Training in progress, step 114, checkpoint

last-checkpoint/README.md

@@ -1,5 +1,5 @@
 ---
-base_model: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
+base_model: unsloth/llama-3.2-3b-instruct-bnb-4bit
 library_name: peft
 ---
 

last-checkpoint/adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit",
+  "base_model_name_or_path": "unsloth/llama-3.2-3b-instruct-bnb-4bit",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -25,11 +25,11 @@
   "target_modules": [
     "gate_proj",
     "down_proj",
-    "o_proj",
-    "v_proj",
+    "up_proj",
     "q_proj",
     "k_proj",
-    "up_proj"
+    "v_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 sha256:674201cda7990812ad89a0ac22c31df0b82d264ffcdd8a5bdb1dd62baf293d81
+oid sha256:f6aec35e09ff7cf30637b3f962aa52b1697faf4ad3cca422cec1820c7f5b65cd
 size 389074464

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93975c5b076ce7d294a4f8acb8ef330cf5533dda15b666fec59a388f8c4aa1a9
-size 198011700
+oid sha256:f0d3fd82d9118f258b6b2d10b83e40e4c1cce05da4ab9333b5f51df337b36958
+size 198011252

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:336ad624cfb7adf5821759ee06496a34d9d2a658dd99d3dbdda29b76da15094d
+oid sha256:dd934acdab29b3dbe7dec7ebf9aa0c7d670bf9c37b6ec1d10cfdea1e691d24f3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,124 +1,26 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
+  "epoch": 0.09982486865148861,
   "eval_steps": 500,
-  "global_step": 1569,
+  "global_step": 114,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.19120458891013384,
-      "grad_norm": 0.3175047039985657,
-      "learning_rate": 4.951737451737452e-05,
-      "loss": 1.0677,
-      "step": 100
-    },
-    {
-      "epoch": 0.3824091778202677,
-      "grad_norm": 0.3452897071838379,
-      "learning_rate": 4.8552123552123555e-05,
-      "loss": 0.9592,
-      "step": 200
-    },
-    {
-      "epoch": 0.5736137667304015,
-      "grad_norm": 0.5109040141105652,
-      "learning_rate": 4.758687258687259e-05,
-      "loss": 0.9311,
-      "step": 300
-    },
-    {
-      "epoch": 0.7648183556405354,
-      "grad_norm": 0.5286597609519958,
-      "learning_rate": 4.662162162162162e-05,
-      "loss": 0.8667,
-      "step": 400
-    },
-    {
-      "epoch": 0.9560229445506692,
-      "grad_norm": 0.40717196464538574,
-      "learning_rate": 4.565637065637066e-05,
-      "loss": 0.8142,
-      "step": 500
-    },
-    {
-      "epoch": 1.147227533460803,
-      "grad_norm": 0.5934731960296631,
-      "learning_rate": 4.4691119691119696e-05,
-      "loss": 0.7658,
-      "step": 600
-    },
-    {
-      "epoch": 1.338432122370937,
-      "grad_norm": 0.5729045271873474,
-      "learning_rate": 4.3725868725868726e-05,
-      "loss": 0.7155,
-      "step": 700
-    },
-    {
-      "epoch": 1.5296367112810707,
-      "grad_norm": 0.8239750862121582,
-      "learning_rate": 4.276061776061776e-05,
-      "loss": 0.7286,
-      "step": 800
-    },
-    {
-      "epoch": 1.7208413001912046,
-      "grad_norm": 0.7240690588951111,
-      "learning_rate": 4.17953667953668e-05,
-      "loss": 0.6913,
-      "step": 900
-    },
-    {
-      "epoch": 1.9120458891013383,
-      "grad_norm": 0.6800572872161865,
-      "learning_rate": 4.083011583011583e-05,
-      "loss": 0.7385,
-      "step": 1000
-    },
-    {
-      "epoch": 2.1032504780114722,
-      "grad_norm": 0.9010747671127319,
-      "learning_rate": 3.986486486486487e-05,
-      "loss": 0.6386,
-      "step": 1100
-    },
-    {
-      "epoch": 2.294455066921606,
-      "grad_norm": 1.2023605108261108,
-      "learning_rate": 3.8899613899613905e-05,
-      "loss": 0.5685,
-      "step": 1200
-    },
-    {
-      "epoch": 2.48565965583174,
-      "grad_norm": 1.032483458518982,
-      "learning_rate": 3.7934362934362935e-05,
-      "loss": 0.5601,
-      "step": 1300
-    },
-    {
-      "epoch": 2.676864244741874,
-      "grad_norm": 0.979926347732544,
-      "learning_rate": 3.696911196911197e-05,
-      "loss": 0.6145,
-      "step": 1400
-    },
-    {
-      "epoch": 2.8680688336520075,
-      "grad_norm": 0.6987595558166504,
-      "learning_rate": 3.6003861003861e-05,
-      "loss": 0.5834,
-      "step": 1500
+      "epoch": 0.09982486865148861,
+      "grad_norm": 0.259847491979599,
+      "learning_rate": 4.9718557607739666e-05,
+      "loss": 1.1436,
+      "step": 114
     }
   ],
-  "logging_steps": 100,
-  "max_steps": 5230,
+  "logging_steps": 114,
+  "max_steps": 11420,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
-  "save_steps": 500,
+  "save_steps": 114,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -131,7 +33,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.55174687846912e+16,
+  "total_flos": 6430276097753088.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9961853a27f5829fc673e059d81c28ebfd690e6e74dc2ffd482865d556612698
+oid sha256:9e30f0bfd5e4ce7f4926064b814f4f21d1ca2b5d03ca3afd1066872e09df743b
 size 5880