Upload 8 files

README.md

@@ -0,0 +1,20 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: True
+- load_in_4bit: False
+- 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: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+### Framework versions
+
+
+- PEFT 0.5.0

adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "/gpfsscratch/rech/cwa/umm59ig/llm/internlm-20b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a7f1718552d886c9b667180b76a8fce8832db0766fac86dc92d83409dffc14b
+size 157460365

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a06c9a87367052345336140a05909fee4d52ace15fa2f3f482b65856519109f3
+size 314857797

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09b72fde4030db787d3b51fe4509e1020d05bf3e7fa2333b6f38526f39b9815b
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a46eb73e18fb848663efbf0d3c4de58d38ae92b33b789d69d28f59ef030a6dc
+size 627

trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.02,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1e-05,
+      "loss": 2.1779,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "eval_loss": 2.1520326137542725,
+      "eval_runtime": 452.4776,
+      "eval_samples_per_second": 0.643,
+      "eval_steps_per_second": 0.643,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2e-05,
+      "loss": 2.1108,
+      "step": 20
+    },
+    {
+      "epoch": 0.02,
+      "eval_loss": 2.097604990005493,
+      "eval_runtime": 452.1046,
+      "eval_samples_per_second": 0.644,
+      "eval_steps_per_second": 0.644,
+      "step": 20
+    }
+  ],
+  "max_steps": 1000,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 1.541392224485376e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4b09ab17c5ad07a9b78bb18a0e3f1c4a32a6cfb150bd1d5c5546b8d67f405bc
+size 4027