Training in progress, step 1100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:624b055197f3606c6eb4eb68495cba1cb3612390711cd369d9751c0de46decb1
+oid sha256:4c73e07128bb088f8bcbf97c6f5261f63629182e9503740b1e501e8959f040b3
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02250fadcda502c739eeb1c85cb88d86f2afd595b0bc32fbddb661b3038abb37
+oid sha256:38a05380d9f6374fc5062148f4dadd8d259578dff3de58b8b97becb49e0a48fb
 size 25222341

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bd2949875db2332096831c954b2d0057ba1bf8d4b09f9a5ce64cdf0ae619b0a
+oid sha256:313f56ae2c1e0da8e12142d22545bec21fabdaaa831671aaab809f1bcb08d8a7
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
+oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.098088026046753,
-  "best_model_checkpoint": "./outputs/checkpoint-1000",
-  "epoch": 1.3333333333333333,
+  "best_metric": 1.0934962034225464,
+  "best_model_checkpoint": "./outputs/checkpoint-1100",
+  "epoch": 1.4666666666666668,
   "eval_steps": 100,
-  "global_step": 1000,
+  "global_step": 1100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,20 @@
       "eval_samples_per_second": 10.364,
       "eval_steps_per_second": 1.3,
       "step": 1000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.0002,
+      "loss": 0.9445,
+      "step": 1100
+    },
+    {
+      "epoch": 1.47,
+      "eval_loss": 1.0934962034225464,
+      "eval_runtime": 186.2589,
+      "eval_samples_per_second": 10.362,
+      "eval_steps_per_second": 1.299,
+      "step": 1100
     }
   ],
   "logging_steps": 100,
@@ -154,7 +168,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.413720701218898e+17,
+  "total_flos": 1.555051176866857e+17,
   "trial_name": null,
   "trial_params": null
 }