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:db1c9e331fb5a52724da94922ba7ec2a99f904ca02fd11e82f6070d731cbeb3d
+oid sha256:64ecb17853e45e69bb8875ed21ded472a9727881f9e0d05de3c9e9ac813eee29
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a0fc602e653da55781500d01df1ddc857704267d3a24382e1b6eca1f0e68561
+oid sha256:c75ace2c3360791dd2c68d043ef3b4052bd633c09740eb37d236ba5f1d7b2678
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14f7ced314baf64ed2febbea1a34ffbacbc38099cb191144ca5b001afd0de3f6
+oid sha256:8aa98b654a6ad98d9998c44f95a9ec59c7edf25202ad9a4080fb894c3b37d6e0
 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": 4.440037296313289e-05,
+  "epoch": 8.880074592626579e-05,
   "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": 34.075,
       "eval_steps_per_second": 17.037,
       "step": 3
+    },
+    {
+      "epoch": 5.9200497284177184e-05,
+      "grad_norm": 5.206923007965088,
+      "learning_rate": 8e-05,
+      "loss": 7.2314,
+      "step": 4
+    },
+    {
+      "epoch": 7.400062160522149e-05,
+      "grad_norm": 8.670096397399902,
+      "learning_rate": 0.0001,
+      "loss": 7.2969,
+      "step": 5
+    },
+    {
+      "epoch": 8.880074592626579e-05,
+      "grad_norm": 7.160818099975586,
+      "learning_rate": 0.00012,
+      "loss": 7.756,
+      "step": 6
+    },
+    {
+      "epoch": 8.880074592626579e-05,
+      "eval_loss": 6.845438480377197,
+      "eval_runtime": 834.7376,
+      "eval_samples_per_second": 34.083,
+      "eval_steps_per_second": 17.041,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 72163654631424.0,
+  "total_flos": 144327309262848.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null