Training in progress, epoch 19, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bc15b677d7150c7b8662bd74693f8bc1a9a699b300ead6787ebc2b78994dc0e
+oid sha256:0ee5576c5f1026abaeac1844024bd4d9b26c80d3552b0a02a96d7db04ae8d0bf
 size 778096664

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c46bc5b2c7e9b5e48195cbfc828007cb18335ca89de3bfc0c1082595fc425e8f
+oid sha256:dad3791c8f2b4864fb5026c9f40cea0748aba372d869400d34dc8ece1a4c56f4
 size 395561780

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f86f749dc73bc16a2502fef2f98f5c00b4400cb2c67fbe62653b7ed104d13779
+oid sha256:c013855f1f203be97dafecaefb623110a70641991f8c85f3b86fa91a81df5017
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf7fa1f56d27577f751c642d07f9880522dad42fca9e9c239a8267e1a6058139
+oid sha256:28df73b3d2574d5e7d5989c9c1976ff625cb4c34411f21da816c1ceb48b6e74b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.002446170896291733,
   "best_model_checkpoint": "/Workspace/Users/[email protected]/Projects/FRED/models/unsloth/Llama-3.2-3B-Instruct/checkpoint-5250",
-  "epoch": 18.0,
+  "epoch": 19.0,
   "eval_steps": 500,
-  "global_step": 6300,
+  "global_step": 6650,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -592,6 +592,35 @@
       "eval_samples_per_second": 10.643,
       "eval_steps_per_second": 2.661,
       "step": 6300
+    },
+    {
+      "epoch": 18.285714285714285,
+      "grad_norm": 0.000776465458329767,
+      "learning_rate": 4.316546762589929e-06,
+      "loss": -0.0001,
+      "step": 6400
+    },
+    {
+      "epoch": 18.571428571428573,
+      "grad_norm": 0.0008999446872621775,
+      "learning_rate": 3.5971223021582732e-06,
+      "loss": -0.0001,
+      "step": 6500
+    },
+    {
+      "epoch": 18.857142857142858,
+      "grad_norm": 0.0010123606771230698,
+      "learning_rate": 2.877697841726619e-06,
+      "loss": -0.0001,
+      "step": 6600
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 0.002609863178804517,
+      "eval_runtime": 65.3789,
+      "eval_samples_per_second": 10.707,
+      "eval_steps_per_second": 2.677,
+      "step": 6650
     }
   ],
   "logging_steps": 100,
@@ -611,7 +640,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7813440167702528e+17,
+  "total_flos": 1.879853696212992e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null