Training in progress, step 10

README.md

@@ -52,6 +52,18 @@ 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
@@ -69,5 +81,6 @@ 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_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75b7cbced5aaf55b4676459233174fca5aa8e63d7ee9515a2bafbbbdd72274e2
+oid sha256:e877cf672df3d94e5a16765f9ec9ae2990abf7eb5a339fb68e217c35f38207d1
 size 100733709

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ceda947757e8e863957b7c0ac6282dda8be63d6aff7d21ca866b79d3024273c
-size 261131840
+oid sha256:0dc4f031b070a3eeff0f3bc486b8b7591e15859c95ec15b6d98269d64ced9671
+size 100690288

config.json

@@ -1,33 +1,33 @@
 {
-  "_name_or_path": "tiiuae/falcon-7b",
-  "alibi": false,
+  "_name_or_path": "tiiuae/falcon-rw-1b",
+  "alibi": true,
   "apply_residual_connection_post_layernorm": false,
   "architectures": [
     "FalconForCausalLM"
   ],
   "attention_dropout": 0.0,
   "auto_map": {
-    "AutoConfig": "tiiuae/falcon-7b--configuration_falcon.FalconConfig",
-    "AutoModel": "tiiuae/falcon-7b--modeling_falcon.FalconModel",
-    "AutoModelForCausalLM": "tiiuae/falcon-7b--modeling_falcon.FalconForCausalLM",
-    "AutoModelForQuestionAnswering": "tiiuae/falcon-7b--modeling_falcon.FalconForQuestionAnswering",
-    "AutoModelForSequenceClassification": "tiiuae/falcon-7b--modeling_falcon.FalconForSequenceClassification",
-    "AutoModelForTokenClassification": "tiiuae/falcon-7b--modeling_falcon.FalconForTokenClassification"
+    "AutoConfig": "tiiuae/falcon-rw-1b--configuration_falcon.FalconConfig",
+    "AutoModel": "tiiuae/falcon-rw-1b--modeling_falcon.FalconModel",
+    "AutoModelForCausalLM": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForCausalLM",
+    "AutoModelForQuestionAnswering": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForQuestionAnswering",
+    "AutoModelForSequenceClassification": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForSequenceClassification",
+    "AutoModelForTokenClassification": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForTokenClassification"
   },
-  "bias": false,
-  "bos_token_id": 11,
-  "eos_token_id": 11,
+  "bias": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "hidden_dropout": 0.0,
-  "hidden_size": 4544,
+  "hidden_size": 2048,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "falcon",
-  "multi_query": true,
+  "multi_query": false,
   "new_decoder_architecture": false,
-  "num_attention_heads": 71,
-  "num_hidden_layers": 32,
-  "num_kv_heads": 71,
-  "parallel_attn": true,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_kv_heads": 32,
+  "parallel_attn": false,
   "quantization_config": {
     "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_type": "nf4",
@@ -43,5 +43,5 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.34.1",
   "use_cache": false,
-  "vocab_size": 65024
+  "vocab_size": 50304
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46dfa040a93c7f61a97e86a998ade17bf1b307d0aa4af935c733a7c7ad2cd6b3
+oid sha256:e952a35dab9b7558195f77eab50ba42c6f635e30bceddcfbeac8e0ede9843ec8
 size 4091