Add files using upload-large-folder tool

exp2b/swap_require_to_carry_1032/tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "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": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

exp2b/swap_require_to_carry_1032/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 28.812761993479274,
+    "total_flos": 2.068898812526592e+18,
+    "train_loss": 3.39577836932558,
+    "train_runtime": 43934.9422,
+    "train_samples": 274807,
+    "train_samples_per_second": 312.743,
+    "train_steps_per_second": 3.91
+}

exp2b/swap_require_to_carry_2128/README.md

@@ -0,0 +1,173 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: exceptions_exp2_swap_require_to_carry_2128
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/craaaa/exceptions_exp2/runs/p40av614)
+# exceptions_exp2_swap_require_to_carry_2128
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.5558
+- Accuracy: 0.3698
+
+## 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: 0.0006
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 2128
+- gradient_accumulation_steps: 5
+- total_train_batch_size: 80
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 50.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step   | Accuracy | Validation Loss |
+|:-------------:|:-------:|:------:|:--------:|:---------------:|
+| 4.8289        | 0.2911  | 1000   | 0.2545   | 4.7522          |
+| 4.3295        | 0.5822  | 2000   | 0.2993   | 4.2868          |
+| 4.1452        | 0.8733  | 3000   | 0.3157   | 4.0962          |
+| 3.9889        | 1.1642  | 4000   | 0.3255   | 3.9910          |
+| 3.9314        | 1.4553  | 5000   | 0.3320   | 3.9145          |
+| 3.8805        | 1.7464  | 6000   | 0.3373   | 3.8562          |
+| 3.7514        | 2.0373  | 7000   | 0.3416   | 3.8151          |
+| 3.7624        | 2.3284  | 8000   | 0.3443   | 3.7867          |
+| 3.7472        | 2.6195  | 9000   | 0.3473   | 3.7572          |
+| 3.73          | 2.9106  | 10000  | 0.3497   | 3.7268          |
+| 3.6305        | 3.2014  | 11000  | 0.3517   | 3.7154          |
+| 3.6491        | 3.4925  | 12000  | 0.3532   | 3.6969          |
+| 3.6344        | 3.7837  | 13000  | 0.3551   | 3.6789          |
+| 3.5324        | 4.0745  | 14000  | 0.3564   | 3.6751          |
+| 3.5684        | 4.3656  | 15000  | 0.3573   | 3.6606          |
+| 3.5802        | 4.6567  | 16000  | 0.3585   | 3.6468          |
+| 3.5646        | 4.9478  | 17000  | 0.3593   | 3.6362          |
+| 3.5021        | 5.2387  | 18000  | 0.3602   | 3.6348          |
+| 3.5145        | 5.5298  | 19000  | 0.3611   | 3.6240          |
+| 3.5278        | 5.8209  | 20000  | 0.3621   | 3.6141          |
+| 3.4424        | 6.1118  | 21000  | 0.3628   | 3.6201          |
+| 3.4676        | 6.4029  | 22000  | 0.3636   | 3.6072          |
+| 3.4864        | 6.6940  | 23000  | 0.3643   | 3.5997          |
+| 3.4952        | 6.9851  | 24000  | 0.3649   | 3.5905          |
+| 3.4255        | 7.2760  | 25000  | 0.3647   | 3.5982          |
+| 3.4437        | 7.5671  | 26000  | 0.3657   | 3.5909          |
+| 3.4696        | 7.8582  | 27000  | 0.3664   | 3.5787          |
+| 3.3754        | 8.1490  | 28000  | 0.3660   | 3.5915          |
+| 3.4158        | 8.4401  | 29000  | 0.3668   | 3.5868          |
+| 3.4278        | 8.7313  | 30000  | 0.3674   | 3.5733          |
+| 3.3285        | 9.0221  | 31000  | 0.3673   | 3.5804          |
+| 3.3768        | 9.3132  | 32000  | 0.3675   | 3.5769          |
+| 3.3918        | 9.6043  | 33000  | 0.3678   | 3.5706          |
+| 3.4235        | 9.8954  | 34000  | 0.3686   | 3.5624          |
+| 3.3301        | 10.1863 | 35000  | 0.3684   | 3.5713          |
+| 3.3657        | 10.4774 | 36000  | 0.3688   | 3.5657          |
+| 3.3882        | 10.7685 | 37000  | 0.3694   | 3.5586          |
+| 3.2774        | 11.0594 | 38000  | 0.3694   | 3.5661          |
+| 3.3418        | 11.3505 | 39000  | 0.3696   | 3.5666          |
+| 3.3626        | 11.6416 | 40000  | 0.3697   | 3.5558          |
+| 3.3769        | 11.9327 | 41000  | 0.3706   | 3.5470          |
+| 3.3102        | 12.2236 | 42000  | 0.3700   | 3.5622          |
+| 3.3311        | 12.5147 | 43000  | 0.3704   | 3.5521          |
+| 3.3529        | 12.8058 | 44000  | 0.3708   | 3.5514          |
+| 3.2645        | 13.0966 | 45000  | 0.3704   | 3.5610          |
+| 3.3027        | 13.3878 | 46000  | 0.3708   | 3.5551          |
+| 3.3317        | 13.6789 | 47000  | 0.3714   | 3.5486          |
+| 3.3341        | 13.9700 | 48000  | 0.3716   | 3.5409          |
+| 3.2718        | 14.2608 | 49000  | 0.3712   | 3.5574          |
+| 3.3059        | 14.5519 | 50000  | 0.3718   | 3.5486          |
+| 3.321         | 14.8430 | 51000  | 0.3722   | 3.5415          |
+| 3.2297        | 15.1339 | 52000  | 0.3714   | 3.5563          |
+| 3.2868        | 15.4250 | 53000  | 0.3716   | 3.5502          |
+| 3.291         | 15.7161 | 54000  | 0.3723   | 3.5414          |
+| 3.2615        | 16.0070 | 55000  | 0.3721   | 3.5496          |
+| 3.2497        | 16.2981 | 56000  | 0.3722   | 3.5505          |
+| 3.2737        | 16.5892 | 57000  | 0.3726   | 3.5432          |
+| 3.3034        | 16.8803 | 58000  | 0.3731   | 3.5342          |
+| 3.2227        | 17.1712 | 59000  | 0.3724   | 3.5486          |
+| 3.2673        | 17.4623 | 60000  | 0.3726   | 3.5469          |
+| 3.2939        | 17.7534 | 61000  | 0.3732   | 3.5381          |
+| 3.1934        | 18.0442 | 62000  | 0.3728   | 3.5510          |
+| 3.2315        | 18.3354 | 63000  | 0.3729   | 3.5466          |
+| 3.2589        | 18.6265 | 64000  | 0.3729   | 3.5403          |
+| 3.2753        | 18.9176 | 65000  | 0.3737   | 3.5333          |
+| 3.2123        | 19.2084 | 66000  | 0.3729   | 3.5489          |
+| 3.2533        | 19.4995 | 67000  | 0.3732   | 3.5407          |
+| 3.2451        | 19.7906 | 68000  | 0.3735   | 3.5344          |
+| 3.1742        | 20.0815 | 69000  | 0.3732   | 3.5475          |
+| 3.213         | 20.3726 | 70000  | 0.3732   | 3.5459          |
+| 3.238         | 20.6637 | 71000  | 0.3739   | 3.5350          |
+| 3.2504        | 20.9548 | 72000  | 0.3745   | 3.5290          |
+| 3.1916        | 21.2457 | 73000  | 0.3733   | 3.5467          |
+| 3.2117        | 21.5368 | 74000  | 0.3740   | 3.5397          |
+| 3.2279        | 21.8279 | 75000  | 0.3744   | 3.5343          |
+| 3.1556        | 22.1188 | 76000  | 0.3735   | 3.5510          |
+| 3.1982        | 22.4099 | 77000  | 0.3739   | 3.5434          |
+| 3.2193        | 22.7010 | 78000  | 0.3742   | 3.5373          |
+| 3.2446        | 22.9921 | 79000  | 0.3747   | 3.5279          |
+| 3.1809        | 23.2830 | 80000  | 0.3741   | 3.5482          |
+| 3.1964        | 23.5741 | 81000  | 0.3741   | 3.5391          |
+| 3.2268        | 23.8652 | 82000  | 0.3748   | 3.5308          |
+| 3.1506        | 24.1560 | 83000  | 0.3740   | 3.5501          |
+| 3.18          | 24.4471 | 84000  | 0.3740   | 3.5447          |
+| 3.2124        | 24.7382 | 85000  | 0.3747   | 3.5349          |
+| 3.1181        | 25.0291 | 86000  | 0.3742   | 3.5465          |
+| 3.1627        | 25.3202 | 87000  | 0.3742   | 3.5454          |
+| 3.1809        | 25.6113 | 88000  | 0.3746   | 3.5398          |
+| 3.2053        | 25.9024 | 89000  | 0.3753   | 3.5295          |
+| 3.1337        | 26.1933 | 90000  | 0.3742   | 3.5487          |
+| 3.1622        | 26.4844 | 91000  | 3.5508   | 0.3741          |
+| 3.1757        | 26.7755 | 92000  | 3.5435   | 0.3746          |
+| 3.1123        | 27.0667 | 93000  | 3.5498   | 0.3742          |
+| 3.1531        | 27.3578 | 94000  | 3.5481   | 0.3745          |
+| 3.1674        | 27.6489 | 95000  | 3.5386   | 0.3747          |
+| 3.1848        | 27.9400 | 96000  | 3.5311   | 0.3757          |
+| 3.1228        | 28.2308 | 97000  | 3.5527   | 0.3743          |
+| 3.1465        | 28.5219 | 98000  | 3.5446   | 0.3751          |
+| 3.167         | 28.8131 | 99000  | 3.5344   | 0.3754          |
+| 3.1033        | 29.1039 | 100000 | 3.5509   | 0.3742          |
+| 3.1225        | 29.3950 | 101000 | 3.5461   | 0.3747          |
+| 3.1671        | 29.6861 | 102000 | 3.5416   | 0.3752          |
+| 3.1634        | 29.9772 | 103000 | 3.5333   | 0.3758          |
+| 3.1025        | 30.2681 | 104000 | 3.5496   | 0.3748          |
+| 3.132         | 30.5592 | 105000 | 3.5431   | 0.3751          |
+| 3.1561        | 30.8503 | 106000 | 3.5347   | 0.3758          |
+| 3.0942        | 31.1412 | 107000 | 3.5555   | 0.3744          |
+| 3.1232        | 31.4323 | 108000 | 3.5457   | 0.3753          |
+| 3.1337        | 31.7234 | 109000 | 3.5392   | 0.3757          |
+| 3.0579        | 32.0143 | 110000 | 3.5478   | 0.3752          |
+
+
+### Framework versions
+
+- Transformers 4.55.2
+- Pytorch 2.8.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.21.4

exp2b/swap_require_to_carry_2128/all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 32.01426408942711,
+    "eval_accuracy": 0.36975571126878837,
+    "eval_loss": 3.555778980255127,
+    "eval_runtime": 53.0499,
+    "eval_samples": 16651,
+    "eval_samples_per_second": 313.874,
+    "eval_steps_per_second": 19.623,
+    "perplexity": 35.01508540685898,
+    "total_flos": 2.298780406775808e+18,
+    "train_loss": 0.5710641534978693,
+    "train_runtime": 8871.8926,
+    "train_samples": 274807,
+    "train_samples_per_second": 1548.751,
+    "train_steps_per_second": 19.365
+}

exp2b/swap_require_to_carry_2128/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": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "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": "4.55.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

exp2b/swap_require_to_carry_2128/eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 32.01426408942711,
+    "eval_accuracy": 0.36975571126878837,
+    "eval_loss": 3.555778980255127,
+    "eval_runtime": 53.0499,
+    "eval_samples": 16651,
+    "eval_samples_per_second": 313.874,
+    "eval_steps_per_second": 19.623,
+    "perplexity": 35.01508540685898
+}

exp2b/swap_require_to_carry_2128/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.55.2"
+}

exp2b/swap_require_to_carry_2128/special_tokens_map.json

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

exp2b/swap_require_to_carry_2128/tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "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": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

exp2b/swap_require_to_carry_2128/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 32.01426408942711,
+    "total_flos": 2.298780406775808e+18,
+    "train_loss": 0.5710641534978693,
+    "train_runtime": 8871.8926,
+    "train_samples": 274807,
+    "train_samples_per_second": 1548.751,
+    "train_steps_per_second": 19.365
+}

exp2b/swap_require_to_carry_3591/README.md

@@ -0,0 +1,163 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: exceptions_exp2_swap_require_to_carry_3591
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/craaaa/exceptions_exp2/runs/5p1kloyr)
+# exceptions_exp2_swap_require_to_carry_3591
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.5545
+- Accuracy: 0.3743
+
+## 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: 0.0006
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 3591
+- gradient_accumulation_steps: 5
+- total_train_batch_size: 80
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 50.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step   | Accuracy | Validation Loss |
+|:-------------:|:-------:|:------:|:--------:|:---------------:|
+| 4.8353        | 0.2911  | 1000   | 0.2531   | 4.7629          |
+| 4.3374        | 0.5822  | 2000   | 0.2996   | 4.2795          |
+| 4.1489        | 0.8733  | 3000   | 0.3155   | 4.0955          |
+| 3.996         | 1.1642  | 4000   | 0.3252   | 3.9965          |
+| 3.9347        | 1.4553  | 5000   | 0.3318   | 3.9166          |
+| 3.8665        | 1.7464  | 6000   | 0.3372   | 3.8597          |
+| 3.7343        | 2.0373  | 7000   | 0.3416   | 3.8142          |
+| 3.7434        | 2.3284  | 8000   | 0.3447   | 3.7804          |
+| 3.7318        | 2.6195  | 9000   | 0.3477   | 3.7533          |
+| 3.7166        | 2.9106  | 10000  | 0.3496   | 3.7269          |
+| 3.6328        | 3.2014  | 11000  | 0.3518   | 3.7136          |
+| 3.6293        | 3.4925  | 12000  | 0.3536   | 3.6956          |
+| 3.6383        | 3.7837  | 13000  | 0.3553   | 3.6771          |
+| 3.5359        | 4.0745  | 14000  | 0.3568   | 3.6693          |
+| 3.5563        | 4.3656  | 15000  | 0.3578   | 3.6573          |
+| 3.569         | 4.6567  | 16000  | 0.3587   | 3.6432          |
+| 3.5858        | 4.9478  | 17000  | 0.3601   | 3.6322          |
+| 3.4991        | 5.2387  | 18000  | 0.3605   | 3.6344          |
+| 3.5221        | 5.5298  | 19000  | 0.3616   | 3.6235          |
+| 3.5329        | 5.8209  | 20000  | 0.3624   | 3.6119          |
+| 3.4393        | 6.1118  | 21000  | 0.3629   | 3.6139          |
+| 3.4739        | 6.4029  | 22000  | 0.3634   | 3.6083          |
+| 3.4852        | 6.6940  | 23000  | 0.3639   | 3.6001          |
+| 3.4901        | 6.9851  | 24000  | 0.3646   | 3.5918          |
+| 3.4147        | 7.2760  | 25000  | 0.3649   | 3.5968          |
+| 3.4439        | 7.5671  | 26000  | 0.3658   | 3.5878          |
+| 3.4694        | 7.8582  | 27000  | 0.3663   | 3.5779          |
+| 3.3723        | 8.1490  | 28000  | 0.3661   | 3.5911          |
+| 3.405         | 8.4401  | 29000  | 0.3668   | 3.5804          |
+| 3.4347        | 8.7313  | 30000  | 0.3675   | 3.5715          |
+| 3.3197        | 9.0221  | 31000  | 0.3673   | 3.5790          |
+| 3.3719        | 9.3132  | 32000  | 0.3678   | 3.5758          |
+| 3.394         | 9.6043  | 33000  | 0.3685   | 3.5682          |
+| 3.4089        | 9.8954  | 34000  | 0.3688   | 3.5599          |
+| 3.3351        | 10.1863 | 35000  | 0.3686   | 3.5718          |
+| 3.3608        | 10.4774 | 36000  | 0.3686   | 3.5644          |
+| 3.3839        | 10.7685 | 37000  | 0.3696   | 3.5576          |
+| 3.2872        | 11.0594 | 38000  | 0.3697   | 3.5635          |
+| 3.3239        | 11.3505 | 39000  | 0.3692   | 3.5649          |
+| 3.3604        | 11.6416 | 40000  | 0.3702   | 3.5563          |
+| 3.3633        | 11.9327 | 41000  | 0.3705   | 3.5486          |
+| 3.3018        | 12.2236 | 42000  | 0.3699   | 3.5617          |
+| 3.3237        | 12.5147 | 43000  | 0.3704   | 3.5561          |
+| 3.3553        | 12.8058 | 44000  | 0.3710   | 3.5454          |
+| 3.266         | 13.0966 | 45000  | 0.3703   | 3.5622          |
+| 3.298         | 13.3878 | 46000  | 0.3706   | 3.5562          |
+| 3.3193        | 13.6789 | 47000  | 0.3712   | 3.5511          |
+| 3.3377        | 13.9700 | 48000  | 0.3719   | 3.5380          |
+| 3.2707        | 14.2608 | 49000  | 0.3711   | 3.5559          |
+| 3.2986        | 14.5519 | 50000  | 0.3714   | 3.5475          |
+| 3.3352        | 14.8430 | 51000  | 0.3721   | 3.5395          |
+| 3.2328        | 15.1339 | 52000  | 0.3717   | 3.5531          |
+| 3.278         | 15.4250 | 53000  | 0.3720   | 3.5493          |
+| 3.2919        | 15.7161 | 54000  | 0.3724   | 3.5413          |
+| 3.2682        | 16.0070 | 55000  | 0.3720   | 3.5475          |
+| 3.2366        | 16.2981 | 56000  | 0.3725   | 3.5493          |
+| 3.2881        | 16.5892 | 57000  | 0.3725   | 3.5421          |
+| 3.2976        | 16.8803 | 58000  | 0.3728   | 3.5371          |
+| 3.2211        | 17.1712 | 59000  | 0.3723   | 3.5510          |
+| 3.265         | 17.4623 | 60000  | 0.3727   | 3.5464          |
+| 3.2771        | 17.7534 | 61000  | 0.3732   | 3.5357          |
+| 3.1751        | 18.0442 | 62000  | 0.3724   | 3.5497          |
+| 3.2348        | 18.3354 | 63000  | 0.3728   | 3.5502          |
+| 3.2587        | 18.6265 | 64000  | 0.3730   | 3.5414          |
+| 3.2776        | 18.9176 | 65000  | 0.3738   | 3.5317          |
+| 3.1939        | 19.2084 | 66000  | 0.3728   | 3.5513          |
+| 3.2337        | 19.4995 | 67000  | 0.3731   | 3.5424          |
+| 3.2667        | 19.7906 | 68000  | 0.3738   | 3.5364          |
+| 3.1624        | 20.0815 | 69000  | 0.3732   | 3.5489          |
+| 3.2091        | 20.3726 | 70000  | 0.3737   | 3.5438          |
+| 3.245         | 20.6637 | 71000  | 0.3735   | 3.5370          |
+| 3.2399        | 20.9548 | 72000  | 0.3742   | 3.5309          |
+| 3.1951        | 21.2457 | 73000  | 0.3732   | 3.5491          |
+| 3.2234        | 21.5368 | 74000  | 0.3738   | 3.5366          |
+| 3.2386        | 21.8279 | 75000  | 0.3742   | 3.5339          |
+| 3.1712        | 22.1188 | 76000  | 0.3735   | 3.5475          |
+| 3.1945        | 22.4099 | 77000  | 0.3739   | 3.5480          |
+| 3.2309        | 22.7010 | 78000  | 0.3742   | 3.5343          |
+| 3.2372        | 22.9921 | 79000  | 0.3750   | 3.5286          |
+| 3.1752        | 23.2830 | 80000  | 0.3739   | 3.5466          |
+| 3.1701        | 23.5741 | 81000  | 3.5533   | 0.3735          |
+| 3.1977        | 23.8652 | 82000  | 3.5408   | 0.3741          |
+| 3.154         | 24.1563 | 83000  | 3.5521   | 0.3736          |
+| 3.1835        | 24.4474 | 84000  | 3.5442   | 0.3743          |
+| 3.205         | 24.7385 | 85000  | 3.5376   | 0.3747          |
+| 3.1135        | 25.0294 | 86000  | 3.5489   | 0.3740          |
+| 3.1552        | 25.3205 | 87000  | 3.5517   | 0.3737          |
+| 3.1777        | 25.6116 | 88000  | 3.5409   | 0.3743          |
+| 3.2144        | 25.9027 | 89000  | 3.5334   | 0.3751          |
+| 3.1364        | 26.1936 | 90000  | 3.5503   | 0.3742          |
+| 3.1675        | 26.4847 | 91000  | 3.5466   | 0.3746          |
+| 3.201         | 26.7758 | 92000  | 3.5364   | 0.3751          |
+| 3.1089        | 27.0667 | 93000  | 3.5548   | 0.3741          |
+| 3.151         | 27.3578 | 94000  | 3.5441   | 0.3744          |
+| 3.1649        | 27.6489 | 95000  | 3.5373   | 0.3750          |
+| 3.1918        | 27.9400 | 96000  | 3.5342   | 0.3752          |
+| 3.1161        | 28.2308 | 97000  | 3.5515   | 0.3745          |
+| 3.1603        | 28.5219 | 98000  | 3.5428   | 0.3747          |
+| 3.1628        | 28.8131 | 99000  | 3.5394   | 0.3754          |
+| 3.087         | 29.1039 | 100000 | 3.5545   | 0.3743          |
+
+
+### Framework versions
+
+- Transformers 4.55.2
+- Pytorch 2.8.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.21.4

exp2b/swap_require_to_carry_3591/all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 29.103924080111785,
+    "eval_accuracy": 0.3742630009586702,
+    "eval_loss": 3.554548978805542,
+    "eval_runtime": 178.3723,
+    "eval_samples": 16651,
+    "eval_samples_per_second": 93.35,
+    "eval_steps_per_second": 5.836,
+    "perplexity": 34.97204327741856,
+    "total_flos": 2.089804004130816e+18,
+    "train_loss": 0.6329161505126953,
+    "train_runtime": 39779.2124,
+    "train_samples": 274807,
+    "train_samples_per_second": 345.415,
+    "train_steps_per_second": 4.319
+}

exp2b/swap_require_to_carry_3591/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": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "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": "4.55.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

exp2b/swap_require_to_carry_3591/eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 29.103924080111785,
+    "eval_accuracy": 0.3742630009586702,
+    "eval_loss": 3.554548978805542,
+    "eval_runtime": 178.3723,
+    "eval_samples": 16651,
+    "eval_samples_per_second": 93.35,
+    "eval_steps_per_second": 5.836,
+    "perplexity": 34.97204327741856
+}

exp2b/swap_require_to_carry_3591/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.55.2"
+}

exp2b/swap_require_to_carry_3591/special_tokens_map.json

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

exp2b/swap_require_to_carry_3591/tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "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": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

exp2b/swap_require_to_carry_3591/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 29.103924080111785,
+    "total_flos": 2.089804004130816e+18,
+    "train_loss": 0.6329161505126953,
+    "train_runtime": 39779.2124,
+    "train_samples": 274807,
+    "train_samples_per_second": 345.415,
+    "train_steps_per_second": 4.319
+}

exp2b/swap_require_to_carry_40817/README.md

@@ -0,0 +1,163 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: exceptions_exp2_swap_require_to_carry_40817
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/craaaa/exceptions_exp2/runs/o14k5cy9)
+# exceptions_exp2_swap_require_to_carry_40817
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.5533
+- Accuracy: 0.3699
+
+## 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: 0.0006
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 40817
+- gradient_accumulation_steps: 5
+- total_train_batch_size: 80
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 50.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step   | Accuracy | Validation Loss |
+|:-------------:|:-------:|:------:|:--------:|:---------------:|
+| 4.8165        | 0.2911  | 1000   | 0.2568   | 4.7391          |
+| 4.3333        | 0.5822  | 2000   | 0.2995   | 4.2766          |
+| 4.1412        | 0.8733  | 3000   | 0.3155   | 4.0926          |
+| 3.9991        | 1.1642  | 4000   | 0.3250   | 3.9883          |
+| 3.933         | 1.4553  | 5000   | 0.3325   | 3.9106          |
+| 3.8824        | 1.7464  | 6000   | 0.3375   | 3.8533          |
+| 3.7539        | 2.0373  | 7000   | 0.3419   | 3.8091          |
+| 3.7421        | 2.3284  | 8000   | 0.3446   | 3.7809          |
+| 3.7406        | 2.6195  | 9000   | 0.3474   | 3.7504          |
+| 3.7255        | 2.9106  | 10000  | 0.3499   | 3.7260          |
+| 3.6348        | 3.2014  | 11000  | 0.3514   | 3.7142          |
+| 3.6457        | 3.4925  | 12000  | 0.3534   | 3.6941          |
+| 3.6447        | 3.7837  | 13000  | 0.3549   | 3.6771          |
+| 3.539         | 4.0745  | 14000  | 0.3566   | 3.6698          |
+| 3.55          | 4.3656  | 15000  | 0.3576   | 3.6586          |
+| 3.5796        | 4.6567  | 16000  | 0.3590   | 3.6455          |
+| 3.576         | 4.9478  | 17000  | 0.3600   | 3.6317          |
+| 3.4957        | 5.2387  | 18000  | 0.3602   | 3.6345          |
+| 3.5063        | 5.5298  | 19000  | 0.3615   | 3.6241          |
+| 3.5306        | 5.8209  | 20000  | 0.3622   | 3.6127          |
+| 3.4346        | 6.1118  | 21000  | 0.3626   | 3.6142          |
+| 3.472         | 6.4029  | 22000  | 0.3633   | 3.6078          |
+| 3.4887        | 6.6940  | 23000  | 0.3639   | 3.5991          |
+| 3.4872        | 6.9851  | 24000  | 0.3648   | 3.5891          |
+| 3.4348        | 7.2760  | 25000  | 0.3648   | 3.5988          |
+| 3.4425        | 7.5671  | 26000  | 0.3653   | 3.5901          |
+| 3.4498        | 7.8582  | 27000  | 0.3661   | 3.5791          |
+| 3.3936        | 8.1490  | 28000  | 0.3660   | 3.5864          |
+| 3.3962        | 8.4401  | 29000  | 0.3664   | 3.5809          |
+| 3.4249        | 8.7313  | 30000  | 0.3671   | 3.5757          |
+| 3.3161        | 9.0221  | 31000  | 0.3672   | 3.5793          |
+| 3.387         | 9.3132  | 32000  | 0.3674   | 3.5782          |
+| 3.3924        | 9.6043  | 33000  | 0.3682   | 3.5694          |
+| 3.4094        | 9.8954  | 34000  | 0.3685   | 3.5596          |
+| 3.3295        | 10.1863 | 35000  | 0.3683   | 3.5720          |
+| 3.362         | 10.4774 | 36000  | 0.3686   | 3.5671          |
+| 3.3768        | 10.7685 | 37000  | 0.3692   | 3.5588          |
+| 3.2931        | 11.0594 | 38000  | 0.3691   | 3.5665          |
+| 3.3272        | 11.3505 | 39000  | 0.3697   | 3.5626          |
+| 3.3696        | 11.6416 | 40000  | 0.3699   | 3.5533          |
+| 3.3642        | 11.9327 | 41000  | 0.3705   | 3.5477          |
+| 3.3012        | 12.2236 | 42000  | 0.3701   | 3.5630          |
+| 3.3354        | 12.5147 | 43000  | 0.3706   | 3.5529          |
+| 3.3443        | 12.8058 | 44000  | 0.3708   | 3.5489          |
+| 3.2808        | 13.0966 | 45000  | 0.3704   | 3.5610          |
+| 3.2958        | 13.3878 | 46000  | 0.3707   | 3.5527          |
+| 3.3062        | 13.6789 | 47000  | 0.3714   | 3.5490          |
+| 3.3443        | 13.9700 | 48000  | 0.3718   | 3.5406          |
+| 3.272         | 14.2608 | 49000  | 0.3708   | 3.5555          |
+| 3.2966        | 14.5519 | 50000  | 0.3717   | 3.5500          |
+| 3.3184        | 14.8430 | 51000  | 0.3719   | 3.5418          |
+| 3.2363        | 15.1339 | 52000  | 0.3713   | 3.5552          |
+| 3.2768        | 15.4250 | 53000  | 0.3714   | 3.5532          |
+| 3.2983        | 15.7161 | 54000  | 0.3721   | 3.5444          |
+| 3.2505        | 16.0070 | 55000  | 0.3717   | 3.5532          |
+| 3.2394        | 16.2981 | 56000  | 0.3719   | 3.5511          |
+| 3.2745        | 16.5892 | 57000  | 0.3723   | 3.5431          |
+| 3.2797        | 16.8803 | 58000  | 0.3730   | 3.5383          |
+| 3.225         | 17.1712 | 59000  | 0.3721   | 3.5553          |
+| 3.2534        | 17.4623 | 60000  | 0.3726   | 3.5480          |
+| 3.2683        | 17.7534 | 61000  | 0.3733   | 3.5342          |
+| 3.1819        | 18.0442 | 62000  | 0.3724   | 3.5529          |
+| 3.2276        | 18.3354 | 63000  | 0.3727   | 3.5463          |
+| 3.2585        | 18.6265 | 64000  | 0.3731   | 3.5394          |
+| 3.2731        | 18.9176 | 65000  | 0.3736   | 3.5341          |
+| 3.1994        | 19.2084 | 66000  | 0.3728   | 3.5523          |
+| 3.2267        | 19.4995 | 67000  | 0.3731   | 3.5473          |
+| 3.2469        | 19.7906 | 68000  | 0.3736   | 3.5351          |
+| 3.1667        | 20.0815 | 69000  | 0.3732   | 3.5486          |
+| 3.2161        | 20.3726 | 70000  | 0.3732   | 3.5458          |
+| 3.2206        | 20.6637 | 71000  | 0.3739   | 3.5391          |
+| 3.2496        | 20.9548 | 72000  | 0.3743   | 3.5302          |
+| 3.1786        | 21.2457 | 73000  | 0.3733   | 3.5517          |
+| 3.2064        | 21.5368 | 74000  | 0.3737   | 3.5392          |
+| 3.224         | 21.8279 | 75000  | 0.3741   | 3.5349          |
+| 3.1679        | 22.1188 | 76000  | 0.3733   | 3.5520          |
+| 3.1935        | 22.4099 | 77000  | 0.3735   | 3.5461          |
+| 3.2103        | 22.7010 | 78000  | 0.3736   | 3.5389          |
+| 3.2216        | 22.9921 | 79000  | 0.3745   | 3.5328          |
+| 3.1856        | 23.2830 | 80000  | 0.3737   | 3.5483          |
+| 3.1841        | 23.5741 | 81000  | 3.5561   | 0.3735          |
+| 3.2075        | 23.8652 | 82000  | 3.5405   | 0.3741          |
+| 3.141         | 24.1563 | 83000  | 3.5551   | 0.3733          |
+| 3.1806        | 24.4474 | 84000  | 3.5472   | 0.3741          |
+| 3.2036        | 24.7385 | 85000  | 3.5373   | 0.3745          |
+| 3.1092        | 25.0294 | 86000  | 3.5521   | 0.3740          |
+| 3.1682        | 25.3205 | 87000  | 3.5488   | 0.3741          |
+| 3.1867        | 25.6116 | 88000  | 3.5393   | 0.3748          |
+| 3.2031        | 25.9027 | 89000  | 3.5329   | 0.3748          |
+| 3.1405        | 26.1936 | 90000  | 3.5546   | 0.3740          |
+| 3.1605        | 26.4847 | 91000  | 3.5474   | 0.3742          |
+| 3.1786        | 26.7758 | 92000  | 3.5363   | 0.3749          |
+| 3.1217        | 27.0667 | 93000  | 3.5516   | 0.3744          |
+| 3.1474        | 27.3578 | 94000  | 3.5476   | 0.3743          |
+| 3.1783        | 27.6489 | 95000  | 3.5408   | 0.3748          |
+| 3.1755        | 27.9400 | 96000  | 3.5334   | 0.3752          |
+| 3.1254        | 28.2308 | 97000  | 3.5512   | 0.3743          |
+| 3.16          | 28.5219 | 98000  | 3.5444   | 0.3746          |
+| 3.1722        | 28.8131 | 99000  | 3.5362   | 0.3754          |
+| 3.0868        | 29.1039 | 100000 | 3.5495   | 0.3747          |
+
+
+### Framework versions
+
+- Transformers 4.55.2
+- Pytorch 2.8.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.21.4

exp2b/swap_require_to_carry_40817/all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 29.103924080111785,
+    "eval_accuracy": 0.3699379961194834,
+    "eval_loss": 3.5532639026641846,
+    "eval_runtime": 54.799,
+    "eval_samples": 16651,
+    "eval_samples_per_second": 303.856,
+    "eval_steps_per_second": 18.997,
+    "perplexity": 34.92713040340048,
+    "total_flos": 2.089804004130816e+18,
+    "train_loss": 0.6326026982116699,
+    "train_runtime": 8947.5804,
+    "train_samples": 274807,
+    "train_samples_per_second": 1535.65,
+    "train_steps_per_second": 19.201
+}

exp2b/swap_require_to_carry_40817/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": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "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": "4.55.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

exp2b/swap_require_to_carry_40817/eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 29.103924080111785,
+    "eval_accuracy": 0.3699379961194834,
+    "eval_loss": 3.5532639026641846,
+    "eval_runtime": 54.799,
+    "eval_samples": 16651,
+    "eval_samples_per_second": 303.856,
+    "eval_steps_per_second": 18.997,
+    "perplexity": 34.92713040340048
+}

exp2b/swap_require_to_carry_40817/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.55.2"
+}

exp2b/swap_require_to_carry_40817/special_tokens_map.json

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

exp2b/swap_require_to_carry_40817/tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "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": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

exp2b/swap_require_to_carry_40817/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 29.103924080111785,
+    "total_flos": 2.089804004130816e+18,
+    "train_loss": 0.6326026982116699,
+    "train_runtime": 8947.5804,
+    "train_samples": 274807,
+    "train_samples_per_second": 1535.65,
+    "train_steps_per_second": 19.201
+}

exp2b/swap_require_to_carry_5039/README.md

@@ -0,0 +1,163 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: exceptions_exp2_swap_require_to_carry_5039
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/craaaa/exceptions_exp2/runs/xqjdnq21)
+# exceptions_exp2_swap_require_to_carry_5039
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.5571
+- Accuracy: 0.3698
+
+## 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: 0.0006
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 5039
+- gradient_accumulation_steps: 5
+- total_train_batch_size: 80
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 50.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step   | Accuracy | Validation Loss |
+|:-------------:|:-------:|:------:|:--------:|:---------------:|
+| 4.8262        | 0.2911  | 1000   | 0.2555   | 4.7465          |
+| 4.3397        | 0.5822  | 2000   | 0.2986   | 4.2876          |
+| 4.1446        | 0.8733  | 3000   | 0.3154   | 4.0953          |
+| 3.9914        | 1.1642  | 4000   | 0.3250   | 3.9918          |
+| 3.9296        | 1.4553  | 5000   | 0.3320   | 3.9154          |
+| 3.8717        | 1.7464  | 6000   | 0.3370   | 3.8568          |
+| 3.7494        | 2.0373  | 7000   | 0.3410   | 3.8178          |
+| 3.7524        | 2.3284  | 8000   | 0.3441   | 3.7847          |
+| 3.7346        | 2.6195  | 9000   | 0.3471   | 3.7535          |
+| 3.7251        | 2.9106  | 10000  | 0.3497   | 3.7285          |
+| 3.6368        | 3.2014  | 11000  | 0.3518   | 3.7140          |
+| 3.649         | 3.4925  | 12000  | 0.3534   | 3.6943          |
+| 3.6418        | 3.7837  | 13000  | 0.3549   | 3.6770          |
+| 3.5435        | 4.0745  | 14000  | 0.3562   | 3.6688          |
+| 3.5655        | 4.3656  | 15000  | 0.3572   | 3.6578          |
+| 3.5787        | 4.6567  | 16000  | 0.3586   | 3.6434          |
+| 3.5848        | 4.9478  | 17000  | 0.3600   | 3.6325          |
+| 3.5054        | 5.2387  | 18000  | 0.3603   | 3.6340          |
+| 3.523         | 5.5298  | 19000  | 0.3612   | 3.6255          |
+| 3.5277        | 5.8209  | 20000  | 0.3623   | 3.6132          |
+| 3.4487        | 6.1118  | 21000  | 0.3622   | 3.6180          |
+| 3.4646        | 6.4029  | 22000  | 0.3631   | 3.6094          |
+| 3.481         | 6.6940  | 23000  | 0.3642   | 3.5993          |
+| 3.4938        | 6.9851  | 24000  | 0.3646   | 3.5899          |
+| 3.4142        | 7.2760  | 25000  | 0.3648   | 3.5975          |
+| 3.4478        | 7.5671  | 26000  | 0.3651   | 3.5915          |
+| 3.4631        | 7.8582  | 27000  | 0.3662   | 3.5803          |
+| 3.3749        | 8.1490  | 28000  | 0.3662   | 3.5870          |
+| 3.4133        | 8.4401  | 29000  | 0.3666   | 3.5811          |
+| 3.4225        | 8.7313  | 30000  | 0.3673   | 3.5725          |
+| 3.3219        | 9.0221  | 31000  | 0.3671   | 3.5783          |
+| 3.3654        | 9.3132  | 32000  | 0.3677   | 3.5790          |
+| 3.3982        | 9.6043  | 33000  | 0.3682   | 3.5692          |
+| 3.4212        | 9.8954  | 34000  | 0.3685   | 3.5597          |
+| 3.3225        | 10.1863 | 35000  | 0.3683   | 3.5731          |
+| 3.3616        | 10.4774 | 36000  | 0.3689   | 3.5647          |
+| 3.3825        | 10.7685 | 37000  | 0.3692   | 3.5593          |
+| 3.2801        | 11.0594 | 38000  | 0.3692   | 3.5667          |
+| 3.339         | 11.3505 | 39000  | 0.3693   | 3.5644          |
+| 3.3612        | 11.6416 | 40000  | 0.3698   | 3.5571          |
+| 3.3701        | 11.9327 | 41000  | 0.3705   | 3.5482          |
+| 3.3009        | 12.2236 | 42000  | 0.3700   | 3.5633          |
+| 3.3302        | 12.5147 | 43000  | 0.3702   | 3.5566          |
+| 3.3491        | 12.8058 | 44000  | 0.3707   | 3.5472          |
+| 3.2576        | 13.0966 | 45000  | 0.3704   | 3.5613          |
+| 3.2977        | 13.3878 | 46000  | 0.3704   | 3.5598          |
+| 3.3316        | 13.6789 | 47000  | 0.3712   | 3.5495          |
+| 3.3497        | 13.9700 | 48000  | 0.3718   | 3.5414          |
+| 3.2817        | 14.2608 | 49000  | 0.3712   | 3.5552          |
+| 3.318         | 14.5519 | 50000  | 0.3717   | 3.5467          |
+| 3.3273        | 14.8430 | 51000  | 0.3719   | 3.5430          |
+| 3.2357        | 15.1339 | 52000  | 0.3717   | 3.5553          |
+| 3.287         | 15.4250 | 53000  | 0.3722   | 3.5472          |
+| 3.2979        | 15.7161 | 54000  | 0.3722   | 3.5443          |
+| 3.252         | 16.0070 | 55000  | 0.3719   | 3.5503          |
+| 3.2599        | 16.2981 | 56000  | 0.3720   | 3.5536          |
+| 3.2756        | 16.5892 | 57000  | 0.3725   | 3.5424          |
+| 3.2867        | 16.8803 | 58000  | 0.3727   | 3.5368          |
+| 3.2299        | 17.1712 | 59000  | 0.3720   | 3.5520          |
+| 3.2512        | 17.4623 | 60000  | 0.3725   | 3.5460          |
+| 3.2785        | 17.7534 | 61000  | 0.3731   | 3.5354          |
+| 3.1904        | 18.0442 | 62000  | 0.3727   | 3.5507          |
+| 3.2443        | 18.3354 | 63000  | 0.3723   | 3.5477          |
+| 3.2472        | 18.6265 | 64000  | 0.3734   | 3.5414          |
+| 3.2763        | 18.9176 | 65000  | 0.3735   | 3.5333          |
+| 3.2195        | 19.2084 | 66000  | 0.3728   | 3.5514          |
+| 3.2467        | 19.4995 | 67000  | 0.3728   | 3.5458          |
+| 3.2588        | 19.7906 | 68000  | 0.3736   | 3.5359          |
+| 3.1685        | 20.0815 | 69000  | 0.3731   | 3.5489          |
+| 3.2232        | 20.3726 | 70000  | 0.3733   | 3.5443          |
+| 3.2488        | 20.6637 | 71000  | 0.3736   | 3.5387          |
+| 3.2565        | 20.9548 | 72000  | 0.3742   | 3.5301          |
+| 3.1906        | 21.2457 | 73000  | 0.3733   | 3.5494          |
+| 3.2239        | 21.5368 | 74000  | 0.3738   | 3.5407          |
+| 3.2318        | 21.8279 | 75000  | 0.3741   | 3.5347          |
+| 3.1707        | 22.1188 | 76000  | 0.3736   | 3.5484          |
+| 3.1951        | 22.4099 | 77000  | 0.3742   | 3.5429          |
+| 3.2248        | 22.7010 | 78000  | 0.3740   | 3.5399          |
+| 3.2531        | 22.9921 | 79000  | 0.3747   | 3.5304          |
+| 3.1904        | 23.2830 | 80000  | 0.3738   | 3.5459          |
+| 3.1894        | 23.5741 | 81000  | 3.5494   | 0.3737          |
+| 3.2002        | 23.8652 | 82000  | 3.5431   | 0.3740          |
+| 3.1577        | 24.1563 | 83000  | 3.5531   | 0.3737          |
+| 3.1872        | 24.4474 | 84000  | 3.5467   | 0.3742          |
+| 3.2142        | 24.7385 | 85000  | 3.5356   | 0.3746          |
+| 3.1189        | 25.0294 | 86000  | 3.5496   | 0.3739          |
+| 3.1528        | 25.3205 | 87000  | 3.5486   | 0.3739          |
+| 3.1898        | 25.6116 | 88000  | 3.5364   | 0.3749          |
+| 3.1999        | 25.9027 | 89000  | 3.5337   | 0.3751          |
+| 3.1493        | 26.1936 | 90000  | 3.5525   | 0.3740          |
+| 3.173         | 26.4847 | 91000  | 3.5433   | 0.3747          |
+| 3.1912        | 26.7758 | 92000  | 3.5381   | 0.3749          |
+| 3.0977        | 27.0667 | 93000  | 3.5522   | 0.3743          |
+| 3.15          | 27.3578 | 94000  | 3.5491   | 0.3743          |
+| 3.1651        | 27.6489 | 95000  | 3.5427   | 0.3747          |
+| 3.1929        | 27.9400 | 96000  | 3.5316   | 0.3754          |
+| 3.1271        | 28.2308 | 97000  | 3.5515   | 0.3747          |
+| 3.1427        | 28.5219 | 98000  | 3.5408   | 0.3751          |
+| 3.1541        | 28.8131 | 99000  | 3.5354   | 0.3754          |
+| 3.0971        | 29.1039 | 100000 | 3.5511   | 0.3744          |
+
+
+### Framework versions
+
+- Transformers 4.55.2
+- Pytorch 2.8.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.21.4

exp2b/swap_require_to_carry_5039/all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 29.103924080111785,
+    "eval_accuracy": 0.36984561965742907,
+    "eval_loss": 3.557094097137451,
+    "eval_runtime": 82.6715,
+    "eval_samples": 16651,
+    "eval_samples_per_second": 201.412,
+    "eval_steps_per_second": 12.592,
+    "perplexity": 35.06116462995438,
+    "total_flos": 2.089804004130816e+18,
+    "train_loss": 0.6335985008239746,
+    "train_runtime": 14868.2953,
+    "train_samples": 274807,
+    "train_samples_per_second": 924.138,
+    "train_steps_per_second": 11.555
+}

exp2b/swap_require_to_carry_5039/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": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "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": "4.55.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

exp2b/swap_require_to_carry_5039/eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 29.103924080111785,
+    "eval_accuracy": 0.36984561965742907,
+    "eval_loss": 3.557094097137451,
+    "eval_runtime": 82.6715,
+    "eval_samples": 16651,
+    "eval_samples_per_second": 201.412,
+    "eval_steps_per_second": 12.592,
+    "perplexity": 35.06116462995438
+}

exp2b/swap_require_to_carry_5039/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.55.2"
+}

exp2b/swap_require_to_carry_5039/special_tokens_map.json

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

exp2b/swap_require_to_carry_5039/tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "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": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}