Model save

last-checkpoint/README.md → README.md

@@ -4,6 +4,17 @@ 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: False
+- bnb_4bit_compute_dtype: float16
+
 The following `bitsandbytes` quantization config was used during training:
 - load_in_8bit: False
 - load_in_4bit: True
@@ -16,5 +27,6 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_compute_dtype: float16
 ### Framework versions
 
+- PEFT 0.4.0.dev0
 
 - PEFT 0.4.0.dev0

last-checkpoint/adapter_config.json

@@ -1,22 +0,0 @@
-{
-  "base_model_name_or_path": "togethercomputer/RedPajama-INCITE-Base-3B-v1",
-  "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": 64,
-  "revision": null,
-  "target_modules": [
-    "query_key_value",
-    "dense",
-    "dense_h_to_4h",
-    "dense_4h_to_h"
-  ],
-  "task_type": "CAUSAL_LM"
-}

last-checkpoint/adapter_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:18d9ad4f8dc933ad6e407f8768604fa8df673a51ff20e3fc2b2b72b58b96296c
-size 335638221

last-checkpoint/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c5645adc0e815427bee2525b551ef19301c3bd58feffe8f523abeea2acf1157d
-size 671246597

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f2a4a57d3543837f3d3fec93400bac8989273bbf35e51c30c34f8bfa85b258ee
-size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:216f76b8039f833c337db298c81f13b12082d5fd4f9d866cecd34b2ca7550b37
-size 627

last-checkpoint/special_tokens_map.json

@@ -1,6 +0,0 @@
-{
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
-  "pad_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
-}

last-checkpoint/tokenizer_config.json

@@ -1,9 +0,0 @@
-{
-  "add_prefix_space": false,
-  "bos_token": "<|endoftext|>",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
-  "model_max_length": 2048,
-  "tokenizer_class": "GPTNeoXTokenizer",
-  "unk_token": "<|endoftext|>"
-}

last-checkpoint/trainer_state.json

@@ -1,76 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.6498781478472786,
-  "global_step": 100,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.06,
-      "learning_rate": 0.0002,
-      "loss": 1.6209,
-      "step": 10
-    },
-    {
-      "epoch": 0.13,
-      "learning_rate": 0.0002,
-      "loss": 1.5431,
-      "step": 20
-    },
-    {
-      "epoch": 0.19,
-      "learning_rate": 0.0002,
-      "loss": 1.5206,
-      "step": 30
-    },
-    {
-      "epoch": 0.26,
-      "learning_rate": 0.0002,
-      "loss": 1.5347,
-      "step": 40
-    },
-    {
-      "epoch": 0.32,
-      "learning_rate": 0.0002,
-      "loss": 1.5357,
-      "step": 50
-    },
-    {
-      "epoch": 0.39,
-      "learning_rate": 0.0002,
-      "loss": 1.485,
-      "step": 60
-    },
-    {
-      "epoch": 0.45,
-      "learning_rate": 0.0002,
-      "loss": 1.4854,
-      "step": 70
-    },
-    {
-      "epoch": 0.52,
-      "learning_rate": 0.0002,
-      "loss": 1.5324,
-      "step": 80
-    },
-    {
-      "epoch": 0.58,
-      "learning_rate": 0.0002,
-      "loss": 1.4887,
-      "step": 90
-    },
-    {
-      "epoch": 0.65,
-      "learning_rate": 0.0002,
-      "loss": 1.5132,
-      "step": 100
-    }
-  ],
-  "max_steps": 100,
-  "num_train_epochs": 1,
-  "total_flos": 5.7895286734848e+16,
-  "trial_name": null,
-  "trial_params": null
-}

last-checkpoint/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a937e9698d9377e313f6374c2abd56957ca2182371fcd2fc70c7320f2a02f75a
-size 3963

runs/Jul04_00-42-28_06a0078a8833/events.out.tfevents.1688431447.06a0078a8833.315.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:234d3567338b4b818eea4a3bd8f27e320b5f47d2eccf3c8fa4319bb780be8fbc
-size 5965
+oid sha256:b8c1541b2c430463344f4374106318cf6177e954bf008dd11b70985c3df3a83e
+size 6313