Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:136d978c2302936c6fed7f294a83c45816874d842826b8cadc2d58940d34692b
+oid sha256:6aff20f37d772976c5634a8882c18cb4da4ce2b251090b6ba066f2f887063014
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87b8b7972930c56517f690e015c4a46d71f14bfac9aec3990eec0faaca5e27bb
+oid sha256:df0e8459953fb690e3ffc2e8560ba7a0b9f24faa5ab691fa44fb7205fa3c1156
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d1b8821978c7450bd2cb49e068182933549eb330933b29022697a95533c47a4
+oid sha256:8dd60e9ba809120cc78feb8bd27109edcdf93018d99882fdeecb2257ff3c3de7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005179334455522465,
+  "epoch": 0.007769001683283698,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 0.2797,
       "step": 18
+    },
+    {
+      "epoch": 0.005438301178298589,
+      "grad_norm": 1.3260667324066162,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.3583,
+      "step": 21
+    },
+    {
+      "epoch": 0.006215201346626958,
+      "grad_norm": 1.1539181470870972,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.3132,
+      "step": 24
+    },
+    {
+      "epoch": 0.006215201346626958,
+      "eval_loss": 0.2725517749786377,
+      "eval_runtime": 209.9977,
+      "eval_samples_per_second": 7.743,
+      "eval_steps_per_second": 3.871,
+      "step": 24
+    },
+    {
+      "epoch": 0.006992101514955328,
+      "grad_norm": 0.7530409097671509,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.2945,
+      "step": 27
+    },
+    {
+      "epoch": 0.007769001683283698,
+      "grad_norm": 0.7379133105278015,
+      "learning_rate": 0.0,
+      "loss": 0.2486,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7418872835604480.0,
+  "total_flos": 1.112830925340672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null