KamranUmer
/

Docker-command-llama-7b

Model card Files Files and versions Community

KamranUmer commited on Aug 6, 2024

Commit

a13d95c

verified ·

1 Parent(s): 43700a1

Upload 13 files

Browse files

Files changed (13) hide show

checkpoint-575/README.md +32 -0
checkpoint-575/adapter_config.json +21 -0
checkpoint-575/adapter_model.bin +3 -0
checkpoint-575/added_tokens.json +3 -0
checkpoint-575/optimizer.pt +3 -0
checkpoint-575/rng_state.pth +3 -0
checkpoint-575/scheduler.pt +3 -0
checkpoint-575/special_tokens_map.json +24 -0
checkpoint-575/tokenizer.json +0 -0
checkpoint-575/tokenizer.model +3 -0
checkpoint-575/tokenizer_config.json +32 -0
checkpoint-575/trainer_state.json +154 -0
checkpoint-575/training_args.bin +3 -0

checkpoint-575/README.md ADDED Viewed

	@@ -0,0 +1,32 @@

+---
+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
+- 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
+### Framework versions
+- PEFT 0.4.0
+- PEFT 0.4.0

checkpoint-575/adapter_config.json ADDED Viewed

	@@ -0,0 +1,21 @@

+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/llama-2-7b-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"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-575/adapter_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:af54c1bcda9a8c32922d1acf1184c7b939836a29307cca2a748381ad8d4d584b
+size 134264202

checkpoint-575/added_tokens.json ADDED Viewed

	@@ -0,0 +1,3 @@

+{
+  "<pad>": 32000
+}

checkpoint-575/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4f309693026017553e2d1835751865f662936359f195abe877b5cad6e203d9b3
+size 268515002

checkpoint-575/rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:644cbdc4fe449c46ac2b5eb8fac15b6725b24235cdf2ca52aec37d76a8592e98
+size 14244

checkpoint-575/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:281480f2fc14dfc29ae6d5376c87bebc1086a04957c458dc99ed429e3b6800a0
+size 1064

checkpoint-575/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,24 @@

+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-575/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-575/tokenizer.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-575/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,32 @@

+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-575/trainer_state.json ADDED Viewed

	@@ -0,0 +1,154 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9519867549668874,
+  "global_step": 575,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002,
+      "loss": 2.7914,
+      "step": 25
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0002,
+      "loss": 1.4679,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0002,
+      "loss": 1.5903,
+      "step": 75
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0002,
+      "loss": 1.1581,
+      "step": 100
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0002,
+      "loss": 1.296,
+      "step": 125
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0002,
+      "loss": 1.1129,
+      "step": 150
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0002,
+      "loss": 1.2062,
+      "step": 175
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0002,
+      "loss": 1.0971,
+      "step": 200
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0002,
+      "loss": 1.0956,
+      "step": 225
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0002,
+      "loss": 1.0916,
+      "step": 250
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0002,
+      "loss": 1.0732,
+      "step": 275
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0002,
+      "loss": 1.0739,
+      "step": 300
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0002,
+      "loss": 1.0146,
+      "step": 325
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002,
+      "loss": 0.9848,
+      "step": 350
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002,
+      "loss": 0.8995,
+      "step": 375
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002,
+      "loss": 0.9952,
+      "step": 400
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002,
+      "loss": 0.9132,
+      "step": 425
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002,
+      "loss": 0.9205,
+      "step": 450
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002,
+      "loss": 0.8912,
+      "step": 475
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0002,
+      "loss": 0.9571,
+      "step": 500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002,
+      "loss": 0.8457,
+      "step": 525
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002,
+      "loss": 0.9529,
+      "step": 550
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002,
+      "loss": 0.8344,
+      "step": 575
+    }
+  ],
+  "max_steps": 604,
+  "num_train_epochs": 1,
+  "total_flos": 1101476393287680.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-575/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:98738569d44dc592a52e1893d003288fe616abea0ab93e1d3f8c422a6f9b36f7
+size 4408