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:be298d802331cc78310665f06f97444925b91acebc58997d735d280bbe9823ba
+oid sha256:fa2052aea8d730d6f641daa0283942bbad1566d514d1b0d1d736e2bb25844005
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96f4a610bd1a43e49257a316d968c4eb13077a37c44284abe034bff737d114ba
+oid sha256:60a8142277391c4b72c8427b7445d296effd0ba75847ff57ed83396d655ecd98
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01df7b97b445c21bfe49f63c99d75eb4e03716d822d7dff7f977e3b84a2ecc05
+oid sha256:2cb24b3f3f4c4a67fab43264a5041d5eddbe696e430c47d0bfd9e5f90902b3a0
 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": 0.0026875699888017916,
+  "epoch": 0.005375139977603583,
   "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": 4.264,
       "eval_steps_per_second": 2.132,
       "step": 3
+    },
+    {
+      "epoch": 0.0035834266517357225,
+      "grad_norm": 0.544019877910614,
+      "learning_rate": 8e-05,
+      "loss": 1.046,
+      "step": 4
+    },
+    {
+      "epoch": 0.004479283314669653,
+      "grad_norm": 0.5248474478721619,
+      "learning_rate": 0.0001,
+      "loss": 0.9919,
+      "step": 5
+    },
+    {
+      "epoch": 0.005375139977603583,
+      "grad_norm": 0.4641495943069458,
+      "learning_rate": 0.00012,
+      "loss": 1.0251,
+      "step": 6
+    },
+    {
+      "epoch": 0.005375139977603583,
+      "eval_loss": 1.0897356271743774,
+      "eval_runtime": 110.0518,
+      "eval_samples_per_second": 4.271,
+      "eval_steps_per_second": 2.135,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 617621263220736.0,
+  "total_flos": 1235242526441472.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null