Training in progress, epoch 9, checkpoint

checkpoint-220/README.md

@@ -0,0 +1,34 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+### Framework versions
+
+- PEFT 0.4.0
+
+- PEFT 0.4.0

checkpoint-220/adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_projo_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-220/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd29a4b2b3a913b2623bc8d6a8e38afee8a2d72dfa64058f27beb0a7ec340cd1
+size 13677261

checkpoint-220/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f0fbb7e702fa1b6e9d1ba9ea02bf44f795b6f7b0e2d067a4bf8529a0b4ddbaa
+size 13648432

checkpoint-220/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59d4ee295daa59d9e5c28cc338f347f276ea85126f5bb3f23d7024514258c098
+size 27370181

checkpoint-220/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4366dc18102a760490439498f95a6e02a44393c126751dd5cf68e81835aa9e13
+size 14575

checkpoint-220/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20eb4de2d8e272d1f6ce785c6c0eb33de7dcc5b4787f4f08e815234e7e6fe6ac
+size 627

checkpoint-220/special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

checkpoint-220/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-220/trainer_state.json

@@ -0,0 +1,99 @@
+{
+  "best_metric": 1.0401246547698975,
+  "best_model_checkpoint": "./Mistral/04-12-23-mistralai-Mistral-7B-v0.1_teste-multilang-dataset-3.0.3-portuguese-2_epochs-10_batch_2/checkpoints/checkpoint-67",
+  "epoch": 9.777777777777779,
+  "eval_steps": 500,
+  "global_step": 220,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.98,
+      "eval_loss": 1.666649580001831,
+      "eval_runtime": 0.5837,
+      "eval_samples_per_second": 17.132,
+      "eval_steps_per_second": 3.426,
+      "step": 22
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.125360131263733,
+      "eval_runtime": 0.5844,
+      "eval_samples_per_second": 17.112,
+      "eval_steps_per_second": 3.422,
+      "step": 45
+    },
+    {
+      "epoch": 2.98,
+      "eval_loss": 1.0401246547698975,
+      "eval_runtime": 0.5839,
+      "eval_samples_per_second": 17.127,
+      "eval_steps_per_second": 3.425,
+      "step": 67
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.064213514328003,
+      "eval_runtime": 0.5866,
+      "eval_samples_per_second": 17.049,
+      "eval_steps_per_second": 3.41,
+      "step": 90
+    },
+    {
+      "epoch": 4.98,
+      "eval_loss": 1.0575947761535645,
+      "eval_runtime": 0.5832,
+      "eval_samples_per_second": 17.146,
+      "eval_steps_per_second": 3.429,
+      "step": 112
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.145155906677246,
+      "eval_runtime": 0.5836,
+      "eval_samples_per_second": 17.136,
+      "eval_steps_per_second": 3.427,
+      "step": 135
+    },
+    {
+      "epoch": 6.98,
+      "eval_loss": 1.1963560581207275,
+      "eval_runtime": 0.5826,
+      "eval_samples_per_second": 17.165,
+      "eval_steps_per_second": 3.433,
+      "step": 157
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.2468668222427368,
+      "eval_runtime": 0.5861,
+      "eval_samples_per_second": 17.061,
+      "eval_steps_per_second": 3.412,
+      "step": 180
+    },
+    {
+      "epoch": 8.98,
+      "eval_loss": 1.319059133529663,
+      "eval_runtime": 0.5831,
+      "eval_samples_per_second": 17.15,
+      "eval_steps_per_second": 3.43,
+      "step": 202
+    },
+    {
+      "epoch": 9.78,
+      "eval_loss": 1.31288743019104,
+      "eval_runtime": 0.5859,
+      "eval_samples_per_second": 17.069,
+      "eval_steps_per_second": 3.414,
+      "step": 220
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 220,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.2265876796522496e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-220/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79a18da895b74ce34bf1ff540f6210d20d6f96a6588878f580fbe1198c0fd6a5
+size 4411