Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/models--google--gemma-2b-it/snapshots/060189a16d5d2713425599b533a9e8ece8f5cca6",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_activation": null,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "float16",
+  "transformers_version": "4.39.1",
+  "use_cache": false,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.39.1"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e382f218644489e985048c62ed67c0f977c76eaec31f9a7f9b01c3116f9b9700
+size 1948301196

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e745d71c4c8fef4dba1b4090deebbb69cf012c3faa6151733e5078815abc5529
+size 1981910044

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ef48cc5f182ee26a1e57ed191f58c44ff34e5bcb5202a3223f254a13bbaabe5
+size 1082189982

pytorch_model.bin.index.json

@@ -0,0 +1,172 @@
+{
+  "metadata": {
+    "total_size": 5012344832
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00001-of-00003.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05e97791a5e007260de1db7e1692e53150e08cea481e2bf25435553380c147ee
+size 17477929

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,71 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

xtuner_config.py

@@ -0,0 +1,193 @@
+SYSTEM = 'xtuner.utils.SYSTEM_TEMPLATE.alpaca'
+accumulative_counts = 16
+alpaca_en = dict(
+    dataset=dict(
+        data_files='/petrobr/parceirosbr/radiar/llama_test/ultracabrita3.json',
+        path='json',
+        type='datasets.load_dataset'),
+    dataset_map_fn='xtuner.dataset.map_fns.ultracabrita_map_fn',
+    max_length=2048,
+    pack_to_max_length=True,
+    remove_unused_columns=True,
+    shuffle_before_pack=True,
+    template_map_fn=dict(
+        template='xtuner.utils.PROMPT_TEMPLATE.gemma',
+        type='xtuner.dataset.map_fns.template_map_fn_factory'),
+    tokenizer=dict(
+        padding_side='right',
+        pretrained_model_name_or_path=
+        '/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/models--google--gemma-2b-it/snapshots/060189a16d5d2713425599b533a9e8ece8f5cca6',
+        trust_remote_code=True,
+        type='transformers.AutoTokenizer.from_pretrained'),
+    type='xtuner.dataset.process_hf_dataset',
+    use_varlen_attn=False)
+alpaca_en_path = '/petrobr/parceirosbr/radiar/llama_test/ultracabrita3.json'
+batch_size = 1
+betas = (
+    0.9,
+    0.999,
+)
+custom_hooks = [
+    dict(
+        tokenizer=dict(
+            padding_side='right',
+            pretrained_model_name_or_path=
+            '/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/models--google--gemma-2b-it/snapshots/060189a16d5d2713425599b533a9e8ece8f5cca6',
+            trust_remote_code=True,
+            type='transformers.AutoTokenizer.from_pretrained'),
+        type='xtuner.engine.hooks.DatasetInfoHook'),
+    dict(
+        evaluation_inputs=[
+            'O que é um bode?',
+            'Qual a capital da França?',
+            'Você pode me explicar o Teorema de Pitágoras com um exemplo, por favor?',
+            'Olá, tudo bem? Estou procurando livros de ficção científica para ler, você teria sugestões para mim?',
+            'Resolva a equação de segundo grau x² - x - 30 = 0',
+            'Escreva um código em python para calcular x^y usando divisão e conquista.',
+        ],
+        every_n_iters=500,
+        prompt_template='xtuner.utils.PROMPT_TEMPLATE.gemma',
+        system='xtuner.utils.SYSTEM_TEMPLATE.alpaca',
+        tokenizer=dict(
+            padding_side='right',
+            pretrained_model_name_or_path=
+            '/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/models--google--gemma-2b-it/snapshots/060189a16d5d2713425599b533a9e8ece8f5cca6',
+            trust_remote_code=True,
+            type='transformers.AutoTokenizer.from_pretrained'),
+        type='xtuner.engine.hooks.EvaluateChatHook'),
+]
+dataloader_num_workers = 0
+default_hooks = dict(
+    checkpoint=dict(
+        by_epoch=False,
+        interval=500,
+        max_keep_ckpts=2,
+        type='mmengine.hooks.CheckpointHook'),
+    logger=dict(
+        interval=10,
+        log_metric_by_epoch=False,
+        type='mmengine.hooks.LoggerHook'),
+    param_scheduler=dict(type='mmengine.hooks.ParamSchedulerHook'),
+    sampler_seed=dict(type='mmengine.hooks.DistSamplerSeedHook'),
+    timer=dict(type='mmengine.hooks.IterTimerHook'))
+env_cfg = dict(
+    cudnn_benchmark=False,
+    dist_cfg=dict(backend='nccl'),
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
+evaluation_freq = 500
+evaluation_inputs = [
+    'O que é um bode?',
+    'Qual a capital da França?',
+    'Você pode me explicar o Teorema de Pitágoras com um exemplo, por favor?',
+    'Olá, tudo bem? Estou procurando livros de ficção científica para ler, você teria sugestões para mim?',
+    'Resolva a equação de segundo grau x² - x - 30 = 0',
+    'Escreva um código em python para calcular x^y usando divisão e conquista.',
+]
+launcher = 'pytorch'
+load_from = None
+log_level = 'INFO'
+log_processor = dict(by_epoch=False)
+lr = 2e-05
+max_epochs = 1
+max_length = 2048
+max_norm = 1
+model = dict(
+    llm=dict(
+        pretrained_model_name_or_path=
+        '/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/models--google--gemma-2b-it/snapshots/060189a16d5d2713425599b533a9e8ece8f5cca6',
+        trust_remote_code=True,
+        type='transformers.AutoModelForCausalLM.from_pretrained'),
+    type='xtuner.model.SupervisedFinetune',
+    use_varlen_attn=False)
+optim_type = 'torch.optim.AdamW'
+optim_wrapper = dict(
+    optimizer=dict(
+        betas=(
+            0.9,
+            0.999,
+        ),
+        lr=2e-05,
+        type='torch.optim.AdamW',
+        weight_decay=0),
+    type='DeepSpeedOptimWrapper')
+pack_to_max_length = True
+param_scheduler = [
+    dict(
+        begin=0,
+        by_epoch=True,
+        convert_to_iter_based=True,
+        end=0.03,
+        start_factor=1e-05,
+        type='mmengine.optim.LinearLR'),
+    dict(
+        begin=0.03,
+        by_epoch=True,
+        convert_to_iter_based=True,
+        end=1,
+        eta_min=0.0,
+        type='mmengine.optim.CosineAnnealingLR'),
+]
+pretrained_model_name_or_path = '/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/models--google--gemma-2b-it/snapshots/060189a16d5d2713425599b533a9e8ece8f5cca6'
+prompt_template = 'xtuner.utils.PROMPT_TEMPLATE.gemma'
+randomness = dict(deterministic=False, seed=None)
+resume = False
+runner_type = 'FlexibleRunner'
+save_steps = 500
+save_total_limit = 2
+strategy = dict(
+    config=dict(
+        bf16=dict(enabled=False),
+        fp16=dict(enabled=True, initial_scale_power=16),
+        gradient_accumulation_steps='auto',
+        gradient_clipping='auto',
+        train_micro_batch_size_per_gpu='auto',
+        zero_allow_untested_optimizer=True,
+        zero_force_ds_cpu_optimizer=False,
+        zero_optimization=dict(overlap_comm=True, stage=2)),
+    exclude_frozen_parameters=True,
+    gradient_accumulation_steps=16,
+    gradient_clipping=1,
+    sequence_parallel_size=1,
+    train_micro_batch_size_per_gpu=1,
+    type='xtuner.engine.DeepSpeedStrategy')
+tokenizer = dict(
+    padding_side='right',
+    pretrained_model_name_or_path=
+    '/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/models--google--gemma-2b-it/snapshots/060189a16d5d2713425599b533a9e8ece8f5cca6',
+    trust_remote_code=True,
+    type='transformers.AutoTokenizer.from_pretrained')
+train_cfg = dict(max_epochs=1, type='xtuner.engine.runner.TrainLoop')
+train_dataloader = dict(
+    batch_size=1,
+    collate_fn=dict(
+        type='xtuner.dataset.collate_fns.default_collate_fn',
+        use_varlen_attn=False),
+    dataset=dict(
+        dataset=dict(
+            data_files=
+            '/petrobr/parceirosbr/radiar/llama_test/ultracabrita3.json',
+            path='json',
+            type='datasets.load_dataset'),
+        dataset_map_fn='xtuner.dataset.map_fns.ultracabrita_map_fn',
+        max_length=2048,
+        pack_to_max_length=True,
+        remove_unused_columns=True,
+        shuffle_before_pack=True,
+        template_map_fn=dict(
+            template='xtuner.utils.PROMPT_TEMPLATE.gemma',
+            type='xtuner.dataset.map_fns.template_map_fn_factory'),
+        tokenizer=dict(
+            padding_side='right',
+            pretrained_model_name_or_path=
+            '/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/models--google--gemma-2b-it/snapshots/060189a16d5d2713425599b533a9e8ece8f5cca6',
+            trust_remote_code=True,
+            type='transformers.AutoTokenizer.from_pretrained'),
+        type='xtuner.dataset.process_hf_dataset',
+        use_varlen_attn=False),
+    num_workers=0,
+    sampler=dict(shuffle=True, type='mmengine.dataset.DefaultSampler'))
+use_varlen_attn = False
+visualizer = None
+warmup_ratio = 0.03
+weight_decay = 0
+work_dir = './work_dirs/gemma_2b_it_full_ultracabrita'