Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6079166fcdc2bd13b64d53cfb85d3c306e87206d021e6fe72844eeaf41401839
+oid sha256:bd1405c0e2350a85c3e7a4ae08e5cddc84368680945ea2860f1578be4b0edb72
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:200a8b834c97dc2cbb331c004b422f64b05d95a6d6951f9768b25ef326286dc2
+oid sha256:8aea21055eb0215e7160cebe87d1e37f58135a2ee307fb7a1aa603fd25695b0d
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:943b3306f5b2d7b55b823ff42546cc7ec09145d1c7aa468ed4fe93c5d91e3551
+oid sha256:a1f361a3b4435659bf75e7f78b3cb2cce6f6e79dd73ac2623b2346c3044eb4a7
 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": 0.00015710096355257646,
+  "epoch": 0.0003142019271051529,
   "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": 11.127,
       "eval_steps_per_second": 5.564,
       "step": 3
+    },
+    {
+      "epoch": 0.00020946795140343527,
+      "grad_norm": 0.47606730461120605,
+      "learning_rate": 8e-05,
+      "loss": 0.5238,
+      "step": 4
+    },
+    {
+      "epoch": 0.0002618349392542941,
+      "grad_norm": 0.46592414379119873,
+      "learning_rate": 0.0001,
+      "loss": 0.5844,
+      "step": 5
+    },
+    {
+      "epoch": 0.0003142019271051529,
+      "grad_norm": 0.5224045515060425,
+      "learning_rate": 0.00012,
+      "loss": 0.6448,
+      "step": 6
+    },
+    {
+      "epoch": 0.0003142019271051529,
+      "eval_loss": 0.6183779835700989,
+      "eval_runtime": 723.037,
+      "eval_samples_per_second": 11.121,
+      "eval_steps_per_second": 5.561,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1231436170395648.0,
+  "total_flos": 2462872340791296.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null