my-awesome-model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,51 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- null
+model_index:
+- name: distilgpt2-finetuned-amazon-reviews
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+---
+
+<!-- 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-amazon-reviews
+
+This model was trained from scratch 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: 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
+
+### Framework versions
+
+- Transformers 4.8.2
+- Pytorch 1.9.0+cu102
+- Datasets 1.9.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "/content/test-clm/checkpoint-23500",
+  "_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,
+  "gradient_checkpointing": false,
+  "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,
+  "resid_pdrop": 0.1,
+  "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
+    }
+  },
+  "transformers_version": "4.8.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcc9c3d19788cc9b4c3929cc4b386999a55f01f13cd86d2de8536856b6cab5af
+size 333972957

runs/Jul21_08-20-09_fd3fa8d86bcc/1626855630.467104/events.out.tfevents.1626855630.fd3fa8d86bcc.63.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cbeec289bba025c0e6a8ae95e34e3d2ee2805476d9654ccc37cc132a23c047c
+size 4199

runs/Jul21_08-20-09_fd3fa8d86bcc/events.out.tfevents.1626855630.fd3fa8d86bcc.63.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d33026364b4a49457037539be0f9af78687e99a2e0d683577497058a2c2e571
+size 11858

runs/Jul21_08-20-09_fd3fa8d86bcc/events.out.tfevents.1626860941.fd3fa8d86bcc.63.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf11cc98d0c3554047350551a0a9a57f12d064350df664376d3f301f941a774c
+size 316

runs/Jul21_10-14-06_fd3fa8d86bcc/events.out.tfevents.1626862472.fd3fa8d86bcc.4845.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:930958136111653b98b971bb160e9333ff53a3d8c8cb4b5a907de15ac4de372f
+size 249

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72f613d3d7b56def3683c4b0fabf6f97a496b1ad34bc98ac6ec295790e60d8a9
+size 2671