Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63a5b66bb5cdf13092a0931b868dc49722c0c159ebf5360a226abe1d4473218f
+oid sha256:7277a7d9af7a1fa8a3e8028cceeb9e97e711a244ec7c3ddfde9a181602586595
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a2359906f8660facbbf435cdea237820c31f9e940a763a301c53421776fdd41
+oid sha256:f370811d72d121644374d2116bb35cb890c1948ec4d6ae843bf6c071e0f8cdc3
 size 90310010

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cab4d6c2ce43e24d19e16d85f2f7af6e830104f5a5c4b29ee3dac335d1d10f59
+oid sha256:1bd0f89b229cfeaa8b1bf1cf4a142955879943acc15ca9084fb458bceded42a4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55cc6a3635d19619caf820a77458fa3cfe7756f7bb9d10678c62733cb46f36c0
+oid sha256:1e2ed9259304616a8ecebc61c5d000777b2978635f7a705b8d7081c480ce0bde
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.028011204481792718,
+  "epoch": 0.03734827264239029,
   "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": 29.64,
       "eval_steps_per_second": 14.82,
       "step": 15
+    },
+    {
+      "epoch": 0.029878618113912233,
+      "grad_norm": 22.597171783447266,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 5.0543,
+      "step": 16
+    },
+    {
+      "epoch": 0.031746031746031744,
+      "grad_norm": 16.657546997070312,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 4.5644,
+      "step": 17
+    },
+    {
+      "epoch": 0.03361344537815126,
+      "grad_norm": 16.687297821044922,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 5.7406,
+      "step": 18
+    },
+    {
+      "epoch": 0.035480859010270774,
+      "grad_norm": 15.421487808227539,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 4.554,
+      "step": 19
+    },
+    {
+      "epoch": 0.03734827264239029,
+      "grad_norm": 16.13042640686035,
+      "learning_rate": 0.0,
+      "loss": 4.4114,
+      "step": 20
+    },
+    {
+      "epoch": 0.03734827264239029,
+      "eval_loss": 4.8963775634765625,
+      "eval_runtime": 7.6333,
+      "eval_samples_per_second": 29.607,
+      "eval_steps_per_second": 14.804,
+      "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": 1451583854346240.0,
+  "total_flos": 1935445139128320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null