Training in progress, step 4800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:522baa3295580d0a477ccbf634e4d7745722419e4d0a6ca3c0b036eba920c680
+oid sha256:aa42da0a15c323cb30a8a23ad04a2f91dda438add8549801e89e35ad6851e5ff
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa37b5b222889c3f4b9685b74b8bc5a4c7e6211b9306d32cf4856d712f31e2ba
+oid sha256:af7a6113bbc3c7964b2223df922240b6cd5b2143269435fcabeaa7e2c8a5c570
 size 640010002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:216a35202103f6785993d6394e0cf3ddd33323b87f3ecab01cb5eb640ec670dd
+oid sha256:fd517e1e1cfd43ab38eb9c513a110085b9d38a5d09c69d0052001093328ce0e8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:657bbe4e559d5f9e7581fbbb12237706f640d94bb8a67370d9ae890c56e7c61f
+oid sha256:c3ecab210fbeef159cafb78be4b3e45fddac96a485c1a8431fd12fe8ae378aa1
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5525649785995483,
-  "best_model_checkpoint": "./output/checkpoint-4650",
-  "epoch": 0.4378943403333647,
+  "best_metric": 1.5524957180023193,
+  "best_model_checkpoint": "./output/checkpoint-4800",
+  "epoch": 0.45201996421508617,
   "eval_steps": 150,
-  "global_step": 4650,
+  "global_step": 4800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3510,6 +3510,119 @@
       "eval_samples_per_second": 13.189,
       "eval_steps_per_second": 13.189,
       "step": 4650
+    },
+    {
+      "epoch": 0.43883604859214614,
+      "grad_norm": 3.5562143325805664,
+      "learning_rate": 8.874548095798464e-08,
+      "loss": 1.3575,
+      "step": 4660
+    },
+    {
+      "epoch": 0.43977775685092757,
+      "grad_norm": 4.702554702758789,
+      "learning_rate": 8.362113243093245e-08,
+      "loss": 1.5063,
+      "step": 4670
+    },
+    {
+      "epoch": 0.440719465109709,
+      "grad_norm": 4.083225250244141,
+      "learning_rate": 7.864749437890173e-08,
+      "loss": 1.5242,
+      "step": 4680
+    },
+    {
+      "epoch": 0.4416611733684904,
+      "grad_norm": 5.257496356964111,
+      "learning_rate": 7.382477124867282e-08,
+      "loss": 1.5159,
+      "step": 4690
+    },
+    {
+      "epoch": 0.44260288162727185,
+      "grad_norm": 3.3656086921691895,
+      "learning_rate": 6.915316128350461e-08,
+      "loss": 1.4988,
+      "step": 4700
+    },
+    {
+      "epoch": 0.4435445898860533,
+      "grad_norm": 2.969943046569824,
+      "learning_rate": 6.463285651498563e-08,
+      "loss": 1.3161,
+      "step": 4710
+    },
+    {
+      "epoch": 0.44448629814483476,
+      "grad_norm": 4.175876140594482,
+      "learning_rate": 6.026404275513875e-08,
+      "loss": 1.259,
+      "step": 4720
+    },
+    {
+      "epoch": 0.4454280064036162,
+      "grad_norm": 5.987540245056152,
+      "learning_rate": 5.604689958878723e-08,
+      "loss": 1.4463,
+      "step": 4730
+    },
+    {
+      "epoch": 0.4463697146623976,
+      "grad_norm": 5.366607666015625,
+      "learning_rate": 5.198160036616898e-08,
+      "loss": 1.3034,
+      "step": 4740
+    },
+    {
+      "epoch": 0.44731142292117904,
+      "grad_norm": 3.249971866607666,
+      "learning_rate": 4.8068312195811847e-08,
+      "loss": 1.2685,
+      "step": 4750
+    },
+    {
+      "epoch": 0.44825313117996046,
+      "grad_norm": 4.363810062408447,
+      "learning_rate": 4.4307195937666194e-08,
+      "loss": 1.5111,
+      "step": 4760
+    },
+    {
+      "epoch": 0.4491948394387419,
+      "grad_norm": 3.4074866771698,
+      "learning_rate": 4.069840619648935e-08,
+      "loss": 1.6763,
+      "step": 4770
+    },
+    {
+      "epoch": 0.4501365476975233,
+      "grad_norm": 6.260430335998535,
+      "learning_rate": 3.72420913154932e-08,
+      "loss": 1.4295,
+      "step": 4780
+    },
+    {
+      "epoch": 0.45107825595630474,
+      "grad_norm": 3.294346809387207,
+      "learning_rate": 3.3938393370244876e-08,
+      "loss": 1.4655,
+      "step": 4790
+    },
+    {
+      "epoch": 0.45201996421508617,
+      "grad_norm": 4.4235639572143555,
+      "learning_rate": 3.078744816282731e-08,
+      "loss": 1.4596,
+      "step": 4800
+    },
+    {
+      "epoch": 0.45201996421508617,
+      "eval_loss": 1.5524957180023193,
+      "eval_runtime": 37.2391,
+      "eval_samples_per_second": 13.427,
+      "eval_steps_per_second": 13.427,
+      "step": 4800
     }
   ],
   "logging_steps": 10,
@@ -3529,7 +3642,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.935943914686382e+17,
+  "total_flos": 3.0222991715077325e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null