Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a6072cc4da62ca3748044e40d0324e30ae7520884bc42d381475f4c221ad650
+oid sha256:a3e09adcbe21b5df89b7d1e1f5af9ddba31c4b433779657751c9fa0479d449e5
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b55953c240e0a547652b16aaad9d219b770465d8ff414fa110fa1ea2d5f1c73
+oid sha256:bf4aa3b63a2ce8b61a12bd02632d3e9962b730642708ce5b55830a0715b160cf
 size 85723284

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3465f7c25c9aa7b7d0f0ef97318a58a46caf1594972ff0b6ab587309c9932dd4
+oid sha256:b8c18207ce7ee2ddacfa18c9a8f55fcbe8f805abb8a9724ef4d3acaabf638e46
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9246be5539fbdfee7619655397cf993f2cfdd3b876b2e2fabfeeeb5329222011
+oid sha256:d27942c6270c04f832a607b6c07e14f4fe411c0ad6212a4f1bafc74f8c6ba806
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.030816640986132512,
+  "epoch": 0.04108885464817668,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 11.235,
       "eval_steps_per_second": 2.809,
       "step": 15
+    },
+    {
+      "epoch": 0.03287108371854135,
+      "grad_norm": 89.2127456665039,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 62.5249,
+      "step": 16
+    },
+    {
+      "epoch": 0.03492552645095018,
+      "grad_norm": 77.51390075683594,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 59.9075,
+      "step": 17
+    },
+    {
+      "epoch": 0.03697996918335902,
+      "grad_norm": 63.38047790527344,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 58.074,
+      "step": 18
+    },
+    {
+      "epoch": 0.03903441191576785,
+      "grad_norm": 67.86468505859375,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 56.1145,
+      "step": 19
+    },
+    {
+      "epoch": 0.04108885464817668,
+      "grad_norm": 66.08454895019531,
+      "learning_rate": 0.0,
+      "loss": 58.0635,
+      "step": 20
+    },
+    {
+      "epoch": 0.04108885464817668,
+      "eval_loss": 1.7998082637786865,
+      "eval_runtime": 291.8631,
+      "eval_samples_per_second": 11.238,
+      "eval_steps_per_second": 2.81,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.3750254591410176e+17,
+  "total_flos": 4.500033945521357e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null