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:c302e89b218f98577e052fd6f9ae6583d00c39f84fff987a701313ab02e477ae
+oid sha256:dfa8c53e5e820044af6c50ee1224154243471f291bb2ea626ff5f3dbb284aa50
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fef6524a33a4c5d88382f225ea87d038cc2a45b3239e2c50653ef19cfd0fcfeb
+oid sha256:f0381c9373d63945244b6821e06cbd4bd417ba7642a79644335119bda023a7c7
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4e6470455f66907a19173307202d571c6c3f1f8cd4ddcc5b663dc15013ec0cd
+oid sha256:5b37c228faac27493d5dc2700eeaf67fe98afdbd0e55a68eaf314f21f0aea103
 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": 0.921,
       "step": 115
+    },
+    {
+      "epoch": 0.056727183813191515,
+      "grad_norm": 1.1520406007766724,
+      "learning_rate": 9.815210950408704e-05,
+      "loss": 0.9206,
+      "step": 116
+    },
+    {
+      "epoch": 0.05721621125985696,
+      "grad_norm": 1.240869402885437,
+      "learning_rate": 9.630485006108553e-05,
+      "loss": 1.0142,
+      "step": 117
+    },
+    {
+      "epoch": 0.0577052387065224,
+      "grad_norm": 1.4092172384262085,
+      "learning_rate": 9.4458852508403e-05,
+      "loss": 1.2377,
+      "step": 118
+    },
+    {
+      "epoch": 0.058194266153187846,
+      "grad_norm": 1.3101301193237305,
+      "learning_rate": 9.261474725251261e-05,
+      "loss": 1.1154,
+      "step": 119
+    },
+    {
+      "epoch": 0.05868329359985329,
+      "grad_norm": 1.2811529636383057,
+      "learning_rate": 9.077316405366981e-05,
+      "loss": 0.9481,
+      "step": 120
     }
   ],
   "logging_steps": 1,
@@ -863,7 +898,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.104797324882739e+17,
+  "total_flos": 5.3267450346602496e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null