End of training

README.md

@@ -1,5 +1,4 @@
 ---
-library_name: transformers
 license: gemma
 base_model: google/gemma-2-2b
 tags:
@@ -18,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/gemma-2-2b](https://huggingface.co/google/gemma-2-2b) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6828
-- Num Input Tokens Seen: 5070660
+- Loss: 1.6314
+- Num Input Tokens Seen: 4852992
 
 ## Model description
 
@@ -44,21 +43,38 @@ The following hyperparameters were used during training:
 - seed: 0
 - gradient_accumulation_steps: 16
 - total_train_batch_size: 128
-- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant_with_warmup
 - lr_scheduler_warmup_ratio: 0.05
 - num_epochs: 1
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
-|:-------------:|:-----:|:----:|:---------------:|:-----------------:|
-| No log        | 0     | 0    | 1.3864          | 0                 |
+| Training Loss | Epoch  | Step | Validation Loss | Input Tokens Seen |
+|:-------------:|:------:|:----:|:---------------:|:-----------------:|
+| No log        | 0      | 0    | 1.3911          | 0                 |
+| 1.5169        | 0.0579 | 5    | 1.2663          | 285536            |
+| 1.3736        | 0.1158 | 10   | 1.1918          | 567456            |
+| 1.1135        | 0.1737 | 15   | 1.2205          | 844248            |
+| 0.8215        | 0.2315 | 20   | 1.2889          | 1125792           |
+| 0.7           | 0.2894 | 25   | 1.3912          | 1408488           |
+| 0.4534        | 0.3473 | 30   | 1.4630          | 1691120           |
+| 0.4168        | 0.4052 | 35   | 1.5283          | 1974504           |
+| 0.3295        | 0.4631 | 40   | 1.5404          | 2257232           |
+| 0.1989        | 0.5210 | 45   | 1.4892          | 2538768           |
+| 0.2135        | 0.5789 | 50   | 1.5781          | 2821752           |
+| 0.1784        | 0.6368 | 55   | 1.4920          | 3105616           |
+| 0.1314        | 0.6946 | 60   | 1.5251          | 3381944           |
+| 0.1645        | 0.7525 | 65   | 1.5864          | 3666096           |
+| 0.0937        | 0.8104 | 70   | 1.4925          | 3946448           |
+| 0.1406        | 0.8683 | 75   | 1.5310          | 4234720           |
+| 0.1477        | 0.9262 | 80   | 1.5799          | 4512080           |
+| 0.0654        | 0.9841 | 85   | 1.6488          | 4796248           |
 
 
 ### Framework versions
 
-- Transformers 4.57.3
-- Pytorch 2.8.0+cu128
+- Transformers 4.44.0
+- Pytorch 2.4.0+cu121
 - Datasets 2.20.0
-- Tokenizers 0.22.2
+- Tokenizers 0.19.1

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "google/gemma-2-2b",
   "architectures": [
     "Gemma2ForCausalLM"
   ],
@@ -7,7 +8,6 @@
   "attn_logit_softcapping": 50.0,
   "bos_token_id": 2,
   "cache_implementation": "hybrid",
-  "dtype": "bfloat16",
   "eos_token_id": 1,
   "final_logit_softcapping": 30.0,
   "head_dim": 256,
@@ -16,34 +16,6 @@
   "hidden_size": 2304,
   "initializer_range": 0.02,
   "intermediate_size": 9216,
-  "layer_types": [
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention"
-  ],
   "max_position_embeddings": 8192,
   "model_type": "gemma2",
   "num_attention_heads": 8,
@@ -54,7 +26,8 @@
   "rms_norm_eps": 1e-06,
   "rope_theta": 10000.0,
   "sliding_window": 4096,
-  "transformers_version": "4.57.3",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0",
   "use_cache": true,
   "vocab_size": 256000
 }

generation_config.json

@@ -2,9 +2,7 @@
   "_from_model_config": true,
   "bos_token_id": 2,
   "cache_implementation": "hybrid",
-  "eos_token_id": [
-    1
-  ],
+  "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.57.3"
+  "transformers_version": "4.44.0"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a707b35e51fe72361d4faa2c45c0e3078adea49e94af6fbfdf0af57f4bc431c
+oid sha256:0ebdabc4e2a36de76df046e3f24338397f229eaa5ff99a891004842cfb25b48f
 size 4988025760

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f9a539be5a716cfee5a5e3f3d2c79d90643158fbb6f538c7f373106b6ed5462
+oid sha256:3ce7eef45ce40e6fa759e436b51a5d8a76d238d32fdeba8b7028ddde073c530f
 size 240691728

model.safetensors.index.json

@@ -1,6 +1,5 @@
 {
   "metadata": {
-    "total_parameters": 2614341888,
     "total_size": 5228683776
   },
   "weight_map": {

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
-size 34362873
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357

tokenizer_config.json

@@ -2002,7 +2002,6 @@
   "bos_token": "<bos>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<eos>",
-  "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "sp_model_kwargs": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f03556477a2b0b57f743d385d30da7ccea834ad244b2acff4ffde53f3b7b817b
-size 6225
+oid sha256:0d3b740889feecfbadcf41816b09816d287b510cc35c4cfa56f63da5a4b06d48
+size 5624