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:ef6ba19c66ac9a3a4ee548e7928424a565d5dc8b7f603b2356d833ae456679da
+oid sha256:951e93330ee5a56d0b49de14196597b628afa52a6b128ee5142188cd1b1ada8f
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:612fa90776de5e2787fa1200ea643b27e7b789a300ce358e9ca0b5f22e8f91ed
+oid sha256:1c478eccdf4531f6935e700952e58379d7b9210bf86d9ebb1ca0a829620b5dd8
 size 81730196

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:299d32ba3c4f9a5ab4a21087102ae4b639368b773d74f8bfc38b1764af303b1f
+oid sha256:82d58cdefbfa206272ae0f49b7c1ab4333ed43fed8f691ed4fab228d76a03af4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e8ea7001babd42c36d0b764fe2f954b69df1df0ca7a8b27d01310ed7fcccd93
+oid sha256:e5b1b3e059101187bfc3dbbbf83ace53384f686f1746265194c4a97e6f99011f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a4d122056e184e0bf39d1921b31f622c351cf793f7dcc9f28c9280f10d63fd3
+oid sha256:4f6de54275f346101ff8b49b7b00b2a5e3c3f833bea127dd1d85c05840e8e91e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38b936ede91333d7d85cb134faedabe7287c14c2d2b393eb9209dcbe03207aca
+oid sha256:7088bfeda8ca84a250864306b44e2cb8f6e645d52ec0d290b01d09803cdac7f4
 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": 0.02586206896551724,
+  "epoch": 0.05172413793103448,
   "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": 20.542,
       "eval_steps_per_second": 2.634,
       "step": 3
+    },
+    {
+      "epoch": 0.034482758620689655,
+      "grad_norm": 1.8984614610671997,
+      "learning_rate": 8e-05,
+      "loss": 4.18,
+      "step": 4
+    },
+    {
+      "epoch": 0.04310344827586207,
+      "grad_norm": 1.8628818988800049,
+      "learning_rate": 0.0001,
+      "loss": 4.0706,
+      "step": 5
+    },
+    {
+      "epoch": 0.05172413793103448,
+      "grad_norm": 2.0986077785491943,
+      "learning_rate": 0.00012,
+      "loss": 3.887,
+      "step": 6
+    },
+    {
+      "epoch": 0.05172413793103448,
+      "eval_loss": 3.8300561904907227,
+      "eval_runtime": 9.5102,
+      "eval_samples_per_second": 20.504,
+      "eval_steps_per_second": 2.629,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5682996845674496e+16,
+  "total_flos": 3.136599369134899e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null