Training in progress, step 20000

README.md

@@ -0,0 +1,111 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+datasets:
+- craa/100M
+metrics:
+- accuracy
+model-index:
+- name: 100M_1208
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: craa/100M
+      type: craa/100M
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.396690747155734
+---
+
+<!-- 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. -->
+
+# 100M_1208
+
+This model is a fine-tuned version of [](https://huggingface.co/) on the craa/100M dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.2743
+- Accuracy: 0.3967
+
+## 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: 16
+- seed: 1208
+- gradient_accumulation_steps: 5
+- total_train_batch_size: 160
+- optimizer: Use OptimizerNames.ADAMW_TORCH 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: 20.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step  | Validation Loss | Accuracy |
+|:-------------:|:-------:|:-----:|:---------------:|:--------:|
+| 21.4151       | 0.5391  | 1000  | 4.1905          | 0.3008   |
+| 19.0701       | 1.0782  | 2000  | 3.7933          | 0.3383   |
+| 18.4085       | 1.6173  | 3000  | 3.6443          | 0.3525   |
+| 17.6787       | 2.1563  | 4000  | 3.5533          | 0.3620   |
+| 17.4852       | 2.6954  | 5000  | 3.4951          | 0.3677   |
+| 16.9959       | 3.2345  | 6000  | 3.4563          | 0.3724   |
+| 16.9895       | 3.7736  | 7000  | 3.4181          | 0.3761   |
+| 16.5971       | 4.3127  | 8000  | 3.3983          | 0.3787   |
+| 16.629        | 4.8518  | 9000  | 3.3727          | 0.3811   |
+| 16.3035       | 5.3908  | 10000 | 3.3641          | 0.3828   |
+| 16.3522       | 5.9299  | 11000 | 3.3433          | 0.3847   |
+| 16.0895       | 6.4690  | 12000 | 3.3392          | 0.3861   |
+| 16.018        | 7.0081  | 13000 | 3.3281          | 0.3871   |
+| 15.9016       | 7.5472  | 14000 | 3.3211          | 0.3884   |
+| 15.5317       | 8.0863  | 15000 | 3.3181          | 0.3892   |
+| 15.7553       | 8.6253  | 16000 | 3.3057          | 0.3900   |
+| 15.4523       | 9.1644  | 17000 | 3.3084          | 0.3906   |
+| 15.6218       | 9.7035  | 18000 | 3.2949          | 0.3917   |
+| 15.3394       | 10.2426 | 19000 | 3.2980          | 0.3922   |
+| 15.4862       | 10.7817 | 20000 | 3.2827          | 0.3931   |
+| 15.2552       | 11.3208 | 21000 | 3.2885          | 0.3931   |
+| 15.3326       | 11.8598 | 22000 | 3.2771          | 0.3942   |
+| 15.2132       | 12.3989 | 23000 | 3.2817          | 0.3941   |
+| 15.2593       | 12.9380 | 24000 | 3.2723          | 0.3952   |
+| 15.1103       | 13.4771 | 25000 | 3.2763          | 0.3952   |
+| 14.9525       | 14.0162 | 26000 | 3.2771          | 0.3955   |
+| 14.987        | 14.5553 | 27000 | 3.2730          | 0.3958   |
+| 14.7762       | 15.0943 | 28000 | 3.2754          | 0.3959   |
+| 14.9004       | 15.6334 | 29000 | 3.2706          | 0.3966   |
+| 14.7148       | 16.1725 | 30000 | 3.2743          | 0.3967   |
+| 14.8087       | 16.7116 | 31000 | 3.2671          | 0.3973   |
+| 14.6624       | 17.2507 | 32000 | 3.2711          | 0.3973   |
+| 14.7309       | 17.7898 | 33000 | 3.2652          | 0.3976   |
+| 14.5986       | 18.3288 | 34000 | 3.2671          | 0.3977   |
+| 14.6162       | 18.8679 | 35000 | 3.2635          | 0.3982   |
+| 14.5047       | 19.4070 | 36000 | 3.2659          | 0.3981   |
+| 14.4926       | 19.9461 | 37000 | 3.2638          | 0.3984   |
+
+
+### Framework versions
+
+- Transformers 4.47.0.dev0
+- Pytorch 2.5.0+cu124
+- Datasets 3.0.2
+- Tokenizers 0.20.1

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 20.0,
+    "eval_accuracy": 0.396690747155734,
+    "eval_loss": 3.2743115425109863,
+    "eval_runtime": 180.7243,
+    "eval_samples": 18012,
+    "eval_samples_per_second": 99.666,
+    "eval_steps_per_second": 6.23,
+    "perplexity": 26.425026709206048,
+    "total_flos": 1.55087795257344e+18,
+    "train_loss": 16.10652202595919,
+    "train_runtime": 128521.0074,
+    "train_samples": 296771,
+    "train_samples_per_second": 46.182,
+    "train_steps_per_second": 0.289
+}

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": "4.47.0.dev0",
+  "use_cache": true,
+  "vocab_size": 52000
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 20.0,
+    "eval_accuracy": 0.396690747155734,
+    "eval_loss": 3.2743115425109863,
+    "eval_runtime": 180.7243,
+    "eval_samples": 18012,
+    "eval_samples_per_second": 99.666,
+    "eval_steps_per_second": 6.23,
+    "perplexity": 26.425026709206048
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.47.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9122d6804ba9f6b16fbabcd91513f0b7722feb3243a3da6217007b8bb6e23261
+size 503128704

special_tokens_map.json

@@ -0,0 +1 @@
+{}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 20.0,
+    "total_flos": 1.55087795257344e+18,
+    "train_loss": 16.10652202595919,
+    "train_runtime": 128521.0074,
+    "train_samples": 296771,
+    "train_samples_per_second": 46.182,
+    "train_steps_per_second": 0.289
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d06f4686862ac63923246cbe2f6d549ac0e43a2b8d4f78e1b061d7db21b96d5
+size 5304