Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b4f19c6dc3ce188b7bc2468cdc7956e5c378c6c5223026cbd5e6e43697087f9
+oid sha256:96c45b0ebb3f38f5c8a180440d80a8e2496b7690f2fbacdd861658b7dfc1ed0a
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80b30363fdccdb18ec7b001229f2dfbfe819342694ca97dc1fc14d2e36d380aa
+oid sha256:bf5dc4fbfd346e355c7f6778bec926d5e813fcf4e44de0bc9a273971c3d4481e
 size 111142

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44fc8f39a236ff41dd8f3710121e4ad3bacaa037c664e89ad4abf80c969571cf
+oid sha256:9345fe10af0f7cf2c829fcd1c81b1a30d6bed87ebb5af9dd0143336968526052
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
+oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01899736147757256,
+  "epoch": 0.021108179419525065,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 115.867,
       "eval_steps_per_second": 14.489,
       "step": 81
+    },
+    {
+      "epoch": 0.019700967458223397,
+      "grad_norm": 0.030149852856993675,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 11.7631,
+      "step": 84
+    },
+    {
+      "epoch": 0.02040457343887423,
+      "grad_norm": 0.027208149433135986,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 11.7624,
+      "step": 87
+    },
+    {
+      "epoch": 0.021108179419525065,
+      "grad_norm": 0.02712392993271351,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 11.7627,
+      "step": 90
+    },
+    {
+      "epoch": 0.021108179419525065,
+      "eval_loss": 11.762706756591797,
+      "eval_runtime": 61.9821,
+      "eval_samples_per_second": 115.856,
+      "eval_steps_per_second": 14.488,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 62841463504896.0,
+  "total_flos": 69970965037056.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null