Model save

README.md

@@ -1,20 +1,17 @@
 ---
 base_model: BSC-LT/salamandra-7b
-datasets:
-- latam-gpt/es-ultrachat
 library_name: transformers
-model_name: BSC-LT/salamandra-7b
+model_name: salamandra-2B-instruct-ultrachat
 tags:
 - generated_from_trainer
-- alignment-handbook
 - trl
 - sft
 licence: license
 ---
 
-# Model Card for BSC-LT/salamandra-7b
+# Model Card for salamandra-2B-instruct-ultrachat
 
-This model is a fine-tuned version of [BSC-LT/salamandra-7b](https://huggingface.co/BSC-LT/salamandra-7b) on the [['latam-gpt/es-ultrachat']](https://huggingface.co/datasets/['latam-gpt/es-ultrachat']) dataset.
+This model is a fine-tuned version of [BSC-LT/salamandra-7b](https://huggingface.co/BSC-LT/salamandra-7b).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -30,7 +27,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/sebcif-cenia/huggingface/runs/a904c82q) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/sebcif-cenia/huggingface/runs/aq3zw85i) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 1.9995122744269225,
-    "total_flos": 1.5426787958438494e+19,
-    "train_loss": 3.4351423407190405,
-    "train_runtime": 37293.9625,
+    "epoch": 1.998916106655105,
+    "total_flos": 1.542232840692197e+19,
+    "train_loss": 3.6333630210094006,
+    "train_runtime": 27233.3224,
     "train_samples": 207864,
-    "train_samples_per_second": 1.979,
-    "train_steps_per_second": 0.082
+    "train_samples_per_second": 2.71,
+    "train_steps_per_second": 0.085
 }

config.json

@@ -26,6 +26,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.48.1",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 256000
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8956cae1eb07c4bcae2e5b934b117cdacf2f3033674fa1782cba6fc7b5016a74
+oid sha256:7e826d898cacc5f3ee3acaf75e70eb229a994476e1767d488d65f38454d349fa
 size 4982973048

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bb239ce89c80fa3c622e2981ee2c871ce3eb66959d9a770d41262a29542e273
+oid sha256:14002701b7e0caea8d8ded8137c1d5598493da8db4d437136efa12c61adf5a00
 size 4995660232

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dc193ab6a160c9b1dbd883c4fc8c62ca1fcba400c2585e5b17c0e4ae22f53a6
+oid sha256:e5b96b96b523f9c8771cb7cb190a8791f333c2be04aaa469ef629599b0750d56
 size 3460482936

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2d233f9553d8864b8f5e20ade5acacacd61e147c38bddcec81833e07dac2c9a
+oid sha256:121c597ceb5b84c1eae35b560abab0fb244ded3639da924259671a988ac9882e
 size 2097152128

special_tokens_map.json

@@ -1,19 +1,23 @@
 {
-  "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": "</s>",
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|im_end|>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -1084,14 +1084,19 @@
       "special": false
     }
   },
-  "bos_token": "<s>",
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
+  "eos_token": "<|im_end|>",
   "extra_special_tokens": {},
   "legacy": false,
   "local_files_only": true,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
+  "model_max_length": 2048,
+  "pad_token": "<|im_end|>",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 1.9995122744269225,
-    "total_flos": 1.5426787958438494e+19,
-    "train_loss": 3.4351423407190405,
-    "train_runtime": 37293.9625,
+    "epoch": 1.998916106655105,
+    "total_flos": 1.542232840692197e+19,
+    "train_loss": 3.6333630210094006,
+    "train_runtime": 27233.3224,
     "train_samples": 207864,
-    "train_samples_per_second": 1.979,
-    "train_steps_per_second": 0.082
+    "train_samples_per_second": 2.71,
+    "train_steps_per_second": 0.085
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d430db56a35c3305e8b23a60a63cea7d30944d273ee2d3936ccf953376170d1
-size 18673016
+oid sha256:226f4269505212abaaeec8ef162fef5b5022fd8f73bb9ff5e87e83dc01c8243b
+size 7032