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:d3a4f02ad8b07e309a72610440eac89f43b6a73ecbde72d9a64d6223792ec51c
+oid sha256:8d3c76ec54cebb46938dfd41a76f54fe54d8159062baf9b4b6361f0053e986c5
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec8f83f0ef02a599c23b0401bad8ddcbc07b69e20c6324b6049367e21a1d7244
+oid sha256:5cd1743125004b9174b9f01dfc9af28299d878359adee3a296d6c8c2368848a4
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9264abfa6d2cc5145363bf71d2fb16332b1ac4e60642a70827881d9a447c36a4
+oid sha256:af82c1f1d4ec999545a290f8875f59e0434314b9e98a3c2553c0c541daf4cdfa
 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": 0.001177971925002454,
+  "epoch": 0.002355943850004908,
   "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": 213.792,
       "eval_steps_per_second": 106.996,
       "step": 3
+    },
+    {
+      "epoch": 0.0015706292333366055,
+      "grad_norm": 1.4662525653839111,
+      "learning_rate": 8e-05,
+      "loss": 44.4384,
+      "step": 4
+    },
+    {
+      "epoch": 0.0019632865416707567,
+      "grad_norm": 0.8915764093399048,
+      "learning_rate": 0.0001,
+      "loss": 44.4569,
+      "step": 5
+    },
+    {
+      "epoch": 0.002355943850004908,
+      "grad_norm": 0.9424355626106262,
+      "learning_rate": 0.00012,
+      "loss": 44.4515,
+      "step": 6
+    },
+    {
+      "epoch": 0.002355943850004908,
+      "eval_loss": 11.115720748901367,
+      "eval_runtime": 5.1321,
+      "eval_samples_per_second": 209.076,
+      "eval_steps_per_second": 104.635,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 28934406144.0,
+  "total_flos": 57868812288.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null