Training in progress, step 1700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6eb24d9a2fab8b73c0bafe62e61b413d19fcc20d3473bde2091ba296af926d0
+oid sha256:ff01f3a48c198c278d4e196bfe090d26f32dab9fd588ee109ca84d2ab43e22af
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51b088d65cf61007d41d4d9d563bdad313e02732aadda5577049dd0517eed0fa
+oid sha256:4f12b2ccfa5a4acbe8f59b607bdacc1e0c3493de7b65300dc76444f2e7c26194
 size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17f0578d675217093ff9e12f497b1c195d79c069c4b5909c34203361b5c19bb4
+oid sha256:0ba57bccd1bc46c2196bf8529c8ed5ea5a8675c8c74e1de03263cf273e5cb709
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
+oid sha256:0410ad60e6d0138b921a03b0a3e367fd27c6ab07cb9a5006fcb66ea8e5bbacc4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2468171119689941,
-  "best_model_checkpoint": "./outputs/checkpoint-1600",
-  "epoch": 2.1333333333333333,
+  "best_metric": 1.2436426877975464,
+  "best_model_checkpoint": "./outputs/checkpoint-1700",
+  "epoch": 2.2666666666666666,
   "eval_steps": 100,
-  "global_step": 1600,
+  "global_step": 1700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,6 +231,20 @@
       "eval_samples_per_second": 15.308,
       "eval_steps_per_second": 1.919,
       "step": 1600
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.0002,
+      "loss": 1.0727,
+      "step": 1700
+    },
+    {
+      "epoch": 2.27,
+      "eval_loss": 1.2436426877975464,
+      "eval_runtime": 126.3899,
+      "eval_samples_per_second": 15.27,
+      "eval_steps_per_second": 1.915,
+      "step": 1700
     }
   ],
   "logging_steps": 100,
@@ -238,7 +252,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.671234750998528e+16,
+  "total_flos": 6.027920028021965e+16,
   "trial_name": null,
   "trial_params": null
 }