Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c2e967d68e96ccd61ee79881399c519ad4d18c6043e6ad8c12b0ea3b410d6ff
+oid sha256:21a688627a7add1778e261d2d4e1077b44919d3f2d0388a50c047ed1b4dfa43a
 size 792912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10d462a6f24355a0abf88ff34c15521ba7ab72ac35ec3ce9941294abde06d2fb
+oid sha256:eb6422e929ec58f45f900dd0b1c5c022118a6f4a25772d69abab46b54dbc2226
 size 1613434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70d45509bd7bfc32e4469507a5c7cf52b55100292f3cdbadf46a01923d9eca71
+oid sha256:34b8851eacf5716f0f49d0deab94224f985e2f2f788e1ed055d8f63e4c218be4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03740065451145395,
+  "epoch": 0.056100981767180924,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 170.783,
       "eval_steps_per_second": 85.391,
       "step": 20
+    },
+    {
+      "epoch": 0.03927068723702665,
+      "grad_norm": 13065.3056640625,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 35.4466,
+      "step": 21
+    },
+    {
+      "epoch": 0.04488078541374474,
+      "grad_norm": 5766.87890625,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 34.962,
+      "step": 24
+    },
+    {
+      "epoch": 0.04675081813931744,
+      "eval_loss": 8.88081169128418,
+      "eval_runtime": 1.388,
+      "eval_samples_per_second": 162.82,
+      "eval_steps_per_second": 81.41,
+      "step": 25
+    },
+    {
+      "epoch": 0.05049088359046283,
+      "grad_norm": 6992.9677734375,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 35.5057,
+      "step": 27
+    },
+    {
+      "epoch": 0.056100981767180924,
+      "grad_norm": 7209.02197265625,
+      "learning_rate": 0.0,
+      "loss": 34.8763,
+      "step": 30
+    },
+    {
+      "epoch": 0.056100981767180924,
+      "eval_loss": 8.885871887207031,
+      "eval_runtime": 1.8791,
+      "eval_samples_per_second": 120.271,
+      "eval_steps_per_second": 60.135,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7692689080320.0,
+  "total_flos": 11539033620480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null