Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02fd5271a5082d3dd10553ac0dacaa52dba51457a3aff74307473b63cefe6c4a
+oid sha256:d754c4a8436af488cd7efdf956ffbb5fca81bb4e3ce170ebb9767647580233f5
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66aa0e4c989e12a95f6f42d22c36bda35597bfe1e03ceefb281b2327e1df82cf
+oid sha256:f6c2bf27d6bf40f109794f9f06e0704de84dc006e3b6f2ddb6e6883fa667b7cd
 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": 0.3715170278637771,
+  "epoch": 0.4953560371517028,
   "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": 10.954,
       "eval_steps_per_second": 2.738,
       "step": 15
+    },
+    {
+      "epoch": 0.39628482972136225,
+      "grad_norm": 1.3480126857757568,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.9427,
+      "step": 16
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 1.2827550172805786,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.8725,
+      "step": 17
+    },
+    {
+      "epoch": 0.4458204334365325,
+      "grad_norm": 1.2564868927001953,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.8995,
+      "step": 18
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 1.3051279783248901,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.9913,
+      "step": 19
+    },
+    {
+      "epoch": 0.4953560371517028,
+      "grad_norm": 1.0693706274032593,
+      "learning_rate": 0.0,
+      "loss": 1.8631,
+      "step": 20
+    },
+    {
+      "epoch": 0.4953560371517028,
+      "eval_loss": 2.093961000442505,
+      "eval_runtime": 24.8198,
+      "eval_samples_per_second": 10.959,
+      "eval_steps_per_second": 2.74,
+      "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": 3.5610589610901504e+17,
+  "total_flos": 4.748078614786867e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null