Dataset=togethercomputer/RedPajama-Data-1T/github, baseline=True, samples=1000000, bs=8, epochs=3, lr=5e-05

.gitattributes

@@ -33,3 +33,19 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+instgpu-03_1795787.1745668705867758477.pt.trace.json filter=lfs diff=lfs merge=lfs -text
+instgpu-03_1795788.1745668705859014422.pt.trace.json filter=lfs diff=lfs merge=lfs -text
+instgpu-03_1795789.1745668705809938858.pt.trace.json filter=lfs diff=lfs merge=lfs -text
+instgpu-03_1795790.1745668705899264751.pt.trace.json filter=lfs diff=lfs merge=lfs -text
+instgpu-03_1795792.1745668705868155997.pt.trace.json filter=lfs diff=lfs merge=lfs -text
+instgpu-03_1795793.1745668705930905711.pt.trace.json filter=lfs diff=lfs merge=lfs -text
+instgpu-03_1795794.1745668705835796238.pt.trace.json filter=lfs diff=lfs merge=lfs -text
+instgpu-03_1795795.1745668705867679151.pt.trace.json filter=lfs diff=lfs merge=lfs -text
+instgpu-03_2132717.1745696507191483577.pt.trace.json filter=lfs diff=lfs merge=lfs -text
+instgpu-03_2132718.1745696507103473353.pt.trace.json filter=lfs diff=lfs merge=lfs -text
+instgpu-03_2132719.1745696507148687858.pt.trace.json filter=lfs diff=lfs merge=lfs -text
+instgpu-03_2132722.1745696507099390806.pt.trace.json filter=lfs diff=lfs merge=lfs -text
+instgpu-03_2132724.1745696507041367537.pt.trace.json filter=lfs diff=lfs merge=lfs -text
+instgpu-03_2132725.1745696507040881320.pt.trace.json filter=lfs diff=lfs merge=lfs -text
+instgpu-03_2132727.1745696507099575603.pt.trace.json filter=lfs diff=lfs merge=lfs -text
+instgpu-03_2132729.1745696507157804959.pt.trace.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,65 @@
+---
+library_name: transformers
+license: mit
+base_model: gpt2
+tags:
+- generated_from_trainer
+model-index:
+- name: gpt2-finetune-github-baseline-1M
+  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. -->
+
+# gpt2-finetune-github-baseline-1M
+
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1483
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 64
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 1.2864        | 1.0   | 15469 | 1.2212          |
+| 1.2255        | 2.0   | 30938 | 1.1654          |
+| 1.1992        | 3.0   | 46407 | 1.1483          |
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.51.3"
+}

instgpu-03_1795787.1745668705867758477.pt.trace.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec10a027d6445115b1ce362c4930deaaed2ccefa27d9d318654e26ef7acd3779
+size 48970530

instgpu-03_1795788.1745668705859014422.pt.trace.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d6fc2790a7b9186981ad60c991081c423a7ce647017cbb5ef8f43780362e9a4
+size 48054724

instgpu-03_1795789.1745668705809938858.pt.trace.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86f1177884267aa4c0146fe8c25fea9cb6aba57c06b1b10ce1316e2fd5be6982
+size 48054214

instgpu-03_1795790.1745668705899264751.pt.trace.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6abe366b52eb16145eb5e0ebb97fe6886c8ee0b0e7dabc30c86e3ab987af9a5b
+size 48076136

instgpu-03_1795792.1745668705868155997.pt.trace.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3fea377b4305d0753f210e725a446c5f5fa077e53228c574511ec19d7d818f3
+size 48078212

instgpu-03_1795793.1745668705930905711.pt.trace.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77dcf8c30e52e5551675f2e51470f14046d273f2cabc0b11fece221eb1298e63
+size 48074209

instgpu-03_1795794.1745668705835796238.pt.trace.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d3a723422891518be1559ff362b509a81f06c9bfc0bd90c867251c31c69f6f9
+size 48057771

instgpu-03_1795795.1745668705867679151.pt.trace.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecbe35ef9bfed7585251a44246415c7a5e44a9b77879a67e5635450082070081
+size 48054530

instgpu-03_2132717.1745696507191483577.pt.trace.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02b5ac40734cd692cc1bfe4cbc52b02c78e0a91e88def1e0b1e7ca31f57e697f
+size 49001272

instgpu-03_2132718.1745696507103473353.pt.trace.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7a25b8a337ff99a64e28ac193aedb8921e128a7016085da3d2a565d18c7ae47
+size 48060326

instgpu-03_2132719.1745696507148687858.pt.trace.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecb6000a66da6d0b3c2a9d3de4ca02c1f61fb04721b7f60b643ce49ab4786673
+size 48060324

instgpu-03_2132722.1745696507099390806.pt.trace.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42927b18d2fd95b50fb94ff137f302cbd247d0cd67c8943bae51a7b6e26fe7f2
+size 48060338

instgpu-03_2132724.1745696507041367537.pt.trace.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70a33f2a5bb0f33c7f6077ef3459d97fb64885508a1a87787c567d6b35697887
+size 48061506

instgpu-03_2132725.1745696507040881320.pt.trace.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a1d52f05c3dc81f311e447f7fb101a4987322db0bfcd9ed20cf2245ef4613bc
+size 48060331

instgpu-03_2132727.1745696507099575603.pt.trace.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7c710d810adf044db626a8799e399bd6ebdcb98a28b89ddea7e9ad8d8aa389c
+size 48057320

instgpu-03_2132729.1745696507157804959.pt.trace.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ef523006ec5258674bba131742f6b9997c063eff5a97352ba95679fb2c53df3
+size 48056995

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c2b5dd7a8451101a76db3087b7432c0573ad81eae9ebe65917ef967539a82f3
+size 497774208

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 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a75619dc0ab47532e3996d11238ee8734264754572881d8ec32209ed7b081a0
+size 5304