Training in progress, step 160, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fac95e774e97b55512fcc70b8ca237b4535609299198e2fe9920860bf7ea9204
+oid sha256:07d576f44960ee50c7b5c410926b2877d9d947e1001a7bc925a4c43b5a0906f1
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1235e0eca65a1b54775ee9e48fa2698a5797e1eb1c7f89b3725c444571d58309
+oid sha256:342a7eddb67fb91234085ee861ceaff6d928aad6d8bf765bc31c537b4abc0118
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ac98ec33c30c0e3952ed2ea254164399d74cb186c12e615f9f641292346b49c
+oid sha256:9a11026151701891f1e51da87b129435ea3f0c8a57006941ff93af609e5428fd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:080e787c96fa8b09f9b8bcf88f51a3766bad6b6691637c9fc0b084cb355db333
+oid sha256:500b1c78c9d3af1c55fbf9cc6e380394ac567579f265e54ad9607c3dc9f74108
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013150955156612807,
+  "epoch": 0.017534606875483742,
   "eval_steps": 40,
-  "global_step": 120,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,21 @@
       "eval_samples_per_second": 15.308,
       "eval_steps_per_second": 7.655,
       "step": 120
+    },
+    {
+      "epoch": 0.017534606875483742,
+      "grad_norm": 16.116289138793945,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 28.0053,
+      "step": 160
+    },
+    {
+      "epoch": 0.017534606875483742,
+      "eval_loss": 1.7280950546264648,
+      "eval_runtime": 1003.515,
+      "eval_samples_per_second": 15.315,
+      "eval_steps_per_second": 7.658,
+      "step": 160
     }
   ],
   "logging_steps": 40,
@@ -79,7 +94,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.817919052382208e+16,
+  "total_flos": 1.0423892069842944e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null