Training in progress, step 113, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e2d5ccac9eb6537d0304c1d9a2664be207cec54a4ffa4f7a1d25f97df0299e7
+oid sha256:71ce0257c9975c8426eef5147f2e169f64e3821e067cd5cc5585cb8ea22f2fb1
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fc6ccd88e5c6b445ddb81486e1b8bb3250cd0ab8d1994a6c77c83f6e34745a6
+oid sha256:8719fa79196e95545a788eed7d70f8cb9e00107d9e8d023232dd7e884b1d981b
 size 41119636

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a57a79985839c1144630cf23e24a752af1717970babccc404e738d94f6a44f55
+oid sha256:00a877456c8253f043f7051f702060848b6888186d2898c19f50e380e8298427
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f78f02857b552b73e80fba53ae03b2fe594f4ff8718b2b7a00f9874950315d8f
+oid sha256:5762c92d924de856e23a69c148ad73656ab908a794479dfbc9eed45e0ea6ce92
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61d763d8dd1b3cf0dec042ca7fcbae7698d20d5c131f3d0f4d2e0fa72962640d
+oid sha256:cfd09b43468bc3c26380f195d7cdbd487a3947aa9fd9338df244051f1d3913d5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:553a6b90849b840223e58a50b84e206a3b835868d03a26f2274252e82e65b480
+oid sha256:f7bec2ec173378a661c585fde43bd276e5b164ea48e7c4439f47a4d480e85f66
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a7a33c3c310055cbe2d20c9c9ebccba7f04bc435d5cf767eccc98d4867335d2
+oid sha256:8f8fe79dd2d524c3a47ebbac1a1fc359d4473e07185866008e654d72a772ea4f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7733333333333333,
+  "epoch": 1.0044444444444445,
   "eval_steps": 29,
-  "global_step": 87,
+  "global_step": 113,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -158,6 +158,41 @@
       "eval_samples_per_second": 38.56,
       "eval_steps_per_second": 4.871,
       "step": 87
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.15183891355991364,
+      "learning_rate": 1.1806917592302762e-05,
+      "loss": 0.3296,
+      "step": 90
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 0.14968590438365936,
+      "learning_rate": 7.348083332917926e-06,
+      "loss": 0.3245,
+      "step": 95
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.16398116946220398,
+      "learning_rate": 3.879310116241042e-06,
+      "loss": 0.319,
+      "step": 100
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.14950266480445862,
+      "learning_rate": 1.4811171192794627e-06,
+      "loss": 0.3243,
+      "step": 105
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.15962573885917664,
+      "learning_rate": 2.0917258966953733e-07,
+      "loss": 0.3512,
+      "step": 110
     }
   ],
   "logging_steps": 5,
@@ -172,12 +207,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.78283317752234e+17,
+  "total_flos": 2.3185047145362227e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null