Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:961161834d2a7e538f5f2105c26ccd5c33f54f3a44183926c84f95b435bc7d03
+oid sha256:0bb7bbe2b2a7d9e0439efe7f82aeaf066bd82199d25ffd231bb8b8c62ae7dd2b
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:139dc9495b911d5b50addc02efc4f0d294a19b6fa55087fcf946d5d51a32e600
+oid sha256:8c71609279b43cc40b31af1567ae590baec167f96a5063d62c17499d76a1adc2
 size 41459700

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": 0.01571174982059901,
+  "epoch": 0.023567624730898514,
   "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": 35.736,
       "eval_steps_per_second": 17.875,
       "step": 26
+    },
+    {
+      "epoch": 0.01631604789062205,
+      "grad_norm": 0.8348265290260315,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 2.0727,
+      "step": 27
+    },
+    {
+      "epoch": 0.016920345960645088,
+      "grad_norm": 0.8782357573509216,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 2.1957,
+      "step": 28
+    },
+    {
+      "epoch": 0.017524644030668127,
+      "grad_norm": 0.8670806884765625,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 1.9359,
+      "step": 29
+    },
+    {
+      "epoch": 0.018128942100691166,
+      "grad_norm": 0.9028540849685669,
+      "learning_rate": 5e-05,
+      "loss": 1.9664,
+      "step": 30
+    },
+    {
+      "epoch": 0.018733240170714205,
+      "grad_norm": 0.8907434940338135,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 1.969,
+      "step": 31
+    },
+    {
+      "epoch": 0.019337538240737244,
+      "grad_norm": 0.8233531713485718,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.974,
+      "step": 32
+    },
+    {
+      "epoch": 0.019941836310760283,
+      "grad_norm": 0.8587433099746704,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 1.8521,
+      "step": 33
+    },
+    {
+      "epoch": 0.020546134380783322,
+      "grad_norm": 0.897334098815918,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.9035,
+      "step": 34
+    },
+    {
+      "epoch": 0.02115043245080636,
+      "grad_norm": 0.9631185531616211,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.9148,
+      "step": 35
+    },
+    {
+      "epoch": 0.0217547305208294,
+      "grad_norm": 1.0168321132659912,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 1.9873,
+      "step": 36
+    },
+    {
+      "epoch": 0.02235902859085244,
+      "grad_norm": 0.8644974827766418,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 1.8347,
+      "step": 37
+    },
+    {
+      "epoch": 0.02296332666087548,
+      "grad_norm": 0.8866729140281677,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.0322,
+      "step": 38
+    },
+    {
+      "epoch": 0.023567624730898514,
+      "grad_norm": 0.9013758897781372,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 1.8802,
+      "step": 39
+    },
+    {
+      "epoch": 0.023567624730898514,
+      "eval_loss": 1.8680973052978516,
+      "eval_runtime": 78.0813,
+      "eval_samples_per_second": 35.694,
+      "eval_steps_per_second": 17.853,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.3482020721065984e+16,
+  "total_flos": 3.537551173563187e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null