Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eeeabbcf365606d9bdef99eaa6a346054f3a1b5cab37d9bb166a5abcfbe084fb
+oid sha256:517bae1cbe8e61855e5c9e682798973e5a5563b882428b519e405b4cdf083fe2
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:febfcabbc0d8fa0028b1442a6ef558ecd24148305b440dc9ca1b781236b8de1a
+oid sha256:988765cc0fb5f0ab61abc3bfc4e43f942b8af26c08f9c0dc2de1debf3025f959
 size 1342555602

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc60ce7b7454ee40040b97c5d845c4f43baceb4f0fc660db7ac6d4bec775c901
+oid sha256:1c69b824253ff1a0f68a35d89ef1937ad58396ad24222443cdfdb55bb024185b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09ab64d5ace66796aa9c2fa2fc4e0206d69a1eb4ef03f574f85ee8eb16a64b71
+oid sha256:429c9f0a4ff1909f8cc1cafc3bf6eb6ff29e4592139b5344f1aee9b75eae7379
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6864406779661016,
+  "epoch": 0.7627118644067796,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -199,6 +199,28 @@
       "eval_samples_per_second": 18.891,
       "eval_steps_per_second": 2.384,
       "step": 81
+    },
+    {
+      "epoch": 0.7203389830508474,
+      "grad_norm": 0.5136195421218872,
+      "learning_rate": 1.2639779077309098e-05,
+      "loss": 0.77,
+      "step": 85
+    },
+    {
+      "epoch": 0.7627118644067796,
+      "grad_norm": 0.5830088257789612,
+      "learning_rate": 5.709035061653494e-06,
+      "loss": 0.7518,
+      "step": 90
+    },
+    {
+      "epoch": 0.7627118644067796,
+      "eval_loss": 0.7687093019485474,
+      "eval_runtime": 22.2345,
+      "eval_samples_per_second": 18.89,
+      "eval_steps_per_second": 2.384,
+      "step": 90
     }
   ],
   "logging_steps": 5,
@@ -218,7 +240,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2596088382527898e+17,
+  "total_flos": 1.3953750603399168e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null