Upload folder using huggingface_hub

checkpoint-300/README.md

@@ -207,4 +207,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 ### Framework versions
 
-- PEFT 0.18.0
+- PEFT 0.16.0

checkpoint-300/adapter_config.json

@@ -1,7 +1,5 @@
 {
-  "alora_invocation_tokens": null,
   "alpha_pattern": {},
-  "arrow_config": null,
   "auto_mapping": {
     "base_model_class": "LlamaForCausalLM",
     "parent_library": "transformers.models.llama.modeling_llama",
@@ -10,7 +8,6 @@
   "base_model_name_or_path": "unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit",
   "bias": "none",
   "corda_config": null,
-  "ensure_weight_tying": false,
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
@@ -27,21 +24,19 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "peft_version": "0.18.0",
   "qalora_group_size": 16,
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "gate_proj",
-    "o_proj",
-    "down_proj",
     "k_proj",
     "up_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj",
     "q_proj"
   ],
-  "target_parameters": null,
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,

checkpoint-300/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa56e0371c6a3c0bced56899aa3c9e69e99409ce83c8f020eced9c75deb7cc10
+oid sha256:f2604df7baf920a70fb10c6143f68b206b08ab224fc92bb6736fefc3ddd487ef
 size 97307544

checkpoint-300/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ed4fb5b3648d3f73a00d8f11507d4538b570b85cb6ce9ef2b429bdfd7a095a4
+oid sha256:d5bc159fdb8990bd9af371d26ef1789da3ee619f8082f691c2900ba22835ea53
 size 194846331

checkpoint-300/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1d565802a8e26c4e8a31328752b7a7fdc186d9401aa008e65697d0ad8c22e33
+oid sha256:716d83e48b4ef0ecc739db256420344d8764b568cd2fec53ea128d8653e43804
 size 14645

checkpoint-300/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63d6a3788c539cdc306259ad5c897c2211e3e753ec371fb98ebdb21093c6b778
+oid sha256:1ff715d3693c4d6f6e799dca640277a75bef436dca0650091795c9950ba66b75
 size 1465

checkpoint-300/trainer_state.json

@@ -2,7 +2,7 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.024,
+  "epoch": 0.048,
   "eval_steps": 500,
   "global_step": 300,
   "is_hyper_param_search": false,
@@ -10,7 +10,7 @@
   "is_world_process_zero": true,
   "log_history": [],
   "logging_steps": 9999999,
-  "max_steps": 12500,
+  "max_steps": 6250,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 150,
@@ -26,8 +26,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.775573797319475e+16,
-  "train_batch_size": 2,
+  "total_flos": 6.827864050910822e+16,
+  "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null
 }

checkpoint-300/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd1e61689e67f92937b424f1859bcd30776e97cdda7fe9a43a40ccef44783eb7
-size 6225
+oid sha256:aa7d60f39157d6af42ddf961454a0f16be99637b24b2dc9dcfdb9f7339f17b36
+size 6161