Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fcf40be826f55b07270198e0a6ead902a546dedd458e282c2ffd682c7f06eaa
+oid sha256:099c785d00f552a53e3256c6de344c9c9b068203d4a8da86cbe7d971d6ce297a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eceac72edacc47b86aa1b6436a39c3f9c719c923b943c1c6d4b1f803e72ffbd
+oid sha256:d602eee55c6090dfce8deb583211d914fe5c9ccb9052febe40949d2205aad5b3
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd3b0103484cbe9033aa207b10c52e72e6e07124b9b9355e171cb765f0460e37
+oid sha256:ab2ed981c27f8081d81d2039e0485e05b085c6f7d5fed74c55bf1d3c4164f221
 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": 1.0976,
       "step": 35
+    },
+    {
+      "epoch": 0.017604988079955988,
+      "grad_norm": 0.46739837527275085,
+      "learning_rate": 0.0001993859136895274,
+      "loss": 1.0089,
+      "step": 36
+    },
+    {
+      "epoch": 0.018094015526621432,
+      "grad_norm": 0.3970998227596283,
+      "learning_rate": 0.00019916446955107428,
+      "loss": 1.1005,
+      "step": 37
+    },
+    {
+      "epoch": 0.018583042973286876,
+      "grad_norm": 0.5996494293212891,
+      "learning_rate": 0.0001989091608371146,
+      "loss": 0.9741,
+      "step": 38
+    },
+    {
+      "epoch": 0.01907207041995232,
+      "grad_norm": 0.27929016947746277,
+      "learning_rate": 0.00019862007473534025,
+      "loss": 0.9607,
+      "step": 39
+    },
+    {
+      "epoch": 0.019561097866617763,
+      "grad_norm": 0.33169642090797424,
+      "learning_rate": 0.0001982973099683902,
+      "loss": 1.1173,
+      "step": 40
     }
   ],
   "logging_steps": 1,
@@ -287,7 +322,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5536339684425728e+17,
+  "total_flos": 1.7755816782200832e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null