Training in progress, epoch 0

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bd832ceed0dda34061a7cedfbc184cfcd0c375b99183a2879e678f1f1395531
+oid sha256:edc22c267e7aa37bf6b7f9f4ef954d618ffe3dbe3264e5fbb821a765f1f96896
 size 1329119768

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/gemma-2-2b",
+  "_name_or_path": "google/gemma-2-2b-jpn-it",
   "architectures": [
     "Gemma2ForCausalLM"
   ],
@@ -8,10 +8,10 @@
   "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,
-  "hidden_act": "gelu_pytorch_tanh",
   "hidden_activation": "gelu_pytorch_tanh",
   "hidden_size": 2304,
   "initializer_range": 0.02,
@@ -22,12 +22,12 @@
   "num_hidden_layers": 26,
   "num_key_value_heads": 4,
   "pad_token_id": 0,
-  "query_pre_attn_scalar": 256,
+  "query_pre_attn_scalar": 224,
   "rms_norm_eps": 1e-06,
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "torch_dtype": "float16",
   "transformers_version": "4.46.2",
   "use_cache": true,
-  "vocab_size": 256002
+  "vocab_size": 256000
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd2916eed3aed1261e5f4fc4d5d86eb1d417dc6da16471bd36b250a788a1ab7a
-size 1986635568
+oid sha256:715e0b9d67c1e6fa832ac095772048eb72aba5aaae4f42f01256329657962d74
+size 1986626352

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ad23210a25dfc369a9e23d7c3bd4323ac965f8b22c7f6e38d2bc2e19c32c3c1
+oid sha256:fedb437118c3e5fdc799378195e2eb0108132da003e47b459cf9dc7b9ba43fe5
 size 1996220064

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbc1e84fa7a26daffd4c6432eb4c03836e42b5404b345deeb429a74278d68d59
+oid sha256:95010c90fc1c0461c80f893bcdcf906f2370bdbab0f4f032f364c4391799d5a2
 size 1245870584

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 5228692992
+    "total_size": 5228683776
   },
   "weight_map": {
     "model.embed_tokens.weight": "model-00001-of-00003.safetensors",

runs/Nov13_09-50-23_ba51c2ee83f1/events.out.tfevents.1731491462.ba51c2ee83f1.114.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:465642ddbe0d10f75feb536e09e61d63ce424b940c8755984221af279386320b
+size 17809

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:016032967fbf27c359174fb43657e6226cb94d838aec135d4ce046f241b91737
+oid sha256:8eddf5a5e18c8b308dca83202131aecd0e7249f83fe65af629d408140efe64d8
 size 5624