Update model files for opt-random_error_10pct_42_1e-3

README.md

@@ -0,0 +1,68 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: opt-random_error_10pct_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-random_error_10pct_42_1e-3
+
+This model is a fine-tuned version of [/work/10368/siyuansong/vista/models/opt-random_error_10pct_42_1e-3/config.json](https://huggingface.co//work/10368/siyuansong/vista/models/opt-random_error_10pct_42_1e-3/config.json) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.8656
+
+## 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   | 264  | 7.1199          |
+| No log        | 2.0   | 528  | 5.5849          |
+| No log        | 3.0   | 792  | 5.0255          |
+| 6.3758        | 4.0   | 1056 | 4.7238          |
+| 6.3758        | 5.0   | 1320 | 4.4931          |
+| 6.3758        | 6.0   | 1584 | 4.3182          |
+| 6.3758        | 7.0   | 1848 | 4.1768          |
+| 4.4398        | 8.0   | 2112 | 4.0604          |
+| 4.4398        | 9.0   | 2376 | 3.9612          |
+| 4.4398        | 10.0  | 2640 | 3.8656          |
+
+
+### Framework versions
+
+- Transformers 4.54.0.dev0
+- Pytorch 2.5.1
+- Datasets 3.6.0
+- Tokenizers 0.21.1

checkpoint-2640/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-2640/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-2640/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cc5bff4d3c608b8e3ac3a434bfbe3fe1fcb80772df38d8484ab99208c64f02e
+size 495474576

checkpoint-2640/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4180684efa2c9d14da8cdb7093bb13012adb45b4a3bba202dcf27a741b3c69fd
+size 991068282

checkpoint-2640/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d22b29b9a1c48eec92a4ddadf402b8b1093f37d516edfbd6b0c178a5d99cb2c
+size 14244

checkpoint-2640/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11fe02b90ebb5353c571f0f23fb64763dc8de5ee62320c0575f0a7d7c6e0028a
+size 1064

checkpoint-2640/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-2640/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-2640/trainer_state.json

@@ -0,0 +1,137 @@
+{
+  "best_global_step": 2640,
+  "best_metric": 3.865570068359375,
+  "best_model_checkpoint": "/work/10368/siyuansong/vista/models/opt-random_error_10pct_42_1e-3/checkpoint-2640",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 2640,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 7.119865894317627,
+      "eval_runtime": 35.1493,
+      "eval_samples_per_second": 1475.506,
+      "eval_steps_per_second": 5.775,
+      "step": 264
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 5.5848894119262695,
+      "eval_runtime": 35.3324,
+      "eval_samples_per_second": 1467.859,
+      "eval_steps_per_second": 5.745,
+      "step": 528
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 5.025453090667725,
+      "eval_runtime": 35.5046,
+      "eval_samples_per_second": 1460.74,
+      "eval_steps_per_second": 5.718,
+      "step": 792
+    },
+    {
+      "epoch": 3.7901234567901234,
+      "grad_norm": 0.36077043414115906,
+      "learning_rate": 3.121875e-05,
+      "loss": 6.3758,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 4.723816394805908,
+      "eval_runtime": 35.3979,
+      "eval_samples_per_second": 1465.145,
+      "eval_steps_per_second": 5.735,
+      "step": 1056
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 4.493129253387451,
+      "eval_runtime": 35.4762,
+      "eval_samples_per_second": 1461.912,
+      "eval_steps_per_second": 5.722,
+      "step": 1320
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 4.318204879760742,
+      "eval_runtime": 35.5592,
+      "eval_samples_per_second": 1458.497,
+      "eval_steps_per_second": 5.709,
+      "step": 1584
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 4.176829814910889,
+      "eval_runtime": 35.4134,
+      "eval_samples_per_second": 1464.5,
+      "eval_steps_per_second": 5.732,
+      "step": 1848
+    },
+    {
+      "epoch": 7.577397910731244,
+      "grad_norm": 0.5245909690856934,
+      "learning_rate": 6.246875000000001e-05,
+      "loss": 4.4398,
+      "step": 2000
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 4.060357570648193,
+      "eval_runtime": 35.4265,
+      "eval_samples_per_second": 1463.959,
+      "eval_steps_per_second": 5.73,
+      "step": 2112
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 3.961210012435913,
+      "eval_runtime": 35.4119,
+      "eval_samples_per_second": 1464.562,
+      "eval_steps_per_second": 5.733,
+      "step": 2376
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 3.865570068359375,
+      "eval_runtime": 35.4045,
+      "eval_samples_per_second": 1464.871,
+      "eval_steps_per_second": 5.734,
+      "step": 2640
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 2640,
+  "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": 7.0435970482176e+17,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2640/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:effd0b4583e594a84139ecba9f4e7f68c39591ad196c13eac20607bdae8c72cc
+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
+}

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 sha256:9cc5bff4d3c608b8e3ac3a434bfbe3fe1fcb80772df38d8484ab99208c64f02e
+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>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:effd0b4583e594a84139ecba9f4e7f68c39591ad196c13eac20607bdae8c72cc
+size 5496