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:f9a02553b5b185e15d5c42c9d7556062e35b8089414609f09a2f74af2afc3f0f
+oid sha256:871806b2dfe9f805fed9d8d8566b21a125d8fde7945d13658c1c717f0bb92ca5
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8ba28f5ebc9e1955fe68553be222e02c1aaf93a44b34b8cffe8966daac64761
+oid sha256:ae5f9164b5168f63d6a7e6dcc936890297b53a2cfe54a3b6ed0bf3eb18763595
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3dd893c207e3d1f2bc028be6b52b91d3d83dc4d2ada4afcc861658c1da027ab
+oid sha256:bb8533fae84b8bbe35ecff98d5d66a1e19344edfcde38ca202b781a73c8943ca
 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": 0.006718924972004479,
+  "epoch": 0.013437849944008958,
   "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": 21.256,
       "eval_steps_per_second": 10.628,
       "step": 3
+    },
+    {
+      "epoch": 0.008958566629339306,
+      "grad_norm": 1.0633552074432373,
+      "learning_rate": 8e-05,
+      "loss": 5.781,
+      "step": 4
+    },
+    {
+      "epoch": 0.011198208286674132,
+      "grad_norm": 1.2751410007476807,
+      "learning_rate": 0.0001,
+      "loss": 5.8456,
+      "step": 5
+    },
+    {
+      "epoch": 0.013437849944008958,
+      "grad_norm": 0.9956833124160767,
+      "learning_rate": 0.00012,
+      "loss": 5.8907,
+      "step": 6
+    },
+    {
+      "epoch": 0.013437849944008958,
+      "eval_loss": 5.812419414520264,
+      "eval_runtime": 8.9729,
+      "eval_samples_per_second": 20.952,
+      "eval_steps_per_second": 10.476,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 615718085197824.0,
+  "total_flos": 1231436170395648.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null