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:b0497fe0a7c7c34cd6afb89dfb179983c043b386b2d5181f0f05ffb61b41fac4
+oid sha256:9699ed72d949d07ac14b024a69fb8b84493a7e4da928df110ed7cbf4e1c0e267
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91a07098b90399fe4194436a5ea224345553b2a297afd8c47dd612e0adf7ae2d
+oid sha256:aeaabde01ecfcfb358d60e2374fd1fd686ed218580abf22f8f3c4e9aff9ba56e
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba1cddb81a0f217517c0500b0f01493decc296111738c617b0b321989b1fc2b0
+oid sha256:03a67e1218a684240a269d75069a02f196a9c9742eb0114d107b808e267b1450
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011918951132300357,
+  "epoch": 0.023837902264600714,
   "eval_steps": 3,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,57 @@
       "learning_rate": 0.0001,
       "loss": 2.993,
       "step": 5
+    },
+    {
+      "epoch": 0.014302741358760428,
+      "grad_norm": 1.3507497310638428,
+      "learning_rate": 0.00012,
+      "loss": 2.5632,
+      "step": 6
+    },
+    {
+      "epoch": 0.014302741358760428,
+      "eval_loss": 4.79640007019043,
+      "eval_runtime": 23.1984,
+      "eval_samples_per_second": 7.63,
+      "eval_steps_per_second": 3.836,
+      "step": 6
+    },
+    {
+      "epoch": 0.0166865315852205,
+      "grad_norm": 1.5210137367248535,
+      "learning_rate": 0.00014,
+      "loss": 3.0109,
+      "step": 7
+    },
+    {
+      "epoch": 0.01907032181168057,
+      "grad_norm": 1.6760146617889404,
+      "learning_rate": 0.00016,
+      "loss": 2.6024,
+      "step": 8
+    },
+    {
+      "epoch": 0.021454112038140644,
+      "grad_norm": 2.1592094898223877,
+      "learning_rate": 0.00018,
+      "loss": 2.3319,
+      "step": 9
+    },
+    {
+      "epoch": 0.021454112038140644,
+      "eval_loss": 4.315332889556885,
+      "eval_runtime": 23.146,
+      "eval_samples_per_second": 7.647,
+      "eval_steps_per_second": 3.845,
+      "step": 9
+    },
+    {
+      "epoch": 0.023837902264600714,
+      "grad_norm": 1.8350367546081543,
+      "learning_rate": 0.0002,
+      "loss": 2.9011,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -72,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1849564248145920.0,
+  "total_flos": 3699128496291840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null