Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:957d89e92c1a98bc91dcb5e45fbd523ecc4c09333a3280187a26c6e0dfd3c422
+oid sha256:56b5199118dc6ff050db8c686e195a179b7e5ce755fb9564405099f498130011
 size 3152296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf893f15188d2290bbc4405f6da15509aebdf60b7511a09f4de9304354871213
+oid sha256:e6669a86dd9c9b0fb8c05dacb7c9f695449fb4defe2553c4a7d0a8d49b20b1fc
 size 6332154

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2ac488ce1f441ca1ae6806867cc0d824ea5a04d174d746efdffa5a728cba642
+oid sha256:e1ec70e5c25cb47fe3815029290a7edc4d0b592e520ac9a83fe282041e1d4d4f
 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": 0.06535947712418301,
+  "epoch": 0.09803921568627451,
   "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": 141.3177,
       "step": 18
+    },
+    {
+      "epoch": 0.06862745098039216,
+      "grad_norm": 1190.1522216796875,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 127.6396,
+      "step": 21
+    },
+    {
+      "epoch": 0.0784313725490196,
+      "grad_norm": 1978.2467041015625,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 110.43,
+      "step": 24
+    },
+    {
+      "epoch": 0.0784313725490196,
+      "eval_loss": 27.576690673828125,
+      "eval_runtime": 0.6158,
+      "eval_samples_per_second": 209.468,
+      "eval_steps_per_second": 105.546,
+      "step": 24
+    },
+    {
+      "epoch": 0.08823529411764706,
+      "grad_norm": 2955.03564453125,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 85.8593,
+      "step": 27
+    },
+    {
+      "epoch": 0.09803921568627451,
+      "grad_norm": 2815.968505859375,
+      "learning_rate": 0.0,
+      "loss": 102.8639,
+      "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": 44686450360320.0,
+  "total_flos": 67029675540480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null