End of training

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: google/gemma-3-1b-it
+base_model: google/gemma-3-270m-it
 library_name: transformers
 model_name: commentworks_os
 tags:
@@ -11,7 +11,7 @@ licence: license
 
 # Model Card for commentworks_os
 
-This model is a fine-tuned version of [google/gemma-3-1b-it](https://huggingface.co/google/gemma-3-1b-it).
+This model is a fine-tuned version of [google/gemma-3-270m-it](https://huggingface.co/google/gemma-3-270m-it).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

config.json

@@ -7,15 +7,14 @@
   "attention_dropout": 0.0,
   "attn_logit_softcapping": null,
   "bos_token_id": 2,
-  "cache_implementation": "hybrid",
   "dtype": "bfloat16",
   "eos_token_id": 1,
   "final_logit_softcapping": null,
   "head_dim": 256,
   "hidden_activation": "gelu_pytorch_tanh",
-  "hidden_size": 1152,
+  "hidden_size": 640,
   "initializer_range": 0.02,
-  "intermediate_size": 6912,
+  "intermediate_size": 2048,
   "layer_types": [
     "sliding_attention",
     "sliding_attention",
@@ -34,29 +33,20 @@
     "sliding_attention",
     "sliding_attention",
     "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "sliding_attention"
+    "full_attention"
   ],
   "max_position_embeddings": 32768,
   "model_type": "gemma3_text",
   "num_attention_heads": 4,
-  "num_hidden_layers": 26,
+  "num_hidden_layers": 18,
   "num_key_value_heads": 1,
   "pad_token_id": 0,
   "query_pre_attn_scalar": 256,
   "rms_norm_eps": 1e-06,
-  "rope_local_base_freq": 10000,
+  "rope_local_base_freq": 10000.0,
   "rope_scaling": null,
-  "rope_theta": 1000000,
+  "rope_theta": 1000000.0,
   "sliding_window": 512,
-  "sliding_window_pattern": 6,
   "transformers_version": "4.57.1",
   "use_bidirectional_attention": false,
   "use_cache": true,

generation_config.json

@@ -3,7 +3,6 @@
   "cache_implementation": "hybrid",
   "do_sample": true,
   "eos_token_id": [
-    1,
     1,
     106
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bd907b40e126136bfb72731709522efaae3335d96fd4488e7a17320f70bdced
-size 1999811208
+oid sha256:d22a5fda363e2087699d40ef4259a518fabe3168c04ce4931073675a34adff3a
+size 536223056

runs/Oct26_02-12-31_79dba74626d8/events.out.tfevents.1761444767.79dba74626d8.496.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e2963cbb8ad82c5abe775f98f3ac700a84fa576353193bbec28ec50a8947e0a
+size 30754

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9155b08d3846f0c02b81aed67f863522aac463a5e89b284262853f50b43d1058
+oid sha256:ed67c3b356aedb7e213c0d032bab58ba543aa33eba80d5c03b37b9080f939ab1
 size 6289