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:de0b87da2e30483d34b678120d1dff91af08f7c17bf74c9bf6f2c9d1725daae8
+oid sha256:deea8f1e783b773626984886ab029c610e4784a6ec84b96b790561fa610d868d
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8262efbe541a625ece18e3ac43846177c1712679564f7b898f581e6e5d8bfefb
+oid sha256:bd09ef20115ccdfeb57c443c2471cdad3bf98261f28f4cb6e7ff1a5a6cb336cb
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3263d4bcc23a5b2f8dacbc49c8b02636291417ad47b1291c84ef12307fc7d93
+oid sha256:9d5c51856a73f7bc59089afabbf3e78ff64adb1c34833e96c5b147cbb8666adf
 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": 0.0013824884792626728,
+  "epoch": 0.0027649769585253456,
   "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": 18.187,
       "eval_steps_per_second": 9.094,
       "step": 3
+    },
+    {
+      "epoch": 0.0018433179723502304,
+      "grad_norm": 1.7767750024795532,
+      "learning_rate": 8e-05,
+      "loss": 1.9123,
+      "step": 4
+    },
+    {
+      "epoch": 0.002304147465437788,
+      "grad_norm": 1.192010521888733,
+      "learning_rate": 0.0001,
+      "loss": 2.0913,
+      "step": 5
+    },
+    {
+      "epoch": 0.0027649769585253456,
+      "grad_norm": 1.4868011474609375,
+      "learning_rate": 0.00012,
+      "loss": 1.794,
+      "step": 6
+    },
+    {
+      "epoch": 0.0027649769585253456,
+      "eval_loss": 1.7426038980484009,
+      "eval_runtime": 50.5081,
+      "eval_samples_per_second": 18.096,
+      "eval_steps_per_second": 9.048,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 897677650821120.0,
+  "total_flos": 1848159869337600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null