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:c5adf3f5394990b1d7305a5c3fa21c224489f2b82b03729ad02e6b820f8905f4
+oid sha256:07fcc2c83afa8aef617c8c7a76e8a2d64563403585682fe54b2153efef4a4ce0
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9c6ff4e24e5a87e5ea7abee34986e7fb70c1e9622816bd14ce281dba382c43c
+oid sha256:deb1bcef585fc0d939a9e2979fe46f64f13377b8c9efad0e3e75a0a33398544e
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ff51ad6df91d0e18c7363540ae4bd74313469b3ed151c6ae2ca115845dc21fc
+oid sha256:8041837488fe9482526415d7b12f19e2710ce8aad1458a5a111ab5868da9e865
 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": 0.9570510983467102,
-  "best_model_checkpoint": "./outputs/checkpoint-1600",
-  "epoch": 2.1333333333333333,
+  "best_metric": 0.9513885378837585,
+  "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": 2.467,
       "eval_steps_per_second": 0.309,
       "step": 1600
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.0002,
+      "loss": 0.7676,
+      "step": 1700
+    },
+    {
+      "epoch": 2.27,
+      "eval_loss": 0.9513885378837585,
+      "eval_runtime": 768.2363,
+      "eval_samples_per_second": 2.512,
+      "eval_steps_per_second": 0.315,
+      "step": 1700
     }
   ],
   "logging_steps": 100,
@@ -238,7 +252,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 100,
-  "total_flos": 4.14342522878976e+17,
+  "total_flos": 4.402578582306816e+17,
   "trial_name": null,
   "trial_params": null
 }