End of training

README.md

@@ -0,0 +1,92 @@
+---
+base_model: gpt2
+library_name: Distily
+license: mit
+tags:
+- generated_from_trainer
+model-index:
+- name: distily_bench_obj_cross_v2.11_gpt2
+  results: []
+---
+
+# distily_bench_obj_cross_v2.11_gpt2
+
+This student model is distilled from the teacher model [gpt2](https://huggingface.co/gpt2) using the dataset (unspecified).
+
+The [Distily](https://github.com/lapp0/distily) library was used for this distillation.
+
+It achieves the following results on the evaluation set:
+- eval_enwikippl: 394.4440
+- eval_frwikippl: 376.8607
+- eval_zhwikippl: 132.9248
+- eval_tinystoriesppl: 879.5369
+- eval_loss: 0.6564
+- eval_runtime: 21.3247
+- eval_samples_per_second: 46.894
+- eval_steps_per_second: 11.724
+
+<!-- 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.
+
+## 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:
+- distillation_objective: DistillationObjective(logits_loss_component=LossComponent(label=logits, weight=1, loss_fn=kl, layer_mapper=None, projector=None), hs_loss_component=LossComponent(label=hs, weight=0, loss_fn=None, layer_mapper=None, projector=None), attn_loss_component=LossComponent(label=attn, weight=0, loss_fn=None, layer_mapper=None, projector=None))
+- train_embeddings: True
+- learning_rate: 4e-05
+- train_batch_size: 1
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1.0
+
+### Resource Usage
+Peak GPU Memory: 3.9285 GB
+
+### Eval-Phase Metrics
+| step | epoch | enwikippl | frwikippl | loss | runtime | samples_per_second | steps_per_second | tinystoriesppl | zhwikippl |
+| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
+| **teacher eval** |  | 270.2348 | 76.8142 |  |  |  |  | 671.1238 | 22.8030 |
+| 0 | 0 | 166859.125 | 3884651118592.0 | 20.7305 | 20.9672 | 47.694 | 11.923 | 78.9353 | 8900573134848.0 |
+| 5000 | 0.0505 | 713.4594 | 1011.3455 | 1.2903 | 20.9827 | 47.658 | 11.915 | 1238.3685 | 298.2239 |
+| 10000 | 0.1010 | 601.3743 | 730.4988 | 1.0969 | 21.3361 | 46.869 | 11.717 | 1104.3544 | 265.0505 |
+| 15000 | 0.1515 | 504.4594 | 600.9854 | 0.9815 | 21.1535 | 47.274 | 11.818 | 935.7164 | 249.6911 |
+| 20000 | 0.2020 | 546.4334 | 695.7017 | 0.9179 | 21.1018 | 47.389 | 11.847 | 1108.5160 | 222.1384 |
+| 25000 | 0.2525 | 435.9988 | 478.2172 | 0.7794 | 21.1029 | 47.387 | 11.847 | 909.0684 | 166.1946 |
+| 30000 | 0.3030 | 408.8560 | 428.7766 | 0.7228 | 21.311 | 46.924 | 11.731 | 866.9764 | 155.9177 |
+| 35000 | 0.3535 | 415.0065 | 423.1964 | 0.7142 | 21.3097 | 46.927 | 11.732 | 897.1238 | 147.4223 |
+| 40000 | 0.4040 | 417.0611 | 438.1946 | 0.7138 | 21.0917 | 47.412 | 11.853 | 902.5912 | 137.5701 |
+| 45000 | 0.4545 | 410.7367 | 423.2858 | 0.7031 | 21.1335 | 47.318 | 11.83 | 889.1501 | 144.9844 |
+| 50000 | 0.5051 | 409.4502 | 412.4997 | 0.6987 | 21.3483 | 46.842 | 11.711 | 892.8698 | 159.3132 |
+| 55000 | 0.5556 | 406.3222 | 416.2205 | 0.6960 | 21.3527 | 46.832 | 11.708 | 884.7875 | 141.1298 |
+| 60000 | 0.6061 | 404.2499 | 392.8503 | 0.6944 | 21.3318 | 46.878 | 11.72 | 879.3189 | 131.7685 |
+| 65000 | 0.6566 | 395.6986 | 379.7383 | 0.6676 | 21.3383 | 46.864 | 11.716 | 873.5950 | 134.9347 |
+| 70000 | 0.7071 | 394.2606 | 379.3372 | 0.6649 | 21.3522 | 46.834 | 11.708 | 872.5484 | 138.0020 |
+| 75000 | 0.7576 | 392.1590 | 377.4717 | 0.6629 | 21.3581 | 46.821 | 11.705 | 870.7470 | 126.5486 |
+| 80000 | 0.8081 | 394.0469 | 381.8300 | 0.6625 | 21.0719 | 47.457 | 11.864 | 876.5246 | 132.6237 |
+| 85000 | 0.8586 | 393.9400 | 373.6366 | 0.6581 | 21.2823 | 46.987 | 11.747 | 877.9388 | 132.0940 |
+| 90000 | 0.9091 | 395.3693 | 377.8174 | 0.6574 | 21.391 | 46.749 | 11.687 | 883.5812 | 134.0020 |
+| 95000 | 0.9596 | 394.5662 | 377.2059 | 0.6567 | 21.0529 | 47.499 | 11.875 | 880.1915 | 132.9958 |
+| 99000 | 1.0 | 394.4440 | 376.8607 | 0.6564 | 21.3247 | 46.894 | 11.724 | 879.5369 | 132.9248 |
+
+### Framework versions
+- Distily 0.2.0
+- Transformers 4.44.0
+- Pytorch 2.3.0
+- Datasets 2.21.0

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "gpt2",
+  "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,
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "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": "bfloat16",
+  "transformers_version": "4.44.0",
+  "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": "4.44.0"
+}

logs/dataset_subset=20231101.en, dataset_uri=wikimedia_wikipedia/events.out.tfevents.1724055571.f383272e719b

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7351a3073db9c85582cf772b34585603a4cd0ef375086fe9fcac8000f51ab242
+size 47487443

logs/dataset_subset=20231101.en, dataset_uri=wikimedia_wikipedia/events.out.tfevents.1724068324.f383272e719b

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71305889602628eb47afd6acfb819dc71643365dc37094d07a09b35dcc136172
+size 312

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:355dfb0af4ca0f00c55f33279db7ca97cbe98a3bdf12903bb00d1a8a66bb39a0
+size 248894656

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 +1,20 @@
+{
+  "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": true,
+  "eos_token": "<|endoftext|>",
+  "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 sha256:5ff2d2b2a5bff76eb930c12eaca6d7bd9a243fc1210782f3cbf0109477f344a7
+size 1017948104