Training in progress, step 500

README.md

@@ -0,0 +1,69 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- wikitext
+metrics:
+- accuracy
+model-index:
+- name: test_pretrain
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: wikitext wikitext-2-v1
+      type: wikitext
+      args: wikitext-2-v1
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.28011557471332055
+---
+
+<!-- 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_pretrain
+
+This model is a fine-tuned version of [](https://huggingface.co/) on the wikitext wikitext-2-v1 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.0612
+- Accuracy: 0.2801
+
+## 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: 4
+- 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
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.37.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.28011557471332055,
+    "eval_loss": 5.061196804046631,
+    "eval_runtime": 16.9445,
+    "eval_samples": 249,
+    "eval_samples_per_second": 14.695,
+    "eval_steps_per_second": 1.889,
+    "perplexity": 157.77923419764554,
+    "train_loss": 5.833661626916525,
+    "train_runtime": 1259.5482,
+    "train_samples": 2346,
+    "train_samples_per_second": 5.588,
+    "train_steps_per_second": 1.398
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_remove_final_layer_norm": false,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 3072,
+  "hidden_size": 768,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 768
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.28011557471332055,
+    "eval_loss": 5.061196804046631,
+    "eval_runtime": 16.9445,
+    "eval_samples": 249,
+    "eval_samples_per_second": 14.695,
+    "eval_steps_per_second": 1.889,
+    "perplexity": 157.77923419764554
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.37.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:123e2468f32e41c988079bbddb9498d70f05f2923b803a528af1268907af8756
+size 500979600

runs/Jan16_12-14-01_0048b83c9bcc/events.out.tfevents.1705407250.0048b83c9bcc.6626.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bba1d17b4945892e9a48476eabe96419c7f502520f2270289cc6e8882ab32bf
+size 4374

runs/Jan16_12-16-45_0048b83c9bcc/events.out.tfevents.1705407414.0048b83c9bcc.7361.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:194c96f09026ef6458fbbfed747a0625abb0940e72ba093a5a5959ab8cdf9f6d
+size 4383

runs/Jan16_12-19-24_0048b83c9bcc/events.out.tfevents.1705407574.0048b83c9bcc.8085.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bb7861555220dc618b8582668c1dff0deb47aa694e82398c6fc31a168c92452
+size 5208

runs/Jan16_12-19-24_0048b83c9bcc/events.out.tfevents.1705408904.0048b83c9bcc.8085.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdccfc534e36e0ef05618e84cfb2030fcda248989d02f6fb1ae9ed49b5dc571d
+size 411

runs/Jan16_13-08-13_0048b83c9bcc/events.out.tfevents.1705410502.0048b83c9bcc.20471.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3329ad656997119ea93fb833895bf5a6edcbb0b3c812805cd4b76e66496367a
+size 4291

runs/Jan16_13-13-03_0048b83c9bcc/events.out.tfevents.1705410793.0048b83c9bcc.21728.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08d6817be3228b52320a4838a850965b5391424f4048efa4b12579896173b391
+size 4450

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 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 5.833661626916525,
+    "train_runtime": 1259.5482,
+    "train_samples": 2346,
+    "train_samples_per_second": 5.588,
+    "train_steps_per_second": 1.398
+}

trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1761,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.580352072685974e-05,
+      "loss": 6.4049,
+      "step": 500
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 2.160704145371948e-05,
+      "loss": 5.7387,
+      "step": 1000
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.410562180579217e-06,
+      "loss": 5.5475,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "step": 1761,
+      "total_flos": 3677946642432000.0,
+      "train_loss": 5.833661626916525,
+      "train_runtime": 1259.5482,
+      "train_samples_per_second": 5.588,
+      "train_steps_per_second": 1.398
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1761,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 3677946642432000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d31abb3889a7d1fe0d33f662ab8e5a693765d499037e0128d37c03d5b1b422d9
+size 4728