craa commited on 2 days ago

Commit

54eae85

verified ·

1 Parent(s): 205aa2f

Add files using upload-large-folder tool

Browse files

This view is limited to 50 files because it contains too many changes. See raw diff

Files changed (50) hide show

exp2b/swap_0.7_cost_to_carry_2128/eval_results.json +10 -0
exp2b/swap_0.7_cost_to_carry_2128/generation_config.json +6 -0
exp2b/swap_0.7_cost_to_carry_2128/merges.txt +0 -0
exp2b/swap_0.7_cost_to_carry_2128/special_tokens_map.json +5 -0
exp2b/swap_0.7_cost_to_carry_2128/tokenizer.json +0 -0
exp2b/swap_0.7_cost_to_carry_2128/tokenizer_config.json +20 -0
exp2b/swap_0.7_cost_to_carry_2128/train_results.json +9 -0
exp2b/swap_0.7_cost_to_carry_2128/trainer_state.json +0 -0
exp2b/swap_0.7_cost_to_carry_2128/vocab.json +0 -0
exp2b/swap_0.7_cost_to_carry_3591/README.md +148 -0
exp2b/swap_0.7_cost_to_carry_3591/all_results.json +16 -0
exp2b/swap_0.7_cost_to_carry_3591/config.json +31 -0
exp2b/swap_0.7_cost_to_carry_3591/eval_results.json +10 -0
exp2b/swap_0.7_cost_to_carry_3591/generation_config.json +6 -0
exp2b/swap_0.7_cost_to_carry_3591/merges.txt +0 -0
exp2b/swap_0.7_cost_to_carry_3591/special_tokens_map.json +5 -0
exp2b/swap_0.7_cost_to_carry_3591/tokenizer.json +0 -0
exp2b/swap_0.7_cost_to_carry_3591/tokenizer_config.json +20 -0
exp2b/swap_0.7_cost_to_carry_3591/train_results.json +9 -0
exp2b/swap_0.7_cost_to_carry_3591/trainer_state.json +0 -0
exp2b/swap_0.7_cost_to_carry_3591/vocab.json +0 -0
exp2b/swap_0.7_cost_to_carry_40817/README.md +155 -0
exp2b/swap_0.7_cost_to_carry_40817/all_results.json +16 -0
exp2b/swap_0.7_cost_to_carry_40817/config.json +31 -0
exp2b/swap_0.7_cost_to_carry_40817/eval_results.json +10 -0
exp2b/swap_0.7_cost_to_carry_40817/generation_config.json +6 -0
exp2b/swap_0.7_cost_to_carry_40817/merges.txt +0 -0
exp2b/swap_0.7_cost_to_carry_40817/special_tokens_map.json +5 -0
exp2b/swap_0.7_cost_to_carry_40817/tokenizer.json +0 -0
exp2b/swap_0.7_cost_to_carry_40817/tokenizer_config.json +20 -0
exp2b/swap_0.7_cost_to_carry_40817/train_results.json +9 -0
exp2b/swap_0.7_cost_to_carry_40817/trainer_state.json +0 -0
exp2b/swap_0.7_cost_to_carry_40817/vocab.json +0 -0
exp2b/swap_0.7_cost_to_carry_5039/README.md +172 -0
exp2b/swap_0.7_cost_to_carry_5039/all_results.json +16 -0
exp2b/swap_0.7_cost_to_carry_5039/config.json +31 -0
exp2b/swap_0.7_cost_to_carry_5039/eval_results.json +10 -0
exp2b/swap_0.7_cost_to_carry_5039/generation_config.json +6 -0
exp2b/swap_0.7_cost_to_carry_5039/merges.txt +0 -0
exp2b/swap_0.7_cost_to_carry_5039/special_tokens_map.json +5 -0
exp2b/swap_0.7_cost_to_carry_5039/tokenizer.json +0 -0
exp2b/swap_0.7_cost_to_carry_5039/tokenizer_config.json +20 -0
exp2b/swap_0.7_cost_to_carry_5039/train_results.json +9 -0
exp2b/swap_0.7_cost_to_carry_5039/trainer_state.json +0 -0
exp2b/swap_0.7_cost_to_carry_5039/vocab.json +0 -0
exp2b/swap_0.7_cost_to_drop_1032/README.md +148 -0
exp2b/swap_0.7_cost_to_drop_1032/all_results.json +16 -0
exp2b/swap_0.7_cost_to_drop_1032/config.json +31 -0
exp2b/swap_0.7_cost_to_drop_1032/eval_results.json +10 -0
exp2b/swap_0.7_cost_to_drop_1032/generation_config.json +6 -0

exp2b/swap_0.7_cost_to_carry_2128/eval_results.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+    "epoch": 26.830124839575312,
+    "eval_accuracy": 0.3660083672624672,
+    "eval_loss": 3.580906867980957,
+    "eval_runtime": 91.9534,
+    "eval_samples": 16614,
+    "eval_samples_per_second": 180.678,
+    "eval_steps_per_second": 11.299,
+    "perplexity": 35.90608816845173
+}

exp2b/swap_0.7_cost_to_carry_2128/generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.55.2"
+}

exp2b/swap_0.7_cost_to_carry_2128/merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

exp2b/swap_0.7_cost_to_carry_2128/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,5 @@

+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

exp2b/swap_0.7_cost_to_carry_2128/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

exp2b/swap_0.7_cost_to_carry_2128/tokenizer_config.json ADDED Viewed

	@@ -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_0.7_cost_to_carry_2128/train_results.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+    "epoch": 26.830124839575312,
+    "total_flos": 1.9227696758784e+18,
+    "train_loss": 3.418094652424688,
+    "train_runtime": 70665.9395,
+    "train_samples": 274270,
+    "train_samples_per_second": 194.061,
+    "train_steps_per_second": 2.426
+}

exp2b/swap_0.7_cost_to_carry_2128/trainer_state.json ADDED Viewed

The diff for this file is too large to render. See raw diff

exp2b/swap_0.7_cost_to_carry_2128/vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff

exp2b/swap_0.7_cost_to_carry_3591/README.md ADDED Viewed

	@@ -0,0 +1,148 @@

+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: exceptions_exp2_swap_0.7_cost_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/alkuofcx)
+# exceptions_exp2_swap_0.7_cost_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: 3.5624
+- Accuracy: 0.3692
+## 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  | Validation Loss | Accuracy |
+|:-------------:|:-------:|:-----:|:---------------:|:--------:|
+| 4.8362        | 0.2917  | 1000  | 4.7704          | 0.2523   |
+| 4.3333        | 0.5834  | 2000  | 4.2875          | 0.2990   |
+| 4.1454        | 0.8750  | 3000  | 4.1005          | 0.3150   |
+| 3.9922        | 1.1665  | 4000  | 3.9924          | 0.3250   |
+| 3.9385        | 1.4582  | 5000  | 3.9142          | 0.3311   |
+| 3.8819        | 1.7499  | 6000  | 3.8595          | 0.3364   |
+| 3.7528        | 2.0414  | 7000  | 3.8158          | 0.3410   |
+| 3.7629        | 2.3331  | 8000  | 3.7860          | 0.3437   |
+| 3.7428        | 2.6248  | 9000  | 3.7583          | 0.3467   |
+| 3.7208        | 2.9165  | 10000 | 3.7299          | 0.3491   |
+| 3.641         | 3.2080  | 11000 | 3.7165          | 0.3509   |
+| 3.6607        | 3.4996  | 12000 | 3.6995          | 0.3525   |
+| 3.6518        | 3.7913  | 13000 | 3.6806          | 0.3544   |
+| 3.5394        | 4.0828  | 14000 | 3.6759          | 0.3558   |
+| 3.5705        | 4.3745  | 15000 | 3.6644          | 0.3568   |
+| 3.5855        | 4.6662  | 16000 | 3.6487          | 0.3580   |
+| 3.5665        | 4.9579  | 17000 | 3.6365          | 0.3591   |
+| 3.4931        | 5.2494  | 18000 | 3.6386          | 0.3591   |
+| 3.5116        | 5.5411  | 19000 | 3.6291          | 0.3602   |
+| 3.5414        | 5.8327  | 20000 | 3.6186          | 0.3616   |
+| 3.4313        | 6.1243  | 21000 | 3.6188          | 0.3619   |
+| 3.4724        | 6.4159  | 22000 | 3.6149          | 0.3624   |
+| 3.4963        | 6.7076  | 23000 | 3.6043          | 0.3632   |
+| 3.4974        | 6.9993  | 24000 | 3.5945          | 0.3642   |
+| 3.4179        | 7.2908  | 25000 | 3.6033          | 0.3638   |
+| 3.4567        | 7.5825  | 26000 | 3.5936          | 0.3645   |
+| 3.467         | 7.8742  | 27000 | 3.5834          | 0.3654   |
+| 3.3857        | 8.1657  | 28000 | 3.5951          | 0.3652   |
+| 3.4216        | 8.4574  | 29000 | 3.5911          | 0.3659   |
+| 3.4213        | 8.7490  | 30000 | 3.5770          | 0.3661   |
+| 3.3325        | 9.0405  | 31000 | 3.5867          | 0.3664   |
+| 3.3676        | 9.3322  | 32000 | 3.5841          | 0.3667   |
+| 3.4038        | 9.6239  | 33000 | 3.5736          | 0.3670   |
+| 3.4186        | 9.9156  | 34000 | 3.5678          | 0.3678   |
+| 3.337         | 10.2071 | 35000 | 3.5762          | 0.3678   |
+| 3.3811        | 10.4988 | 36000 | 3.5723          | 0.3681   |
+| 3.3902        | 10.7905 | 37000 | 3.5624          | 0.3687   |
+| 3.3075        | 11.0820 | 38000 | 3.5757          | 0.3683   |
+| 3.3411        | 11.3736 | 39000 | 3.5690          | 0.3685   |
+| 3.3692        | 11.6653 | 40000 | 3.5624          | 0.3692   |
+| 3.3714        | 11.9570 | 41000 | 3.5541          | 0.3697   |
+| 3.3147        | 12.2485 | 42000 | 3.5698          | 0.3689   |
+| 3.3397        | 12.5402 | 43000 | 3.5611          | 0.3695   |
+| 3.3481        | 12.8319 | 44000 | 3.5515          | 0.3700   |
+| 3.2629        | 13.1234 | 45000 | 3.5647          | 0.3699   |
+| 3.3151        | 13.4151 | 46000 | 3.5584          | 0.3700   |
+| 3.3393        | 13.7067 | 47000 | 3.5518          | 0.3705   |
+| 3.3506        | 13.9984 | 48000 | 3.5436          | 0.3711   |
+| 3.2836        | 14.2899 | 49000 | 3.5592          | 0.3702   |
+| 3.298         | 14.5816 | 50000 | 3.5521          | 0.3709   |
+| 3.3317        | 14.8733 | 51000 | 3.5435          | 0.3714   |
+| 3.239         | 15.1648 | 52000 | 3.5581          | 0.3710   |
+| 3.2946        | 15.4565 | 53000 | 3.5529          | 0.3711   |
+| 3.3124        | 15.7482 | 54000 | 3.5439          | 0.3718   |
+| 3.2093        | 16.0397 | 55000 | 3.5576          | 0.3711   |
+| 3.2681        | 16.3313 | 56000 | 3.5533          | 0.3714   |
+| 3.2903        | 16.6230 | 57000 | 3.5503          | 0.3715   |
+| 3.3014        | 16.9147 | 58000 | 3.5405          | 0.3724   |
+| 3.24          | 17.2062 | 59000 | 3.5589          | 0.3713   |
+| 3.2514        | 17.4979 | 60000 | 3.5477          | 0.3719   |
+| 3.2784        | 17.7896 | 61000 | 3.5419          | 0.3723   |
+| 3.2041        | 18.0811 | 62000 | 3.5556          | 0.3717   |
+| 3.2305        | 18.3728 | 63000 | 3.5537          | 0.3717   |
+| 3.2568        | 18.6644 | 64000 | 3.5421          | 0.3728   |
+| 3.2728        | 18.9561 | 65000 | 3.5354          | 0.3728   |
+| 3.2181        | 19.2476 | 66000 | 3.5513          | 0.3723   |
+| 3.2551        | 19.5393 | 67000 | 3.5471          | 0.3727   |
+| 3.2648        | 19.8310 | 68000 | 3.5404          | 0.3729   |
+| 3.1942        | 20.1225 | 69000 | 3.5566          | 0.3723   |
+| 3.2332        | 20.4142 | 70000 | 3.5514          | 0.3725   |
+| 3.2465        | 20.7059 | 71000 | 3.5421          | 0.3728   |
+| 3.2544        | 20.9975 | 72000 | 3.5366          | 0.3735   |
+| 3.1997        | 21.2891 | 73000 | 3.5538          | 0.3723   |
+| 3.2355        | 21.5807 | 74000 | 3.5440          | 0.3730   |
+| 3.2517        | 21.8724 | 75000 | 3.5395          | 0.3736   |
+| 3.1723        | 22.1639 | 76000 | 3.5543          | 0.3731   |
+| 3.2094        | 22.4556 | 77000 | 3.5496          | 0.3728   |
+| 3.2334        | 22.7473 | 78000 | 3.5391          | 0.3736   |
+| 3.1535        | 23.0388 | 79000 | 3.5548          | 0.3731   |
+| 3.1955        | 23.3305 | 80000 | 3.5506          | 0.3735   |
+| 3.2168        | 23.6222 | 81000 | 3.5413          | 0.3736   |
+| 3.2321        | 23.9138 | 82000 | 3.5362          | 0.3741   |
+| 3.1636        | 24.2053 | 83000 | 3.5528          | 0.3728   |
+| 3.1834        | 24.4970 | 84000 | 3.5452          | 0.3735   |
+| 3.2204        | 24.7887 | 85000 | 3.5397          | 0.3738   |
+### Framework versions
+- Transformers 4.55.2
+- Pytorch 2.8.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.21.4

exp2b/swap_0.7_cost_to_carry_3591/all_results.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "epoch": 24.788706101971766,
+    "eval_accuracy": 0.3692329601069713,
+    "eval_loss": 3.5623669624328613,
+    "eval_runtime": 87.9649,
+    "eval_samples": 16614,
+    "eval_samples_per_second": 188.871,
+    "eval_steps_per_second": 11.812,
+    "perplexity": 35.24652569063271,
+    "total_flos": 1.7764722671616e+18,
+    "train_loss": 3.4347908989401423,
+    "train_runtime": 63882.8663,
+    "train_samples": 274270,
+    "train_samples_per_second": 214.666,
+    "train_steps_per_second": 2.684
+}

exp2b/swap_0.7_cost_to_carry_3591/config.json ADDED Viewed

	@@ -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_0.7_cost_to_carry_3591/eval_results.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+    "epoch": 24.788706101971766,
+    "eval_accuracy": 0.3692329601069713,
+    "eval_loss": 3.5623669624328613,
+    "eval_runtime": 87.9649,
+    "eval_samples": 16614,
+    "eval_samples_per_second": 188.871,
+    "eval_steps_per_second": 11.812,
+    "perplexity": 35.24652569063271
+}

exp2b/swap_0.7_cost_to_carry_3591/generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.55.2"
+}

exp2b/swap_0.7_cost_to_carry_3591/merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

exp2b/swap_0.7_cost_to_carry_3591/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,5 @@

+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

exp2b/swap_0.7_cost_to_carry_3591/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

exp2b/swap_0.7_cost_to_carry_3591/tokenizer_config.json ADDED Viewed

	@@ -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_0.7_cost_to_carry_3591/train_results.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+    "epoch": 24.788706101971766,
+    "total_flos": 1.7764722671616e+18,
+    "train_loss": 3.4347908989401423,
+    "train_runtime": 63882.8663,
+    "train_samples": 274270,
+    "train_samples_per_second": 214.666,
+    "train_steps_per_second": 2.684
+}

exp2b/swap_0.7_cost_to_carry_3591/trainer_state.json ADDED Viewed

The diff for this file is too large to render. See raw diff

exp2b/swap_0.7_cost_to_carry_3591/vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff

exp2b/swap_0.7_cost_to_carry_40817/README.md ADDED Viewed

	@@ -0,0 +1,155 @@

+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: exceptions_exp2_swap_0.7_cost_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/xssczvke)
+# exceptions_exp2_swap_0.7_cost_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: 3.5678
+- Accuracy: 0.3681
+## 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  | Validation Loss | Accuracy |
+|:-------------:|:-------:|:-----:|:---------------:|:--------:|
+| 4.8301        | 0.2917  | 1000  | 4.7575          | 0.2541   |
+| 4.3486        | 0.5834  | 2000  | 4.2903          | 0.2983   |
+| 4.151         | 0.8750  | 3000  | 4.1045          | 0.3137   |
+| 4.0029        | 1.1665  | 4000  | 3.9993          | 0.3233   |
+| 3.943         | 1.4582  | 5000  | 3.9266          | 0.3307   |
+| 3.8895        | 1.7499  | 6000  | 3.8661          | 0.3358   |
+| 3.7599        | 2.0414  | 7000  | 3.8252          | 0.3397   |
+| 3.7708        | 2.3331  | 8000  | 3.7931          | 0.3431   |
+| 3.7523        | 2.6248  | 9000  | 3.7650          | 0.3459   |
+| 3.7163        | 2.9165  | 10000 | 3.7377          | 0.3483   |
+| 3.6534        | 3.2080  | 11000 | 3.7240          | 0.3504   |
+| 3.6556        | 3.4996  | 12000 | 3.7051          | 0.3519   |
+| 3.6454        | 3.7913  | 13000 | 3.6903          | 0.3537   |
+| 3.5639        | 4.0828  | 14000 | 3.6797          | 0.3546   |
+| 3.5946        | 4.3745  | 15000 | 3.6679          | 0.3560   |
+| 3.5971        | 4.6662  | 16000 | 3.6541          | 0.3571   |
+| 3.5844        | 4.9579  | 17000 | 3.6434          | 0.3583   |
+| 3.5061        | 5.2494  | 18000 | 3.6471          | 0.3588   |
+| 3.5432        | 5.5411  | 19000 | 3.6343          | 0.3598   |
+| 3.5267        | 5.8327  | 20000 | 3.6227          | 0.3607   |
+| 3.4531        | 6.1243  | 21000 | 3.6279          | 0.3610   |
+| 3.4732        | 6.4159  | 22000 | 3.6212          | 0.3616   |
+| 3.5053        | 6.7076  | 23000 | 3.6081          | 0.3624   |
+| 3.4999        | 6.9993  | 24000 | 3.6019          | 0.3634   |
+| 3.4312        | 7.2908  | 25000 | 3.6102          | 0.3633   |
+| 3.4582        | 7.5825  | 26000 | 3.6012          | 0.3638   |
+| 3.4585        | 7.8742  | 27000 | 3.5917          | 0.3647   |
+| 3.3953        | 8.1657  | 28000 | 3.6004          | 0.3646   |
+| 3.4218        | 8.4574  | 29000 | 3.5929          | 0.3651   |
+| 3.4533        | 8.7490  | 30000 | 3.5832          | 0.3658   |
+| 3.3363        | 9.0405  | 31000 | 3.5899          | 0.3659   |
+| 3.3905        | 9.3322  | 32000 | 3.5883          | 0.3658   |
+| 3.418         | 9.6239  | 33000 | 3.5793          | 0.3668   |
+| 3.4051        | 9.9156  | 34000 | 3.5742          | 0.3670   |
+| 3.3435        | 10.2071 | 35000 | 3.5806          | 0.3672   |
+| 3.388         | 10.4988 | 36000 | 3.5767          | 0.3670   |
+| 3.3823        | 10.7905 | 37000 | 3.5710          | 0.3680   |
+| 3.3081        | 11.0820 | 38000 | 3.5791          | 0.3676   |
+| 3.3369        | 11.3736 | 39000 | 3.5739          | 0.3682   |
+| 3.3757        | 11.6653 | 40000 | 3.5678          | 0.3681   |
+| 3.3852        | 11.9570 | 41000 | 3.5594          | 0.3689   |
+| 3.3048        | 12.2485 | 42000 | 3.5723          | 0.3684   |
+| 3.3532        | 12.5402 | 43000 | 3.5644          | 0.3690   |
+| 3.367         | 12.8319 | 44000 | 3.5602          | 0.3691   |
+| 3.2762        | 13.1234 | 45000 | 3.5748          | 0.3687   |
+| 3.3099        | 13.4151 | 46000 | 3.5679          | 0.3690   |
+| 3.3324        | 13.7067 | 47000 | 3.5581          | 0.3696   |
+| 3.3437        | 13.9984 | 48000 | 3.5511          | 0.3702   |
+| 3.2975        | 14.2899 | 49000 | 3.5657          | 0.3695   |
+| 3.3225        | 14.5816 | 50000 | 3.5598          | 0.3702   |
+| 3.3356        | 14.8733 | 51000 | 3.5503          | 0.3707   |
+| 3.2608        | 15.1648 | 52000 | 3.5670          | 0.3697   |
+| 3.2884        | 15.4565 | 53000 | 3.5597          | 0.3700   |
+| 3.3005        | 15.7482 | 54000 | 3.5502          | 0.3707   |
+| 3.2013        | 16.0397 | 55000 | 3.5633          | 0.3706   |
+| 3.2553        | 16.3313 | 56000 | 3.5654          | 0.3705   |
+| 3.2987        | 16.6230 | 57000 | 3.5556          | 0.3709   |
+| 3.3011        | 16.9147 | 58000 | 3.5492          | 0.3716   |
+| 3.2305        | 17.2062 | 59000 | 3.5619          | 0.3706   |
+| 3.2706        | 17.4979 | 60000 | 3.5560          | 0.3711   |
+| 3.2863        | 17.7896 | 61000 | 3.5471          | 0.3716   |
+| 3.205         | 18.0811 | 62000 | 3.5629          | 0.3712   |
+| 3.2492        | 18.3728 | 63000 | 3.5590          | 0.3714   |
+| 3.2735        | 18.6644 | 64000 | 3.5498          | 0.3718   |
+| 3.2878        | 18.9561 | 65000 | 3.5449          | 0.3722   |
+| 3.2248        | 19.2476 | 66000 | 3.5597          | 0.3713   |
+| 3.2494        | 19.5393 | 67000 | 3.5502          | 0.3718   |
+| 3.2803        | 19.8310 | 68000 | 3.5451          | 0.3722   |
+| 3.1923        | 20.1225 | 69000 | 3.5581          | 0.3716   |
+| 3.2183        | 20.4142 | 70000 | 3.5567          | 0.3717   |
+| 3.242         | 20.7059 | 71000 | 3.5510          | 0.3722   |
+| 3.2699        | 20.9975 | 72000 | 3.5392          | 0.3729   |
+| 3.2087        | 21.2891 | 73000 | 3.5543          | 0.3722   |
+| 3.2337        | 21.5807 | 74000 | 3.5495          | 0.3722   |
+| 3.2494        | 21.8724 | 75000 | 3.5426          | 0.3725   |
+| 3.1719        | 22.1639 | 76000 | 3.5594          | 0.3720   |
+| 3.2187        | 22.4556 | 77000 | 3.5540          | 0.3721   |
+| 3.2241        | 22.7473 | 78000 | 3.5453          | 0.3730   |
+| 3.1486        | 23.0388 | 79000 | 3.5574          | 0.3724   |
+| 3.1855        | 23.3305 | 80000 | 3.5552          | 0.3722   |
+| 3.2115        | 23.6222 | 81000 | 3.5485          | 0.3728   |
+| 3.23          | 23.9138 | 82000 | 3.5402          | 0.3733   |
+| 3.1697        | 24.2053 | 83000 | 3.5561          | 0.3726   |
+| 3.1902        | 24.4970 | 84000 | 3.5511          | 0.3728   |
+| 3.2124        | 24.7887 | 85000 | 3.5448          | 0.3734   |
+| 3.1468        | 25.0802 | 86000 | 3.5587          | 0.3726   |
+| 3.1786        | 25.3719 | 87000 | 3.5556          | 0.3728   |
+| 3.1946        | 25.6636 | 88000 | 3.5459          | 0.3734   |
+| 3.2125        | 25.9553 | 89000 | 3.5403          | 0.3737   |
+| 3.1521        | 26.2468 | 90000 | 3.5599          | 0.3728   |
+| 3.1818        | 26.5384 | 91000 | 3.5531          | 0.3729   |
+| 3.1924        | 26.8301 | 92000 | 3.5420          | 0.3739   |
+### Framework versions
+- Transformers 4.55.2
+- Pytorch 2.8.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.21.4

exp2b/swap_0.7_cost_to_carry_40817/all_results.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "epoch": 26.830124839575312,
+    "eval_accuracy": 0.3680858126160075,
+    "eval_loss": 3.567763328552246,
+    "eval_runtime": 90.1222,
+    "eval_samples": 16614,
+    "eval_samples_per_second": 184.35,
+    "eval_steps_per_second": 11.529,
+    "perplexity": 35.43724297502235,
+    "total_flos": 1.9227696758784e+18,
+    "train_loss": 3.4198313907125724,
+    "train_runtime": 69816.4036,
+    "train_samples": 274270,
+    "train_samples_per_second": 196.422,
+    "train_steps_per_second": 2.456
+}

exp2b/swap_0.7_cost_to_carry_40817/config.json ADDED Viewed

	@@ -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_0.7_cost_to_carry_40817/eval_results.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+    "epoch": 26.830124839575312,
+    "eval_accuracy": 0.3680858126160075,
+    "eval_loss": 3.567763328552246,
+    "eval_runtime": 90.1222,
+    "eval_samples": 16614,
+    "eval_samples_per_second": 184.35,
+    "eval_steps_per_second": 11.529,
+    "perplexity": 35.43724297502235
+}

exp2b/swap_0.7_cost_to_carry_40817/generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.55.2"
+}

exp2b/swap_0.7_cost_to_carry_40817/merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

exp2b/swap_0.7_cost_to_carry_40817/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,5 @@

+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

exp2b/swap_0.7_cost_to_carry_40817/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

exp2b/swap_0.7_cost_to_carry_40817/tokenizer_config.json ADDED Viewed

	@@ -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_0.7_cost_to_carry_40817/train_results.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+    "epoch": 26.830124839575312,
+    "total_flos": 1.9227696758784e+18,
+    "train_loss": 3.4198313907125724,
+    "train_runtime": 69816.4036,
+    "train_samples": 274270,
+    "train_samples_per_second": 196.422,
+    "train_steps_per_second": 2.456
+}

exp2b/swap_0.7_cost_to_carry_40817/trainer_state.json ADDED Viewed

The diff for this file is too large to render. See raw diff

exp2b/swap_0.7_cost_to_carry_40817/vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff

exp2b/swap_0.7_cost_to_carry_5039/README.md ADDED Viewed

	@@ -0,0 +1,172 @@

+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: exceptions_exp2_swap_0.7_cost_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/yd74m30q)
+# exceptions_exp2_swap_0.7_cost_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: 3.5813
+- Accuracy: 0.3660
+## 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   | Validation Loss | Accuracy |
+|:-------------:|:-------:|:------:|:---------------:|:--------:|
+| 4.8495        | 0.2917  | 1000   | 4.7681          | 0.2531   |
+| 4.3448        | 0.5834  | 2000   | 4.2971          | 0.2978   |
+| 4.1576        | 0.8750  | 3000   | 4.1055          | 0.3141   |
+| 4.0179        | 1.1665  | 4000   | 4.0037          | 0.3232   |
+| 3.9363        | 1.4582  | 5000   | 3.9245          | 0.3301   |
+| 3.8954        | 1.7499  | 6000   | 3.8654          | 0.3356   |
+| 3.7561        | 2.0414  | 7000   | 3.8211          | 0.3404   |
+| 3.7679        | 2.3331  | 8000   | 3.7919          | 0.3434   |
+| 3.7508        | 2.6248  | 9000   | 3.7634          | 0.3460   |
+| 3.7392        | 2.9165  | 10000  | 3.7330          | 0.3483   |
+| 3.6454        | 3.2080  | 11000  | 3.7238          | 0.3501   |
+| 3.6489        | 3.4996  | 12000  | 3.7063          | 0.3518   |
+| 3.654         | 3.7913  | 13000  | 3.6838          | 0.3539   |
+| 3.5456        | 4.0828  | 14000  | 3.6791          | 0.3552   |
+| 3.5855        | 4.3745  | 15000  | 3.6678          | 0.3561   |
+| 3.5876        | 4.6662  | 16000  | 3.6548          | 0.3573   |
+| 3.5934        | 4.9579  | 17000  | 3.6400          | 0.3587   |
+| 3.5238        | 5.2494  | 18000  | 3.6425          | 0.3591   |
+| 3.5289        | 5.5411  | 19000  | 3.6325          | 0.3603   |
+| 3.5296        | 5.8327  | 20000  | 3.6223          | 0.3610   |
+| 3.4496        | 6.1243  | 21000  | 3.6246          | 0.3614   |
+| 3.4715        | 6.4159  | 22000  | 3.6187          | 0.3620   |
+| 3.5           | 6.7076  | 23000  | 3.6083          | 0.3626   |
+| 3.4973        | 6.9993  | 24000  | 3.5957          | 0.3636   |
+| 3.44          | 7.2908  | 25000  | 3.6067          | 0.3634   |
+| 3.4574        | 7.5825  | 26000  | 3.5990          | 0.3643   |
+| 3.4748        | 7.8742  | 27000  | 3.5894          | 0.3649   |
+| 3.3905        | 8.1657  | 28000  | 3.5968          | 0.3648   |
+| 3.4085        | 8.4574  | 29000  | 3.5889          | 0.3656   |
+| 3.4401        | 8.7490  | 30000  | 3.5813          | 0.3660   |
+| 3.3334        | 9.0405  | 31000  | 3.5882          | 0.3657   |
+| 3.3827        | 9.3322  | 32000  | 3.5863          | 0.3661   |
+| 3.4003        | 9.6239  | 33000  | 3.5744          | 0.3669   |
+| 3.417         | 9.9156  | 34000  | 3.5681          | 0.3674   |
+| 3.3425        | 10.2071 | 35000  | 3.5823          | 0.3671   |
+| 3.389         | 10.4988 | 36000  | 3.5734          | 0.3675   |
+| 3.4016        | 10.7905 | 37000  | 3.5658          | 0.3682   |
+| 3.3073        | 11.0820 | 38000  | 3.5728          | 0.3680   |
+| 3.3501        | 11.3736 | 39000  | 3.5740          | 0.3680   |
+| 3.3746        | 11.6653 | 40000  | 3.5662          | 0.3688   |
+| 3.3773        | 11.9570 | 41000  | 3.5572          | 0.3695   |
+| 3.3141        | 12.2485 | 42000  | 3.5711          | 0.3684   |
+| 3.3499        | 12.5402 | 43000  | 3.5616          | 0.3692   |
+| 3.345         | 12.8319 | 44000  | 3.5553          | 0.3696   |
+| 3.2648        | 13.1234 | 45000  | 3.5678          | 0.3693   |
+| 3.3126        | 13.4151 | 46000  | 3.5607          | 0.3694   |
+| 3.3294        | 13.7067 | 47000  | 3.5539          | 0.3703   |
+| 3.3524        | 13.9984 | 48000  | 3.5477          | 0.3706   |
+| 3.2961        | 14.2899 | 49000  | 3.5666          | 0.3698   |
+| 3.3065        | 14.5816 | 50000  | 3.5565          | 0.3700   |
+| 3.3238        | 14.8733 | 51000  | 3.5494          | 0.3708   |
+| 3.2633        | 15.1648 | 52000  | 3.5653          | 0.3701   |
+| 3.2915        | 15.4565 | 53000  | 3.5572          | 0.3710   |
+| 3.3027        | 15.7482 | 54000  | 3.5493          | 0.3710   |
+| 3.2114        | 16.0397 | 55000  | 3.5605          | 0.3707   |
+| 3.2694        | 16.3313 | 56000  | 3.5598          | 0.3709   |
+| 3.3015        | 16.6230 | 57000  | 3.5504          | 0.3713   |
+| 3.2965        | 16.9147 | 58000  | 3.5434          | 0.3719   |
+| 3.2518        | 17.2062 | 59000  | 3.5610          | 0.3710   |
+| 3.2699        | 17.4979 | 60000  | 3.5537          | 0.3715   |
+| 3.2833        | 17.7896 | 61000  | 3.5451          | 0.3720   |
+| 3.205         | 18.0811 | 62000  | 3.5603          | 0.3713   |
+| 3.2405        | 18.3728 | 63000  | 3.5543          | 0.3716   |
+| 3.2622        | 18.6644 | 64000  | 3.5477          | 0.3721   |
+| 3.2853        | 18.9561 | 65000  | 3.5399          | 0.3728   |
+| 3.2136        | 19.2476 | 66000  | 3.5571          | 0.3717   |
+| 3.2421        | 19.5393 | 67000  | 3.5518          | 0.3718   |
+| 3.247         | 19.8310 | 68000  | 3.5424          | 0.3725   |
+| 3.1915        | 20.1225 | 69000  | 3.5618          | 0.3720   |
+| 3.2315        | 20.4142 | 70000  | 3.5545          | 0.3723   |
+| 3.2387        | 20.7059 | 71000  | 3.5445          | 0.3727   |
+| 3.2681        | 20.9975 | 72000  | 3.5392          | 0.3732   |
+| 3.1985        | 21.2891 | 73000  | 3.5578          | 0.3719   |
+| 3.2263        | 21.5807 | 74000  | 3.5477          | 0.3727   |
+| 3.241         | 21.8724 | 75000  | 3.5404          | 0.3730   |
+| 3.1623        | 22.1639 | 76000  | 3.5533          | 0.3726   |
+| 3.2073        | 22.4556 | 77000  | 3.5501          | 0.3726   |
+| 3.2213        | 22.7473 | 78000  | 3.5449          | 0.3731   |
+| 3.1494        | 23.0388 | 79000  | 3.5543          | 0.3727   |
+| 3.1892        | 23.3305 | 80000  | 3.5524          | 0.3726   |
+| 3.211         | 23.6222 | 81000  | 3.5505          | 0.3730   |
+| 3.2331        | 23.9138 | 82000  | 3.5388          | 0.3735   |
+| 3.1621        | 24.2053 | 83000  | 3.5566          | 0.3725   |
+| 3.2148        | 24.4970 | 84000  | 3.5493          | 0.3731   |
+| 3.206         | 24.7887 | 85000  | 3.5413          | 0.3736   |
+| 3.12          | 25.0802 | 86000  | 3.5574          | 0.3730   |
+| 3.1795        | 25.3719 | 87000  | 3.5528          | 0.3731   |
+| 3.1956        | 25.6636 | 88000  | 3.5424          | 0.3738   |
+| 3.2272        | 25.9553 | 89000  | 3.5368          | 0.3739   |
+| 3.1544        | 26.2468 | 90000  | 3.5519          | 0.3732   |
+| 3.1801        | 26.5384 | 91000  | 3.5500          | 0.3734   |
+| 3.2106        | 26.8301 | 92000  | 3.5401          | 0.3741   |
+| 3.1296        | 27.1216 | 93000  | 3.5584          | 0.3732   |
+| 3.1701        | 27.4133 | 94000  | 3.5518          | 0.3735   |
+| 3.1742        | 27.7050 | 95000  | 3.5419          | 0.3741   |
+| 3.1993        | 27.9967 | 96000  | 3.5368          | 0.3742   |
+| 3.1572        | 28.2882 | 97000  | 3.5559          | 0.3732   |
+| 3.169         | 28.5799 | 98000  | 3.5508          | 0.3736   |
+| 3.189         | 28.8715 | 99000  | 3.5381          | 0.3743   |
+| 3.1151        | 29.1630 | 100000 | 3.5557          | 0.3736   |
+| 3.1515        | 29.4547 | 101000 | 3.5521          | 0.3739   |
+| 3.1737        | 29.7464 | 102000 | 3.5451          | 0.3743   |
+| 3.0872        | 30.0379 | 103000 | 3.5587          | 0.3737   |
+| 3.1245        | 30.3296 | 104000 | 3.5546          | 0.3737   |
+| 3.15          | 30.6213 | 105000 | 3.5496          | 0.3740   |
+| 3.1683        | 30.9130 | 106000 | 3.5438          | 0.3744   |
+| 3.0999        | 31.2045 | 107000 | 3.5577          | 0.3737   |
+| 3.1229        | 31.4961 | 108000 | 3.5498          | 0.3743   |
+| 3.1502        | 31.7878 | 109000 | 3.5434          | 0.3747   |
+### Framework versions
+- Transformers 4.55.2
+- Pytorch 2.8.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.21.4

exp2b/swap_0.7_cost_to_carry_5039/all_results.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "epoch": 31.787831058219577,
+    "eval_accuracy": 0.36600059318562117,
+    "eval_loss": 3.581315517425537,
+    "eval_runtime": 92.554,
+    "eval_samples": 16614,
+    "eval_samples_per_second": 179.506,
+    "eval_steps_per_second": 11.226,
+    "perplexity": 35.920764169904494,
+    "total_flos": 2.2780615163904e+18,
+    "train_loss": 3.3771269543849,
+    "train_runtime": 84364.6883,
+    "train_samples": 274270,
+    "train_samples_per_second": 162.55,
+    "train_steps_per_second": 2.032
+}

exp2b/swap_0.7_cost_to_carry_5039/config.json ADDED Viewed

	@@ -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_0.7_cost_to_carry_5039/eval_results.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+    "epoch": 31.787831058219577,
+    "eval_accuracy": 0.36600059318562117,
+    "eval_loss": 3.581315517425537,
+    "eval_runtime": 92.554,
+    "eval_samples": 16614,
+    "eval_samples_per_second": 179.506,
+    "eval_steps_per_second": 11.226,
+    "perplexity": 35.920764169904494
+}

exp2b/swap_0.7_cost_to_carry_5039/generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.55.2"
+}

exp2b/swap_0.7_cost_to_carry_5039/merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

exp2b/swap_0.7_cost_to_carry_5039/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,5 @@

+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

exp2b/swap_0.7_cost_to_carry_5039/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

exp2b/swap_0.7_cost_to_carry_5039/tokenizer_config.json ADDED Viewed

	@@ -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_0.7_cost_to_carry_5039/train_results.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+    "epoch": 31.787831058219577,
+    "total_flos": 2.2780615163904e+18,
+    "train_loss": 3.3771269543849,
+    "train_runtime": 84364.6883,
+    "train_samples": 274270,
+    "train_samples_per_second": 162.55,
+    "train_steps_per_second": 2.032
+}

exp2b/swap_0.7_cost_to_carry_5039/trainer_state.json ADDED Viewed

The diff for this file is too large to render. See raw diff

exp2b/swap_0.7_cost_to_carry_5039/vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff

exp2b/swap_0.7_cost_to_drop_1032/README.md ADDED Viewed

	@@ -0,0 +1,148 @@

+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: exceptions_exp2_swap_0.7_cost_to_drop_1032
+  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/clg27e2x)
+# exceptions_exp2_swap_0.7_cost_to_drop_1032
+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: 3.5648
+- Accuracy: 0.3685
+## 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: 1032
+- 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  | Validation Loss | Accuracy |
+|:-------------:|:-------:|:-----:|:---------------:|:--------:|
+| 4.8248        | 0.2917  | 1000  | 4.7620          | 0.2540   |
+| 4.3406        | 0.5834  | 2000  | 4.2890          | 0.2984   |
+| 4.1489        | 0.8750  | 3000  | 4.1041          | 0.3145   |
+| 3.9987        | 1.1665  | 4000  | 3.9986          | 0.3235   |
+| 3.9326        | 1.4582  | 5000  | 3.9220          | 0.3305   |
+| 3.8882        | 1.7499  | 6000  | 3.8644          | 0.3361   |
+| 3.7546        | 2.0414  | 7000  | 3.8234          | 0.3396   |
+| 3.764         | 2.3331  | 8000  | 3.7900          | 0.3430   |
+| 3.7419        | 2.6248  | 9000  | 3.7618          | 0.3459   |
+| 3.7225        | 2.9165  | 10000 | 3.7343          | 0.3484   |
+| 3.6388        | 3.2080  | 11000 | 3.7232          | 0.3503   |
+| 3.6638        | 3.4996  | 12000 | 3.7044          | 0.3518   |
+| 3.6478        | 3.7913  | 13000 | 3.6864          | 0.3537   |
+| 3.5579        | 4.0828  | 14000 | 3.6806          | 0.3546   |
+| 3.5815        | 4.3745  | 15000 | 3.6711          | 0.3559   |
+| 3.5842        | 4.6662  | 16000 | 3.6555          | 0.3571   |
+| 3.583         | 4.9579  | 17000 | 3.6432          | 0.3583   |
+| 3.5165        | 5.2494  | 18000 | 3.6462          | 0.3588   |
+| 3.5252        | 5.5411  | 19000 | 3.6340          | 0.3597   |
+| 3.5507        | 5.8327  | 20000 | 3.6241          | 0.3605   |
+| 3.455         | 6.1243  | 21000 | 3.6269          | 0.3610   |
+| 3.4813        | 6.4159  | 22000 | 3.6178          | 0.3621   |
+| 3.5001        | 6.7076  | 23000 | 3.6084          | 0.3628   |
+| 3.5018        | 6.9993  | 24000 | 3.6007          | 0.3634   |
+| 3.4475        | 7.2908  | 25000 | 3.6083          | 0.3633   |
+| 3.4491        | 7.5825  | 26000 | 3.5996          | 0.3640   |
+| 3.4656        | 7.8742  | 27000 | 3.5922          | 0.3645   |
+| 3.4013        | 8.1657  | 28000 | 3.5995          | 0.3646   |
+| 3.4293        | 8.4574  | 29000 | 3.5913          | 0.3653   |
+| 3.4323        | 8.7490  | 30000 | 3.5854          | 0.3655   |
+| 3.3299        | 9.0405  | 31000 | 3.5907          | 0.3657   |
+| 3.3788        | 9.3322  | 32000 | 3.5892          | 0.3659   |
+| 3.4058        | 9.6239  | 33000 | 3.5806          | 0.3664   |
+| 3.4188        | 9.9156  | 34000 | 3.5720          | 0.3670   |
+| 3.3383        | 10.2071 | 35000 | 3.5819          | 0.3668   |
+| 3.3669        | 10.4988 | 36000 | 3.5775          | 0.3675   |
+| 3.3929        | 10.7905 | 37000 | 3.5692          | 0.3677   |
+| 3.3083        | 11.0820 | 38000 | 3.5793          | 0.3676   |
+| 3.3325        | 11.3736 | 39000 | 3.5746          | 0.3677   |
+| 3.3675        | 11.6653 | 40000 | 3.5648          | 0.3685   |
+| 3.3735        | 11.9570 | 41000 | 3.5574          | 0.3689   |
+| 3.3232        | 12.2485 | 42000 | 3.5710          | 0.3686   |
+| 3.3335        | 12.5402 | 43000 | 3.5629          | 0.3691   |
+| 3.3466        | 12.8319 | 44000 | 3.5589          | 0.3695   |
+| 3.2702        | 13.1234 | 45000 | 3.5689          | 0.3688   |
+| 3.3164        | 13.4151 | 46000 | 3.5643          | 0.3691   |
+| 3.3378        | 13.7067 | 47000 | 3.5567          | 0.3697   |
+| 3.3462        | 13.9984 | 48000 | 3.5483          | 0.3703   |
+| 3.2838        | 14.2899 | 49000 | 3.5651          | 0.3695   |
+| 3.3036        | 14.5816 | 50000 | 3.5569          | 0.3702   |
+| 3.3254        | 14.8733 | 51000 | 3.5556          | 0.3701   |
+| 3.2589        | 15.1648 | 52000 | 3.5678          | 0.3697   |
+| 3.2853        | 15.4565 | 53000 | 3.5603          | 0.3703   |
+| 3.3027        | 15.7482 | 54000 | 3.5535          | 0.3703   |
+| 3.2245        | 16.0397 | 55000 | 3.5661          | 0.3702   |
+| 3.2718        | 16.3313 | 56000 | 3.5584          | 0.3705   |
+| 3.2702        | 16.6230 | 57000 | 3.5498          | 0.3710   |
+| 3.3126        | 16.9147 | 58000 | 3.5469          | 0.3714   |
+| 3.2443        | 17.2062 | 59000 | 3.5668          | 0.3704   |
+| 3.2604        | 17.4979 | 60000 | 3.5541          | 0.3712   |
+| 3.2926        | 17.7896 | 61000 | 3.5467          | 0.3717   |
+| 3.1954        | 18.0811 | 62000 | 3.5618          | 0.3709   |
+| 3.2459        | 18.3728 | 63000 | 3.5565          | 0.3714   |
+| 3.2651        | 18.6644 | 64000 | 3.5510          | 0.3715   |
+| 3.2855        | 18.9561 | 65000 | 3.5430          | 0.3721   |
+| 3.2179        | 19.2476 | 66000 | 3.5620          | 0.3711   |
+| 3.2502        | 19.5393 | 67000 | 3.5504          | 0.3718   |
+| 3.2587        | 19.8310 | 68000 | 3.5435          | 0.3722   |
+| 3.1811        | 20.1225 | 69000 | 3.5604          | 0.3715   |
+| 3.227         | 20.4142 | 70000 | 3.5571          | 0.3714   |
+| 3.2613        | 20.7059 | 71000 | 3.5472          | 0.3721   |
+| 3.2561        | 20.9975 | 72000 | 3.5449          | 0.3723   |
+| 3.2074        | 21.2891 | 73000 | 3.5570          | 0.3720   |
+| 3.2265        | 21.5807 | 74000 | 3.5502          | 0.3725   |
+| 3.2463        | 21.8724 | 75000 | 3.5453          | 0.3728   |
+| 3.1738        | 22.1639 | 76000 | 3.5614          | 0.3718   |
+| 3.2158        | 22.4556 | 77000 | 3.5527          | 0.3724   |
+| 3.2276        | 22.7473 | 78000 | 3.5468          | 0.3728   |
+| 3.1475        | 23.0388 | 79000 | 3.5580          | 0.3722   |
+| 3.1835        | 23.3305 | 80000 | 3.5616          | 0.3719   |
+| 3.2186        | 23.6222 | 81000 | 3.5483          | 0.3728   |
+| 3.2286        | 23.9138 | 82000 | 3.5435          | 0.3732   |
+| 3.1577        | 24.2053 | 83000 | 3.5560          | 0.3727   |
+| 3.1893        | 24.4970 | 84000 | 3.5525          | 0.3728   |
+| 3.2137        | 24.7887 | 85000 | 3.5451          | 0.3730   |
+### Framework versions
+- Transformers 4.55.2
+- Pytorch 2.8.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.21.4

exp2b/swap_0.7_cost_to_drop_1032/all_results.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "epoch": 24.788706101971766,
+    "eval_accuracy": 0.36849316246454483,
+    "eval_loss": 3.5647897720336914,
+    "eval_runtime": 88.8396,
+    "eval_samples": 16613,
+    "eval_samples_per_second": 187.0,
+    "eval_steps_per_second": 11.695,
+    "perplexity": 35.332024843733,
+    "total_flos": 1.776459725144064e+18,
+    "train_loss": 3.4370154289694392,
+    "train_runtime": 64367.1276,
+    "train_samples": 274268,
+    "train_samples_per_second": 213.05,
+    "train_steps_per_second": 2.664
+}

exp2b/swap_0.7_cost_to_drop_1032/config.json ADDED Viewed

	@@ -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_0.7_cost_to_drop_1032/eval_results.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+    "epoch": 24.788706101971766,
+    "eval_accuracy": 0.36849316246454483,
+    "eval_loss": 3.5647897720336914,
+    "eval_runtime": 88.8396,
+    "eval_samples": 16613,
+    "eval_samples_per_second": 187.0,
+    "eval_steps_per_second": 11.695,
+    "perplexity": 35.332024843733
+}

exp2b/swap_0.7_cost_to_drop_1032/generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.55.2"
+}