Training in progress, step 120

README.md

@@ -1,19 +1,20 @@
 ---
-base_model: HuggingFaceM4/idefics2-8b
-license: apache-2.0
+base_model: HuggingFaceM4/idefics-9b-instruct
+library_name: peft
+license: other
 tags:
 - generated_from_trainer
 model-index:
-- name: idefics2-frozenlake
+- name: idefics-frozenlake
   results: []
 ---
 
 <!-- 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. -->
 
-# idefics2-frozenlake
+# idefics-frozenlake
 
-This model is a fine-tuned version of [HuggingFaceM4/idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b) on an unknown dataset.
+This model is a fine-tuned version of [HuggingFaceM4/idefics-9b-instruct](https://huggingface.co/HuggingFaceM4/idefics-9b-instruct) on an unknown dataset.
 
 ## Model description
 
@@ -50,7 +51,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.41.2
-- Pytorch 2.1.1+cu121
-- Datasets 2.20.0
-- Tokenizers 0.19.1
+- PEFT 0.12.0
+- 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": "Idefics2ForConditionalGeneration",
+    "parent_library": "transformers.models.idefics2.modeling_idefics2"
+  },
   "base_model_name_or_path": "HuggingFaceM4/idefics2-8b",
   "bias": "none",
   "fan_in_fan_out": false,
-  "inference_mode": false,
+  "inference_mode": true,
   "init_lora_weights": "gaussian",
   "layer_replication": null,
   "layers_pattern": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87e79329754ab9a2d72ff37115cd2032d32033eb572e10a71f63cbf5838520a6
+oid sha256:c9839be56cb740b79528ed01d5549e2d47fc920db3998b041e46a73673beca51
 size 93378688

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"
 }

runs/Jul31_15-43-03_ananke/events.out.tfevents.1722433386.ananke.31988.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce75119eb99c0c325d3ed007177c942413a2d4746f44ca84de99113746fcbb0
+size 5947

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dff79ecc78535c10e2728a33beecbd0699a59c812d86d07b89fe50048982f643
-size 5048
+oid sha256:1b43490a3fe649c6b004f00482289139911ff811809a2541d2f69c7a92cd4b84
+size 5176