Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d7d5ace59301ef71be2bd6d8698b351177428b85baa65d64373f38ea09b6c7f
+oid sha256:c1a0be86756541ae19b56068952bbf4301aa137e4d7e3163e56645c3c9e5c1da
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3cf6327c2c5b6ff9a6384114a5cf5f865390434caf0f950d1aa124a7222b9d5
+oid sha256:c1265e9bbacac34100524b9490614c78f35ba67a0a4ff557e95311a6e189c3e4
 size 33424212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b663b5eda4d0da2dcb843509e2c21a870da154750c8ea7d398f43a7e0cf8632
+oid sha256:27e83968c2d0fcbd9ce3decdbd850180096a3c3813ec3f1e2e7fbcdcb1b335e3
 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": 0.009811937857726901,
+  "epoch": 0.019623875715453803,
   "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": 37.235,
       "eval_steps_per_second": 18.762,
       "step": 3
+    },
+    {
+      "epoch": 0.013082583810302535,
+      "grad_norm": 1.4563934803009033,
+      "learning_rate": 8e-05,
+      "loss": 7.0282,
+      "step": 4
+    },
+    {
+      "epoch": 0.016353229762878167,
+      "grad_norm": 3.0670440196990967,
+      "learning_rate": 0.0001,
+      "loss": 9.6027,
+      "step": 5
+    },
+    {
+      "epoch": 0.019623875715453803,
+      "grad_norm": 1.7290756702423096,
+      "learning_rate": 0.00012,
+      "loss": 8.393,
+      "step": 6
+    },
+    {
+      "epoch": 0.019623875715453803,
+      "eval_loss": 2.274766445159912,
+      "eval_runtime": 3.5282,
+      "eval_samples_per_second": 36.563,
+      "eval_steps_per_second": 18.423,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 489743409217536.0,
+  "total_flos": 979486818435072.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null