Training in progress, epoch 1, checkpoint

checkpoint-915/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-915/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "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_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-915/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42ce698dde7344b1ac125ca395bbb235093182b280f2b18a4cfbc59dc99753e9
+size 27354957

checkpoint-915/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c87476b3c7a3dfc5c0726ee0166314dd4eb7480aa986858cd8cd464fa076f19b
+size 27297032

checkpoint-915/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cee7f728265b413bb4a7fa8e6fca0a886a59fbd0a05534a161abace1dca98375
+size 54740293

checkpoint-915/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d13fc5ffc36bef005766528591e80914c61ac396f2d01de54f19d259496d333
+size 14575

checkpoint-915/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:797ab517854af5d0271612dd0d3f991cd2a975e012e034aa25db504c9b22c43d
+size 627

checkpoint-915/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-915/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-915/trainer_state.json

@@ -0,0 +1,33 @@
+{
+  "best_metric": NaN,
+  "best_model_checkpoint": "./Mistral/07-12-23-mistralai-Mistral-7B-v0.1_multilang-dataset-3.0.3-portuguese-2_epochs-1_batch_2/checkpoints/checkpoint-915",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 915,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002026719920227699,
+      "loss": 267.2109,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": NaN,
+      "eval_runtime": 393.8494,
+      "eval_samples_per_second": 8.257,
+      "eval_steps_per_second": 0.518,
+      "step": 915
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 915,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 6.206687759435366e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-915/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8be2683609287dd8e6db197c4b0ae992b704980dafb7a8e2594371a18b4d109c
+size 4411