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:a1b47066d281224800157218be6406ececdd2286603c2e1ad3e9be8499b482a0
+oid sha256:9b8e7ec63f00c08a0d78de870428c4cdb987deac18b80648eecdc9bcf7f2db6b
 size 21919400

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12c7b02a7e59e73a2eb6a7f3431f42bfdb155e1599879d95c17b98ec483399dd
+oid sha256:8a86be7b6fbcc19bcc5ffa9bb3027746f006a1b13ceed203486c580889aee16f
 size 4954713

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2d7b30bbc78ad96757ed3b11234079b342b927b44c7a0dc91a7a50d6cb68fc8
+oid sha256:267a692e774fa423b3e8019601554a0456febdd9da57d9f82e4289f21b314860
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8243f0a109b91beab79a35b3dd3faac5ede1958c4b7a02d418057e71733530c7
+oid sha256:54129884a43fac233d16f8f024313b97a23fce2899d2b6122913d1d94ddf2e29
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.487832069396973,
   "best_model_checkpoint": "./output/checkpoint-3900",
-  "epoch": 15.397350993377483,
+  "epoch": 15.894039735099337,
   "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": 123.62,
       "eval_steps_per_second": 123.62,
       "step": 4650
+    },
+    {
+      "epoch": 15.43046357615894,
+      "grad_norm": 0.5005173087120056,
+      "learning_rate": 1.1832730794397948e-06,
+      "loss": 11.4594,
+      "step": 4660
+    },
+    {
+      "epoch": 15.463576158940397,
+      "grad_norm": 0.3516858220100403,
+      "learning_rate": 1.1149484324124322e-06,
+      "loss": 11.4586,
+      "step": 4670
+    },
+    {
+      "epoch": 15.496688741721854,
+      "grad_norm": 0.43980923295021057,
+      "learning_rate": 1.048633258385356e-06,
+      "loss": 11.4724,
+      "step": 4680
+    },
+    {
+      "epoch": 15.52980132450331,
+      "grad_norm": 0.391050785779953,
+      "learning_rate": 9.843302833156374e-07,
+      "loss": 11.47,
+      "step": 4690
+    },
+    {
+      "epoch": 15.562913907284768,
+      "grad_norm": 0.4212386906147003,
+      "learning_rate": 9.220421504467278e-07,
+      "loss": 11.4647,
+      "step": 4700
+    },
+    {
+      "epoch": 15.596026490066226,
+      "grad_norm": 0.4143437445163727,
+      "learning_rate": 8.617714201998081e-07,
+      "loss": 11.4658,
+      "step": 4710
+    },
+    {
+      "epoch": 15.629139072847682,
+      "grad_norm": 0.46835222840309143,
+      "learning_rate": 8.035205700685165e-07,
+      "loss": 11.4813,
+      "step": 4720
+    },
+    {
+      "epoch": 15.66225165562914,
+      "grad_norm": 0.38814619183540344,
+      "learning_rate": 7.472919945171628e-07,
+      "loss": 11.4636,
+      "step": 4730
+    },
+    {
+      "epoch": 15.695364238410596,
+      "grad_norm": 0.3894265592098236,
+      "learning_rate": 6.930880048822528e-07,
+      "loss": 11.4568,
+      "step": 4740
+    },
+    {
+      "epoch": 15.728476821192054,
+      "grad_norm": 0.3959190249443054,
+      "learning_rate": 6.40910829277491e-07,
+      "loss": 11.4678,
+      "step": 4750
+    },
+    {
+      "epoch": 15.76158940397351,
+      "grad_norm": 0.42889001965522766,
+      "learning_rate": 5.907626125022157e-07,
+      "loss": 11.4679,
+      "step": 4760
+    },
+    {
+      "epoch": 15.794701986754967,
+      "grad_norm": 0.34252163767814636,
+      "learning_rate": 5.426454159531912e-07,
+      "loss": 11.4672,
+      "step": 4770
+    },
+    {
+      "epoch": 15.827814569536423,
+      "grad_norm": 0.5112998485565186,
+      "learning_rate": 4.965612175399091e-07,
+      "loss": 11.4672,
+      "step": 4780
+    },
+    {
+      "epoch": 15.860927152317881,
+      "grad_norm": 0.38379812240600586,
+      "learning_rate": 4.525119116032649e-07,
+      "loss": 11.4695,
+      "step": 4790
+    },
+    {
+      "epoch": 15.894039735099337,
+      "grad_norm": 0.40494051575660706,
+      "learning_rate": 4.104993088376973e-07,
+      "loss": 11.4611,
+      "step": 4800
+    },
+    {
+      "epoch": 15.894039735099337,
+      "eval_loss": 11.487883567810059,
+      "eval_runtime": 2.1723,
+      "eval_samples_per_second": 123.373,
+      "eval_steps_per_second": 123.373,
+      "step": 4800
     }
   ],
   "logging_steps": 10,
@@ -3529,7 +3642,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 84096091750608.0,
+  "total_flos": 86880464660304.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null