Training in progress, step 120, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bc94ba8450a510cff44d172874e2147b62017a7b09db70a03ff21bb97b364a7
+oid sha256:6635fb1a5a4d1e52befb48d9c1dd6d22cef487e7060ad2ae8c77bf218b621c64
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb753185eaccdb5442e4ae0d8f1881afb3f2df47cdcd9c592fca0c8a776ea638
+oid sha256:69f88a4454de958ff0c771396808a3201dd5527422259556c25c03c7e282c3fb
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94bc56f9e3ed1cb490edfa6ed817ab5a627f1fa72c4c42df8f65738ad0756b7b
+oid sha256:f268972a397e2af6ad977488ad986f34c2f5a772c90c6a6cc2e109003c5ffb16
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edf0fb1dfa2c7ca025c1bcf4459d1d508b2f798ad95b431872a2ea669647ad00
+oid sha256:f61ff627b3e4926c6ec03a811654366b4e4d6e1e7047b7acc119ae7fc1df0c10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14881915237787124,
+  "epoch": 0.1552895503073439,
   "eval_steps": 386,
-  "global_step": 115,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -820,6 +820,41 @@
       "learning_rate": 9.992820196634273e-05,
       "loss": 0.9785,
       "step": 115
+    },
+    {
+      "epoch": 0.15011323196376578,
+      "grad_norm": 0.8342046737670898,
+      "learning_rate": 9.992597635191509e-05,
+      "loss": 0.9291,
+      "step": 116
+    },
+    {
+      "epoch": 0.1514073115496603,
+      "grad_norm": 0.8460632562637329,
+      "learning_rate": 9.992371679244658e-05,
+      "loss": 0.8797,
+      "step": 117
+    },
+    {
+      "epoch": 0.15270139113555484,
+      "grad_norm": 0.933060348033905,
+      "learning_rate": 9.992142328947345e-05,
+      "loss": 0.9657,
+      "step": 118
+    },
+    {
+      "epoch": 0.15399547072144937,
+      "grad_norm": 0.8822593688964844,
+      "learning_rate": 9.991909584455511e-05,
+      "loss": 0.8872,
+      "step": 119
+    },
+    {
+      "epoch": 0.1552895503073439,
+      "grad_norm": 0.9599350094795227,
+      "learning_rate": 9.991673445927398e-05,
+      "loss": 0.9064,
+      "step": 120
     }
   ],
   "logging_steps": 1,
@@ -839,7 +874,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2856277474476032e+17,
+  "total_flos": 1.3415246060322816e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null