Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c1cdac4fa56d293a7582944309515f89235ded7ec882480f161d01950e3bc31
+oid sha256:5d571c3a8eab6a750c1b1766683368d199ff123aa287ad8f192a93d2356ee7a8
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38a597126ab62251347c6985bfd1c58fd6ad8492715bef299161ca8e22e75268
+oid sha256:ab667f6e70cfc59dc7c436e76f82b73435149572f267b3409d867c0c19b83e83
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:424d06375131df3df5d4883391c61f995c66d877e893fd245f2c624058954297
+oid sha256:652365ff63294ffff01ffedb52e831cc2560ab06b5699bca21d63e81dd0efbe7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
+oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0026489391508112375,
+  "epoch": 0.003973408726216856,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 28.587,
       "eval_steps_per_second": 14.294,
       "step": 26
+    },
+    {
+      "epoch": 0.002750821425842439,
+      "grad_norm": 2.156219720840454,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 0.1494,
+      "step": 27
+    },
+    {
+      "epoch": 0.0028527037008736406,
+      "grad_norm": 0.3473513722419739,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.0356,
+      "step": 28
+    },
+    {
+      "epoch": 0.0029545859759048418,
+      "grad_norm": 1.3672902584075928,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 0.1603,
+      "step": 29
+    },
+    {
+      "epoch": 0.0030564682509360433,
+      "grad_norm": 2.2377445697784424,
+      "learning_rate": 5e-05,
+      "loss": 0.0971,
+      "step": 30
+    },
+    {
+      "epoch": 0.003158350525967245,
+      "grad_norm": 0.6241983771324158,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 0.042,
+      "step": 31
+    },
+    {
+      "epoch": 0.0032602328009984465,
+      "grad_norm": 0.8559085130691528,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.0415,
+      "step": 32
+    },
+    {
+      "epoch": 0.0033621150760296476,
+      "grad_norm": 0.60133296251297,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.0377,
+      "step": 33
+    },
+    {
+      "epoch": 0.003463997351060849,
+      "grad_norm": 0.6471958160400391,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0148,
+      "step": 34
+    },
+    {
+      "epoch": 0.0035658796260920507,
+      "grad_norm": 0.7025775909423828,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0149,
+      "step": 35
+    },
+    {
+      "epoch": 0.0036677619011232523,
+      "grad_norm": 0.6499977707862854,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.0519,
+      "step": 36
+    },
+    {
+      "epoch": 0.0037696441761544534,
+      "grad_norm": 0.6970950365066528,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.0287,
+      "step": 37
+    },
+    {
+      "epoch": 0.003871526451185655,
+      "grad_norm": 0.49171292781829834,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0359,
+      "step": 38
+    },
+    {
+      "epoch": 0.003973408726216856,
+      "grad_norm": 0.8748102188110352,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.0462,
+      "step": 39
+    },
+    {
+      "epoch": 0.003973408726216856,
+      "eval_loss": 0.05458526685833931,
+      "eval_runtime": 577.9867,
+      "eval_samples_per_second": 28.601,
+      "eval_steps_per_second": 14.301,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7497924728586240.0,
+  "total_flos": 1.124688709287936e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null