Training in progress, step 32476, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d064f2332ced8d589411b314d74aa64dbff4eaac037d31068824e3f0f523bb4
+oid sha256:33340270abd0409af6d05e61ef0599813be5c1844119d7769c7068db632d1d9b
 size 355967616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ab97c4aa3f15e2600cfe333e231ff19c0e23e67658b81c4a2261ae5c1af8966
+oid sha256:be70fd8ab879b6d39326b6d12348412b03e6ccfb19399bc1393d6d85e5db7863
 size 712029114

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cae11df3d2278a8ff4a04dff28369bcaea0cb0b7c145bd92f25a776466f1de16
+oid sha256:148ed913b32e8721d0e239a3585a6304177384e08458813be1eba0a7d8567889
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7303cf337b0f3230e3aa10fc27672d49524c56a76ad0cc51d0583606599733d7
+oid sha256:ff90769edad154332f3106098071f15e0ed13400ddcc176f41814d521feb3838
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9976444506027435,
+  "epoch": 0.9999846042523055,
   "eval_steps": 500,
-  "global_step": 32400,
+  "global_step": 32476,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -22687,6 +22687,55 @@
       "learning_rate": 9.773355068215528e-10,
       "loss": 0.6151,
       "step": 32400
+    },
+    {
+      "epoch": 0.9979523655566332,
+      "grad_norm": 13.585440635681152,
+      "learning_rate": 7.722167650797696e-10,
+      "loss": 0.4538,
+      "step": 32410
+    },
+    {
+      "epoch": 0.998260280510523,
+      "grad_norm": 16.41465187072754,
+      "learning_rate": 5.912291741405618e-10,
+      "loss": 0.3448,
+      "step": 32420
+    },
+    {
+      "epoch": 0.9985681954644128,
+      "grad_norm": 17.536109924316406,
+      "learning_rate": 4.343729087002979e-10,
+      "loss": 0.3335,
+      "step": 32430
+    },
+    {
+      "epoch": 0.9988761104183025,
+      "grad_norm": 17.59690284729004,
+      "learning_rate": 3.016481201739696e-10,
+      "loss": 0.539,
+      "step": 32440
+    },
+    {
+      "epoch": 0.9991840253721922,
+      "grad_norm": 23.103965759277344,
+      "learning_rate": 1.930549366757628e-10,
+      "loss": 0.5025,
+      "step": 32450
+    },
+    {
+      "epoch": 0.9994919403260819,
+      "grad_norm": 13.974841117858887,
+      "learning_rate": 1.0859346302460882e-10,
+      "loss": 0.4925,
+      "step": 32460
+    },
+    {
+      "epoch": 0.9997998552799716,
+      "grad_norm": 12.541289329528809,
+      "learning_rate": 4.826378075528659e-11,
+      "loss": 0.5266,
+      "step": 32470
     }
   ],
   "logging_steps": 10,
@@ -22701,12 +22750,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.1672606302208e+18,
+  "total_flos": 2.172344327995392e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null