Model save

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 3.3658
+- Loss: 3.1637
 
 ## Model description
 
@@ -41,16 +41,17 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
 - num_epochs: 5
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 493  | 3.6997          |
-| No log        | 2.0   | 986  | 3.4864          |
-| No log        | 3.0   | 1479 | 3.4203          |
-| No log        | 4.0   | 1972 | 3.3822          |
-| No log        | 5.0   | 2465 | 3.3658          |
+| 4.5769        | 1.0   | 503  | 3.5197          |
+| 3.322         | 2.0   | 1006 | 3.3003          |
+| 3.1705        | 3.0   | 1509 | 3.2238          |
+| 3.0902        | 4.0   | 2012 | 3.1822          |
+| 3.0374        | 5.0   | 2515 | 3.1637          |
 
 
 ### Framework versions

check-2510/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "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": 1024,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 30000
+}

check-2510/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

check-2510/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2651707f45ca6facea4d549e33f84da29e7b2ea1c293b3ceab792bff7ed03f91
+size 435544704

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8717aa21b0740749a4e61786e986144b808551ae45a1f7bb92d83176fd8b0ba8
+oid sha256:2651707f45ca6facea4d549e33f84da29e7b2ea1c293b3ceab792bff7ed03f91
 size 435544704