anllmendpoint

README.md

@@ -0,0 +1,58 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- /apdcephfs/share_733425/vinnylywang/jianhuipang/datasets/RedPajama-Data-1T-Sample
+model-index:
+- name: allm-juhao-7b
+  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. -->
+
+# allm-juhao-7b
+
+This model is a fine-tuned version of [/apdcephfs/share_733425/vinnylywang/jianhuipang/opensourcellms/llama2/Llama-2-7b-hf](https://huggingface.co//apdcephfs/share_733425/vinnylywang/jianhuipang/opensourcellms/llama2/Llama-2-7b-hf) on the /apdcephfs/share_733425/vinnylywang/jianhuipang/datasets/RedPajama-Data-1T-Sample 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: 2e-05
+- train_batch_size: 2
+- eval_batch_size: 1
+- seed: 34
+- distributed_type: multi-GPU
+- num_devices: 32
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 512
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant_with_warmup
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.28.0.dev0
+- Pytorch 1.13.1+cu117
+- Datasets 2.14.6
+- Tokenizers 0.13.3

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.9985291261100875,
+    "train_runtime": 103339.7122,
+    "train_samples": 930514,
+    "train_samples_per_second": 9.004,
+    "train_steps_per_second": 0.018
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/apdcephfs/share_733425/vinnylywang/jianhuipang/opensourcellms/llama2/Llama-2-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.28.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e57ff11f3c5a350f305014f832520422b80fee7064a69f5402a1acf40ad16dd7
+size 13476958625

runs/Jan26_23-10-15_ts-cbba87c5e7504a249f5127103d9ce40f-launcher/1706281937.3461273/events.out.tfevents.1706281937.ts-cbba87c5e7504a249f5127103d9ce40f-launcher.69166.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df90933f568c28a34929feb02f01120e1f2e777562dfe58c165e5ed868a28670
+size 6008

runs/Jan26_23-10-15_ts-cbba87c5e7504a249f5127103d9ce40f-launcher/events.out.tfevents.1706281937.ts-cbba87c5e7504a249f5127103d9ce40f-launcher.69166.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:706f4d8429b6b7a662ca86c5b892924c89001bd16aea5e266a3a3d64c626bbbf
+size 289434

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "<unk>"
+}

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": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "special_tokens_map_file": "/apdcephfs/share_733425/vinnylywang/jianhuipang/opensourcellms/llama2/Llama-2-7b-hf/special_tokens_map.json",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.9985291261100875,
+    "train_runtime": 103339.7122,
+    "train_samples": 930514,
+    "train_samples_per_second": 9.004,
+    "train_steps_per_second": 0.018
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37fcc47c594104b4a35b61c38e83f6e0730b9f13cc65aaa3f9fafbdf5735aba8
+size 4795