0.2634860133658033,0.3083760408920908,0.3641939637052689,0.3143688188949664,0.1022732513904408,0.1231935696888519,0.1061505173202719,0.1366654941744046,0.1619876288426343,0.1387847257382091,0.1783473709510714,0.2101453928900783,0.1797982054917218,0.4999999999999998,0.4999999999999998,0.4999999999999998
-15,1537.4830854419854,lemmatization set True    stemming set True    classification_of_valuems set True,17.170920610427856,0,0.3137446610565907,0.346938031739325,0.3116890258549815,0.36716366175121,0.4078239534610949,0.3658593356405938,0.4216956378639542,0.4672338475399563,0.4174884317080075,0.1868318428239036,0.2090565062942769,0.1872856926409339,0.2333035163819085,0.2570762720696271,0.2307891585347144,0.2805117716175197,0.3026827885812185,0.2738993050878683,0.25,0.25,0.25
+17,1537.4830854419854,lemmatization set True    stemming set True    classification_of_valuems set True,17.170920610427856,0,0.3137446610565907,0.346938031739325,0.3116890258549815,0.36716366175121,0.4078239534610949,0.3658593356405938,0.4216956378639542,0.4672338475399563,0.4174884317080075,0.1868318428239036,0.2090565062942769,0.1872856926409339,0.2333035163819085,0.2570762720696271,0.2307891585347144,0.2805117716175197,0.3026827885812185,0.2738993050878683,0.25,0.25,0.25

26_10_23_results_test.csv

@@ -14,3 +14,5 @@ run_number,items_per_minute,changed_settings,total_time_taken,rouge_scores_unnes
 0,0.0,0,0.0,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0
 0,0.0,0,0.0,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0
 0,0.0,0,0.0,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0
+0,0.0,0,0.0,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0
+0,0.0,0,0.0,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0

README.md

@@ -988,6 +988,18 @@ 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
@@ -1083,5 +1095,6 @@ 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:cb8f3af67514077e6934af24b4d5109b8d72d2300e017c58c8179afe7b046dcd
-size 261189453
+oid sha256:c84509185299bd4f6bf3ce9f6325f6a41a75ef2a24fb231a9576afd2657fb7f6
+size 100733709

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f619bac221ad47d5e75d145e26ade5d18998b4360842d8357557853adf65ebdf
+oid sha256:fc30f8a1f8cbc7e6e739a3bccd24e9771a9a66560696bd18ec550294cffdb65d
 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 sha256:17e1d6ea179881703aebc9cf5ee9455199d40dcc06ec43acb88843d785a2245b
+oid sha256:2fe4cff4aa028bf0d1b54503e9abf8913f14b438d2594b62310162bb76256de1
 size 4283