Training in progress, step 10

README.md

@@ -6,6 +6,7 @@ tags:
 model-index:
 - name: adapter_ingredients_base
   results: []
+library_name: peft
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,6 +30,18 @@ More information needed
 
 ## Training procedure
 
+
+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
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
@@ -49,6 +62,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
+- PEFT 0.5.0
 - Transformers 4.33.3
 - Pytorch 2.0.1+cu117
 - Datasets 2.14.5

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb7afac1431b80479e961624ac63a3070b4f7d90bb41b880c5f0860195decd94
+oid sha256:e00621218bcf3e7e1ddd2951430483aabc9ecdc39b11c8dd507ace0d08045f71
 size 261189453

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c6a7412cf0b2849f6776167701fd1beddbc0ef6b9730fa98233ae9744c3f9c3
+size 261131840

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "vilsonrodrigues/falcon-7b-sharded",
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "FalconForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "vilsonrodrigues/falcon-7b-sharded--configuration_falcon.FalconConfig",
+    "AutoModel": "vilsonrodrigues/falcon-7b-sharded--modeling_falcon.FalconModel",
+    "AutoModelForCausalLM": "vilsonrodrigues/falcon-7b-sharded--modeling_falcon.FalconForCausalLM",
+    "AutoModelForQuestionAnswering": "vilsonrodrigues/falcon-7b-sharded--modeling_falcon.FalconForQuestionAnswering",
+    "AutoModelForSequenceClassification": "vilsonrodrigues/falcon-7b-sharded--modeling_falcon.FalconForSequenceClassification",
+    "AutoModelForTokenClassification": "vilsonrodrigues/falcon-7b-sharded--modeling_falcon.FalconForTokenClassification"
+  },
+  "bias": false,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4544,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "falcon",
+  "multi_query": true,
+  "new_decoder_architecture": false,
+  "num_attention_heads": 71,
+  "num_hidden_layers": 32,
+  "num_kv_heads": 71,
+  "parallel_attn": true,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "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": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.33.3",
+  "use_cache": false,
+  "vocab_size": 65024
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d546616dbd04c8948360f0fb6f63edcaf490bb64d04790ed0b027a17b59ad8f
+oid sha256:7ba8a8ef281b481bc21613c47d4ff159f21426ebac0a03dd9baa07efd93d2753
 size 4027