Training in progress, step 2200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abe60bad46f899f939b7c17c2d43697f9b909078c68a01da494eef295e68e107
+oid sha256:619955d8d015fd17e9928e336fc170c7917e55cc67a48e6b71bfaed7f06b3d51
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f43b54595d294ee751a841db18e005002b296bde2a41c16d86c1fb2474411a67
+oid sha256:15bb80eb6b19011e3654c10478edfbacc8c6556f2eb4ce7cc7b07dea8b64c5bd
 size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72ca6365dbbc2f86eaa3db35582d2708ce0b1665aa0b50d90a15b774de232618
+oid sha256:9f9f6b90727f763e225653866388919108823474c7eb02d67d864e53ff7938d0
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
+oid sha256:f10a983aa914555fea6e5c0db8d7ddbaebbe7e28546c78ee0e93ac76cbc28436
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2370983362197876,
-  "best_model_checkpoint": "./outputs/checkpoint-2100",
-  "epoch": 2.8,
+  "best_metric": 1.2338846921920776,
+  "best_model_checkpoint": "./outputs/checkpoint-2200",
+  "epoch": 2.9333333333333336,
   "eval_steps": 100,
-  "global_step": 2100,
+  "global_step": 2200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -301,6 +301,20 @@
       "eval_samples_per_second": 15.268,
       "eval_steps_per_second": 1.914,
       "step": 2100
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 0.0002,
+      "loss": 1.0597,
+      "step": 2200
+    },
+    {
+      "epoch": 2.93,
+      "eval_loss": 1.2338846921920776,
+      "eval_runtime": 126.5018,
+      "eval_samples_per_second": 15.257,
+      "eval_steps_per_second": 1.913,
+      "step": 2200
     }
   ],
   "logging_steps": 100,
@@ -308,7 +322,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.44517848768553e+16,
+  "total_flos": 7.800080571706982e+16,
   "trial_name": null,
   "trial_params": null
 }