Training in progress, step 50

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6fb2c47944fd2f4753270ee8c6d1227502fbbae8e6e3288d2bf4ea334ad6b88
+size 228150120

config.json

@@ -1,37 +1,29 @@
 {
+  "_attn_implementation_autoset": true,
   "architectures": [
-    "LlamaForCausalLM"
+    "MistralForCausalLM"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "eos_token_id": 128009,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "head_dim": 128,
   "hidden_act": "silu",
-  "hidden_size": 4096,
+  "hidden_size": 5120,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
   "max_position_embeddings": 131072,
-  "mlp_bias": false,
-  "model_type": "llama",
+  "model_type": "mistral",
   "num_attention_heads": 32,
-  "num_hidden_layers": 32,
+  "num_hidden_layers": 40,
   "num_key_value_heads": 8,
-  "pad_token_id": 128004,
-  "pretraining_tp": 1,
+  "pad_token_id": 10,
   "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 8.0,
-    "high_freq_factor": 4.0,
-    "low_freq_factor": 1.0,
-    "original_max_position_embeddings": 8192,
-    "rope_type": "llama3"
-  },
-  "rope_theta": 500000.0,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.51.3",
   "unsloth_fixed": true,
   "use_cache": false,
-  "vocab_size": 128256
+  "vocab_size": 131072
 }

runs/May14_10-03-19_ebc80799ced7/events.out.tfevents.1747217007.ebc80799ced7.317.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:040694dfe09a955942032e0894affd5eba6190e9ea0cf3199e4e584ea2ddb549
+size 95184

special_tokens_map.json

@@ -1,20 +1,27 @@
 {
   "bos_token": {
-    "content": "<|begin_of_text|>",
+    "content": "<s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|eot_id|>",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<|finetune_right_pad_id|>",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a65c6c5f9764771aa485e6a1f5e63d7d9af8477fe0777148c17476ecb2e09a05
-size 17210099
+oid sha256:8bf3b3d6214dce22c2aa088e17fd3d059bb7069b0b1c8098ace2867d4b96b20a
+size 17078447

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff6285bdabe274e5aeca6214ff1535bead1951e6928a03913d8d6340a406062f
+oid sha256:226b438e87695b85d63c151ba818b85c53ddf1a754680309eee987646ce50f52
 size 7864