Training in progress, step 1100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4adb1c8f8b56ee50aa97d7ba230528c914fd94683df1aa17d6a63c84541eb731
+oid sha256:a6cdebc96bbb12ba1dc5010d41742892ed7dd71d09701c694d110068729765cc
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d1033a2be5be69441043806828dffbba91710d79f647e17e6e37e8cc2e8b186
+oid sha256:155ee9c0bf029d819e901529b42f931c256a1d48a8d83fe1f9b4c82f009787b8
 size 39357829

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17812da58821a9378ebc24a70d2a909be55cf6346ab49b39cc73bc804822d6bd
+oid sha256:cb85d675da79c9f128ba95f0e91ab83c431eb4fb41307c6d9686f45b7ede1b07
 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": 0.9874381422996521,
-  "best_model_checkpoint": "./outputs/checkpoint-1000",
-  "epoch": 1.3333333333333333,
+  "best_metric": 0.9812790751457214,
+  "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": 2.664,
       "eval_steps_per_second": 0.334,
       "step": 1000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.0002,
+      "loss": 0.8156,
+      "step": 1100
+    },
+    {
+      "epoch": 1.47,
+      "eval_loss": 0.9812790751457214,
+      "eval_runtime": 726.6666,
+      "eval_samples_per_second": 2.656,
+      "eval_steps_per_second": 0.333,
+      "step": 1100
     }
   ],
   "logging_steps": 100,
@@ -154,7 +168,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.5910459214483456e+17,
+  "total_flos": 2.8493512017395712e+17,
   "trial_name": null,
   "trial_params": null
 }