Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3914f354b806aef060e9fcaccc1ae004894064b793bed864b50b5e4e55b8b03c
+oid sha256:25a7197e8efc57ac411679cbee8d9b1e64a59cef81446b6d1613615082078f1d
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32db12b95ecedd45b176f99706a5824c7fec16201d11dda360deb73f6c7e6b42
+oid sha256:b35d6d46b4261ec803e6ce9c5bb51c6ba521112bd58810a8cfcf693df0c96432
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb35249a84d7bcb3cccf7fe5b59ee8dc0f174103950c84a23cc071b3089b5686
+oid sha256:1f9d63457fb0762bec521007b4b65dfde2dbfedf3cf13f579982482514a7d902
 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": 0.010425716768027803,
+  "epoch": 0.020851433536055605,
   "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": 4.795,
       "eval_steps_per_second": 4.795,
       "step": 3
+    },
+    {
+      "epoch": 0.013900955690703735,
+      "grad_norm": 3.6273467540740967,
+      "learning_rate": 8e-05,
+      "loss": 3.9102,
+      "step": 4
+    },
+    {
+      "epoch": 0.01737619461337967,
+      "grad_norm": 2.674269914627075,
+      "learning_rate": 0.0001,
+      "loss": 3.4218,
+      "step": 5
+    },
+    {
+      "epoch": 0.020851433536055605,
+      "grad_norm": 3.4425220489501953,
+      "learning_rate": 0.00012,
+      "loss": 3.2851,
+      "step": 6
+    },
+    {
+      "epoch": 0.020851433536055605,
+      "eval_loss": 3.34614634513855,
+      "eval_runtime": 12.7399,
+      "eval_samples_per_second": 4.788,
+      "eval_steps_per_second": 4.788,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2225661850681344.0,
+  "total_flos": 4451323701362688.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null