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:d6a1d1c418171e0f8a02ffe8e36d4f48c69bee384ceda5aeb95b0be4a490e0dc
+oid sha256:98cc27ac06f036a1fed78d6941442b00a3aab5f6768798e12d9e6b5b2bfe41fc
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ece7e5e6460dcfa7527b50e4d3556ef7462e8b0fdfb49413490d743da2f13fa
+oid sha256:b8231cf2fa686f6f40f7d9a08c593dd03e806457a2b9311cd9afe1fa3c91b147
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cdf2e72b02826124ca59f8c820f38649bf8b862d21d1b6a4a97177560c2e1d6
+oid sha256:021fd4d755be57c1b9d6e2e382d8dd33b208ab2b49ffb3a980c787eaa9b807c1
 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": 0.0018992450500925882,
+  "epoch": 0.0028488675751388824,
   "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": 3.6524,
       "step": 18
+    },
+    {
+      "epoch": 0.0019942073025972177,
+      "grad_norm": 5.910211086273193,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 3.5474,
+      "step": 21
+    },
+    {
+      "epoch": 0.002279094060111106,
+      "grad_norm": 4.693480491638184,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 3.9454,
+      "step": 24
+    },
+    {
+      "epoch": 0.002279094060111106,
+      "eval_loss": 3.245171070098877,
+      "eval_runtime": 183.7955,
+      "eval_samples_per_second": 24.125,
+      "eval_steps_per_second": 12.062,
+      "step": 24
+    },
+    {
+      "epoch": 0.002563980817624994,
+      "grad_norm": 4.464496612548828,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 3.1348,
+      "step": 27
+    },
+    {
+      "epoch": 0.0028488675751388824,
+      "grad_norm": 5.4965620040893555,
+      "learning_rate": 0.0,
+      "loss": 2.8183,
+      "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": 2010596581048320.0,
+  "total_flos": 3015894871572480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null