Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fd33871aa0d0f51b50cba1fb0203d90329d7f9bc19b87afacf4e3b7de373cf9
+oid sha256:ccc589b2ed469d8a16232a491c057d453a94adf4cd274e82f0b342e01d824ff2
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:552898063b868e317d27cfc9b338084437d472a45e29a3d3340009e045e4fd71
+oid sha256:a871ec41e604afb96042dea37a84812778c4c7a8a56a252ab39de0dfed853d4f
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a40d8d1ccbbf842428d29e94ecbd596d022ee374a0fead6b74a48581009e7248
+oid sha256:1fd06e640d4dc34cb78b41e592a516f89687f6f43b09f38b29ad5a3384483f5b
 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": 0.00015266592878134422,
+  "epoch": 0.00030533185756268844,
   "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": 6.848,
       "eval_steps_per_second": 3.424,
       "step": 3
+    },
+    {
+      "epoch": 0.00020355457170845897,
+      "grad_norm": 6.498128414154053,
+      "learning_rate": 8e-05,
+      "loss": 4.2921,
+      "step": 4
+    },
+    {
+      "epoch": 0.0002544432146355737,
+      "grad_norm": 7.741085052490234,
+      "learning_rate": 0.0001,
+      "loss": 4.3936,
+      "step": 5
+    },
+    {
+      "epoch": 0.00030533185756268844,
+      "grad_norm": 5.888733863830566,
+      "learning_rate": 0.00012,
+      "loss": 3.6026,
+      "step": 6
+    },
+    {
+      "epoch": 0.00030533185756268844,
+      "eval_loss": 3.5490193367004395,
+      "eval_runtime": 1208.0744,
+      "eval_samples_per_second": 6.85,
+      "eval_steps_per_second": 3.425,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1146654849761280.0,
+  "total_flos": 2293309699522560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null