Training in progress, step 300

adapter_config.json

@@ -3,7 +3,7 @@
   "base_model_name_or_path": "/workspace/webui/models/TheBloke_Llama-2-13B-fp16",
   "bias": "none",
   "fan_in_fan_out": null,
-  "inference_mode": false,
+  "inference_mode": true,
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
@@ -15,12 +15,12 @@
   "revision": null,
   "target_modules": [
     "v_proj",
-    "k_proj",
     "q_proj",
-    "down_proj",
     "up_proj",
     "gate_proj",
-    "o_proj"
+    "o_proj",
+    "k_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:270a3a4f5c73387541b23f7d1aef9c581af7a4c782995100b756d2d571ea381a
-size 290
+oid sha256:6361cf788eb2eecf574488f94018046acb7d636e2b8c01e3508587db412f3cd2
+size 500897101

checkpoint-300/README.md

@@ -0,0 +1,20 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- 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 0.5.0.dev0

checkpoint-300/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/webui/models/TheBloke_Llama-2-13B-fp16",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-300/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6361cf788eb2eecf574488f94018046acb7d636e2b8c01e3508587db412f3cd2
+size 500897101

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd2fe5fdce6d5e52a0f219229ef5e391d0a99183721768728e8618542924bce8
+size 1001752701

checkpoint-300/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f73e30dba1eba7a17e72336e01b55d9f45cc4bc93ae7772a5dd6d51e3eb71bc0
+size 27772

checkpoint-300/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:032ef3580361793ee9ae976197f72bd9d02821e12612fe786271ce9e4dcd88b5
+size 27772

checkpoint-300/rng_state_10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:366a4f691f1434c9d766f311626db4378598647acca195bc6d82610e0bad0cb7
+size 27789

checkpoint-300/rng_state_11.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8338173967d92a4366c887b8a90ea8dd942131116116d87e8664c05dc74c5b8
+size 27789

checkpoint-300/rng_state_12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cc877da8acd38bfe8a82ebad2bbdbbcb635a54553f3f0c69a81c306dd090b33
+size 27789

checkpoint-300/rng_state_13.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce8e16c1236a73d6d5a05b3abccc1b499017b6d4e023e6a3fb938ee4da8e12e6
+size 27789

checkpoint-300/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e538c7cbe0d4aa5816d8891148177e39eec3caba14d5d438714c5025dbb7b63
+size 27772

checkpoint-300/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49c89b7ec9b7d44c53d61af4eb045658960f0e49e18017e5b57efd1ede7c9dd3
+size 27772

checkpoint-300/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51d5c7202dac1a2747fe82418a615633cd49f78d8b50431a951d19cb06f5df1c
+size 27772

checkpoint-300/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c701298fb37793e83edaddc3029806245162b95a14c7e799b7d21c004ec3ad6
+size 27772

checkpoint-300/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50ae123c5d62d3799cc74217f729393187b853cdd0560d27d2237f7a7305463c
+size 27772

checkpoint-300/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:352860b2c59c403aebafef8048b27372066afd9fb8461941c15fc3b27039dee7
+size 27772

checkpoint-300/rng_state_8.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d43a150c0c1d9fae996e73e5aab606c75628ca1d714f5428c2efe9ab14b1d382
+size 27772

checkpoint-300/rng_state_9.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea39e6e01b60b67bbf2308b1fa8ffb4f498f576373d684099f9db2ad38980129
+size 27772

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b902cbfc5361903023808ab50ffb35c827f082341566e01dcf44743fa063659
+size 627

checkpoint-300/trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.11632415664986429,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001999867761371633,
+      "loss": 1.0435,
+      "step": 50
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019993306018843102,
+      "loss": 0.8918,
+      "step": 100
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019983804784290833,
+      "loss": 0.8874,
+      "step": 150
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00019970177836355307,
+      "loss": 0.8839,
+      "step": 200
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00019961818913082012,
+      "loss": 0.8801,
+      "step": 225
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019952430806244534,
+      "loss": 0.8753,
+      "step": 250
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019942014485754635,
+      "loss": 0.8754,
+      "step": 275
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00019930571027751713,
+      "loss": 0.8751,
+      "step": 300
+    }
+  ],
+  "max_steps": 7737,
+  "num_train_epochs": 3,
+  "total_flos": 1.290261776910254e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe6d7bbf6b8ed54bb30d4fb9291907ac865f24b396951fe9912d2874dc58e000
+size 4027

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7d8e6ca3ee52d610ea6af580762703958acb68894884ff8627b9a467240686f
+oid sha256:fe6d7bbf6b8ed54bb30d4fb9291907ac865f24b396951fe9912d2874dc58e000
 size 4027