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_v2.10_gpt2
+  results: []
+---
+
+# distily_bench_obj_cross_v2.10_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: 3656.4097
+- eval_frwikippl: 998935.5
+- eval_zhwikippl: 3651930.25
+- eval_tinystoriesppl: 853.0071
+- eval_loss: 4.7666
+- eval_runtime: 21.3363
+- eval_samples_per_second: 46.868
+- eval_steps_per_second: 11.717
+
+<!-- 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: 1e-06
+- 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 | 154372.75 | 3250976718848.0 | 19.5745 | 21.9663 | 45.524 | 11.381 | 81.0696 | 3865309085696.0 |
+| 5000 | 0.0505 | 3591.7734 | 994582.8125 | 4.7672 | 21.3712 | 46.792 | 11.698 | 830.4290 | 3622816.25 |
+| 10000 | 0.1010 | 3615.9900 | 994303.0 | 4.7657 | 21.1745 | 47.227 | 11.807 | 836.8727 | 3641715.75 |
+| 15000 | 0.1515 | 3671.0986 | 1001083.1875 | 4.7665 | 21.6571 | 46.174 | 11.544 | 857.9221 | 3659244.25 |
+| 20000 | 0.2020 | 3636.2166 | 997810.125 | 4.7657 | 21.4908 | 46.532 | 11.633 | 844.9362 | 3650955.25 |
+| 25000 | 0.2525 | 3617.9526 | 996265.0 | 4.7661 | 21.7815 | 45.91 | 11.478 | 837.2188 | 3639771.25 |
+| 30000 | 0.3030 | 3649.9016 | 997669.25 | 4.7663 | 21.6219 | 46.249 | 11.562 | 851.5274 | 3646090.75 |
+| 35000 | 0.3535 | 3636.2166 | 998372.625 | 4.7663 | 21.533 | 46.44 | 11.61 | 845.2155 | 3649983.75 |
+| 40000 | 0.4040 | 3632.8369 | 998090.875 | 4.7660 | 21.5429 | 46.419 | 11.605 | 843.6451 | 3651930.25 |
+| 45000 | 0.4545 | 3662.2236 | 1001083.1875 | 4.7662 | 21.5033 | 46.505 | 11.626 | 855.9031 | 3661199.0 |
+| 50000 | 0.5051 | 3627.9138 | 997810.125 | 4.7659 | 21.4372 | 46.648 | 11.662 | 841.2076 | 3650955.25 |
+| 55000 | 0.5556 | 3650.6084 | 999075.5625 | 4.7662 | 21.5382 | 46.429 | 11.607 | 850.9644 | 3649983.75 |
+| 60000 | 0.6061 | 3654.9941 | 999216.5625 | 4.7663 | 21.743 | 45.992 | 11.498 | 852.0205 | 3650955.25 |
+| 65000 | 0.6566 | 3649.6199 | 998090.875 | 4.7664 | 21.5302 | 46.446 | 11.612 | 851.1754 | 3649009.25 |
+| 70000 | 0.7071 | 3655.5625 | 998935.5 | 4.7663 | 21.6494 | 46.191 | 11.548 | 852.5842 | 3650955.25 |
+| 75000 | 0.7576 | 3652.7292 | 999497.75 | 4.7662 | 21.745 | 45.988 | 11.497 | 851.7739 | 3649009.25 |
+| 80000 | 0.8081 | 3649.6199 | 998231.75 | 4.7664 | 21.5478 | 46.408 | 11.602 | 851.4572 | 3649983.75 |
+| 85000 | 0.8586 | 3654.9941 | 998794.5 | 4.7664 | 21.5285 | 46.45 | 11.613 | 852.6545 | 3649983.75 |
+| 90000 | 0.9091 | 3658.1118 | 998653.5625 | 4.7664 | 21.5544 | 46.394 | 11.599 | 853.7831 | 3650955.25 |
+| 95000 | 0.9596 | 3656.9780 | 999497.75 | 4.7665 | 21.3927 | 46.745 | 11.686 | 852.7249 | 3649983.75 |
+| 99000 | 1.0 | 3656.4097 | 998935.5 | 4.7666 | 21.3363 | 46.868 | 11.717 | 853.0071 | 3651930.25 |
+
+### 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/copy_teacher_modules=_(_lm_head___False)_, learning_rate=1e-06/events.out.tfevents.1724002808.f383272e719b

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c328bec7f436291cb3341ce9615799ee3ca8fb15be07bef7025959f7e26e459
+size 47487444

logs/copy_teacher_modules=_(_lm_head___False)_, learning_rate=1e-06/events.out.tfevents.1724015863.f383272e719b

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fee9aef1816db0e345b2fb28efc48d0483b84b328136b9fa60b288cc05e26f1
+size 312

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:495690bfdde71bc4fa36f492dbc10fd62ab49ae01713fb9f12631d9ec6c306ee
+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 sha256:51317648eb2f70883b36ab9e8113552dd6ccb30aa1d69e9133b30415cf59d23a
+size 1017948104