Training in progress, step 100, checkpoint

last-checkpoint/README.md

@@ -199,4 +199,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 ### Framework versions
 
-- PEFT 0.13.0
+- PEFT 0.14.0

last-checkpoint/adapter_config.json

@@ -3,6 +3,8 @@
   "auto_mapping": null,
   "base_model_name_or_path": "unsloth/Llama-3.2-1B-Instruct-bnb-4bit",
   "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -11,6 +13,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 16,
+  "lora_bias": false,
   "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "up_proj",
     "v_proj",
-    "gate_proj",
+    "up_proj",
+    "down_proj",
     "q_proj",
     "k_proj",
-    "down_proj"
+    "gate_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e360210c7fe6bc9c91e079ae013f535381a6a13f5485dae05bd22c5d7e5f393
+oid sha256:a92839096cdccaad56ee91ea5f7994c6be6ba9d33a99134e5ed273129ef18ef0
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2e1b5838cd931aa02079ffe7f652864e12610c4e917f3e31958ce7debf53515
+oid sha256:f9402c026f3d7e964601394b7516d2092189b94d8b08e5b09f4062426fb8e7bb
 size 23159290

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bc5c637ed138ad6c1b0f857643b0f621a7e8c72bf01723b5254644a04aa9b48
+oid sha256:2e0bfbbe2be6a1399a4c175bf33e1a680e875704102055b2bbfcb74670a4c677
 size 1064

last-checkpoint/trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00303342838075593,
+  "epoch": 0.07417022065640645,
   "eval_steps": 500,
   "global_step": 100,
   "is_hyper_param_search": false,
@@ -9,15 +9,15 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.00303342838075593,
-      "grad_norm": 3.9159162044525146,
-      "learning_rate": 0.002,
-      "loss": 3.4799,
+      "epoch": 0.07417022065640645,
+      "grad_norm": 1.151120901107788,
+      "learning_rate": 0.0002,
+      "loss": 3.5121,
       "step": 100
     }
   ],
   "logging_steps": 100,
-  "max_steps": 32966,
+  "max_steps": 1348,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 100,
@@ -33,7 +33,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7833024320274432.0,
+  "total_flos": 3.87089027825664e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6fb6b6e3adc261d0a7885521544cee5190193ba91f162fdd596a9773bd61697
+oid sha256:e21f2a882f703e54677b6d29c5166af27a38da370fe6b9685b41d457c46a3d9d
 size 5688