Upload folder using huggingface_hub

README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- autotrain
+- text-generation
+widget:
+- text: "I love AutoTrain because "
+---
+
+# Model Trained Using AutoTrain

adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "abhishek/llama-2-7b-hf-small-shards",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80484d7543d0031a830cf2ef16c33f972a9b4e3795820ab5b28a0f893e67062b
+size 33600461

added_tokens.json

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

checkpoint-25/README.md

@@ -0,0 +1,34 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- 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:
+- quant_method: bitsandbytes
+- 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 0.5.0
+
+- PEFT 0.5.0

checkpoint-25/adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "abhishek/llama-2-7b-hf-small-shards",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-25/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80484d7543d0031a830cf2ef16c33f972a9b4e3795820ab5b28a0f893e67062b
+size 33600461

checkpoint-25/added_tokens.json

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

checkpoint-25/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6609ac9935e095b8fc25cb631bd46f71c7f8c463ad0b018132b5af3a6c501563
+size 67216581

checkpoint-25/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c152074a486243089e4fc0fdee0a373a30fb0e0a6e40eb5fd0d36fdafc97a155
+size 443

checkpoint-25/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f78b2b6bc2e190c408751ffc153ca07e496bfaba09930e1086e756faf090dc9
+size 14575

checkpoint-25/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaf2952b233ef35de02f5ceb6fae08c1f798cceee9407d480c1e2df9abdbc490
+size 627

checkpoint-25/special_tokens_map.json

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

checkpoint-25/tokenizer.model

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

checkpoint-25/tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1024,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-25/trainer_state.json

@@ -0,0 +1,169 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 25.0,
+  "eval_steps": 500,
+  "global_step": 25,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.3065,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.3065,
+      "step": 2
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0002,
+      "loss": 0.3028,
+      "step": 3
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.00019090909090909092,
+      "loss": 0.2954,
+      "step": 4
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.00018181818181818183,
+      "loss": 0.2837,
+      "step": 5
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.00017272727272727275,
+      "loss": 0.2706,
+      "step": 6
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 0.2563,
+      "step": 7
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 0.00015454545454545454,
+      "loss": 0.2414,
+      "step": 8
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 0.00014545454545454546,
+      "loss": 0.2256,
+      "step": 9
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.00013636363636363637,
+      "loss": 0.2083,
+      "step": 10
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.00012727272727272728,
+      "loss": 0.1919,
+      "step": 11
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 0.0001181818181818182,
+      "loss": 0.1825,
+      "step": 12
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 0.1766,
+      "step": 13
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 0.0001,
+      "loss": 0.1706,
+      "step": 14
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 9.090909090909092e-05,
+      "loss": 0.1648,
+      "step": 15
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 8.181818181818183e-05,
+      "loss": 0.1591,
+      "step": 16
+    },
+    {
+      "epoch": 17.0,
+      "learning_rate": 7.272727272727273e-05,
+      "loss": 0.1541,
+      "step": 17
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 6.363636363636364e-05,
+      "loss": 0.1492,
+      "step": 18
+    },
+    {
+      "epoch": 19.0,
+      "learning_rate": 5.4545454545454546e-05,
+      "loss": 0.1448,
+      "step": 19
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 4.545454545454546e-05,
+      "loss": 0.1407,
+      "step": 20
+    },
+    {
+      "epoch": 21.0,
+      "learning_rate": 3.6363636363636364e-05,
+      "loss": 0.1373,
+      "step": 21
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 2.7272727272727273e-05,
+      "loss": 0.1343,
+      "step": 22
+    },
+    {
+      "epoch": 23.0,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 0.1319,
+      "step": 23
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 0.13,
+      "step": 24
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 0.0,
+      "loss": 0.1287,
+      "step": 25
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 25,
+  "num_train_epochs": 25,
+  "save_steps": 500,
+  "total_flos": 4064708395008000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-25/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4318085b1f41232f17235447d953bcd8f2add2dddfd8f6b59191b77dd5481fe5
+size 4027

special_tokens_map.json

@@ -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": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "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 +1,46 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1024,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4318085b1f41232f17235447d953bcd8f2add2dddfd8f6b59191b77dd5481fe5
+size 4027