Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:913ca4ebebe2d38cd866ac1d189683298626ef6453e12b508bc5ded3ff629b28
+oid sha256:06287dd92760c13d42f62e11861618dfed5f857f9b7953f36bd864e833e0fc4c
 size 5752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99f83b3a91b7045f0029cb2d91ec053bfff88a8090d516aceb4354984ff8710b
+oid sha256:e02e562246511e9604df9b9e0f8eb87c517d8a5de1e4477a1b65e19f551e4c2f
 size 15814

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": 0.00015167793718005436,
+  "epoch": 0.00030335587436010873,
   "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": 147.278,
       "eval_steps_per_second": 73.639,
       "step": 3
+    },
+    {
+      "epoch": 0.0002022372495734058,
+      "grad_norm": 5.206894638831727e-05,
+      "learning_rate": 8e-05,
+      "loss": 46.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.00025279656196675726,
+      "grad_norm": 1.0826270226971246e-05,
+      "learning_rate": 0.0001,
+      "loss": 46.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.00030335587436010873,
+      "grad_norm": 1.5332319890148938e-05,
+      "learning_rate": 0.00012,
+      "loss": 46.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.00030335587436010873,
+      "eval_loss": 11.5,
+      "eval_runtime": 56.9386,
+      "eval_samples_per_second": 146.263,
+      "eval_steps_per_second": 73.131,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 109575831552.0,
+  "total_flos": 219151663104.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null