Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c3b13f46fab857b7593afd293acbd2ecc359cd3fc048173aa1f2de4f4b2cda1
+oid sha256:74b7fdbe18f735663f945595812df22419ad68912867e25bbdd6ee5a590e16d7
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c22804634ff2f696f79d4b967dad276d98877eb5c9ebb743f1e7aa2fbb8245a3
+oid sha256:d2b9195ba00ac4d43a2362a30d16aeb1985e0075fba4c979f363cd18ff10b87f
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d725b764a9f7a07542bff2bd49e82f50571269a38edb42c4d371ddaac7f6a8e3
+oid sha256:be9ec3198a68ec65f16686b0f1d5a6ba174d2aca875621b68207c99c69128ae9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a35430a05f2b9748f37dd11667a782564c85a35d840d60cbaddfa2c905ab7c0a
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0953603520997616,
+  "epoch": 0.09780548933308882,
   "eval_steps": 34,
-  "global_step": 195,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1420,6 +1420,41 @@
       "learning_rate": 4.2658237049655323e-07,
       "loss": 1.1014,
       "step": 195
+    },
+    {
+      "epoch": 0.09584937954642704,
+      "grad_norm": 0.4199082851409912,
+      "learning_rate": 2.7308266142119785e-07,
+      "loss": 1.0427,
+      "step": 196
+    },
+    {
+      "epoch": 0.09633840699309248,
+      "grad_norm": 0.26134058833122253,
+      "learning_rate": 1.5363960325660565e-07,
+      "loss": 1.216,
+      "step": 197
+    },
+    {
+      "epoch": 0.09682743443975793,
+      "grad_norm": 0.4043033719062805,
+      "learning_rate": 6.829398569770939e-08,
+      "loss": 1.0911,
+      "step": 198
+    },
+    {
+      "epoch": 0.09731646188642337,
+      "grad_norm": 0.36261600255966187,
+      "learning_rate": 1.7074954194729044e-08,
+      "loss": 1.1118,
+      "step": 199
+    },
+    {
+      "epoch": 0.09780548933308882,
+      "grad_norm": 0.44171595573425293,
+      "learning_rate": 0.0,
+      "loss": 1.0957,
+      "step": 200
     }
   ],
   "logging_steps": 1,
@@ -1434,12 +1469,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.255983853797376e+17,
+  "total_flos": 3.33947061927936e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null