Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75cbc872c534a49966396c255341d9ff2c917040c39e7f926f7533577d857cc2
+oid sha256:b3aae5e22c885800d90b299eaaf44aee69e3a90e7d46275d0085e4ac6a673db3
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0679492656c17132b1f8d6498337064990d913e068a9db428d6dc866229a749a
+oid sha256:358866885ea048cd89ba52e27e6ed69c858994b3c209c6e2637fb566d18d918b
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:710b3f208bedd5f0fd57c1f63cb3947d4bf432afdfc4b07fd7ad25fb3ae74fb4
+oid sha256:58fe55f37e15eaaf48a322b8fab1abce8bcd6c4961dc9be21f59761cc27ae094
 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": 1.187,
       "step": 95
+    },
+    {
+      "epoch": 0.04694663487988263,
+      "grad_norm": 0.4264492392539978,
+      "learning_rate": 0.00013439489186339282,
+      "loss": 1.1103,
+      "step": 96
+    },
+    {
+      "epoch": 0.04743566232654808,
+      "grad_norm": 0.40396761894226074,
+      "learning_rate": 0.0001326538712840083,
+      "loss": 1.0,
+      "step": 97
+    },
+    {
+      "epoch": 0.04792468977321352,
+      "grad_norm": 0.30181634426116943,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.9821,
+      "step": 98
+    },
+    {
+      "epoch": 0.048413717219878964,
+      "grad_norm": 0.37075236439704895,
+      "learning_rate": 0.00012913897468893248,
+      "loss": 1.0607,
+      "step": 99
+    },
+    {
+      "epoch": 0.04890274466654441,
+      "grad_norm": 0.39950835704803467,
+      "learning_rate": 0.0001273662990072083,
+      "loss": 1.011,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -715,7 +750,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.2170064857726976e+17,
+  "total_flos": 4.438954195550208e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null