Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5206b64b2dbfead9aed5d4ffe61b0aefde2dd764fe08312607cb2b94fb8d7932
+oid sha256:2804ca5b5892a76645bfd34d9388ae43f9efcfd8d9f15335cdc723c5a0fed53b
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a26a62fe8b53bf9461820fee5d4f51ec4dd3d81967cb4a1732f165d27c70131
+oid sha256:0b279f97477546bd8157a8dce653efa9e4e2aac00a9e7a0101b5793489729d25
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14a47bb6c7de5708f6f2b75126905ee2455abe93376f11950e796f2aa144c3bf
+oid sha256:94a9b6b38714cd4775330d5c8485f5a42057200cf2746b572faa0571796877a3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3160dd3097641f3bf4d4036c0ddfd8673184925120f088b5ebecc6a1e5c953dd
+oid sha256:07b8a5b9aaab52c529e8225a8efdb5ee4b1c103decfe1101828eac45305d759c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04645760743321719,
+  "epoch": 0.04890274466654441,
   "eval_steps": 34,
-  "global_step": 95,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -696,6 +696,41 @@
       "learning_rate": 0.00013612416661871533,
       "loss": 9.3274,
       "step": 95
+    },
+    {
+      "epoch": 0.04694663487988263,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00013439489186339282,
+      "loss": 8.6449,
+      "step": 96
+    },
+    {
+      "epoch": 0.04743566232654808,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001326538712840083,
+      "loss": 8.9065,
+      "step": 97
+    },
+    {
+      "epoch": 0.04792468977321352,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 8.659,
+      "step": 98
+    },
+    {
+      "epoch": 0.048413717219878964,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00012913897468893248,
+      "loss": 8.259,
+      "step": 99
+    },
+    {
+      "epoch": 0.04890274466654441,
+      "grad_norm": 1.7481951207638434e+19,
+      "learning_rate": 0.0001273662990072083,
+      "loss": 8.2901,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -715,7 +750,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.0942556921593856e+17,
+  "total_flos": 2.204479675957248e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null