Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a73e09e6cc72ba5d62b370d3a119ef23abf1462124e9ba7df16446c8c5d46bdc
+oid sha256:4f1c32dde1db2f60159be6a2d3dd78384aed50f2e1469564eb727a26f49c00ce
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d323a7cad34c4b752cd3bdf60d11fdb3013978e1356244431064232f338d51b
+oid sha256:881ea6d1ea0cb9773dd58938babcba851c7a1eff26e07cd13b430dd92c2a32a3
 size 25222341

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cf68bdef8c75cb1972eb4442e671e85f5e6c9feb32427f2e8036e7ab01b09d0
+oid sha256:8c39f97aa75b72cdd45c6533229ea7444059209f60bb7244cde449b1b2a87c16
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
+oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0725194215774536,
-  "best_model_checkpoint": "./outputs/checkpoint-1900",
-  "epoch": 2.6666666666666665,
+  "best_metric": 1.0695561170578003,
+  "best_model_checkpoint": "./outputs/checkpoint-2100",
+  "epoch": 2.8,
   "eval_steps": 100,
-  "global_step": 2000,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,6 +287,20 @@
       "eval_samples_per_second": 10.358,
       "eval_steps_per_second": 1.299,
       "step": 2000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 0.0002,
+      "loss": 0.9263,
+      "step": 2100
+    },
+    {
+      "epoch": 2.8,
+      "eval_loss": 1.0695561170578003,
+      "eval_runtime": 186.9997,
+      "eval_samples_per_second": 10.321,
+      "eval_steps_per_second": 1.294,
+      "step": 2100
     }
   ],
   "logging_steps": 100,
@@ -294,7 +308,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.8274374036682342e+17,
+  "total_flos": 2.968788818327716e+17,
   "trial_name": null,
   "trial_params": null
 }