End of training

README.md

@@ -0,0 +1,74 @@
+---
+base_model: llava-hf/llava-1.5-7b-hf
+library_name: peft
+license: llama2
+metrics:
+- bleu
+- rouge
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: sft-llava-1.5-7b_new
+  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. -->
+
+# sft-llava-1.5-7b_new
+
+This model is a fine-tuned version of [llava-hf/llava-1.5-7b-hf](https://huggingface.co/llava-hf/llava-1.5-7b-hf) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9503
+- Bleu: 0.1431
+- Rouge1: 0.4595
+- Rouge2: 0.1862
+- Rougel: 0.3572
+- Bertscore Precision: 0.6764
+- Bertscore Recall: 0.7669
+- Bertscore F1: 0.7187
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Bleu   | Rouge1 | Rouge2 | Rougel | Bertscore Precision | Bertscore Recall | Bertscore F1 |
+|:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|:------:|:-------------------:|:----------------:|:------------:|
+| 1.9971        | 0.9922 | 80   | 1.9960          | 0.1392 | 0.4511 | 0.1839 | 0.3524 | 0.6747              | 0.7687           | 0.7185       |
+| 1.9335        | 1.9845 | 160  | 1.9503          | 0.1431 | 0.4595 | 0.1862 | 0.3572 | 0.6764              | 0.7669           | 0.7187       |
+
+
+### Framework versions
+
+- PEFT 0.13.0
+- Transformers 4.45.2
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "llava-hf/llava-1.5-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "out_proj",
+    "v_proj",
+    "q_proj",
+    "lm_head",
+    "fc1",
+    "fc2",
+    "linear_1",
+    "o_proj",
+    "k_proj",
+    "linear_2",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63a53256ce5f4248a3c862fd668a60ce0fcdf8cfa0a268ead0e3fae4253c1de6
+size 454168240

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<image>": 32000,
+  "<pad>": 32001
+}

runs/Oct17_16-31-19_s1840377-4-6lkqx/events.out.tfevents.1729182794.s1840377-4-6lkqx.1466276.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5607679682915ef20b10f5a31ebb51d3373ead7f584027114c5562191ed0ae93
+size 14428

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

test_predictions.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:420df26f6bfcdf695e1f16079a6e9cb1443246afca6f133b231ed00fb5fc1304
+size 33364

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "LlavaProcessor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62feaa51a2e8790b76e3f26c4df8d3f74904f3a0cefe49b3aa018c343ccbab50
+size 5560