Training in progress, step 120, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba93b783b81c2e94cabfc01234958ca8443cdf4654a18c8dc2c0d29444cdc8d3
+oid sha256:fac95e774e97b55512fcc70b8ca237b4535609299198e2fe9920860bf7ea9204
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebebcd39e38ed59af1f27b85e60ad31a5acd876b1a3267271cfd9b9d286fd46b
+oid sha256:1235e0eca65a1b54775ee9e48fa2698a5797e1eb1c7f89b3725c444571d58309
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2de9ef8658f2117d8362bfb287d6a2de136300b08418e7df9cafce40b50294c4
+oid sha256:1ac98ec33c30c0e3952ed2ea254164399d74cb186c12e615f9f641292346b49c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:774252ad2ca59a173251c393bb9775b6ad50592c78a9adb425c0845b0166a283
+oid sha256:080e787c96fa8b09f9b8bcf88f51a3766bad6b6691637c9fc0b084cb355db333
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008767303437741871,
+  "epoch": 0.013150955156612807,
   "eval_steps": 40,
-  "global_step": 80,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 15.32,
       "eval_steps_per_second": 7.661,
       "step": 80
+    },
+    {
+      "epoch": 0.013150955156612807,
+      "grad_norm": 16.177526473999023,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 28.7871,
+      "step": 120
+    },
+    {
+      "epoch": 0.013150955156612807,
+      "eval_loss": 1.7560031414031982,
+      "eval_runtime": 1003.96,
+      "eval_samples_per_second": 15.308,
+      "eval_steps_per_second": 7.655,
+      "step": 120
     }
   ],
   "logging_steps": 40,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.211946034921472e+16,
+  "total_flos": 7.817919052382208e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null