Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b33cef97c05fe4ccc8e72e442cc68ae152fc4c3633e27448ba9c909683b3cf5
+oid sha256:f3b0314ac52fb6912a6f31f674a6ed0e8186906508d8c92b93b3377e8a133295
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54a79d972e6399e51b7dd0e38e3dbbc0c53483f23ba8180a69a30cca5aae15b6
+oid sha256:e882797c496de1b66235e3f6fd3656983331ca8ccf3599532b1ef461e88d3c03
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86b1d1c847833c161251571b388af565d36854d60391836c815a5c304e314a4b
+oid sha256:f89ee07fe03d1a05ba9f35a1ae7e0f887e7de2494b1948e33f324c76bd30d853
 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": 0.013986013986013986,
+  "epoch": 0.027972027972027972,
   "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": 130.534,
       "eval_steps_per_second": 65.984,
       "step": 3
+    },
+    {
+      "epoch": 0.018648018648018648,
+      "grad_norm": 6.709271430969238,
+      "learning_rate": 8e-05,
+      "loss": 9.7886,
+      "step": 4
+    },
+    {
+      "epoch": 0.023310023310023312,
+      "grad_norm": 4.035851001739502,
+      "learning_rate": 0.0001,
+      "loss": 10.4621,
+      "step": 5
+    },
+    {
+      "epoch": 0.027972027972027972,
+      "grad_norm": 7.662912845611572,
+      "learning_rate": 0.00012,
+      "loss": 10.1554,
+      "step": 6
+    },
+    {
+      "epoch": 0.027972027972027972,
+      "eval_loss": 9.638227462768555,
+      "eval_runtime": 0.7434,
+      "eval_samples_per_second": 122.414,
+      "eval_steps_per_second": 61.88,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 327792721920.0,
+  "total_flos": 639195807744.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null