Training in progress, step 1000

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "yosefw/llama-3.2-amharic-32k-1024-v4",
+  "_name_or_path": "yosefw/llama-3.2-amharic-32k-1024-v4-instruct-bs8-256",
   "architectures": [
     "LlamaForCausalLM"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0bc3e57896c63c64c61fa9107de587134e8ed2dffe0173ce9b83f3650a2cfa7
+oid sha256:f6325ee6051bb3b8b9506af0daa84a4fc069dff1142ebe88b0b91dfb475be306
 size 1604485320

runs/Nov22_23-47-22_041318d400e7/events.out.tfevents.1732319476.041318d400e7.23.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd9990e6a5d6f059e2e5dbce42e546e027ee09e84351b03b697feb5055c4376c
+size 6442

special_tokens_map.json

@@ -1,21 +1,27 @@
 {
   "additional_special_tokens": [
-    {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
+    "<|im_start|>",
+    "<|im_end|>"
   ],
-  "bos_token": "<|im_start|>",
-  "eos_token": "<|im_end|>",
-  "pad_token": "<|im_end|>"
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 256,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -2073,11 +2073,15 @@
   "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|im_end|>",
+  "max_length": 256,
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 1024,
   "pad_token": "<|im_end|>",
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "stride": 0,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7700d7638f7b9f1f50c337f0993420ea676945e041866cc8c10891357b09885c
+oid sha256:bc2157e127ca7ff07022d87e76e684fac159a5378e7fd41d592b30f6e2cec6e4
 size 5624