End of training

README.md

@@ -0,0 +1,59 @@
+---
+license: apache-2.0
+base_model: distilgpt2
+tags:
+- generated_from_trainer
+model-index:
+- name: distilgpt2-finetuned-prompts
+  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. -->
+
+# distilgpt2-finetuned-prompts
+
+This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.6516
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 13   | 4.9266          |
+| No log        | 2.0   | 26   | 4.7161          |
+| No log        | 3.0   | 39   | 4.6516          |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "distilgpt2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "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": "4.40.1",
+  "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": "4.40.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f816bd2302e52cfcfce9d2ffc42ae60e1a3d7c651383106e1dc183748ca06d1
+size 327657928

runs/May05_13-47-22_033ea2c12d5b/events.out.tfevents.1714916842.033ea2c12d5b.376.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:866109149b429b5dcbb99318cdd189d68dbdad6843d4c78c86003c91cf940b2d
+size 6192

runs/May05_13-47-22_033ea2c12d5b/events.out.tfevents.1714917333.033ea2c12d5b.376.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2f5004e4c4f55b4596d311ccc9f829ff54836238b31d78d9c66965409c2bf4c
+size 354

runs/May05_14-20-38_033ea2c12d5b/events.out.tfevents.1714918941.033ea2c12d5b.376.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebca7e0113699499b8307e7280397b28f5605f2876fb312c97445984b2c06966
+size 5046

runs/May05_14-22-46_033ea2c12d5b/events.out.tfevents.1714918972.033ea2c12d5b.376.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f59d2ae4a1b2585beeadde8c1d2c5cd2c4c859fec1cb6ab257487678a4aa244d
+size 5046

runs/May05_14-22-46_033ea2c12d5b/events.out.tfevents.1714918991.033ea2c12d5b.376.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55b86fe5f16be7253e0d8e06ff77f0c2528eabb9829641e67fb89e67649ddd49
+size 10004

runs/May05_14-22-46_033ea2c12d5b/events.out.tfevents.1714919022.033ea2c12d5b.376.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f512202abd31124c8cfba832a051695d92d53a91c6aa6907ceb6da6397f40103
+size 5046

runs/May05_15-21-19_033ea2c12d5b/events.out.tfevents.1714922494.033ea2c12d5b.376.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03684ecc165fbb5017034d4a6547b09f957689f9853a9978b97c9aa70c0fd56c
+size 5046

runs/May05_15-21-19_033ea2c12d5b/events.out.tfevents.1714922505.033ea2c12d5b.376.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d641024d26d5438370f5c8582c7158924db8f583e9f78da0aef3c034045389b8
+size 5046

runs/May05_15-21-19_033ea2c12d5b/events.out.tfevents.1714922538.033ea2c12d5b.376.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4642623552e551fb5cacf6c0dc1398e07a63376b3ad448f903663d833f6ce05b
+size 5046

runs/May05_15-21-19_033ea2c12d5b/events.out.tfevents.1714922610.033ea2c12d5b.376.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ebaecba8a4895c3517185c5ce8a2bfc236548f5b74b3a493c9872710466bf06
+size 5046

runs/May05_15-21-19_033ea2c12d5b/events.out.tfevents.1714922649.033ea2c12d5b.376.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a9ac18094b10ad18f925015adce84b25d33aa04ffdfa5daa7061695b4623d5
+size 5046

runs/May05_16-07-58_033ea2c12d5b/events.out.tfevents.1714925279.033ea2c12d5b.376.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:316106230144e3810ab69015e6d968df7790b7bdbc9863ea0f73647072176634
+size 5046

runs/May05_16-48-08_033ea2c12d5b/events.out.tfevents.1714927689.033ea2c12d5b.44629.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:145105f3051d1e971a6d9be1408cfab7ae5ee93711d2655653389db0d741205d
+size 6192

runs/May05_16-48-08_033ea2c12d5b/events.out.tfevents.1714928271.033ea2c12d5b.44629.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:171c6f96e2ee444a0eb9d28afd82901f93965195ff07ad75560ca3a3aa43e025
+size 354

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 sha256:1ddda7451cbac1043a2791683993a9de67b9cbe5e8801b782bee4a05122ce0a4
+size 4984