Upload 10 files

README.md

@@ -1,3 +1,32 @@
 ---
-license: other
+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: float32
+
+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: float32
+### Framework versions
+
+- PEFT 0.5.0.dev0
+
+- PEFT 0.5.0.dev0

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:058654b9697de76a9a28d36ebbc073a633d05d800304a7088b801fbf0777dbfb
+size 33629701

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52e48d6589a1ef940fcdb8c4bed6264b954cf54f3b53a3a6b764d0111db52aec
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cde7e494f5100c7c96fe64af81c3f8dc21426b0d4d499392f18bae287c1d29e
+size 627

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "max_seq_length": 256,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,142 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 210.0,
+  "global_step": 210,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 10.0,
+      "learning_rate": 1.9989834093992945e-05,
+      "loss": 0.2542,
+      "step": 10
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 1.9809681293474693e-05,
+      "loss": 0.2436,
+      "step": 20
+    },
+    {
+      "epoch": 30.0,
+      "learning_rate": 1.9408298407861045e-05,
+      "loss": 0.2287,
+      "step": 30
+    },
+    {
+      "epoch": 40.0,
+      "learning_rate": 1.879473751206489e-05,
+      "loss": 0.2096,
+      "step": 40
+    },
+    {
+      "epoch": 50.0,
+      "learning_rate": 1.798283576604356e-05,
+      "loss": 0.1882,
+      "step": 50
+    },
+    {
+      "epoch": 60.0,
+      "learning_rate": 1.6990903356131125e-05,
+      "loss": 0.1687,
+      "step": 60
+    },
+    {
+      "epoch": 70.0,
+      "learning_rate": 1.5841310559698346e-05,
+      "loss": 0.1537,
+      "step": 70
+    },
+    {
+      "epoch": 80.0,
+      "learning_rate": 1.4559983245748639e-05,
+      "loss": 0.1427,
+      "step": 80
+    },
+    {
+      "epoch": 90.0,
+      "learning_rate": 1.3175818189031326e-05,
+      "loss": 0.1343,
+      "step": 90
+    },
+    {
+      "epoch": 100.0,
+      "learning_rate": 1.1720031383636585e-05,
+      "loss": 0.1261,
+      "step": 100
+    },
+    {
+      "epoch": 110.0,
+      "learning_rate": 1.0225454053046922e-05,
+      "loss": 0.12,
+      "step": 110
+    },
+    {
+      "epoch": 120.0,
+      "learning_rate": 8.72579223318095e-06,
+      "loss": 0.1166,
+      "step": 120
+    },
+    {
+      "epoch": 130.0,
+      "learning_rate": 7.254866626475152e-06,
+      "loss": 0.1139,
+      "step": 130
+    },
+    {
+      "epoch": 140.0,
+      "learning_rate": 5.845849869981137e-06,
+      "loss": 0.1116,
+      "step": 140
+    },
+    {
+      "epoch": 150.0,
+      "learning_rate": 4.530518418775734e-06,
+      "loss": 0.1096,
+      "step": 150
+    },
+    {
+      "epoch": 160.0,
+      "learning_rate": 3.338535916373267e-06,
+      "loss": 0.108,
+      "step": 160
+    },
+    {
+      "epoch": 170.0,
+      "learning_rate": 2.2967842137278706e-06,
+      "loss": 0.1068,
+      "step": 170
+    },
+    {
+      "epoch": 180.0,
+      "learning_rate": 1.4287571238320053e-06,
+      "loss": 0.1059,
+      "step": 180
+    },
+    {
+      "epoch": 190.0,
+      "learning_rate": 7.540305840905371e-07,
+      "loss": 0.1053,
+      "step": 190
+    },
+    {
+      "epoch": 200.0,
+      "learning_rate": 2.878211754847926e-07,
+      "loss": 0.105,
+      "step": 200
+    },
+    {
+      "epoch": 210.0,
+      "learning_rate": 4.0642954899238196e-08,
+      "loss": 0.1048,
+      "step": 210
+    }
+  ],
+  "max_steps": 216,
+  "num_train_epochs": 216,
+  "total_flos": 3.04771919929344e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f6ab0dc0f72aa7252750c6d13320a60e0043460b32921c830c78e71b66954a
+size 4027