Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5586ddddc69320d0095d618c46d2fdacbdb8ef7294baa30229732de67dfceaca
+oid sha256:9a31ab2858e9d66a89cab9c5c25b7e5be905d871ae484e8d815297e1f3f629d4
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8caa2f0e71f4e63762f73f16a688f8cb00964335c19c20452ec57eb93200f56f
+oid sha256:9306beb12e15235296e43ade21ec2baeb35eae9f2a6d37b0710ef585af9a2444
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be49aba643c4c924b8b230e4e5b7acbeb595ea0a298d4ed9fcb7804f045f4cf4
+oid sha256:8ef8df3090ba6573a77d2f727ab3a7630e0e74ae94ec69d6fec04916402509d0
 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": 0.00044477390659747963,
+  "epoch": 0.0008895478131949593,
   "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": 53.004,
       "eval_steps_per_second": 26.502,
       "step": 3
+    },
+    {
+      "epoch": 0.0005930318754633062,
+      "grad_norm": 0.6960687637329102,
+      "learning_rate": 8e-05,
+      "loss": 1.3669,
+      "step": 4
+    },
+    {
+      "epoch": 0.0007412898443291327,
+      "grad_norm": 0.699456512928009,
+      "learning_rate": 0.0001,
+      "loss": 1.5292,
+      "step": 5
+    },
+    {
+      "epoch": 0.0008895478131949593,
+      "grad_norm": 0.778120756149292,
+      "learning_rate": 0.00012,
+      "loss": 1.3721,
+      "step": 6
+    },
+    {
+      "epoch": 0.0008895478131949593,
+      "eval_loss": 1.3613526821136475,
+      "eval_runtime": 53.5086,
+      "eval_samples_per_second": 53.076,
+      "eval_steps_per_second": 26.538,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 51196944187392.0,
+  "total_flos": 95716026089472.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null