Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb70f04bedd070ed7a8ba69c81c86ea2e4dcb583e2b785bb2bb49e10ffc1a62f
+oid sha256:454254aab4119f887a5efa5b0125ebc1c2e943cd4c7415626772323a0d8cf829
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:775b188ad134f29bff3db082f8d51531c11c6f8f2ef484b3a9d373618fd75920
+oid sha256:8105dce85c9dab82365dab5fad70308ea63eaa5c44dd263af5bc66c521bd31ee
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec12f28e479716caa37a47da40d608c7ddf29f4c0d224be7900e717ee835399
+oid sha256:0f5adca46d5768b2528d11214bf50c169d41422785e8b729921c5399a7fed5df
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011933174224343675,
+  "epoch": 0.02386634844868735,
   "eval_steps": 3,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,57 @@
       "learning_rate": 0.0001,
       "loss": 0.7511,
       "step": 5
+    },
+    {
+      "epoch": 0.014319809069212411,
+      "grad_norm": 0.9399459362030029,
+      "learning_rate": 0.00012,
+      "loss": 0.891,
+      "step": 6
+    },
+    {
+      "epoch": 0.014319809069212411,
+      "eval_loss": 0.9594031572341919,
+      "eval_runtime": 124.0791,
+      "eval_samples_per_second": 1.427,
+      "eval_steps_per_second": 0.717,
+      "step": 6
+    },
+    {
+      "epoch": 0.016706443914081145,
+      "grad_norm": 0.5230587124824524,
+      "learning_rate": 0.00014,
+      "loss": 0.7866,
+      "step": 7
+    },
+    {
+      "epoch": 0.01909307875894988,
+      "grad_norm": 0.9042274951934814,
+      "learning_rate": 0.00016,
+      "loss": 1.095,
+      "step": 8
+    },
+    {
+      "epoch": 0.021479713603818614,
+      "grad_norm": 0.45211946964263916,
+      "learning_rate": 0.00018,
+      "loss": 0.6814,
+      "step": 9
+    },
+    {
+      "epoch": 0.021479713603818614,
+      "eval_loss": 0.9087545275688171,
+      "eval_runtime": 124.474,
+      "eval_samples_per_second": 1.422,
+      "eval_steps_per_second": 0.715,
+      "step": 9
+    },
+    {
+      "epoch": 0.02386634844868735,
+      "grad_norm": 0.5287061929702759,
+      "learning_rate": 0.0002,
+      "loss": 0.795,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -72,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 967722569564160.0,
+  "total_flos": 1935445139128320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null