Training in progress, step 70, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c48988e3503672bcd20efe09c5a1bafa0c5cbe364fd5f649d4030f5561ebd2c3
+oid sha256:eac4d276cc8dfb92c122f96d7722331ab2be0a7dc6c1c25b1cfc130e3549acbe
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63347c4edc0740f2f38642ed559ad0cf3aac574c28ee3881620e2607864a653e
+oid sha256:9f916e2d7246d3cb330e058e3e9add21b1926920421856061ad710b18f280217
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:893e1298e33ca8842633f58141fa81768aef1e0b4a74c16a299e4ee46dc662bf
+oid sha256:acf07bbae64cbcf8af6682c534d34cfedf7605fb69a8e1de68349219cb35cbb8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8977565a0b4b10da6945c32ba36caa3dc40fc9a4cdc4d66a537fb19aba96e0c7
+oid sha256:ff360a84775339d0d3e752ae059cb60f5332814e8f938b32d8d690f5d4087fc5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03178678403325386,
+  "epoch": 0.03423192126658109,
   "eval_steps": 34,
-  "global_step": 65,
+  "global_step": 70,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -478,6 +478,49 @@
       "learning_rate": 0.000179801722728024,
       "loss": 9.5723,
       "step": 65
+    },
+    {
+      "epoch": 0.03227581147991931,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00017867449380334834,
+      "loss": 9.943,
+      "step": 66
+    },
+    {
+      "epoch": 0.03276483892658476,
+      "grad_norm": 1.2884108865238467e+18,
+      "learning_rate": 0.00017752039761111297,
+      "loss": 7.8637,
+      "step": 67
+    },
+    {
+      "epoch": 0.0332538663732502,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00017633982827411032,
+      "loss": 8.926,
+      "step": 68
+    },
+    {
+      "epoch": 0.0332538663732502,
+      "eval_loss": 9.323250770568848,
+      "eval_runtime": 881.1726,
+      "eval_samples_per_second": 2.931,
+      "eval_steps_per_second": 0.977,
+      "step": 68
+    },
+    {
+      "epoch": 0.033742893819915645,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00017513318895568737,
+      "loss": 9.5527,
+      "step": 69
+    },
+    {
+      "epoch": 0.03423192126658109,
+      "grad_norm": 8.3439319219857e+17,
+      "learning_rate": 0.00017390089172206592,
+      "loss": 8.2968,
+      "step": 70
     }
   ],
   "logging_steps": 1,
@@ -497,7 +540,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4329117893722112e+17,
+  "total_flos": 1.5431357731700736e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null