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:b3cb6f6d7125e06cad3ce4ec6b4428f4ed2774e750a110f7da03ab5bf042ffad
+oid sha256:0d54e6b341c9be98a4af0715ff6dce711430e07f2f612fd736e4a42ec84184c5
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87e259672daea107618ff5a7819682eca20eb6b044357ae111256fb8aa94ae6e
+oid sha256:26e51d6b5cc9f325500e591745dd70816c1dd1e119df7eac2c5e7dfca71e9003
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0a056a23a2b694850733aa8969819c8c578fa33328554e51a9e924a49fd0982
+oid sha256:63606c73c93c05d27e7758139a39e39228c390bd2d751703d97059d8f583fa7f
 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": 0.0008945143905002571,
+  "epoch": 0.0013417715857503858,
   "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": 1.1612,
       "step": 18
+    },
+    {
+      "epoch": 0.0009392401100252701,
+      "grad_norm": 2.832472324371338,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.014,
+      "step": 21
+    },
+    {
+      "epoch": 0.0010734172686003086,
+      "grad_norm": 2.603668451309204,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.9522,
+      "step": 24
+    },
+    {
+      "epoch": 0.0010734172686003086,
+      "eval_loss": 1.1618468761444092,
+      "eval_runtime": 539.6973,
+      "eval_samples_per_second": 17.445,
+      "eval_steps_per_second": 8.723,
+      "step": 24
+    },
+    {
+      "epoch": 0.0012075944271753472,
+      "grad_norm": 2.582103967666626,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.2137,
+      "step": 27
+    },
+    {
+      "epoch": 0.0013417715857503858,
+      "grad_norm": 2.5562214851379395,
+      "learning_rate": 0.0,
+      "loss": 1.1791,
+      "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