Update model files for opt-clean_plus_vocab_error_5pct_42_1e-3

README.md

@@ -0,0 +1,68 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: opt-clean_plus_vocab_error_5pct_42_1e-3
+  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. -->
+
+# opt-clean_plus_vocab_error_5pct_42_1e-3
+
+This model is a fine-tuned version of [/work/10368/siyuansong/vista/models/opt-clean_plus_vocab_error_5pct_42_1e-3/config.json](https://huggingface.co//work/10368/siyuansong/vista/models/opt-clean_plus_vocab_error_5pct_42_1e-3/config.json) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.8294
+
+## 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: 0.001
+- train_batch_size: 256
+- eval_batch_size: 256
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 2048
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 32000
+- num_epochs: 10.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 275  | 7.0274          |
+| No log        | 2.0   | 550  | 5.5115          |
+| No log        | 3.0   | 825  | 4.9736          |
+| 6.3514        | 4.0   | 1100 | 4.6719          |
+| 6.3514        | 5.0   | 1375 | 4.4466          |
+| 6.3514        | 6.0   | 1650 | 4.2720          |
+| 6.3514        | 7.0   | 1925 | 4.1349          |
+| 4.412         | 8.0   | 2200 | 4.0182          |
+| 4.412         | 9.0   | 2475 | 3.9183          |
+| 4.412         | 10.0  | 2750 | 3.8294          |
+
+
+### Framework versions
+
+- Transformers 4.54.0.dev0
+- Pytorch 2.5.1
+- Datasets 3.6.0
+- Tokenizers 0.21.1

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 3.8293724060058594,
+    "eval_runtime": 34.6492,
+    "eval_samples": 51863,
+    "eval_samples_per_second": 1496.804,
+    "eval_steps_per_second": 5.859,
+    "perplexity": 46.03363873138957,
+    "total_flos": 7.3446054690816e+17,
+    "train_loss": 5.0002771661931815,
+    "train_runtime": 7255.6111,
+    "train_samples": 562202,
+    "train_samples_per_second": 774.851,
+    "train_steps_per_second": 0.379
+}

checkpoint-2750/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": 256,
+  "model_type": "opt",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.54.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 768
+}

checkpoint-2750/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.54.0.dev0"
+}

checkpoint-2750/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b04bbfa272f980c013a0ca7981fac98d92f4da955dc4e81ec324e6855f7e814
+size 495474576

checkpoint-2750/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2a971228d107c104b2f6e6e5e51467b297009d675b2fc95cbdeeb90181e82bf
+size 991068282

checkpoint-2750/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9247a194c71f55d9ede0f665de670353dd25080204b436f37fe30dd21125712f
+size 14244

checkpoint-2750/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08b9c372fdb30aa9fd7737efa312093ea1a7af015f4dc57fd0cfe5eede2887ff
+size 1064

checkpoint-2750/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2750/tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "</s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}

checkpoint-2750/trainer_state.json

@@ -0,0 +1,137 @@
+{
+  "best_global_step": 2750,
+  "best_metric": 3.8293724060058594,
+  "best_model_checkpoint": "/work/10368/siyuansong/vista/models/opt-clean_plus_vocab_error_5pct_42_1e-3/checkpoint-2750",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 2750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 7.02741813659668,
+      "eval_runtime": 34.4123,
+      "eval_samples_per_second": 1507.106,
+      "eval_steps_per_second": 5.899,
+      "step": 275
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 5.511542320251465,
+      "eval_runtime": 34.6866,
+      "eval_samples_per_second": 1495.186,
+      "eval_steps_per_second": 5.852,
+      "step": 550
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 4.973597049713135,
+      "eval_runtime": 34.6026,
+      "eval_samples_per_second": 1498.818,
+      "eval_steps_per_second": 5.867,
+      "step": 825
+    },
+    {
+      "epoch": 3.6375227686703098,
+      "grad_norm": 0.28458723425865173,
+      "learning_rate": 3.121875e-05,
+      "loss": 6.3514,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 4.6719231605529785,
+      "eval_runtime": 34.7122,
+      "eval_samples_per_second": 1494.084,
+      "eval_steps_per_second": 5.848,
+      "step": 1100
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 4.446601867675781,
+      "eval_runtime": 34.7852,
+      "eval_samples_per_second": 1490.95,
+      "eval_steps_per_second": 5.836,
+      "step": 1375
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 4.2719502449035645,
+      "eval_runtime": 34.6807,
+      "eval_samples_per_second": 1495.443,
+      "eval_steps_per_second": 5.853,
+      "step": 1650
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 4.134940147399902,
+      "eval_runtime": 34.5514,
+      "eval_samples_per_second": 1501.039,
+      "eval_steps_per_second": 5.875,
+      "step": 1925
+    },
+    {
+      "epoch": 7.273224043715847,
+      "grad_norm": 0.487853467464447,
+      "learning_rate": 6.246875000000001e-05,
+      "loss": 4.412,
+      "step": 2000
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 4.018152713775635,
+      "eval_runtime": 34.6739,
+      "eval_samples_per_second": 1495.736,
+      "eval_steps_per_second": 5.855,
+      "step": 2200
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 3.918316602706909,
+      "eval_runtime": 34.8253,
+      "eval_samples_per_second": 1489.235,
+      "eval_steps_per_second": 5.829,
+      "step": 2475
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 3.8293724060058594,
+      "eval_runtime": 34.673,
+      "eval_samples_per_second": 1495.776,
+      "eval_steps_per_second": 5.855,
+      "step": 2750
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 2750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.3446054690816e+17,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2750/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d3b6d7f2bacdede2a33434f43fed9e65c4b618c17029b375d85b3300870faab
+size 5496

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": 256,
+  "model_type": "opt",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.54.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 768
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 3.8293724060058594,
+    "eval_runtime": 34.6492,
+    "eval_samples": 51863,
+    "eval_samples_per_second": 1496.804,
+    "eval_steps_per_second": 5.859,
+    "perplexity": 46.03363873138957
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.54.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b04bbfa272f980c013a0ca7981fac98d92f4da955dc4e81ec324e6855f7e814
+size 495474576

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "</s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 7.3446054690816e+17,
+    "train_loss": 5.0002771661931815,
+    "train_runtime": 7255.6111,
+    "train_samples": 562202,
+    "train_samples_per_second": 774.851,
+    "train_steps_per_second": 0.379
+}

trainer_state.json

@@ -0,0 +1,146 @@
+{
+  "best_global_step": 2750,
+  "best_metric": 3.8293724060058594,
+  "best_model_checkpoint": "/work/10368/siyuansong/vista/models/opt-clean_plus_vocab_error_5pct_42_1e-3/checkpoint-2750",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 2750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 7.02741813659668,
+      "eval_runtime": 34.4123,
+      "eval_samples_per_second": 1507.106,
+      "eval_steps_per_second": 5.899,
+      "step": 275
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 5.511542320251465,
+      "eval_runtime": 34.6866,
+      "eval_samples_per_second": 1495.186,
+      "eval_steps_per_second": 5.852,
+      "step": 550
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 4.973597049713135,
+      "eval_runtime": 34.6026,
+      "eval_samples_per_second": 1498.818,
+      "eval_steps_per_second": 5.867,
+      "step": 825
+    },
+    {
+      "epoch": 3.6375227686703098,
+      "grad_norm": 0.28458723425865173,
+      "learning_rate": 3.121875e-05,
+      "loss": 6.3514,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 4.6719231605529785,
+      "eval_runtime": 34.7122,
+      "eval_samples_per_second": 1494.084,
+      "eval_steps_per_second": 5.848,
+      "step": 1100
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 4.446601867675781,
+      "eval_runtime": 34.7852,
+      "eval_samples_per_second": 1490.95,
+      "eval_steps_per_second": 5.836,
+      "step": 1375
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 4.2719502449035645,
+      "eval_runtime": 34.6807,
+      "eval_samples_per_second": 1495.443,
+      "eval_steps_per_second": 5.853,
+      "step": 1650
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 4.134940147399902,
+      "eval_runtime": 34.5514,
+      "eval_samples_per_second": 1501.039,
+      "eval_steps_per_second": 5.875,
+      "step": 1925
+    },
+    {
+      "epoch": 7.273224043715847,
+      "grad_norm": 0.487853467464447,
+      "learning_rate": 6.246875000000001e-05,
+      "loss": 4.412,
+      "step": 2000
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 4.018152713775635,
+      "eval_runtime": 34.6739,
+      "eval_samples_per_second": 1495.736,
+      "eval_steps_per_second": 5.855,
+      "step": 2200
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 3.918316602706909,
+      "eval_runtime": 34.8253,
+      "eval_samples_per_second": 1489.235,
+      "eval_steps_per_second": 5.829,
+      "step": 2475
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 3.8293724060058594,
+      "eval_runtime": 34.673,
+      "eval_samples_per_second": 1495.776,
+      "eval_steps_per_second": 5.855,
+      "step": 2750
+    },
+    {
+      "epoch": 10.0,
+      "step": 2750,
+      "total_flos": 7.3446054690816e+17,
+      "train_loss": 5.0002771661931815,
+      "train_runtime": 7255.6111,
+      "train_samples_per_second": 774.851,
+      "train_steps_per_second": 0.379
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 2750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.3446054690816e+17,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d3b6d7f2bacdede2a33434f43fed9e65c4b618c17029b375d85b3300870faab
+size 5496