Training in progress, step 8

README.md

@@ -1,18 +1,18 @@
 ---
+library_name: transformers
 license: other
 base_model: HuggingFaceM4/idefics-9b-instruct
 tags:
 - generated_from_trainer
 model-index:
-- name: IDEFICS-frozenlake
+- name: idefics-frozenlake
   results: []
-library_name: peft
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# IDEFICS-frozenlake
+# idefics-frozenlake
 
 This model is a fine-tuned version of [HuggingFaceM4/idefics-9b-instruct](https://huggingface.co/HuggingFaceM4/idefics-9b-instruct) on an unknown dataset.
 
@@ -30,21 +30,6 @@ 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: ['lm_head', 'embed_tokens']
-- 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
-- bnb_4bit_quant_storage: uint8
-- load_in_4bit: True
-- load_in_8bit: False
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
@@ -66,8 +51,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.5.0
-- Transformers 4.43.3
+- Transformers 4.44.2
 - Pytorch 2.4.0+cu121
 - Datasets 2.16.1
 - Tokenizers 0.19.1

adapter_config.json

@@ -1,10 +1,13 @@
 {
   "alpha_pattern": {},
-  "auto_mapping": null,
+  "auto_mapping": {
+    "base_model_class": "IdeficsForVisionText2Text",
+    "parent_library": "transformers.models.idefics.modeling_idefics"
+  },
   "base_model_name_or_path": "HuggingFaceM4/idefics-9b-instruct",
   "bias": "none",
   "fan_in_fan_out": false,
-  "inference_mode": false,
+  "inference_mode": true,
   "init_lora_weights": true,
   "layer_replication": null,
   "layers_pattern": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12b16d8e13ed091487ecc21ea9166e8c460c8a8ac80999e55fb0c7e3940b25ad
+oid sha256:aed52d837b559feddb8ad93f11bf3bd8d4701b8acc18725907da8fb1e05ae623
 size 316083632

generation_config.json

@@ -1,18 +1,7 @@
 {
   "_from_model_config": true,
-  "bad_words_ids": [
-    [
-      32000
-    ],
-    [
-      32001
-    ]
-  ],
   "bos_token_id": 1,
-  "eos_token_id": [
-    2,
-    32002
-  ],
+  "eos_token_id": 2,
   "pad_token_id": 0,
-  "transformers_version": "4.41.2"
+  "transformers_version": "4.44.2"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bda840a620fc3fecb4e9232542ff5acc25b83a9e7a9a489bee21308cae32cab
+oid sha256:1e2f04de1e05d3a5b7d49028a0731255792b86d69756b7b498f60b499b343716
 size 5176