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:a386a072d53d4e92267ee41675841f2f159bc4e78a89124c66863c963b7aa307
+oid sha256:525268cf2be2cff2c8e5f406086cdf257d67385527264222bc92fb88129f0413
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:213f6b01d272ab2470e99d39ed860d0f1c384c7c14601c14c9e064a7ee95acd5
+oid sha256:c135f204ccd43133c000be268603006cc522036b84274deb7af9689bb26863bb
 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": 0.001758843898376029,
+  "epoch": 0.0026382658475640436,
   "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": 28.559,
       "eval_steps_per_second": 14.28,
       "step": 26
+    },
+    {
+      "epoch": 0.001826491740621261,
+      "grad_norm": 0.7033780813217163,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 1.8607,
+      "step": 27
+    },
+    {
+      "epoch": 0.0018941395828664927,
+      "grad_norm": 0.8126703500747681,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 1.2693,
+      "step": 28
+    },
+    {
+      "epoch": 0.0019617874251117245,
+      "grad_norm": 0.6983233690261841,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 2.1051,
+      "step": 29
+    },
+    {
+      "epoch": 0.0020294352673569565,
+      "grad_norm": 0.6291278600692749,
+      "learning_rate": 5e-05,
+      "loss": 2.5043,
+      "step": 30
+    },
+    {
+      "epoch": 0.0020970831096021885,
+      "grad_norm": 0.7705021500587463,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 2.0858,
+      "step": 31
+    },
+    {
+      "epoch": 0.0021647309518474205,
+      "grad_norm": 0.7353219985961914,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.121,
+      "step": 32
+    },
+    {
+      "epoch": 0.002232378794092652,
+      "grad_norm": 0.7408473491668701,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 1.4857,
+      "step": 33
+    },
+    {
+      "epoch": 0.002300026636337884,
+      "grad_norm": 0.5902467966079712,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.047,
+      "step": 34
+    },
+    {
+      "epoch": 0.002367674478583116,
+      "grad_norm": 0.7522490620613098,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.6697,
+      "step": 35
+    },
+    {
+      "epoch": 0.002435322320828348,
+      "grad_norm": 0.7086387872695923,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 1.5194,
+      "step": 36
+    },
+    {
+      "epoch": 0.0025029701630735796,
+      "grad_norm": 0.7631036043167114,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 2.1248,
+      "step": 37
+    },
+    {
+      "epoch": 0.0025706180053188116,
+      "grad_norm": 0.5777090191841125,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.13,
+      "step": 38
+    },
+    {
+      "epoch": 0.0026382658475640436,
+      "grad_norm": 0.7917817234992981,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 1.5179,
+      "step": 39
+    },
+    {
+      "epoch": 0.0026382658475640436,
+      "eval_loss": 1.3922735452651978,
+      "eval_runtime": 871.5053,
+      "eval_samples_per_second": 28.568,
+      "eval_steps_per_second": 14.284,
+      "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