Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eac4d276cc8dfb92c122f96d7722331ab2be0a7dc6c1c25b1cfc130e3549acbe
+oid sha256:4e672f97b29a9edce6f91b2e15c39845acd8e5b4753ab13d398e905d5543c13a
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f916e2d7246d3cb330e058e3e9add21b1926920421856061ad710b18f280217
+oid sha256:aea7773082e0f49ff710e5dd6702209f08402f1b7153c857b70854dc0dd63a98
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acf07bbae64cbcf8af6682c534d34cfedf7605fb69a8e1de68349219cb35cbb8
+oid sha256:02cc5e0d782e790ab911b5caf87830bdc24d1c04827eeec883676aadfd733f51
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff360a84775339d0d3e752ae059cb60f5332814e8f938b32d8d690f5d4087fc5
+oid sha256:52408658f8afed2d0ac64c41a3c3f93b4c8a8478fa6362941012d17f634f7dad
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03423192126658109,
+  "epoch": 0.03667705849990831,
   "eval_steps": 34,
-  "global_step": 70,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -521,6 +521,41 @@
       "learning_rate": 0.00017390089172206592,
       "loss": 8.2968,
       "step": 70
+    },
+    {
+      "epoch": 0.03472094871324653,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00017264335740162242,
+      "loss": 9.469,
+      "step": 71
+    },
+    {
+      "epoch": 0.035209976159911976,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00017136101544117525,
+      "loss": 9.3297,
+      "step": 72
+    },
+    {
+      "epoch": 0.03569900360657742,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001700543037593291,
+      "loss": 9.2072,
+      "step": 73
+    },
+    {
+      "epoch": 0.036188031053242864,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00016872366859692627,
+      "loss": 8.5818,
+      "step": 74
+    },
+    {
+      "epoch": 0.03667705849990831,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00016736956436465573,
+      "loss": 9.1275,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -540,7 +575,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5431357731700736e+17,
+  "total_flos": 1.653359756967936e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null