Training in progress, step 170, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9354ab4a7ce8547671b14d84f50c16c066ccb67d905ae21bb089417cb3367e5
+oid sha256:fe631d2abad406695e6d180dced2bde0902c868474b8d2c4f36de4cadffd9e48
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb39ebd7a334944e5a271162b8f2bd07cc32d5062d51c937404ee4aad36c5bb8
+oid sha256:798c2ae1e6dff48072797de0adcb6823ce7a7fdbddb5d729b451780944ef9ef4
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ae36b88f579a5ac24bd63c58055344d0b6ee1ce3c4b9a88d6e3a11fff784ffe
+oid sha256:2da1280f00d05c94b786e42e947c1fdef9fa41c2297c39831ded2e8566dc003e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9d255475980828d00dffcac4a69741da74c7e5ef4f645ab21d69e57306e3317
+oid sha256:963abeacc51d2fd967b0d854376103780952d47675257465be60a3612cecb103
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08068952869979827,
+  "epoch": 0.08313466593312549,
   "eval_steps": 34,
-  "global_step": 165,
+  "global_step": 170,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1202,6 +1202,49 @@
       "learning_rate": 2.0198277271976052e-05,
       "loss": 8.9486,
       "step": 165
+    },
+    {
+      "epoch": 0.08117855614646372,
+      "grad_norm": Infinity,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 8.5101,
+      "step": 166
+    },
+    {
+      "epoch": 0.08166758359312916,
+      "grad_norm": Infinity,
+      "learning_rate": 1.8025951709277898e-05,
+      "loss": 8.4037,
+      "step": 167
+    },
+    {
+      "epoch": 0.0821566110397946,
+      "grad_norm": 1.4232143381118583e+19,
+      "learning_rate": 1.6981596918444953e-05,
+      "loss": 10.2633,
+      "step": 168
+    },
+    {
+      "epoch": 0.08264563848646005,
+      "grad_norm": Infinity,
+      "learning_rate": 1.5965592836210743e-05,
+      "loss": 9.3424,
+      "step": 169
+    },
+    {
+      "epoch": 0.08313466593312549,
+      "grad_norm": Infinity,
+      "learning_rate": 1.4978286427038601e-05,
+      "loss": 8.9031,
+      "step": 170
+    },
+    {
+      "epoch": 0.08313466593312549,
+      "eval_loss": 9.365218162536621,
+      "eval_runtime": 880.7771,
+      "eval_samples_per_second": 2.933,
+      "eval_steps_per_second": 0.978,
+      "step": 170
     }
   ],
   "logging_steps": 1,
@@ -1221,7 +1264,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.637391465329459e+17,
+  "total_flos": 3.7476154491273216e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null