Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:123ed3073d733e547e73cf5c12ef1eab8bdc8d550f93d92d5a679475860b3046
+oid sha256:c3295992c8214d092a638b34aabe60c8b34a02d7b93cfd9e100e6a1e374402a9
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dc2d501999844081088c13d16787de2151850ea07748c492f4140910c07185e
+oid sha256:88dbbf6571d5df609b59f43761718dcb3d7967946d9133ecab6853de58839780
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94c43fb3684f58ec378c5792b819fb9c9b31537503ede8bc56fd06d29944f197
+oid sha256:b1126d57531097ea0026af05faaa9e7a86608f2cddc60cf15e2f7243d9b4b451
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fc7800513a1b4dd006c457152c700dd768bb49ee4ed8e4d9665a4e42095b054
+oid sha256:fd5d42bb0afda20ec4c83d38c6af1131541c335ecab229c74e7f418894f3c13b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1532567049808429,
+  "epoch": 0.22988505747126436,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 13.533,
       "eval_steps_per_second": 6.791,
       "step": 100
+    },
+    {
+      "epoch": 0.1685823754789272,
+      "grad_norm": 1.559457778930664,
+      "learning_rate": 9.174206545276677e-05,
+      "loss": 5.099,
+      "step": 110
+    },
+    {
+      "epoch": 0.1839080459770115,
+      "grad_norm": 3.310197353363037,
+      "learning_rate": 7.54514512859201e-05,
+      "loss": 5.6543,
+      "step": 120
+    },
+    {
+      "epoch": 0.19923371647509577,
+      "grad_norm": 4.15278434753418,
+      "learning_rate": 5.983045753470308e-05,
+      "loss": 4.9435,
+      "step": 130
+    },
+    {
+      "epoch": 0.21455938697318008,
+      "grad_norm": 2.930783271789551,
+      "learning_rate": 4.530518418775733e-05,
+      "loss": 5.2414,
+      "step": 140
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "grad_norm": 3.1982288360595703,
+      "learning_rate": 3.227184283742591e-05,
+      "loss": 5.3515,
+      "step": 150
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "eval_loss": 1.3937908411026,
+      "eval_runtime": 20.353,
+      "eval_samples_per_second": 13.512,
+      "eval_steps_per_second": 6.78,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.48452492263424e+16,
+  "total_flos": 6.85418866016256e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null