Training in progress, step 1011, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1660eed46ba6f0d3fa1ec0731090d018b236a179f4718f8ff7102f222b325f96
+oid sha256:e41bdb0793d89736e61aa90347d62039b1cc5b91d002ff8baba99be9a418e29d
 size 1321024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c32d00e76b7d2bb3304546cfe4632a05f4a37dad22e346b3452ae05d7cb5ecca
+oid sha256:602b1835241dd5c7abd50b47b76431b7081683679692152e8315862e2c995483
 size 2687115

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c96f1bff79da150254573441bd748e86215cf8b6a0ff921f8f2e20b39f409151
+oid sha256:279402b83f987e0900d353b3d8f08d84cf30415c38cb898df2f810aaabbad630
 size 14455

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1da8be2dfd2f4a410756ef5e4eb0e514dd1783dcb1fde6c88b2ea7e89de617f2
+oid sha256:aa023108973b8b5d0e85230f52d73593ff1c13cfe94cfa4694449750a3f0f6c6
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1000,
   "best_metric": 3.7591054439544678,
   "best_model_checkpoint": "/kaggle/working/drive/MyDrive/llama_lora_finetuned/checkpoint-1000",
-  "epoch": 2.9673590504451037,
+  "epoch": 3.0,
   "eval_steps": 50,
-  "global_step": 1000,
+  "global_step": 1011,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7168,6 +7168,83 @@
       "eval_samples_per_second": 1.679,
       "eval_steps_per_second": 0.213,
       "step": 1000
+    },
+    {
+      "epoch": 2.970326409495549,
+      "grad_norm": 0.8667409420013428,
+      "learning_rate": 3.604874476173525e-08,
+      "loss": 3.3783,
+      "step": 1001
+    },
+    {
+      "epoch": 2.973293768545994,
+      "grad_norm": 1.0062025785446167,
+      "learning_rate": 2.9792972446479605e-08,
+      "loss": 3.5963,
+      "step": 1002
+    },
+    {
+      "epoch": 2.9762611275964392,
+      "grad_norm": 0.7768653035163879,
+      "learning_rate": 2.4132763089035338e-08,
+      "loss": 3.8658,
+      "step": 1003
+    },
+    {
+      "epoch": 2.979228486646884,
+      "grad_norm": 1.0506861209869385,
+      "learning_rate": 1.9068184149834134e-08,
+      "loss": 3.8484,
+      "step": 1004
+    },
+    {
+      "epoch": 2.9821958456973294,
+      "grad_norm": 0.7125198245048523,
+      "learning_rate": 1.4599295990352924e-08,
+      "loss": 3.7196,
+      "step": 1005
+    },
+    {
+      "epoch": 2.9851632047477743,
+      "grad_norm": 0.7124053835868835,
+      "learning_rate": 1.0726151872408884e-08,
+      "loss": 4.2165,
+      "step": 1006
+    },
+    {
+      "epoch": 2.9881305637982196,
+      "grad_norm": 1.1544585227966309,
+      "learning_rate": 7.448797957526621e-09,
+      "loss": 3.6743,
+      "step": 1007
+    },
+    {
+      "epoch": 2.991097922848665,
+      "grad_norm": 0.9369633197784424,
+      "learning_rate": 4.767273306405251e-09,
+      "loss": 3.6329,
+      "step": 1008
+    },
+    {
+      "epoch": 2.99406528189911,
+      "grad_norm": 0.8136985301971436,
+      "learning_rate": 2.6816098784188117e-09,
+      "loss": 3.6183,
+      "step": 1009
+    },
+    {
+      "epoch": 2.9970326409495547,
+      "grad_norm": 0.9446889162063599,
+      "learning_rate": 1.1918325312498812e-09,
+      "loss": 4.1876,
+      "step": 1010
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.2427432537078857,
+      "learning_rate": 2.979590206064753e-10,
+      "loss": 3.8464,
+      "step": 1011
     }
   ],
   "logging_steps": 1,
@@ -7182,12 +7259,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 584680067334144.0,
+  "total_flos": 590731906547712.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null