Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a190b10ceee5fe048c381c2608a742d6a57e83f27313b86b4215f601fa46f060
+oid sha256:9d3445873d550d3d73dce2ff50b50052c80fc37c11387922202bd59ba349fc45
 size 5752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5702dd5adf435229e5955857c6d53b75cbd418ba54a6172c4ece8c93a88ca9d5
+oid sha256:2033bee1716df25d0d77a6151661f788f7ca8662bd09fc7efb114972f1ccfc40
 size 15814

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af82c1f1d4ec999545a290f8875f59e0434314b9e98a3c2553c0c541daf4cdfa
+oid sha256:9c4e103f057cbf52631a0f74dec69e271b2b990ec70bac9b6694c66ba4e1959d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00030335587436010873,
+  "epoch": 0.0005055931239335145,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "eval_samples_per_second": 155.267,
       "eval_steps_per_second": 77.634,
       "step": 6
+    },
+    {
+      "epoch": 0.00035391518675346014,
+      "grad_norm": 3.0670395062770694e-05,
+      "learning_rate": 0.00014,
+      "loss": 46.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.0004044744991468116,
+      "grad_norm": 1.8676053514354862e-05,
+      "learning_rate": 0.00016,
+      "loss": 46.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.00045503381154016307,
+      "grad_norm": 2.4990700694615953e-05,
+      "learning_rate": 0.00018,
+      "loss": 46.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.00045503381154016307,
+      "eval_loss": 11.5,
+      "eval_runtime": 51.7209,
+      "eval_samples_per_second": 161.018,
+      "eval_steps_per_second": 80.509,
+      "step": 9
+    },
+    {
+      "epoch": 0.0005055931239335145,
+      "grad_norm": 5.803050589747727e-05,
+      "learning_rate": 0.0002,
+      "loss": 46.0,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 219151663104.0,
+  "total_flos": 368573251584.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null