Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4964deef7def8a5d7b1ecb56311ebe6c9de8b8111a26c6a9951903ada54f7288
+oid sha256:2c29d9a97356f1832814d6c416b6c33661c9b60ff539e30a535f4a2a9868e3fb
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:089e4d33d63493ca83d0c2cee4f0918ab4f366be1b31f125d3f28c7f9fcf4585
+oid sha256:784ed708e0a1827000500d5e93a8b1a3a589298f8622ed4af7c3ebd72f4bade0
 size 102030196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e95342b7972eb34bcf83df59ba126733ad0e109ff06b5e91fa5e6ba3b10a0f05
+oid sha256:083b722e8b556bda137ae078b24a5e36ab3e05cf212936fb76f8e8582540a426
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0016941973739940702,
+  "epoch": 0.0033883947479881405,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 3.501,
       "eval_steps_per_second": 1.751,
       "step": 3
+    },
+    {
+      "epoch": 0.002258929831992094,
+      "grad_norm": 5.976100444793701,
+      "learning_rate": 8e-05,
+      "loss": 3.5525,
+      "step": 4
+    },
+    {
+      "epoch": 0.002823662289990117,
+      "grad_norm": 3.7647323608398438,
+      "learning_rate": 0.0001,
+      "loss": 3.0432,
+      "step": 5
+    },
+    {
+      "epoch": 0.0033883947479881405,
+      "grad_norm": 3.4719369411468506,
+      "learning_rate": 0.00012,
+      "loss": 2.3622,
+      "step": 6
+    },
+    {
+      "epoch": 0.0033883947479881405,
+      "eval_loss": 2.1884851455688477,
+      "eval_runtime": 211.9746,
+      "eval_samples_per_second": 3.519,
+      "eval_steps_per_second": 1.76,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4601366169255936.0,
+  "total_flos": 9202732338511872.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null