Training in progress, step 155

README.md

@@ -0,0 +1,59 @@
+---
+base_model: ahxt/LiteLlama-460M-1T
+library_name: peft
+license: mit
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: YaHaHamaraLlama
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# YaHaHamaraLlama
+
+This model is a fine-tuned version of [ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T) on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 5
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.43.3
+- Pytorch 2.3.1+cu121
+- Datasets 2.17.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ahxt/LiteLlama-460M-1T",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "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",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8334fa9ce17038b2414505a8ab1b8bee86712df9f453e5b1bfbab728eb30131b
+size 19673632

runs/Aug01_10-47-52_fastgpuserv/events.out.tfevents.1722491274.fastgpuserv.2113260.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea32443cb43711c1a8f3b9a7c6fbfc180424cf50862b663ddfcd0468dd88a28
+size 5752

runs/Aug01_10-51-09_fastgpuserv/events.out.tfevents.1722491470.fastgpuserv.2113260.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89db4b1d7228307280aa3594178c3b17922ad3e04d1b2446a8e2ec2aebc66615
+size 5753

runs/Aug01_10-55-04_fastgpuserv/events.out.tfevents.1722491706.fastgpuserv.2113260.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:034df33b3f1320467f8fc105405fffe445e701405a84ac31a39ad367bebcad98
+size 5752

runs/Aug01_11-01-02_fastgpuserv/events.out.tfevents.1722492064.fastgpuserv.2134733.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6f63a830d193f53344febcc33dfa34ab61f00285032e3878af71b493ddde937
+size 5753

runs/Aug01_11-02-42_fastgpuserv/events.out.tfevents.1722492163.fastgpuserv.2134733.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cb01cadc06f59c43c9f071f8a399a5ffb04867d74ead76ccb43c6ca702eb777
+size 12697

runs/Aug01_14-05-55_fastgpuserv/events.out.tfevents.1722503158.fastgpuserv.6531.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:210ecb64a0f7832fb67fe3c9c5b4bb675f3820b2fc78ab7939d5fbbe5c6f8617
+size 4184

runs/Aug01_14-08-57_fastgpuserv/events.out.tfevents.1722503340.fastgpuserv.7077.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fca9054c067e0196ed042b95af7a47122046e9703ad44707d016c515df877980
+size 11399

runs/Aug02_12-33-35_fastgpuserv/events.out.tfevents.1722584019.fastgpuserv.3614347.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0c6f10b29f06bafa4219869f62edd74ac2ee0c026ba695487291d5d021d45dc
+size 5788

runs/Aug02_12-40-23_fastgpuserv/events.out.tfevents.1722584427.fastgpuserv.3637409.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04572ddc12c1592d208edd2336f0e79faa38698d2d3ec790a37da0bcc55790fe
+size 4184

runs/Aug02_12-42-43_fastgpuserv/events.out.tfevents.1722584567.fastgpuserv.3645427.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:942580e7674d76e0a7a957d2920080d65193d6d201bbe5cf2368600e63ea844c
+size 5788

runs/Aug02_12-44-23_fastgpuserv/events.out.tfevents.1722584667.fastgpuserv.3650795.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fba86a4d41e64ccaa9035bfab269568d501df25402abc25104a4b7b802172548
+size 5788

runs/Aug02_12-45-52_fastgpuserv/events.out.tfevents.1722584756.fastgpuserv.3655138.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fb7f2f39d539a2cb3a8ebc962b81040f5f9c2098322a1dc910de94df9d8247d
+size 5788

runs/Aug02_13-00-24_fastgpuserv/events.out.tfevents.1722585628.fastgpuserv.3689700.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:962181f37b84fc09c9d5d465d9486947537ccde5d8879b3c9b91829ebab08902
+size 5792

runs/Aug02_13-04-57_fastgpuserv/events.out.tfevents.1722585901.fastgpuserv.3707066.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f318aa9816b7523059bab4101afe1254434b1b360e65c8eb0d93983ee8ccc4d
+size 4184

runs/Aug02_13-07-01_fastgpuserv/events.out.tfevents.1722586024.fastgpuserv.3714303.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:864b30d31ce12cc86b57b1490237f41dea7afc8cca93868f9902572831cdebef
+size 8992

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "#",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "#",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "\"",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "#",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "#",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": "#",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ceed348154901b64c76c4a1a0fe0fb40b29f54262b4ec481742fde7f5ad76db
+size 5432