Spaces:

Vasudevakrishna
/

ERAV2_S29_QLora_Phi2

Sleeping

App Files Files Community

Vasudevakrishna commited on Sep 5

Commit

35e6e46

•

1 Parent(s): a8709ad

Upload 12 files

Browse files

Files changed (12) hide show

ckpts/adapter_config.json +31 -0
ckpts/added_tokens.json +40 -0
ckpts/merges.txt +0 -0
ckpts/rng_state.pth +3 -0
ckpts/scheduler.pt +3 -0
ckpts/special_tokens_map.json +24 -0
ckpts/tokenizer.json +0 -0
ckpts/tokenizer_config.json +324 -0
ckpts/trainer_state.json +321 -0
ckpts/training_args.bin +3 -0
ckpts/vocab.json +0 -0
requirements.txt +5 -0

ckpts/adapter_config.json ADDED Viewed

	@@ -0,0 +1,31 @@

+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/phi-2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "fc1",
+    "k_proj",
+    "q_proj",
+    "dense",
+    "fc2"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

ckpts/added_tokens.json ADDED Viewed

	@@ -0,0 +1,40 @@

+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

ckpts/merges.txt ADDED Viewed

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

ckpts/rng_state.pth ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:73e2bffa05c4cb4baf7fd6f4d9cfbd562add37f7c6e087471979c9283495ecc4
+size 14244

ckpts/scheduler.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:cb54cffa206db0c12f0795a9e4804d798628be7cb6d50b66106d7441bc5abccf
+size 1064

ckpts/special_tokens_map.json ADDED Viewed

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

+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

ckpts/tokenizer.json ADDED Viewed

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

ckpts/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,324 @@

+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}

ckpts/trainer_state.json ADDED Viewed

	@@ -0,0 +1,321 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0183299389002036,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0002,
+      "loss": 1.6531,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002,
+      "loss": 1.4496,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0002,
+      "loss": 1.5821,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0002,
+      "loss": 1.895,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0002,
+      "loss": 1.9526,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0002,
+      "loss": 1.4505,
+      "step": 60
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0002,
+      "loss": 1.4075,
+      "step": 70
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0002,
+      "loss": 1.472,
+      "step": 80
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0002,
+      "loss": 1.8758,
+      "step": 90
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0002,
+      "loss": 1.9509,
+      "step": 100
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0002,
+      "loss": 1.4616,
+      "step": 110
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0002,
+      "loss": 1.4365,
+      "step": 120
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0002,
+      "loss": 1.5214,
+      "step": 130
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0002,
+      "loss": 1.8216,
+      "step": 140
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0002,
+      "loss": 1.9155,
+      "step": 150
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0002,
+      "loss": 1.4898,
+      "step": 160
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0002,
+      "loss": 1.3915,
+      "step": 170
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0002,
+      "loss": 1.5799,
+      "step": 180
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0002,
+      "loss": 2.0476,
+      "step": 190
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0002,
+      "loss": 1.9179,
+      "step": 200
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0002,
+      "loss": 1.4597,
+      "step": 210
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0002,
+      "loss": 1.4114,
+      "step": 220
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0002,
+      "loss": 1.5009,
+      "step": 230
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0002,
+      "loss": 1.8596,
+      "step": 240
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002,
+      "loss": 1.851,
+      "step": 250
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002,
+      "loss": 1.3758,
+      "step": 260
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002,
+      "loss": 1.3879,
+      "step": 270
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002,
+      "loss": 1.6088,
+      "step": 280
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002,
+      "loss": 1.8558,
+      "step": 290
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002,
+      "loss": 1.8685,
+      "step": 300
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002,
+      "loss": 1.3584,
+      "step": 310
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002,
+      "loss": 1.3976,
+      "step": 320
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002,
+      "loss": 1.5402,
+      "step": 330
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002,
+      "loss": 1.8134,
+      "step": 340
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002,
+      "loss": 1.9623,
+      "step": 350
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002,
+      "loss": 1.3733,
+      "step": 360
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002,
+      "loss": 1.276,
+      "step": 370
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002,
+      "loss": 1.5179,
+      "step": 380
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002,
+      "loss": 1.7899,
+      "step": 390
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002,
+      "loss": 1.8778,
+      "step": 400
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0002,
+      "loss": 1.4008,
+      "step": 410
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0002,
+      "loss": 1.402,
+      "step": 420
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002,
+      "loss": 1.5183,
+      "step": 430
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002,
+      "loss": 1.8471,
+      "step": 440
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0002,
+      "loss": 1.9354,
+      "step": 450
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0002,
+      "loss": 1.4035,
+      "step": 460
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0002,
+      "loss": 1.4147,
+      "step": 470
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0002,
+      "loss": 1.639,
+      "step": 480
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0002,
+      "loss": 1.9683,
+      "step": 490
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0002,
+      "loss": 1.417,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "total_flos": 2.4365101134336e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

ckpts/training_args.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c863c36cb241938d428c573dd639bfd78c550ed3dfefbfd153533898634f7fc0
+size 4728

ckpts/vocab.json ADDED Viewed

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

requirements.txt ADDED Viewed

	@@ -0,0 +1,5 @@

+torch
+transformers
+accelerate
+einops
+git+https://github.com/huggingface/peft.git