Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a8e71f86113fb879d1876dfc599bba0c1b0ad330738a83f0156170f575808f
+oid sha256:016b3660dc0f68a9ab286ae7e03093681e9cf4f6ca446e9e02b79a2f0d8f37ff
 size 28350504

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b41ecee9c568a77236e8cbbfa242b3803b33ed77897857462cf245b3ab45a02
+oid sha256:e6fc19204c89859f7039184c97eb209a8239f3ce14109b361254a314c4b4e1a4
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98c96b5e6811e264a82636893b20993c7fd3b70e662b81fe25e9b6d360eb6062
+oid sha256:400a6d6a18fc16b638aeb824699e8e27e212104bd39097badfed36b500f6402a
 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": 0.004140786749482402,
+  "epoch": 0.008281573498964804,
   "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": 52.326,
       "eval_steps_per_second": 26.249,
       "step": 3
+    },
+    {
+      "epoch": 0.005521048999309869,
+      "grad_norm": 2.0866777896881104,
+      "learning_rate": 8e-05,
+      "loss": 13.8692,
+      "step": 4
+    },
+    {
+      "epoch": 0.006901311249137336,
+      "grad_norm": 2.7461817264556885,
+      "learning_rate": 0.0001,
+      "loss": 13.9277,
+      "step": 5
+    },
+    {
+      "epoch": 0.008281573498964804,
+      "grad_norm": 2.6720032691955566,
+      "learning_rate": 0.00012,
+      "loss": 14.387,
+      "step": 6
+    },
+    {
+      "epoch": 0.008281573498964804,
+      "eval_loss": 3.499831199645996,
+      "eval_runtime": 5.9066,
+      "eval_samples_per_second": 51.637,
+      "eval_steps_per_second": 25.903,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 89618821152768.0,
+  "total_flos": 179237642305536.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null