Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32c5cb01023899a1434ff471f48e798cae1e8a3cbe013c8a6f2044df2841637e
+oid sha256:5eece020ae8c00cd45b64e3adbbabbd4d7fc88050fc9c743fb1ce1f92a32858d
 size 78480072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fa0f486520ccfd7a19b569fdfc55612fb35d054f11b360f4e98c151ef667cad
+oid sha256:68dafe72fc84b7e2ab614a2d4b0ed5ac30cad72a718a8daab974f53fa409724e
 size 40131268

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:847d1959dd2ad2cbb49971c91b977b7b45511251dbd18469c52b56539e0d5412
+oid sha256:123bf0512ee7e92d318f0df765024002679fa6c8d9772a1133e0845594f76a35
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2787bebb68ee3c89090ba2c7025854bfdc8bd44ba56793c8687fa610e8a75c1
+oid sha256:48d26c135a3ab88ceff8afaebade3eca6236181282cfa27b13d7c78cfc7e5660
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f89a12319a173052b7bf94041968a424ea66908f08ec94efa068b521e6d57c3
+oid sha256:d376ae8798f4665b5771f699e3266fe3c29018fd2b9fbef975810586bff4b6bb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dd278bb89e227f64c18391a86f58b68c8f68fbe43b167c08cbc6279d29a9943
+oid sha256:79a2ae5b55351193f6ed73aaecedbcc2045d8e0e97e1e5282428f7201ef51993
 size 15024

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": 0.027649769585253458,
+  "epoch": 0.055299539170506916,
   "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": 36.836,
       "eval_steps_per_second": 4.63,
       "step": 3
+    },
+    {
+      "epoch": 0.03686635944700461,
+      "grad_norm": 13.103915214538574,
+      "learning_rate": 8e-05,
+      "loss": 5.4683,
+      "step": 4
+    },
+    {
+      "epoch": 0.04608294930875576,
+      "grad_norm": 11.824213981628418,
+      "learning_rate": 0.0001,
+      "loss": 4.5965,
+      "step": 5
+    },
+    {
+      "epoch": 0.055299539170506916,
+      "grad_norm": 9.575993537902832,
+      "learning_rate": 0.00012,
+      "loss": 4.1653,
+      "step": 6
+    },
+    {
+      "epoch": 0.055299539170506916,
+      "eval_loss": 3.606476306915283,
+      "eval_runtime": 4.945,
+      "eval_samples_per_second": 37.007,
+      "eval_steps_per_second": 4.651,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4722121657810944.0,
+  "total_flos": 9444243315621888.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null