Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c1de95d59b2855ec1e034905c65648da1885552fabcd047bb53af87e50c51f5
+oid sha256:16a0036913dfbef6bdb0391e3dc7bded61a61dbe1c503d17a36aa13ccf96df32
 size 871457448

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:803e5770879bfe0d4f86ca7a50fedd3a3112013f8a8d41070a89e6a5d976c903
+oid sha256:1e1bb63951665acbf8a0ed480b4cb3574ffb5ccb1c95ecff2a6e92495d51a497
 size 443280340

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:123fa4f90f645fb09c4a28a25d1e143e033c84f7be014dce6a369e410e156b1f
+oid sha256:6ae305d516ac84e8fdd6d823625992e1992fb2a7a404415c5d2367ae763332ef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65558e26afbfb87dd1928966282919939bdee4084add607d42e008ed52d680cd
+oid sha256:6088f970b1f0429ad85e576795204ef9269ce142d6ce9c2595b5649efde833b6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1544748671843073,
+  "epoch": 0.2043318348998774,
   "eval_steps": 63,
-  "global_step": 189,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -165,6 +165,55 @@
       "eval_samples_per_second": 22.83,
       "eval_steps_per_second": 11.415,
       "step": 189
+    },
+    {
+      "epoch": 0.15529219452390683,
+      "grad_norm": 3.192941188812256,
+      "learning_rate": 2.8165064990227252e-05,
+      "loss": 1.4668,
+      "step": 190
+    },
+    {
+      "epoch": 0.1634654679199019,
+      "grad_norm": 3.9128565788269043,
+      "learning_rate": 1.985863781320435e-05,
+      "loss": 1.1991,
+      "step": 200
+    },
+    {
+      "epoch": 0.17163874131589701,
+      "grad_norm": 3.3797149658203125,
+      "learning_rate": 1.286812958766106e-05,
+      "loss": 1.2317,
+      "step": 210
+    },
+    {
+      "epoch": 0.17981201471189212,
+      "grad_norm": 5.179951190948486,
+      "learning_rate": 7.308324265397836e-06,
+      "loss": 1.2102,
+      "step": 220
+    },
+    {
+      "epoch": 0.1879852881078872,
+      "grad_norm": 4.995609283447266,
+      "learning_rate": 3.270513696097055e-06,
+      "loss": 1.3915,
+      "step": 230
+    },
+    {
+      "epoch": 0.1961585615038823,
+      "grad_norm": 2.9310615062713623,
+      "learning_rate": 8.209986176753948e-07,
+      "loss": 1.1888,
+      "step": 240
+    },
+    {
+      "epoch": 0.2043318348998774,
+      "grad_norm": 2.9699037075042725,
+      "learning_rate": 0.0,
+      "loss": 1.2295,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -179,12 +228,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.266978748203008e+16,
+  "total_flos": 3.006445625593037e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null