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:a2dfb904bf97eeaae1bab6dcf3e91fa059a854756d99fd422595fe85cbb3642f
+oid sha256:f645718eddfa5ff97c8ae8d88ce9f90035f38b4876135d0f746438b833c3a278
 size 327040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c3489c147adccaecb21f396e623e77872febdd9f9a7da4355bfec2a91149603
+oid sha256:aa56f6c262fabd77fa269c14378d9e41268d61d8ddb4b93d3154fa8c5884f49a
 size 739258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9af5373aa88895259568af4bb4ee43ae11bdbf1ba2f7d2b539d2b279040940d
+oid sha256:3fb5f1f2063cc0fc9d69930536ad8305cd213d31011d601a76e1f19f1f368b7a
 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": 0.16216216216216217,
+  "epoch": 0.32432432432432434,
   "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": 68.45,
       "eval_steps_per_second": 34.225,
       "step": 3
+    },
+    {
+      "epoch": 0.21621621621621623,
+      "grad_norm": 0.43882226943969727,
+      "learning_rate": 8e-05,
+      "loss": 11.9086,
+      "step": 4
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 0.40448427200317383,
+      "learning_rate": 0.0001,
+      "loss": 11.9007,
+      "step": 5
+    },
+    {
+      "epoch": 0.32432432432432434,
+      "grad_norm": 0.4453897774219513,
+      "learning_rate": 0.00012,
+      "loss": 11.8834,
+      "step": 6
+    },
+    {
+      "epoch": 0.32432432432432434,
+      "eval_loss": 11.873939514160156,
+      "eval_runtime": 0.1194,
+      "eval_samples_per_second": 67.028,
+      "eval_steps_per_second": 33.514,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 375467802624.0,
+  "total_flos": 750935605248.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null