Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f39bab958f1baa84069fb9f9930505c1ffa3ced757bf631e04c7d0b964885eb
+oid sha256:604190b91607495a96c7bb7e7cd1cbec5251930c92d0e89349f627fda735557a
 size 3152296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84209c99b84c49c02d194ff7a5ef69c343251011991e01084ecbfaa9141ffdd1
+oid sha256:585223b93a53a805cffea836299f92d386281b91ed9343edfa576a53986cac69
 size 1656058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfeb6c98fd86c2ec21498af265e94aabd3fba4b6ab1d00da96dd5f98414ec55f
+oid sha256:456bf484f2805c5eb5383d929dec834f74d12009334db2c37db29af2053d4bfc
 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": 4.449767685045443e-05,
+  "epoch": 8.899535370090886e-05,
   "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": 10.614,
       "eval_steps_per_second": 5.307,
       "step": 3
+    },
+    {
+      "epoch": 5.933023580060591e-05,
+      "grad_norm": 1268.106689453125,
+      "learning_rate": 8e-05,
+      "loss": 93.7818,
+      "step": 4
+    },
+    {
+      "epoch": 7.416279475075739e-05,
+      "grad_norm": 1168.54541015625,
+      "learning_rate": 0.0001,
+      "loss": 95.2982,
+      "step": 5
+    },
+    {
+      "epoch": 8.899535370090886e-05,
+      "grad_norm": 1219.5244140625,
+      "learning_rate": 0.00012,
+      "loss": 94.5744,
+      "step": 6
+    },
+    {
+      "epoch": 8.899535370090886e-05,
+      "eval_loss": 23.49866485595703,
+      "eval_runtime": 2649.0765,
+      "eval_samples_per_second": 10.716,
+      "eval_steps_per_second": 5.358,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 26811870216192.0,
+  "total_flos": 53623740432384.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null