Training in progress, step 115, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:351753d46ffc91b1dc947070dd4b639c8388128ee5fe0abea4e2c8d332773b3e
+oid sha256:d36b1de1f39ae474346d7acc59db5021a9c7a2c8672c2f4d288d50c7744c31f2
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd7e5ecec0c8a3684326bea00fcf95dfb59ebc0b2835bd86344757e5488e83f
+oid sha256:d7252d979c6a34506c6c18cd0200c897042ad0cf8bb4ad6f3ffc39a582c59858
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:224a371397cd38e6f33df8d6c03713b6fae877d0326fb5ca5060998390efdc67
+oid sha256:e70b79e981efcee269a85b5335952c01a391777d417097a1d9f7e3a2b47a78dc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:802e09b6cc63e64e726d0b68ba37b81d6a6fcf54cdf00e4821b3e38426a8a5c4
+oid sha256:d445cf5235925cca1a6d5e57200162b082b481744bf739a511d532ac296ab841
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05379301913319885,
+  "epoch": 0.05623815636652607,
   "eval_steps": 34,
-  "global_step": 110,
+  "global_step": 115,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -809,6 +809,41 @@
       "learning_rate": 0.00010922683594633021,
       "loss": 8.693,
       "step": 110
+    },
+    {
+      "epoch": 0.054282046579864296,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00010738525274748741,
+      "loss": 10.5717,
+      "step": 111
+    },
+    {
+      "epoch": 0.05477107402652974,
+      "grad_norm": Infinity,
+      "learning_rate": 0.000105541147491597,
+      "loss": 8.062,
+      "step": 112
+    },
+    {
+      "epoch": 0.05526010147319518,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00010369514993891452,
+      "loss": 9.9227,
+      "step": 113
+    },
+    {
+      "epoch": 0.05574912891986063,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00010184789049591299,
+      "loss": 9.0195,
+      "step": 114
+    },
+    {
+      "epoch": 0.05623815636652607,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001,
+      "loss": 8.6766,
+      "step": 115
     }
   ],
   "logging_steps": 1,
@@ -828,7 +863,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.4249276435529728e+17,
+  "total_flos": 2.5351516273508352e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null