Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c679e7e83d3958ed05823d72368a34816d291f6a1537ef5d0f1943c104a8d40
+oid sha256:f1391a0571db36cc1c4ef4ffde4774937fa4b5b8836077c309ab759629d8e5d7
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f1b8af2e89d67205fa4b8e8c1c47189d2d9273a15a47547871725a62e9adb28
+oid sha256:29f0abfc1b56fbdbfd0f07a416aed4f49c380bfd74fc75b23e61fad894ba1179
 size 212298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3de5ca30ff633d309a9b80db8e8d57d7760528e3bc1867a6faea71254e3b8c07
+oid sha256:d603bfa457862fd98feec418db361ef43e93fdfc27ec02093cd595dc116475d5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f9ab26294f369ba5d99cf6e2514a5d05f3df1a90b36a045191f6b23077ba365
+oid sha256:2188426f4adaa3a6124c181a61860e824dc2136981845a9e9c4162d0d3700af6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6335627316040233,
+  "epoch": 0.6776071995764955,
   "eval_steps": 50,
-  "global_step": 187,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1348,6 +1348,105 @@
       "learning_rate": 1.9222451411073645e-06,
       "loss": 10.3445,
       "step": 187
+    },
+    {
+      "epoch": 0.6369507676019057,
+      "grad_norm": 0.02741316892206669,
+      "learning_rate": 1.6389299449645733e-06,
+      "loss": 10.3437,
+      "step": 188
+    },
+    {
+      "epoch": 0.6403388035997882,
+      "grad_norm": 0.018788231536746025,
+      "learning_rate": 1.3779612414252017e-06,
+      "loss": 10.3452,
+      "step": 189
+    },
+    {
+      "epoch": 0.6437268395976707,
+      "grad_norm": 0.020280800759792328,
+      "learning_rate": 1.1394185240843983e-06,
+      "loss": 10.3459,
+      "step": 190
+    },
+    {
+      "epoch": 0.6471148755955533,
+      "grad_norm": 0.01888551376760006,
+      "learning_rate": 9.233744553646754e-07,
+      "loss": 10.3457,
+      "step": 191
+    },
+    {
+      "epoch": 0.6505029115934357,
+      "grad_norm": 0.020312048494815826,
+      "learning_rate": 7.298948443822228e-07,
+      "loss": 10.3441,
+      "step": 192
+    },
+    {
+      "epoch": 0.6538909475913182,
+      "grad_norm": 0.01959800161421299,
+      "learning_rate": 5.590386269008512e-07,
+      "loss": 10.3434,
+      "step": 193
+    },
+    {
+      "epoch": 0.6572789835892007,
+      "grad_norm": 0.024537065997719765,
+      "learning_rate": 4.108578473795032e-07,
+      "loss": 10.3446,
+      "step": 194
+    },
+    {
+      "epoch": 0.6606670195870831,
+      "grad_norm": 0.020832853391766548,
+      "learning_rate": 2.8539764311908407e-07,
+      "loss": 10.345,
+      "step": 195
+    },
+    {
+      "epoch": 0.6640550555849656,
+      "grad_norm": 0.020389897748827934,
+      "learning_rate": 1.8269623051318515e-07,
+      "loss": 10.3452,
+      "step": 196
+    },
+    {
+      "epoch": 0.6674430915828481,
+      "grad_norm": 0.018793173134326935,
+      "learning_rate": 1.027848934069625e-07,
+      "loss": 10.3462,
+      "step": 197
+    },
+    {
+      "epoch": 0.6708311275807305,
+      "grad_norm": 0.03216562792658806,
+      "learning_rate": 4.568797356781784e-08,
+      "loss": 10.3447,
+      "step": 198
+    },
+    {
+      "epoch": 0.674219163578613,
+      "grad_norm": 0.02798965945839882,
+      "learning_rate": 1.142286327065478e-08,
+      "loss": 10.3446,
+      "step": 199
+    },
+    {
+      "epoch": 0.6776071995764955,
+      "grad_norm": 0.021245818585157394,
+      "learning_rate": 0.0,
+      "loss": 10.3461,
+      "step": 200
+    },
+    {
+      "epoch": 0.6776071995764955,
+      "eval_loss": 10.3442964553833,
+      "eval_runtime": 3.9275,
+      "eval_samples_per_second": 253.34,
+      "eval_steps_per_second": 126.797,
+      "step": 200
     }
   ],
   "logging_steps": 1,
@@ -1362,12 +1461,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 80109921632256.0,
+  "total_flos": 85669769379840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null