Training in progress, step 10

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "base_model_name_or_path": "togethercomputer/RedPajama-INCITE-Base-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": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "revision": null,
+  "target_modules": [
+    "query_key_value",
+    "dense",
+    "dense_h_to_4h",
+    "dense_4h_to_h"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f9fdad47d831159049684336083c0959ad0769e1278456377d6a519230c688f
+size 335638221

last-checkpoint/README.md

@@ -0,0 +1,20 @@
+---
+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
+### Framework versions
+
+
+- PEFT 0.4.0.dev0

last-checkpoint/adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "base_model_name_or_path": "togethercomputer/RedPajama-INCITE-Base-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": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "revision": null,
+  "target_modules": [
+    "query_key_value",
+    "dense",
+    "dense_h_to_4h",
+    "dense_4h_to_h"
+  ],
+  "task_type": "CAUSAL_LM"
+}

last-checkpoint/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f9fdad47d831159049684336083c0959ad0769e1278456377d6a519230c688f
+size 335638221

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:471ff8ffda2727cd8dff75626f97329a9ddbf6cbbdb143e72a0c1165d0a01d52
+size 671246597

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16c8c162e6f27064fc9661a648fe866cd136a47e7fd324e4d23ff985d4b29dbd
+size 14575

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d4cad567fbb4a2962025a51cca0295bf91ab918ffa32bd96189257f7a457427
+size 627

last-checkpoint/special_tokens_map.json

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

last-checkpoint/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|>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,22 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.06498781478472786,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0002,
+      "loss": 1.6209,
+      "step": 10
+    }
+  ],
+  "max_steps": 100,
+  "num_train_epochs": 1,
+  "total_flos": 5789528673484800.0,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a937e9698d9377e313f6374c2abd56957ca2182371fcd2fc70c7320f2a02f75a
+size 3963

runs/Jul04_00-42-28_06a0078a8833/events.out.tfevents.1688431447.06a0078a8833.315.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccc2a94dc4a9a814cf2f60709cf62bbab3d01fd33ffd18112aee4571190a169e
+size 4579

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_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:a937e9698d9377e313f6374c2abd56957ca2182371fcd2fc70c7320f2a02f75a
+size 3963