Upload 15 files

README.md

@@ -1,3 +1,9 @@
 ---
-license: mit
+library_name: peft
 ---
+## Training procedure
+
+### Framework versions
+
+
+- PEFT 0.5.0.dev0

adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/model_files/Llama-2-13b-chat-hf",
+  "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": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65200ffedf2c54ff6f3df2cdb478eeb0f38fdbfa7a346501ec268464c1443a77
+size 896698765

checkpoint/README.md

@@ -0,0 +1,9 @@
+---
+library_name: peft
+---
+## Training procedure
+
+### Framework versions
+
+
+- PEFT 0.5.0.dev0

checkpoint/adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/model_files/Llama-2-13b-chat-hf",
+  "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": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fe4f15042e8380157df26e07bb23edfae9179841be3d353ec9512a85ea99f2e
+size 896705485

checkpoint/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06e2e60c4b71aaf6185263e80b6991fc4969e74fb021b52c61202bfad602be70
+size 14575

checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
+size 627

checkpoint/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint/tokenizer.model

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

checkpoint/tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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,
+  "model_max_length": 1024,
+  "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
+  }
+}

checkpoint/trainer_state.json

@@ -0,0 +1,166 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.8475750577367207,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0002,
+      "loss": 1.0758,
+      "step": 20
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0002,
+      "loss": 1.0262,
+      "step": 40
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0002,
+      "loss": 0.972,
+      "step": 60
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0002,
+      "loss": 0.2251,
+      "step": 80
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0002,
+      "loss": 0.144,
+      "step": 100
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0002,
+      "loss": 0.1766,
+      "step": 120
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0002,
+      "loss": 0.1494,
+      "step": 140
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002,
+      "loss": 0.1483,
+      "step": 160
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002,
+      "loss": 0.1188,
+      "step": 180
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002,
+      "loss": 0.0918,
+      "step": 200
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002,
+      "loss": 0.1356,
+      "step": 220
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002,
+      "loss": 0.0969,
+      "step": 240
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0002,
+      "loss": 0.1145,
+      "step": 260
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0002,
+      "loss": 0.1058,
+      "step": 280
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0002,
+      "loss": 0.0827,
+      "step": 300
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0002,
+      "loss": 0.0537,
+      "step": 320
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0002,
+      "loss": 0.0969,
+      "step": 340
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002,
+      "loss": 0.06,
+      "step": 360
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0002,
+      "loss": 0.0777,
+      "step": 380
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.0002,
+      "loss": 0.071,
+      "step": 400
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.0002,
+      "loss": 0.0487,
+      "step": 420
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.0002,
+      "loss": 0.0871,
+      "step": 440
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.0002,
+      "loss": 0.0577,
+      "step": 460
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.0002,
+      "loss": 0.073,
+      "step": 480
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.0002,
+      "loss": 0.0658,
+      "step": 500
+    }
+  ],
+  "max_steps": 500,
+  "num_train_epochs": 2,
+  "total_flos": 5.366331835972915e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de4f03311647eb822301b74cadc887adbfe8c16d0643ce3f98f232ff4d220308
+size 4283

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.8475750577367207,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0002,
+      "loss": 1.0758,
+      "step": 20
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0002,
+      "loss": 1.0262,
+      "step": 40
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0002,
+      "loss": 0.972,
+      "step": 60
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0002,
+      "loss": 0.2251,
+      "step": 80
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0002,
+      "loss": 0.144,
+      "step": 100
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0002,
+      "loss": 0.1766,
+      "step": 120
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0002,
+      "loss": 0.1494,
+      "step": 140
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002,
+      "loss": 0.1483,
+      "step": 160
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002,
+      "loss": 0.1188,
+      "step": 180
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002,
+      "loss": 0.0918,
+      "step": 200
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002,
+      "loss": 0.1356,
+      "step": 220
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002,
+      "loss": 0.0969,
+      "step": 240
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0002,
+      "loss": 0.1145,
+      "step": 260
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0002,
+      "loss": 0.1058,
+      "step": 280
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0002,
+      "loss": 0.0827,
+      "step": 300
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0002,
+      "loss": 0.0537,
+      "step": 320
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0002,
+      "loss": 0.0969,
+      "step": 340
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002,
+      "loss": 0.06,
+      "step": 360
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0002,
+      "loss": 0.0777,
+      "step": 380
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.0002,
+      "loss": 0.071,
+      "step": 400
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.0002,
+      "loss": 0.0487,
+      "step": 420
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.0002,
+      "loss": 0.0871,
+      "step": 440
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.0002,
+      "loss": 0.0577,
+      "step": 460
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.0002,
+      "loss": 0.073,
+      "step": 480
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.0002,
+      "loss": 0.0658,
+      "step": 500
+    },
+    {
+      "epoch": 1.85,
+      "step": 500,
+      "total_flos": 5.366331835972915e+17,
+      "train_loss": 0.2142012220621109,
+      "train_runtime": 37295.4093,
+      "train_samples_per_second": 0.429,
+      "train_steps_per_second": 0.013
+    }
+  ],
+  "max_steps": 500,
+  "num_train_epochs": 2,
+  "total_flos": 5.366331835972915e+17,
+  "trial_name": null,
+  "trial_params": null
+}