Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bdd11587acfc0a377c7d6ec926f787742ecff49b701e771cd802299663e2e5e
+oid sha256:86f109732b92fb386bb9b8f1fafa4c06892bc1e39f696cac48e5d95af9266fe1
 size 327040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03fe8c911605b8b3b8ae3130a2ab2bce7f140a158c11316934f1655f9119cf16
+oid sha256:2f36625464e7d75986526cb0acd985210b5fe94b1b8eda87561aa62fcaf28549
 size 739258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9af5373aa88895259568af4bb4ee43ae11bdbf1ba2f7d2b539d2b279040940d
+oid sha256:3fb5f1f2063cc0fc9d69930536ad8305cd213d31011d601a76e1f19f1f368b7a
 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": 0.003006012024048096,
+  "epoch": 0.006012024048096192,
   "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": 21.242,
       "eval_steps_per_second": 10.646,
       "step": 3
+    },
+    {
+      "epoch": 0.004008016032064128,
+      "grad_norm": 0.1474914401769638,
+      "learning_rate": 8e-05,
+      "loss": 11.9373,
+      "step": 4
+    },
+    {
+      "epoch": 0.00501002004008016,
+      "grad_norm": 0.14932551980018616,
+      "learning_rate": 0.0001,
+      "loss": 11.9362,
+      "step": 5
+    },
+    {
+      "epoch": 0.006012024048096192,
+      "grad_norm": 0.1468937247991562,
+      "learning_rate": 0.00012,
+      "loss": 11.9331,
+      "step": 6
+    },
+    {
+      "epoch": 0.006012024048096192,
+      "eval_loss": 11.93669319152832,
+      "eval_runtime": 19.8017,
+      "eval_samples_per_second": 21.261,
+      "eval_steps_per_second": 10.656,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 750935605248.0,
+  "total_flos": 1501871210496.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null