Training in progress, step 5, checkpoint

last-checkpoint/README.md

@@ -1,5 +1,5 @@
 ---
-base_model: meta-llama/Llama-3.2-1B-Instruct
+base_model: unsloth/Llama-3.2-1B-Instruct
 library_name: peft
 ---
 

last-checkpoint/adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
+  "base_model_name_or_path": "unsloth/Llama-3.2-1B-Instruct",
   "bias": "none",
   "fan_in_fan_out": null,
   "inference_mode": true,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
+    "v_proj",
     "up_proj",
-    "gate_proj",
     "down_proj",
+    "gate_proj",
     "o_proj",
-    "q_proj",
-    "v_proj",
-    "k_proj"
+    "q_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 sha256:14307fe730856cbaf0dfbb7be4fa93c6514b3842c68373379813bf5e25ed5e41
+oid sha256:fb29d3b53bd465aa7f34d857b9a8d7a67d143a4aa96b687c1e4abc4def144af6
 size 1073255280

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b496e2077406d005a8e00618305c4a96360bdcaae3a1db817fd3f364dca8164
+oid sha256:6a7e16bd03e24919dc12b8d38eac038cb47a87832d537bcc7e3bc062814f9d53
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f6478bb299c9ce1748f21b3376abcd598c4f5e5d476f17a8bb2fb903e082807
+oid sha256:c1b341f5d1cca25903f2af914332ce7846ff94b425ff95396e49d78d4c84d2cd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
 size 1064

last-checkpoint/tokenizer_config.json

@@ -2067,5 +2067,6 @@
   ],
   "model_max_length": 131072,
   "pad_token": " ",
+  "padding_side": "left",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }

last-checkpoint/trainer_state.json

@@ -1,114 +1,63 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04678362573099415,
+  "epoch": 0.023391812865497075,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.004678362573099415,
-      "grad_norm": 5.750593185424805,
+      "grad_norm": 5.251277446746826,
       "learning_rate": 2e-05,
-      "loss": 6.359,
+      "loss": 6.2882,
       "step": 1
     },
     {
       "epoch": 0.004678362573099415,
-      "eval_loss": 6.370258808135986,
-      "eval_runtime": 19.2294,
-      "eval_samples_per_second": 4.68,
-      "eval_steps_per_second": 2.34,
+      "eval_loss": 6.047508239746094,
+      "eval_runtime": 19.3044,
+      "eval_samples_per_second": 4.662,
+      "eval_steps_per_second": 2.331,
       "step": 1
     },
     {
       "epoch": 0.00935672514619883,
-      "grad_norm": 5.035371780395508,
+      "grad_norm": 6.440146446228027,
       "learning_rate": 4e-05,
-      "loss": 5.7429,
+      "loss": 5.7219,
       "step": 2
     },
     {
       "epoch": 0.014035087719298246,
-      "grad_norm": 6.107978820800781,
+      "grad_norm": 6.172605514526367,
       "learning_rate": 6e-05,
-      "loss": 6.4256,
+      "loss": 6.3972,
       "step": 3
     },
     {
       "epoch": 0.014035087719298246,
-      "eval_loss": 6.360498905181885,
-      "eval_runtime": 19.1942,
-      "eval_samples_per_second": 4.689,
-      "eval_steps_per_second": 2.344,
+      "eval_loss": 6.034425258636475,
+      "eval_runtime": 19.2926,
+      "eval_samples_per_second": 4.665,
+      "eval_steps_per_second": 2.332,
       "step": 3
     },
     {
       "epoch": 0.01871345029239766,
-      "grad_norm": 6.911861419677734,
+      "grad_norm": 5.445214748382568,
       "learning_rate": 8e-05,
-      "loss": 5.7963,
+      "loss": 4.9247,
       "step": 4
     },
     {
       "epoch": 0.023391812865497075,
-      "grad_norm": 9.54494857788086,
+      "grad_norm": 6.302439212799072,
       "learning_rate": 0.0001,
-      "loss": 6.5247,
+      "loss": 6.6063,
       "step": 5
-    },
-    {
-      "epoch": 0.028070175438596492,
-      "grad_norm": 7.861940860748291,
-      "learning_rate": 0.00012,
-      "loss": 6.1006,
-      "step": 6
-    },
-    {
-      "epoch": 0.028070175438596492,
-      "eval_loss": 6.05557107925415,
-      "eval_runtime": 19.163,
-      "eval_samples_per_second": 4.697,
-      "eval_steps_per_second": 2.348,
-      "step": 6
-    },
-    {
-      "epoch": 0.03274853801169591,
-      "grad_norm": 8.142016410827637,
-      "learning_rate": 0.00014,
-      "loss": 6.2427,
-      "step": 7
-    },
-    {
-      "epoch": 0.03742690058479532,
-      "grad_norm": 9.977738380432129,
-      "learning_rate": 0.00016,
-      "loss": 5.4087,
-      "step": 8
-    },
-    {
-      "epoch": 0.042105263157894736,
-      "grad_norm": 15.58422565460205,
-      "learning_rate": 0.00018,
-      "loss": 4.5709,
-      "step": 9
-    },
-    {
-      "epoch": 0.042105263157894736,
-      "eval_loss": 3.7143731117248535,
-      "eval_runtime": 19.2587,
-      "eval_samples_per_second": 4.673,
-      "eval_steps_per_second": 2.337,
-      "step": 9
-    },
-    {
-      "epoch": 0.04678362573099415,
-      "grad_norm": 13.564678192138672,
-      "learning_rate": 0.0002,
-      "loss": 4.9167,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -123,12 +72,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 1924364123504640.0,
+  "total_flos": 962182061752320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d3e370b9d6615dabd5613d8b90bf717c2681f461b1cf7375bd2aafe0509e79c
+oid sha256:78b4872ed3ffc7b568bfd68235d51d9bfe0fb0927dd4dd03d89ae03c49e01b2a
 size 6648