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 +1,20 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "togethercomputer/RedPajama-INCITE-Chat-3B-v1",
+  "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": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13688017bcbaddac27fb0b498cd7b6e481e83fdab276d4ecf0514a215964aa39
+size 20995057

checkpoint-990/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.dev0
+
+- PEFT 0.5.0.dev0

checkpoint-990/adapter_config.json

@@ -0,0 +1,20 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "togethercomputer/RedPajama-INCITE-Chat-3B-v1",
+  "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": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-990/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13688017bcbaddac27fb0b498cd7b6e481e83fdab276d4ecf0514a215964aa39
+size 20995057

checkpoint-990/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0d25faa78d73a51f2e2811a309b124ba2fd4318b33c6cc62eb6fc8e00447450
+size 41996805

checkpoint-990/pytorch_model.bin

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

checkpoint-990/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f00ba1a527102846393921a953806d7bce5790eec7cb2b217af3d3161ead7c9c
+size 14575

checkpoint-990/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ac4b706b327e10ff06a5dccc89af7bb73c4bfe4339f968b0211e041d85b8771
+size 627

checkpoint-990/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-990/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-990/trainer_state.json

@@ -0,0 +1,109 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 990,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 1.2414,
+      "step": 66
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0001925925925925926,
+      "loss": 1.0867,
+      "step": 132
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 0.9944,
+      "step": 198
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00016296296296296295,
+      "loss": 0.9678,
+      "step": 264
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00014814814814814815,
+      "loss": 0.97,
+      "step": 330
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.8915,
+      "step": 396
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00011851851851851852,
+      "loss": 0.8615,
+      "step": 462
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0001037037037037037,
+      "loss": 0.8546,
+      "step": 528
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 0.8432,
+      "step": 594
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 7.407407407407407e-05,
+      "loss": 0.8424,
+      "step": 660
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 5.925925925925926e-05,
+      "loss": 0.7897,
+      "step": 726
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.7621,
+      "step": 792
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 2.962962962962963e-05,
+      "loss": 0.7649,
+      "step": 858
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 1.4814814814814815e-05,
+      "loss": 0.7583,
+      "step": 924
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.7589,
+      "step": 990
+    }
+  ],
+  "logging_steps": 66,
+  "max_steps": 990,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 3.38996464975872e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-990/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c1a16bd11a5f4edef5b1360078ef5d5c715209b59b3dc7d9cddc6f55e13e89d
+size 4027

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "togethercomputer/RedPajama-INCITE-Chat-3B-v1",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 1.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.32.0.dev0",
+  "use_cache": true,
+  "use_parallel_residual": false,
+  "vocab_size": 50432
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.32.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbf68ea5ac501eea5b410117d44752ec603db5ca84ac0ff9aac13db8d3349599
+size 5551870277

runs/Aug12_09-46-35_8b7b12bbf1f3/events.out.tfevents.1691833596.8b7b12bbf1f3.3719.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a9f7713208f52949ee2d468012d7d9834064c9fdb949da153fa96df111b276a
+size 7274

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c1a16bd11a5f4edef5b1360078ef5d5c715209b59b3dc7d9cddc6f55e13e89d
+size 4027

training_params.json

@@ -0,0 +1,41 @@
+{
+    "model_name": "togethercomputer/RedPajama-INCITE-Chat-3B-v1",
+    "data_path": "tingkart/NorwayTrivia",
+    "train_split": "train",
+    "valid_split": null,
+    "text_column": "text",
+    "huggingface_token": null,
+    "learning_rate": 0.0002,
+    "num_train_epochs": 3,
+    "train_batch_size": 2,
+    "eval_batch_size": 4,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation_steps": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "add_eos_token": false,
+    "block_size": 2048,
+    "use_peft": true,
+    "lora_r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "training_type": "generic",
+    "train_on_inputs": false,
+    "logging_steps": -1,
+    "project_name": "RedNorway",
+    "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": 2048,
+    "repo_id": "tingkart/MLCNorway",
+    "use_int4": true,
+    "trainer": "sft",
+    "target_modules": null
+}