Add checkpoint

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: BABYLM_20000_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_20000_41
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.8891
+- Accuracy: 0.3569
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 1.1382        | 1.0   | 1035  | 4.3726          | 0.3182   |
+| 1.0291        | 2.0   | 2070  | 4.3597          | 0.3146   |
+| 1.0267        | 3.0   | 3105  | 4.3334          | 0.3179   |
+| 1.0192        | 4.0   | 4140  | 4.2829          | 0.3216   |
+| 1.0042        | 5.0   | 5175  | 4.2311          | 0.3267   |
+| 0.9873        | 6.0   | 6210  | 4.1560          | 0.3320   |
+| 0.9662        | 7.0   | 7245  | 4.0627          | 0.3410   |
+| 0.9422        | 8.0   | 8280  | 3.9768          | 0.3493   |
+| 0.9207        | 9.0   | 9315  | 3.9174          | 0.3542   |
+| 0.9058        | 10.0  | 10350 | 3.8891          | 0.3569   |
+
+
+### 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": 0.3569124320159682,
+    "eval_loss": 3.889129400253296,
+    "eval_runtime": 664.2068,
+    "eval_samples": 34056,
+    "eval_samples_per_second": 51.273,
+    "eval_steps_per_second": 1.603,
+    "perplexity": 48.86832324878982,
+    "total_flos": 8.6487662592e+16,
+    "train_loss": 0.990625182810613,
+    "train_runtime": 16693.5239,
+    "train_samples": 33100,
+    "train_samples_per_second": 19.828,
+    "train_steps_per_second": 0.62
+}

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": 20000
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.3569124320159682,
+    "eval_loss": 3.889129400253296,
+    "eval_runtime": 664.2068,
+    "eval_samples": 34056,
+    "eval_samples_per_second": 51.273,
+    "eval_steps_per_second": 1.603,
+    "perplexity": 48.86832324878982
+}

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 sha256:1a7a8efc94369da74f6cf446c454224b95d15e69dcb6dda4d0a731f1b6449423
+size 403251840

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": 8.6487662592e+16,
+    "train_loss": 0.990625182810613,
+    "train_runtime": 16693.5239,
+    "train_samples": 33100,
+    "train_samples_per_second": 19.828,
+    "train_steps_per_second": 0.62
+}

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": 10350,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.966183574879227,
+      "grad_norm": 18068.357421875,
+      "learning_rate": 0.0005993999999999999,
+      "loss": 1.1382,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.31820882561564307,
+      "eval_loss": 4.372585296630859,
+      "eval_runtime": 671.6885,
+      "eval_samples_per_second": 50.702,
+      "eval_steps_per_second": 1.586,
+      "step": 1035
+    },
+    {
+      "epoch": 1.9323671497584543,
+      "grad_norm": 48934.1015625,
+      "learning_rate": 0.0005358930481283422,
+      "loss": 1.0291,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.31461109065441656,
+      "eval_loss": 4.359684944152832,
+      "eval_runtime": 666.115,
+      "eval_samples_per_second": 51.126,
+      "eval_steps_per_second": 1.599,
+      "step": 2070
+    },
+    {
+      "epoch": 2.898550724637681,
+      "grad_norm": 52002.11328125,
+      "learning_rate": 0.00047172192513368985,
+      "loss": 1.0267,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.31789266625201634,
+      "eval_loss": 4.333441257476807,
+      "eval_runtime": 665.863,
+      "eval_samples_per_second": 51.146,
+      "eval_steps_per_second": 1.599,
+      "step": 3105
+    },
+    {
+      "epoch": 3.864734299516908,
+      "grad_norm": 55701.2734375,
+      "learning_rate": 0.0004075508021390374,
+      "loss": 1.0192,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.3215952705041587,
+      "eval_loss": 4.2829365730285645,
+      "eval_runtime": 664.6956,
+      "eval_samples_per_second": 51.235,
+      "eval_steps_per_second": 1.602,
+      "step": 4140
+    },
+    {
+      "epoch": 4.830917874396135,
+      "grad_norm": 83004.7734375,
+      "learning_rate": 0.000343379679144385,
+      "loss": 1.0042,
+      "step": 5000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.32670145683844315,
+      "eval_loss": 4.2311296463012695,
+      "eval_runtime": 664.7858,
+      "eval_samples_per_second": 51.229,
+      "eval_steps_per_second": 1.602,
+      "step": 5175
+    },
+    {
+      "epoch": 5.797101449275362,
+      "grad_norm": 21215.708984375,
+      "learning_rate": 0.0002792085561497326,
+      "loss": 0.9873,
+      "step": 6000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.33200261385989327,
+      "eval_loss": 4.1559600830078125,
+      "eval_runtime": 666.0654,
+      "eval_samples_per_second": 51.13,
+      "eval_steps_per_second": 1.599,
+      "step": 6210
+    },
+    {
+      "epoch": 6.763285024154589,
+      "grad_norm": 18555.8984375,
+      "learning_rate": 0.0002150374331550802,
+      "loss": 0.9662,
+      "step": 7000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.34101654601813886,
+      "eval_loss": 4.062748908996582,
+      "eval_runtime": 665.7453,
+      "eval_samples_per_second": 51.155,
+      "eval_steps_per_second": 1.6,
+      "step": 7245
+    },
+    {
+      "epoch": 7.729468599033816,
+      "grad_norm": 10123.9931640625,
+      "learning_rate": 0.0001508663101604278,
+      "loss": 0.9422,
+      "step": 8000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.34926088123762544,
+      "eval_loss": 3.976839542388916,
+      "eval_runtime": 665.8149,
+      "eval_samples_per_second": 51.149,
+      "eval_steps_per_second": 1.6,
+      "step": 8280
+    },
+    {
+      "epoch": 8.695652173913043,
+      "grad_norm": 8124.27392578125,
+      "learning_rate": 8.66951871657754e-05,
+      "loss": 0.9207,
+      "step": 9000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.3541727864362461,
+      "eval_loss": 3.9173777103424072,
+      "eval_runtime": 665.3441,
+      "eval_samples_per_second": 51.186,
+      "eval_steps_per_second": 1.601,
+      "step": 9315
+    },
+    {
+      "epoch": 9.66183574879227,
+      "grad_norm": 7507.09521484375,
+      "learning_rate": 2.252406417112299e-05,
+      "loss": 0.9058,
+      "step": 10000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.3569124320159682,
+      "eval_loss": 3.889129400253296,
+      "eval_runtime": 665.1197,
+      "eval_samples_per_second": 51.203,
+      "eval_steps_per_second": 1.601,
+      "step": 10350
+    },
+    {
+      "epoch": 10.0,
+      "step": 10350,
+      "total_flos": 8.6487662592e+16,
+      "train_loss": 0.990625182810613,
+      "train_runtime": 16693.5239,
+      "train_samples_per_second": 19.828,
+      "train_steps_per_second": 0.62
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 10350,
+  "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": 8.6487662592e+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 sha256:123926261311a364c333adcd5e20a2073e9b0d35759b0cbdc8d78c2f40b99afe
+size 5304