Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8921c24fb85777e94eb66781d2305c8e098ea47ea9369793d0673ea3c5221ad6
+oid sha256:6a52b10c74c9a401a1135b0b3ef4d653611fa1c945776c688880c7222798edb7
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a92dd043e8c0c40a86da3045973602258a9caa9b5e256ca972957c2f1162ed8e
+oid sha256:ee28496989d105945f7c6121bf5a20aa7aae99d28fa7fb5573512c7f71c18f12
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e7f37d1795b3a5f2badef6331eeaa3b12ee884a2d3e04816a3d1b46104eacde
+oid sha256:bd67821c9edb352a2a7a6b1031c16b950b3518af15c398996c9dc36265dc4d1a
 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": 0.0007545746085644218,
+  "epoch": 0.0015091492171288435,
   "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": 29.832,
       "eval_steps_per_second": 14.925,
       "step": 3
+    },
+    {
+      "epoch": 0.0010060994780858958,
+      "grad_norm": 0.23829740285873413,
+      "learning_rate": 8e-05,
+      "loss": 0.8838,
+      "step": 4
+    },
+    {
+      "epoch": 0.0012576243476073697,
+      "grad_norm": 0.18251283466815948,
+      "learning_rate": 0.0001,
+      "loss": 0.4454,
+      "step": 5
+    },
+    {
+      "epoch": 0.0015091492171288435,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.703,
+      "step": 6
+    },
+    {
+      "epoch": 0.0015091492171288435,
+      "eval_loss": NaN,
+      "eval_runtime": 56.3421,
+      "eval_samples_per_second": 29.729,
+      "eval_steps_per_second": 14.873,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 417433827409920.0,
+  "total_flos": 834867654819840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null