Training in progress, step 120, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dec3c804efa9b563024db4635abb8ecc020fd426099ca968882c32fe12e562a
+oid sha256:fd44c789e94023670df94d9de7cfa0e23d457636e1aeb572f4ded2879fe37671
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e0d4a08033d58fa22883192773140e30c677ea4e64c03ce876a6535fa131af1
+oid sha256:06dab9484f890d1c34767578aa1fd8330ed4e238fd7cdf94a5d0b30b4579ca79
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e519c0fe8adb4134a5a25f1cc3e9e326cde40d4e0100debb0f8a4835d48f6c61
+oid sha256:bc859039bcc6b781df2a009ffb4406a80f5812d9799e1fc6a37d172ad3a00b52
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d445cf5235925cca1a6d5e57200162b082b481744bf739a511d532ac296ab841
+oid sha256:ba16893b2c4735e8eaf86592331a8dda9b3bcccecd302e828000513277487239
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05623815636652607,
+  "epoch": 0.05868329359985329,
   "eval_steps": 34,
-  "global_step": 115,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -844,6 +844,41 @@
       "learning_rate": 0.0001,
       "loss": 1.0625,
       "step": 115
+    },
+    {
+      "epoch": 0.056727183813191515,
+      "grad_norm": 1.5200375318527222,
+      "learning_rate": 9.815210950408704e-05,
+      "loss": 1.1155,
+      "step": 116
+    },
+    {
+      "epoch": 0.05721621125985696,
+      "grad_norm": 1.8069548606872559,
+      "learning_rate": 9.630485006108553e-05,
+      "loss": 1.226,
+      "step": 117
+    },
+    {
+      "epoch": 0.0577052387065224,
+      "grad_norm": 1.832614779472351,
+      "learning_rate": 9.4458852508403e-05,
+      "loss": 1.3931,
+      "step": 118
+    },
+    {
+      "epoch": 0.058194266153187846,
+      "grad_norm": 1.797018051147461,
+      "learning_rate": 9.261474725251261e-05,
+      "loss": 1.3913,
+      "step": 119
+    },
+    {
+      "epoch": 0.05868329359985329,
+      "grad_norm": 1.7891651391983032,
+      "learning_rate": 9.077316405366981e-05,
+      "loss": 1.1728,
+      "step": 120
     }
   ],
   "logging_steps": 1,
@@ -863,7 +898,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.639056226091008e+16,
+  "total_flos": 6.927710844616704e+16,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null