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:d36b1de1f39ae474346d7acc59db5021a9c7a2c8672c2f4d288d50c7744c31f2
+oid sha256:1e7950327da01392443cc2b7f37b2c125ed93ce974ba68872e001c1e4864c342
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7252d979c6a34506c6c18cd0200c897042ad0cf8bb4ad6f3ffc39a582c59858
+oid sha256:ce3bb0ac6988a7ccfed473206a359b6472da41742b949fe87b1a58da8fa50e05
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e70b79e981efcee269a85b5335952c01a391777d417097a1d9f7e3a2b47a78dc
+oid sha256:dc20ee7bacf5c95c2142e506581a4d197785697bff9c378cd497db51cba9e5a9
 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": 8.6766,
       "step": 115
+    },
+    {
+      "epoch": 0.056727183813191515,
+      "grad_norm": Infinity,
+      "learning_rate": 9.815210950408704e-05,
+      "loss": 9.2254,
+      "step": 116
+    },
+    {
+      "epoch": 0.05721621125985696,
+      "grad_norm": 1.6816025393206133e+19,
+      "learning_rate": 9.630485006108553e-05,
+      "loss": 8.8447,
+      "step": 117
+    },
+    {
+      "epoch": 0.0577052387065224,
+      "grad_norm": Infinity,
+      "learning_rate": 9.4458852508403e-05,
+      "loss": 9.6149,
+      "step": 118
+    },
+    {
+      "epoch": 0.058194266153187846,
+      "grad_norm": Infinity,
+      "learning_rate": 9.261474725251261e-05,
+      "loss": 9.6149,
+      "step": 119
+    },
+    {
+      "epoch": 0.05868329359985329,
+      "grad_norm": Infinity,
+      "learning_rate": 9.077316405366981e-05,
+      "loss": 9.4713,
+      "step": 120
     }
   ],
   "logging_steps": 1,
@@ -863,7 +898,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5351516273508352e+17,
+  "total_flos": 2.6453756111486976e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null