Upload folder using huggingface_hub

README.md

@@ -0,0 +1,15 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+### Framework versions
+
+
+- PEFT 0.5.0.dev0

adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "/tmp/model",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "c_proj",
+    "c_attn",
+    "q_attn"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b228d055c781906585629b5ea0304641fd3323d035c7faada1eb6a03a2afdd88
+size 142298829

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "/tmp/model",
+  "activation_function": "gelu",
+  "architectures": [
+    "GPTBigCodeForCausalLM"
+  ],
+  "attention_softmax_in_fp32": true,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "inference_runner": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_batch_size": null,
+  "max_sequence_length": null,
+  "model_type": "gpt_bigcode",
+  "multi_query": true,
+  "n_embd": 6144,
+  "n_head": 48,
+  "n_inner": 24576,
+  "n_layer": 40,
+  "n_positions": 8192,
+  "pad_key_length": true,
+  "pre_allocate_kv_cache": false,
+  "quantization_config": {
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_8bit": true
+  },
+  "resid_pdrop": 0.1,
+  "scale_attention_softmax_in_fp32": true,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "validate_runner_input": true,
+  "vocab_size": 49152
+}

my_data.json

@@ -0,0 +1 @@
+{"finetuned_from": "/tmp/model", "tasks": "language-modeling", "dataset": "/tmp", "tags": ["language-modeling", "nlp"]}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:839ea7dd2124f1301588025fbf29900eeec3e4be34c5f6dabe0c938c82b51f8c
+size 284568453

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c152074a486243089e4fc0fdee0a373a30fb0e0a6e40eb5fd0d36fdafc97a155
+size 443

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ca4c1d8dcf16ca8cef509702d9f0ff30851fb7b69e07d11c3004b20e16f9f7a
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e01603029631eb6dca3506f525e23c61280dd09e656d56b627cb98b8334c78d
+size 627

trainer_state.json

@@ -0,0 +1,30 @@
+{
+  "best_metric": 1.6104975938796997,
+  "best_model_checkpoint": "./outputdir/checkpoint-10",
+  "epoch": 1.0,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 1.6036,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.6104975938796997,
+      "eval_runtime": 2007.0049,
+      "eval_samples_per_second": 1.466,
+      "eval_steps_per_second": 1.466,
+      "step": 10
+    }
+  ],
+  "max_steps": 10,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.988576972000461e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c79ae3b5552ec7081ff5bdc30db051c0d206d5916db498cd68787ee48c4f10
+size 3643