Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61aece05d6fca5a9a455223f54d11788fb69baa3a1bb939dcd1217cf74f42a8c
+oid sha256:ff5c01536603146100222abf6146eff05cffdc5e94edde6aa0956c0eace6df18
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:595168fc88acc93538dac96ad7075991c7f5e24a1f60aa1e44636d2f2ebc40fe
+oid sha256:16a0c26d020a13b36df9d82b4b4293d1eb88d9fe2c629f9fc0d03af5f234ea0e
 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": 8.2064,
       "step": 95
+    },
+    {
+      "epoch": 0.04694663487988263,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00013439489186339282,
+      "loss": 8.2788,
+      "step": 96
+    },
+    {
+      "epoch": 0.04743566232654808,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001326538712840083,
+      "loss": 10.1197,
+      "step": 97
+    },
+    {
+      "epoch": 0.04792468977321352,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 9.6074,
+      "step": 98
+    },
+    {
+      "epoch": 0.048413717219878964,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00012913897468893248,
+      "loss": 8.1992,
+      "step": 99
+    },
+    {
+      "epoch": 0.04890274466654441,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001273662990072083,
+      "loss": 10.0557,
+      "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