End of training

README.md

@@ -0,0 +1,49 @@
+---
+license: apache-2.0
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+tags:
+- generated_from_trainer
+model-index:
+- name: tinyllama-mixpretrain-quinoa-sciphi
+  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. -->
+
+# tinyllama-mixpretrain-quinoa-sciphi
+
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) 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: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 15000
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43077882e23408e76ddb24f1e2f07f5b98eca8b3b411fcf18fd5436aafc0ad5b
+size 4400216536

runs/Apr21_22-22-53_5778b0f30e47/events.out.tfevents.1713738178.5778b0f30e47.1017.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:418925cb062a4a8665ecf98427d016cbb837163789cc9cc09a12bd1cffde93d9
+size 4184

runs/Apr21_22-24-38_5778b0f30e47/events.out.tfevents.1713738279.5778b0f30e47.2744.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0473e4a35749d0557eb5de213072549926e338ea23c3fb0e2983fa94f6dc1c0e
+size 4719

runs/Apr21_22-27-32_5778b0f30e47/events.out.tfevents.1713738454.5778b0f30e47.3646.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b7e7775679a23bd1fdf99b7a4e7ceea68b773c4cac20efe4add91f7bf91c629
+size 4719

runs/Apr21_22-31-23_5778b0f30e47/events.out.tfevents.1713738684.5778b0f30e47.4786.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:335fa37b6ea4243e686685ae3d949e5021ddb13f86a52d1ffdb285e70c9b3c46
+size 4719

runs/Apr21_22-34-28_5778b0f30e47/events.out.tfevents.1713738872.5778b0f30e47.4786.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3d7db1bdcc52bfa1b840990ee110c6784725ac276aa8fc63078ee057cbe8253
+size 4723

runs/Apr21_22-36-26_5778b0f30e47/events.out.tfevents.1713738988.5778b0f30e47.4786.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1119205579b65f443d90a34871dabe894c25fbb9f6693d723ee9c8878b3ba60
+size 4723

runs/Apr21_22-39-10_5778b0f30e47/events.out.tfevents.1713739151.5778b0f30e47.6539.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b924d1b5499c03616d3510f30868471c05d717934d3f4360ee2c34ef023c48ce
+size 11053

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 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "max_length": 400,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation": true,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:012b4e197281bc536a7807247021b0d6a8234b8cef14bf147b7a55b2b199a1aa
+size 4920