danushkhanna/FPO-falcon-rw-1b-instruct-openorca

README.md

@@ -0,0 +1,55 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: ericzzz/falcon-rw-1b-instruct-openorca
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [ericzzz/falcon-rw-1b-instruct-openorca](https://huggingface.co/ericzzz/falcon-rw-1b-instruct-openorca) on an unknown dataset.
+
+## 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: 1
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.2
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "ericzzz/falcon-rw-1b-instruct-openorca",
+  "activation": "gelu",
+  "alibi": true,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "FalconForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bias": true,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "ffn_hidden_size": 8192,
+  "hidden_dropout": 0.0,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "falcon",
+  "multi_query": false,
+  "new_decoder_architecture": false,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_kv_heads": 32,
+  "num_ln_in_parallel_attn": null,
+  "parallel_attn": false,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.2",
+  "use_cache": false,
+  "vocab_size": 50304
+}

emissions.csv

@@ -0,0 +1,2 @@
+timestamp,project_name,run_id,experiment_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
+2024-11-24T11:04:28,codecarbon,ffecbe2e-dbeb-47fc-9c90-9861435fef83,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,1188.7255009170003,0.04234573360115125,3.562280237824891e-05,42.5,56.50246183980127,31.30389261245728,0.014026415363663863,0.069204406196814,0.010325939257073183,0.09355676081755109,United States,USA,iowa,,,Linux-6.1.85+-x86_64-with-glibc2.35,3.10.12,2.7.4,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,-95.8517,41.2591,83.47704696655273,machine,N,1.0

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.46.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62717f60b801abf55f7a9d0b9c82527380085998737ea889ee25040a1c878f69
+size 2623284400

runs/Nov24_10-04-54_972e0c2302d7/events.out.tfevents.1732442702.972e0c2302d7.2097.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9e38c6adfa09c461c4fbc54959077eabebc6aeb2c99efe311f10177a9b5b83b
+size 6002

runs/Nov24_10-15-47_972e0c2302d7/events.out.tfevents.1732443356.972e0c2302d7.5110.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e33c6ed760de4ee3f1961e16cd70bcf23a4b648b107fe9c06df05e146b91ba5
+size 4184

runs/Nov24_10-24-30_972e0c2302d7/events.out.tfevents.1732443879.972e0c2302d7.8246.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12df217bc9eaeebd8942ff168a716b17bd4fb65dd561b34bea5194caddddf033
+size 6011

runs/Nov24_10-27-55_972e0c2302d7/events.out.tfevents.1732444084.972e0c2302d7.10999.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:143ba24c8496788fb7136bff582cd9b341fba9495e990f97803d6be6f142c9bc
+size 6011

runs/Nov24_10-33-17_972e0c2302d7/events.out.tfevents.1732444405.972e0c2302d7.12530.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:684d7b60fe377263f4d2f25cf328ffde48a0491fef8c39b73d11d639e5d2ed85
+size 6036

runs/Nov24_10-35-33_972e0c2302d7/events.out.tfevents.1732444540.972e0c2302d7.12530.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ad95e1772ccad44b57e4373428408bcc5b2ed4bd5964694be30d033979f6c63
+size 4184

runs/Nov24_10-37-47_972e0c2302d7/events.out.tfevents.1732444676.972e0c2302d7.14379.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29b58b60a9cbb004adb1d57bbc65bb230f59fa0e37faef5940c7e6075c55dbbf
+size 6002

runs/Nov24_10-41-03_972e0c2302d7/events.out.tfevents.1732444872.972e0c2302d7.15650.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:164975d67c0e49c0a8d6bdc4d1dc75970d061901a91a979d52b52830003d8cf6
+size 6002

runs/Nov24_10-44-27_972e0c2302d7/events.out.tfevents.1732445077.972e0c2302d7.16943.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7052ee30491064a58be0b288cc41b39118168b9af95d068139a7d6150582483d
+size 11172

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63ed6e5565334fc389eb330bebc64b62242646c039a6b3f4c17fd76cf10053f0
+size 6072