Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5585c6924a730d5daaf1f973162db2f2c1a290bd7fd584ad739b9869eb545f6b
+oid sha256:8a3a1d4e26de45ce1a1d6f3fcc2f9080c7593fc8f9a99549892b999259373558
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28af08b0ab76394e22c3ba8b79d2e867b8de5c58d47cb613e7bfbc5a1109a681
+oid sha256:459d0bdb85627d36604c66aca8fd43277b3ab782c361fe7160745f318b190065
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9264abfa6d2cc5145363bf71d2fb16332b1ac4e60642a70827881d9a447c36a4
+oid sha256:af82c1f1d4ec999545a290f8875f59e0434314b9e98a3c2553c0c541daf4cdfa
 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": 0.0042387848816672555,
+  "epoch": 0.008477569763334511,
   "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": 466.764,
       "eval_steps_per_second": 233.382,
       "step": 3
+    },
+    {
+      "epoch": 0.00565171317555634,
+      "grad_norm": 1.0016391277313232,
+      "learning_rate": 8e-05,
+      "loss": 44.3014,
+      "step": 4
+    },
+    {
+      "epoch": 0.007064641469445425,
+      "grad_norm": 0.913105309009552,
+      "learning_rate": 0.0001,
+      "loss": 44.3583,
+      "step": 5
+    },
+    {
+      "epoch": 0.008477569763334511,
+      "grad_norm": 1.0485588312149048,
+      "learning_rate": 0.00012,
+      "loss": 44.2542,
+      "step": 6
+    },
+    {
+      "epoch": 0.008477569763334511,
+      "eval_loss": 11.075966835021973,
+      "eval_runtime": 0.655,
+      "eval_samples_per_second": 454.935,
+      "eval_steps_per_second": 227.467,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2241331200.0,
+  "total_flos": 4482662400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null