Add checkpoint

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: BABYLM_30000_41
+  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. -->
+
+# BABYLM_30000_41
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.8423
+- Accuracy: 0.3664
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 41
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 10.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 1.1428        | 1.0   | 1020  | 4.3943          | 0.3208   |
+| 1.0267        | 2.0   | 2040  | 4.3414          | 0.3214   |
+| 1.0196        | 3.0   | 3060  | 4.3037          | 0.3261   |
+| 1.0028        | 4.0   | 4080  | 4.2439          | 0.3305   |
+| 0.9826        | 5.0   | 5100  | 4.1674          | 0.3380   |
+| 0.9647        | 6.0   | 6120  | 4.0897          | 0.3450   |
+| 0.9376        | 7.0   | 7140  | 3.9938          | 0.3535   |
+| 0.9117        | 8.0   | 8160  | 3.9159          | 0.3597   |
+| 0.8938        | 9.0   | 9180  | 3.8661          | 0.3645   |
+| 0.8816        | 10.0  | 10200 | 3.8423          | 0.3664   |
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.5.1+cu121
+- Datasets 3.6.0
+- Tokenizers 0.21.1

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.3663948328676292,
+    "eval_loss": 3.842345714569092,
+    "eval_runtime": 725.6789,
+    "eval_samples": 33610,
+    "eval_samples_per_second": 46.315,
+    "eval_steps_per_second": 1.448,
+    "perplexity": 46.63473802350585,
+    "total_flos": 8.525436420096e+16,
+    "train_loss": 0.9743627047071269,
+    "train_runtime": 17661.1762,
+    "train_samples": 32628,
+    "train_samples_per_second": 18.474,
+    "train_steps_per_second": 0.578
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 512,
+  "pad_token_id": 0,
+  "prefix": "<|endoftext|>",
+  "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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 30000
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.3663948328676292,
+    "eval_loss": 3.842345714569092,
+    "eval_runtime": 725.6789,
+    "eval_samples": 33610,
+    "eval_samples_per_second": 46.315,
+    "eval_steps_per_second": 1.448,
+    "perplexity": 46.63473802350585
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba97342d0a3d4381cc10a7170007ea5283a90a99f7788052cf0a65e70f3d4e5
+size 433971840

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<pad>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 8.525436420096e+16,
+    "train_loss": 0.9743627047071269,
+    "train_runtime": 17661.1762,
+    "train_samples": 32628,
+    "train_samples_per_second": 18.474,
+    "train_steps_per_second": 0.578
+}

trainer_state.json

@@ -0,0 +1,203 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 10200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9803921568627451,
+      "grad_norm": 19500.830078125,
+      "learning_rate": 0.0005993999999999999,
+      "loss": 1.1428,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.3207814862667259,
+      "eval_loss": 4.39427375793457,
+      "eval_runtime": 724.8975,
+      "eval_samples_per_second": 46.365,
+      "eval_steps_per_second": 1.45,
+      "step": 1020
+    },
+    {
+      "epoch": 1.9607843137254903,
+      "grad_norm": 34896.4453125,
+      "learning_rate": 0.0005348478260869565,
+      "loss": 1.0267,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.32142458300605947,
+      "eval_loss": 4.34135627746582,
+      "eval_runtime": 725.3947,
+      "eval_samples_per_second": 46.333,
+      "eval_steps_per_second": 1.449,
+      "step": 2040
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 36974.3828125,
+      "learning_rate": 0.00046963043478260864,
+      "loss": 1.0196,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.32609924709063504,
+      "eval_loss": 4.303652286529541,
+      "eval_runtime": 725.0526,
+      "eval_samples_per_second": 46.355,
+      "eval_steps_per_second": 1.45,
+      "step": 3060
+    },
+    {
+      "epoch": 3.9215686274509802,
+      "grad_norm": 24522.501953125,
+      "learning_rate": 0.0004044130434782608,
+      "loss": 1.0028,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.33053349954671724,
+      "eval_loss": 4.243885517120361,
+      "eval_runtime": 724.6953,
+      "eval_samples_per_second": 46.378,
+      "eval_steps_per_second": 1.45,
+      "step": 4080
+    },
+    {
+      "epoch": 4.901960784313726,
+      "grad_norm": 42106.47265625,
+      "learning_rate": 0.000339195652173913,
+      "loss": 0.9826,
+      "step": 5000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.33797758448323145,
+      "eval_loss": 4.16740083694458,
+      "eval_runtime": 724.9419,
+      "eval_samples_per_second": 46.362,
+      "eval_steps_per_second": 1.45,
+      "step": 5100
+    },
+    {
+      "epoch": 5.882352941176471,
+      "grad_norm": 14265.330078125,
+      "learning_rate": 0.0002739782608695652,
+      "loss": 0.9647,
+      "step": 6000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.3449917349405026,
+      "eval_loss": 4.089650630950928,
+      "eval_runtime": 725.2922,
+      "eval_samples_per_second": 46.34,
+      "eval_steps_per_second": 1.449,
+      "step": 6120
+    },
+    {
+      "epoch": 6.862745098039216,
+      "grad_norm": 9816.4091796875,
+      "learning_rate": 0.00020876086956521736,
+      "loss": 0.9376,
+      "step": 7000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.3534573218412422,
+      "eval_loss": 3.99379825592041,
+      "eval_runtime": 725.1507,
+      "eval_samples_per_second": 46.349,
+      "eval_steps_per_second": 1.449,
+      "step": 7140
+    },
+    {
+      "epoch": 7.8431372549019605,
+      "grad_norm": 8245.6923828125,
+      "learning_rate": 0.00014354347826086956,
+      "loss": 0.9117,
+      "step": 8000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.3596525938429237,
+      "eval_loss": 3.915853261947632,
+      "eval_runtime": 725.91,
+      "eval_samples_per_second": 46.301,
+      "eval_steps_per_second": 1.448,
+      "step": 8160
+    },
+    {
+      "epoch": 8.823529411764707,
+      "grad_norm": 7736.12646484375,
+      "learning_rate": 7.832608695652173e-05,
+      "loss": 0.8938,
+      "step": 9000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.3645499108864138,
+      "eval_loss": 3.866149663925171,
+      "eval_runtime": 724.9064,
+      "eval_samples_per_second": 46.365,
+      "eval_steps_per_second": 1.45,
+      "step": 9180
+    },
+    {
+      "epoch": 9.803921568627452,
+      "grad_norm": 7472.7890625,
+      "learning_rate": 1.3108695652173912e-05,
+      "loss": 0.8816,
+      "step": 10000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.3663948328676292,
+      "eval_loss": 3.842345714569092,
+      "eval_runtime": 725.2736,
+      "eval_samples_per_second": 46.341,
+      "eval_steps_per_second": 1.449,
+      "step": 10200
+    },
+    {
+      "epoch": 10.0,
+      "step": 10200,
+      "total_flos": 8.525436420096e+16,
+      "train_loss": 0.9743627047071269,
+      "train_runtime": 17661.1762,
+      "train_samples_per_second": 18.474,
+      "train_steps_per_second": 0.578
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 10200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.525436420096e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d36d6ca851480246cac8a7744a3b4917394dd9e5af29a7d07d8932941e1a1948
+size 5304