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:de869d995ec5d6d4a239aa4f5034ce2e007d6d43454be80f15e05a8a851896d2
+oid sha256:a2f746929b0766a9a8c55c85358e466c997fe6c51aaac178a726d4e656307d5d
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77f2eceb5007b5510ee40c75cfcbf241bc33a1849fc3d32b39d4c02c39b6581d
+oid sha256:7cdfb49f4f045bd7e2dd4cd6a9445f34715a8e3070fd1fdc9824a9c05c05faa0
 size 51244020

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": 0.06985726280436608,
+  "epoch": 0.10478589420654912,
   "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": 39.127,
       "eval_steps_per_second": 19.595,
       "step": 26
+    },
+    {
+      "epoch": 0.072544080604534,
+      "grad_norm": 1.1186634302139282,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 2.3918,
+      "step": 27
+    },
+    {
+      "epoch": 0.07523089840470193,
+      "grad_norm": 1.239710807800293,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 2.3986,
+      "step": 28
+    },
+    {
+      "epoch": 0.07791771620486986,
+      "grad_norm": 1.718079686164856,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 2.3816,
+      "step": 29
+    },
+    {
+      "epoch": 0.08060453400503778,
+      "grad_norm": 1.1218688488006592,
+      "learning_rate": 5e-05,
+      "loss": 2.2879,
+      "step": 30
+    },
+    {
+      "epoch": 0.08329135180520571,
+      "grad_norm": 1.3196156024932861,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 2.3083,
+      "step": 31
+    },
+    {
+      "epoch": 0.08597816960537363,
+      "grad_norm": 1.2913845777511597,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.4363,
+      "step": 32
+    },
+    {
+      "epoch": 0.08866498740554156,
+      "grad_norm": 1.186840534210205,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 2.2568,
+      "step": 33
+    },
+    {
+      "epoch": 0.09135180520570949,
+      "grad_norm": 1.1380304098129272,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.2333,
+      "step": 34
+    },
+    {
+      "epoch": 0.09403862300587741,
+      "grad_norm": 1.1696350574493408,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.1891,
+      "step": 35
+    },
+    {
+      "epoch": 0.09672544080604534,
+      "grad_norm": 1.155229926109314,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 2.2588,
+      "step": 36
+    },
+    {
+      "epoch": 0.09941225860621326,
+      "grad_norm": 1.1977050304412842,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 2.3242,
+      "step": 37
+    },
+    {
+      "epoch": 0.10209907640638119,
+      "grad_norm": 1.2246061563491821,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.3783,
+      "step": 38
+    },
+    {
+      "epoch": 0.10478589420654912,
+      "grad_norm": 1.1910125017166138,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 2.2939,
+      "step": 39
+    },
+    {
+      "epoch": 0.10478589420654912,
+      "eval_loss": 2.2964117527008057,
+      "eval_runtime": 16.0505,
+      "eval_samples_per_second": 39.064,
+      "eval_steps_per_second": 19.563,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.987535072919552e+16,
+  "total_flos": 2.981302609379328e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null