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": "meta-llama/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": 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 sha256:5e4b54ad78a585050ccd204ccdbf1a5fc34e2594f2e3ddd8e5fe189188d74c78
+size 33600461

checkpoint-48/README.md

@@ -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-48/adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/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": 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-48/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e4b54ad78a585050ccd204ccdbf1a5fc34e2594f2e3ddd8e5fe189188d74c78
+size 33600461

checkpoint-48/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eb43e43f97805afac2fd55b89b4d9a0ad1c12f25a169433e5a8b5b8da5b3459
+size 67216581

checkpoint-48/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18f55f528bdf77873e47f9f7ebfea3b611ab91c7618f8ae2616e7abb68d1eed0
+size 14575

checkpoint-48/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:473be4db9f4fc1f3137bcd6f393f6bf53db57d0216bd83a5bf1d9a333d0ab3ca
+size 627

checkpoint-48/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
+  }
+}

checkpoint-48/tokenizer.model

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

checkpoint-48/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "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-48/trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.461538461538462,
+  "global_step": 48,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15,
+      "learning_rate": 5.454545454545454e-05,
+      "loss": 0.8622,
+      "step": 2
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00010909090909090908,
+      "loss": 0.8607,
+      "step": 4
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0001636363636363636,
+      "loss": 0.8091,
+      "step": 6
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00021818181818181816,
+      "loss": 0.738,
+      "step": 8
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0002727272727272727,
+      "loss": 0.6651,
+      "step": 10
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.0002967741935483871,
+      "loss": 0.5799,
+      "step": 12
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 0.00029032258064516127,
+      "loss": 0.4795,
+      "step": 14
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 0.00028387096774193545,
+      "loss": 0.4095,
+      "step": 16
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 0.0002774193548387096,
+      "loss": 0.2854,
+      "step": 18
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 0.00027096774193548386,
+      "loss": 0.2146,
+      "step": 20
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 0.00026451612903225804,
+      "loss": 0.176,
+      "step": 22
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 0.0002580645161290322,
+      "loss": 0.1498,
+      "step": 24
+    },
+    {
+      "epoch": 4.15,
+      "learning_rate": 0.00025161290322580645,
+      "loss": 0.1382,
+      "step": 26
+    },
+    {
+      "epoch": 4.31,
+      "learning_rate": 0.0002451612903225806,
+      "loss": 0.1273,
+      "step": 28
+    },
+    {
+      "epoch": 4.46,
+      "learning_rate": 0.0002387096774193548,
+      "loss": 0.1222,
+      "step": 30
+    },
+    {
+      "epoch": 5.15,
+      "learning_rate": 0.000232258064516129,
+      "loss": 0.1074,
+      "step": 32
+    },
+    {
+      "epoch": 5.31,
+      "learning_rate": 0.00022580645161290321,
+      "loss": 0.1078,
+      "step": 34
+    },
+    {
+      "epoch": 5.46,
+      "learning_rate": 0.0002193548387096774,
+      "loss": 0.1087,
+      "step": 36
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 0.0002129032258064516,
+      "loss": 0.0975,
+      "step": 38
+    },
+    {
+      "epoch": 6.31,
+      "learning_rate": 0.0002064516129032258,
+      "loss": 0.0958,
+      "step": 40
+    },
+    {
+      "epoch": 6.46,
+      "learning_rate": 0.00019999999999999998,
+      "loss": 0.0843,
+      "step": 42
+    },
+    {
+      "epoch": 7.15,
+      "learning_rate": 0.00019354838709677416,
+      "loss": 0.0783,
+      "step": 44
+    },
+    {
+      "epoch": 7.31,
+      "learning_rate": 0.00018709677419354837,
+      "loss": 0.0781,
+      "step": 46
+    },
+    {
+      "epoch": 7.46,
+      "learning_rate": 0.00018064516129032257,
+      "loss": 0.079,
+      "step": 48
+    }
+  ],
+  "max_steps": 104,
+  "num_train_epochs": 8,
+  "total_flos": 3984531891683328.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-48/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:945e493b64c7a168b12e4f0c5961f6be2ec1d5474c76963526ac2808e8fb4f23
+size 3963

runs/Aug21_22-02-39_a60da81ce041/events.out.tfevents.1692655360.a60da81ce041.3435.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:139f28246ae53033c9e27660a341c30bc6a84314c4a108f1699262652e6eb7cd
+size 8418

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 +1,33 @@
+{
+  "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
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:945e493b64c7a168b12e4f0c5961f6be2ec1d5474c76963526ac2808e8fb4f23
+size 3963

training_params.json

@@ -0,0 +1 @@
+{"model": "meta-llama/Llama-2-7b-chat-hf", "data_path": "/content/train", "project_name": "llama2-planner", "train_split": "train", "valid_split": null, "text_column": "text", "lr": 0.0003, "epochs": 8, "batch_size": 4, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.0, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": false, "block_size": -1, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "logging_steps": -1, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": false, "push_to_hub": true, "use_int8": false, "model_max_length": 1024, "repo_id": "johaanm/llama2-openassistant-studyplanner", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false}