Training in progress, step 1800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed11fb73cc04a87e68ded9633b47c1fde2d5bffc0acfb5a17aa3f594a897d0f8
+oid sha256:b91d095485061cacc52848d009683c2c2de0fe78624fa1db88084e7830c2eb95
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5315835fda300944b9c2ae9cb8438dcb2dde6b6885ee28fcdfb592464903f02d
+oid sha256:8202ffaa20a18c9541815411dd29971db77932dba31f55655579cd21c3034d30
 size 25222341

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28bd09398ec9af0456a9ee14166cd961943ffc74000ebb4c1108e377da2d32df
+oid sha256:b0ed68540abf53877f31d72dfb49b5e75b15e4cc70f9158d4c016264864ea60a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0410ad60e6d0138b921a03b0a3e367fd27c6ab07cb9a5006fcb66ea8e5bbacc4
+oid sha256:c0e0a1736a46fd1627af3c246e44261aaac909256abbd413b5ee5c968f6b2d8e
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.0760257244110107,
   "best_model_checkpoint": "./outputs/checkpoint-1700",
-  "epoch": 2.2666666666666666,
+  "epoch": 2.4,
   "eval_steps": 100,
-  "global_step": 1700,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -245,6 +245,20 @@
       "eval_samples_per_second": 10.321,
       "eval_steps_per_second": 1.294,
       "step": 1700
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.0002,
+      "loss": 0.9245,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 1.077230453491211,
+      "eval_runtime": 187.3361,
+      "eval_samples_per_second": 10.302,
+      "eval_steps_per_second": 1.292,
+      "step": 1800
     }
   ],
   "logging_steps": 100,
@@ -252,7 +266,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.403652458643538e+17,
+  "total_flos": 2.545114966391931e+17,
   "trial_name": null,
   "trial_params": null
 }