Training in progress, epoch 2

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,19 @@
+{%- set begin_transcript = "<custom_token_3><|begin_of_text|>" -%}
+
+{%- set end_transcript = "<|eot_id|><custom_token_4>" -%}
+
+{%- set begin_audio = "<custom_token_5><custom_token_1>" -%}
+
+{%- set end_audio = "<custom_token_2><custom_token_6>" -%}
+
+{%- for message in messages -%}
+    {%-   if message.role == 'user' -%}
+        {{- begin_transcript + message['content'] | trim + end_transcript -}}
+    {%- elif message.role == 'assistant' -%}
+        {{- begin_audio + message['content'] | trim + end_audio -}}
+    {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+    {{- begin_audio -}}
+{%- endif -%}

config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128004,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "unsloth_version": "2025.6.2",
+  "use_cache": true,
+  "vocab_size": 156939
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2c503bcf3b6173cadc8b5d5db71c6247993933e5f17b6c02cf10bcf1cf25d65
+size 2589131192

runs/Jun17_17-51-49_io/events.out.tfevents.1750207924.io.1128789.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c78336e469ce912d0cc6e7b6d44a642c31fc5e12ff35eb1d12b8adb02040813d
+size 5171

runs/Jun17_17-53-24_io/events.out.tfevents.1750208019.io.1132037.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:674e236ccebb3cff61d86556ee04974fb5f1292cdade87212716ba983776345d
+size 276897

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:948f905693e9d7f3f7881e01a30299ec92b98999b7c06e1faada462519dc6b5d
+size 22849361

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a96923573b939d012eaf7c8629dbb04fde4447df4593812e4d8a385c23fdfd50
+size 5713