Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff0260d1e3631bfaf3aad882c37dfe986418a9da16b6a4e18e4aa30e93aa2502
+oid sha256:bc401528be5fc9de4bb49982a7dc2a42745c3f4f115ade208627dbca7071c7f8
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5661af4bb46bd4690466f1c6547cb2605855d735bc15f0f625b75eddd477b21b
+oid sha256:f6bf2cb94ce5eba23af2a09df9e2a5daa15283bd4cbf0db5a31caaac8e36bb51
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c9d6305112455934908c7bfd9606d4794d06684c6273dfde936a82028d5a005
+oid sha256:4eb55320a08e50ed394cd960f98070f7af223236ab26cee8318395f23a36d7e2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:666e3907648b0318630be4f0e9270d7d902986930986134493537abd333e959c
+oid sha256:35e2941b1419d36fedcd8eb55488740cb386508ea401393ade4c1f5fd25ff6c8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.017115960633290545,
+  "epoch": 0.019561097866617763,
   "eval_steps": 34,
-  "global_step": 35,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -268,6 +268,41 @@
       "learning_rate": 0.00019957341762950344,
       "loss": 10.3859,
       "step": 35
+    },
+    {
+      "epoch": 0.017604988079955988,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001993859136895274,
+      "loss": 8.1513,
+      "step": 36
+    },
+    {
+      "epoch": 0.018094015526621432,
+      "grad_norm": 7.999064190058758e+18,
+      "learning_rate": 0.00019916446955107428,
+      "loss": 9.6598,
+      "step": 37
+    },
+    {
+      "epoch": 0.018583042973286876,
+      "grad_norm": 2.2595998866116444e+18,
+      "learning_rate": 0.0001989091608371146,
+      "loss": 8.1904,
+      "step": 38
+    },
+    {
+      "epoch": 0.01907207041995232,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00019862007473534025,
+      "loss": 9.4891,
+      "step": 39
+    },
+    {
+      "epoch": 0.019561097866617763,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001982973099683902,
+      "loss": 9.481,
+      "step": 40
     }
   ],
   "logging_steps": 1,
@@ -287,7 +322,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.715678865850368e+16,
+  "total_flos": 8.817918703828992e+16,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null