Upload 14 files

README.md

@@ -0,0 +1,68 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- wikitext
+metrics:
+- accuracy
+model-index:
+- name: test-plm
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: wikitext wikitext-2-raw-v1
+      type: wikitext
+      args: wikitext-2-raw-v1
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.2304371642779472
+---
+
+<!-- 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. -->
+
+# test-plm
+
+This model is a fine-tuned version of [](https://huggingface.co/) on the wikitext wikitext-2-raw-v1 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.6030
+- Accuracy: 0.2304
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.42.0.dev0
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.2304371642779472,
+    "eval_loss": 5.603015422821045,
+    "eval_runtime": 359.2844,
+    "eval_samples": 2422,
+    "eval_samples_per_second": 6.741,
+    "eval_steps_per_second": 0.423,
+    "perplexity": 271.2430880864446,
+    "total_flos": 2.60103732553728e+16,
+    "train_loss": 5.880197445605802,
+    "train_runtime": 24831.4743,
+    "train_samples": 23431,
+    "train_samples_per_second": 2.831,
+    "train_steps_per_second": 0.177
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "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_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 48,
+  "n_positions": 102,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.2304371642779472,
+    "eval_loss": 5.603015422821045,
+    "eval_runtime": 359.2844,
+    "eval_samples": 2422,
+    "eval_samples_per_second": 6.741,
+    "eval_steps_per_second": 0.423,
+    "perplexity": 271.2430880864446
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.42.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49bd12f93bfe857e2eba635c6ad6d322b6874d52dc4425970703a846583960f8
+size 2624814304

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "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,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 2.60103732553728e+16,
+    "train_loss": 5.880197445605802,
+    "train_runtime": 24831.4743,
+    "train_samples": 23431,
+    "train_samples_per_second": 2.831,
+    "train_steps_per_second": 0.177
+}

trainer_state.json

@@ -0,0 +1,98 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 4395,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3412969283276451,
+      "grad_norm": 1.9755513668060303,
+      "learning_rate": 4.431171786120592e-05,
+      "loss": 7.0043,
+      "step": 500
+    },
+    {
+      "epoch": 0.6825938566552902,
+      "grad_norm": 2.0670814514160156,
+      "learning_rate": 3.862343572241183e-05,
+      "loss": 6.3637,
+      "step": 1000
+    },
+    {
+      "epoch": 1.023890784982935,
+      "grad_norm": 1.9433873891830444,
+      "learning_rate": 3.293515358361775e-05,
+      "loss": 6.1006,
+      "step": 1500
+    },
+    {
+      "epoch": 1.36518771331058,
+      "grad_norm": 2.0810210704803467,
+      "learning_rate": 2.7246871444823664e-05,
+      "loss": 5.8529,
+      "step": 2000
+    },
+    {
+      "epoch": 1.7064846416382253,
+      "grad_norm": 2.127770185470581,
+      "learning_rate": 2.1558589306029582e-05,
+      "loss": 5.7272,
+      "step": 2500
+    },
+    {
+      "epoch": 2.04778156996587,
+      "grad_norm": 2.3847897052764893,
+      "learning_rate": 1.5870307167235497e-05,
+      "loss": 5.5975,
+      "step": 3000
+    },
+    {
+      "epoch": 2.3890784982935154,
+      "grad_norm": 2.466097354888916,
+      "learning_rate": 1.0182025028441412e-05,
+      "loss": 5.4416,
+      "step": 3500
+    },
+    {
+      "epoch": 2.73037542662116,
+      "grad_norm": 2.4412147998809814,
+      "learning_rate": 4.493742889647327e-06,
+      "loss": 5.3805,
+      "step": 4000
+    },
+    {
+      "epoch": 3.0,
+      "step": 4395,
+      "total_flos": 2.60103732553728e+16,
+      "train_loss": 5.880197445605802,
+      "train_runtime": 24831.4743,
+      "train_samples_per_second": 2.831,
+      "train_steps_per_second": 0.177
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4395,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.60103732553728e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5259cd8ca30efb60912b86cc9ca7a8404f033aac6987e38fbe2f7f1b5cb7d40
+size 5112