Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37d7307b1ab7606d396b2c07bcd797d79f2dcb319a486f398f7e6d5c8384655a
+oid sha256:369d6f91d16eaebb6b9e7a4d3110a8c8d6f87f4226794e33a28b6645426e210d
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70047662bd8d70318fb7c750c85dea89d6049b1ca9bf4e43a6e6fd5b4df971d1
+oid sha256:bc2b0abc111609da6eb7147fd196cced7f523168f93293ce56cf2b3feb6ebdae
 size 39398

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": 0.010529513010023287,
+  "epoch": 0.01579426951503493,
   "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": 590.143,
       "eval_steps_per_second": 295.142,
       "step": 26
+    },
+    {
+      "epoch": 0.010934494279639566,
+      "grad_norm": 0.01646103709936142,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 11.9288,
+      "step": 27
+    },
+    {
+      "epoch": 0.011339475549255847,
+      "grad_norm": 0.01632491685450077,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 11.9289,
+      "step": 28
+    },
+    {
+      "epoch": 0.011744456818872127,
+      "grad_norm": 0.015698088333010674,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 11.929,
+      "step": 29
+    },
+    {
+      "epoch": 0.012149438088488408,
+      "grad_norm": 0.016495509073138237,
+      "learning_rate": 5e-05,
+      "loss": 11.9298,
+      "step": 30
+    },
+    {
+      "epoch": 0.012554419358104687,
+      "grad_norm": 0.016273178160190582,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 11.9295,
+      "step": 31
+    },
+    {
+      "epoch": 0.012959400627720968,
+      "grad_norm": 0.015034040436148643,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 11.9304,
+      "step": 32
+    },
+    {
+      "epoch": 0.013364381897337248,
+      "grad_norm": 0.014879411086440086,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 11.9288,
+      "step": 33
+    },
+    {
+      "epoch": 0.013769363166953529,
+      "grad_norm": 0.014941861853003502,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 11.9293,
+      "step": 34
+    },
+    {
+      "epoch": 0.014174344436569808,
+      "grad_norm": 0.01598219946026802,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.9287,
+      "step": 35
+    },
+    {
+      "epoch": 0.01457932570618609,
+      "grad_norm": 0.015294226817786694,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 11.9286,
+      "step": 36
+    },
+    {
+      "epoch": 0.014984306975802369,
+      "grad_norm": 0.015234192833304405,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 11.9291,
+      "step": 37
+    },
+    {
+      "epoch": 0.01538928824541865,
+      "grad_norm": 0.016300296410918236,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 11.9293,
+      "step": 38
+    },
+    {
+      "epoch": 0.01579426951503493,
+      "grad_norm": 0.015601075254380703,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 11.9291,
+      "step": 39
+    },
+    {
+      "epoch": 0.01579426951503493,
+      "eval_loss": 11.929096221923828,
+      "eval_runtime": 7.0495,
+      "eval_samples_per_second": 589.971,
+      "eval_steps_per_second": 295.056,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 12288786432.0,
+  "total_flos": 18433179648.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null