Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e1e03227b48fd587ee7874f243abf16c587613dbf330b6c315dbff5aced61e1
+oid sha256:75cfd74181050bef43a27315159beb35622b4333d607566656b9ce4be47a549d
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a968e2e803512552dcab8e86dd4f65e9f843c294d08ad778d2dac5ed84ed803
+oid sha256:8e0bdcc03446a4cbd70e551731c18325a07b9c218c7a83804546820b591e020a
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b442f4ad3d45725cb9c1409df4d7144db2df15412302cdb8f0e43f2773cdd8c3
+oid sha256:16e646edd2ea41dcbb58b14a0367bd9fd104a3ac0ecfceb51defe786d1a8f660
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddaa639affba9b89222fee046caf8a7f8b52a142c3b2d35ccd1f461973cfdc78
+oid sha256:b5b325ea4e14a510f9eb0108f2923753e246a5ec70e919cdd84a9afd64b95afd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0042739608932578265,
+  "epoch": 0.00641094133988674,
   "eval_steps": 4,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -195,6 +195,92 @@
       "eval_samples_per_second": 4.791,
       "eval_steps_per_second": 1.198,
       "step": 20
+    },
+    {
+      "epoch": 0.004487658937920718,
+      "grad_norm": 2.3242313861846924,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 4.729,
+      "step": 21
+    },
+    {
+      "epoch": 0.004701356982583609,
+      "grad_norm": 2.1803932189941406,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 4.4493,
+      "step": 22
+    },
+    {
+      "epoch": 0.004915055027246501,
+      "grad_norm": 3.0520858764648438,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 4.7408,
+      "step": 23
+    },
+    {
+      "epoch": 0.005128753071909392,
+      "grad_norm": 3.3410630226135254,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 4.6984,
+      "step": 24
+    },
+    {
+      "epoch": 0.005128753071909392,
+      "eval_loss": 2.328244924545288,
+      "eval_runtime": 411.355,
+      "eval_samples_per_second": 4.791,
+      "eval_steps_per_second": 1.198,
+      "step": 24
+    },
+    {
+      "epoch": 0.005342451116572284,
+      "grad_norm": 2.358137845993042,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 4.4836,
+      "step": 25
+    },
+    {
+      "epoch": 0.005556149161235174,
+      "grad_norm": 2.9494125843048096,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 5.1003,
+      "step": 26
+    },
+    {
+      "epoch": 0.005769847205898066,
+      "grad_norm": 3.0665676593780518,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 4.7526,
+      "step": 27
+    },
+    {
+      "epoch": 0.005983545250560957,
+      "grad_norm": 2.681220293045044,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 4.6398,
+      "step": 28
+    },
+    {
+      "epoch": 0.005983545250560957,
+      "eval_loss": 2.3202476501464844,
+      "eval_runtime": 411.2537,
+      "eval_samples_per_second": 4.793,
+      "eval_steps_per_second": 1.199,
+      "step": 28
+    },
+    {
+      "epoch": 0.006197243295223849,
+      "grad_norm": 3.1423282623291016,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 4.7534,
+      "step": 29
+    },
+    {
+      "epoch": 0.00641094133988674,
+      "grad_norm": 2.7747702598571777,
+      "learning_rate": 0.0,
+      "loss": 4.8573,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -209,12 +295,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.26956599246848e+16,
+  "total_flos": 1.90434898870272e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null