Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cc02fd43e25995d948ff5a8177ca79ced4fdf51dac67363f4009c993423fca4
+oid sha256:185ce97fcd1c43f9feba89584e0e36068f454f887953320059bfef07dde0579d
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac9ce8dc263184046bf6293ea72a208ec949beca5c673192a61f4b15f49524ef
+oid sha256:206751f5ac652ebd41d3ef53e32275b1294488d9410f1bf8b811ae29075ad0b3
 size 164464564

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7879bd19611883e5d281e49eada2eff2b8d6757724e0b4286e51a4b828b4131d
+oid sha256:6a937956d0c90e6c5a701a5a605999f72be15feb0a9d8dd43eea7820a3ef7982
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
+oid sha256:859ff0676471245c9481ca25d6d6778d1c7963c39b7877af46bb8ca30a9ead21
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0637890708058686,
+  "epoch": 0.0850520944078248,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 22.456,
       "eval_steps_per_second": 11.251,
       "step": 150
+    },
+    {
+      "epoch": 0.06804167552625984,
+      "grad_norm": 0.8512522578239441,
+      "learning_rate": 0.0002,
+      "loss": 2.1169,
+      "step": 160
+    },
+    {
+      "epoch": 0.07229428024665108,
+      "grad_norm": 0.722571849822998,
+      "learning_rate": 0.0002,
+      "loss": 2.1697,
+      "step": 170
+    },
+    {
+      "epoch": 0.07654688496704232,
+      "grad_norm": 0.7691695094108582,
+      "learning_rate": 0.0002,
+      "loss": 2.1291,
+      "step": 180
+    },
+    {
+      "epoch": 0.08079948968743356,
+      "grad_norm": 0.7802684903144836,
+      "learning_rate": 0.0002,
+      "loss": 2.1554,
+      "step": 190
+    },
+    {
+      "epoch": 0.0850520944078248,
+      "grad_norm": 0.6906216144561768,
+      "learning_rate": 0.0002,
+      "loss": 2.1277,
+      "step": 200
+    },
+    {
+      "epoch": 0.0850520944078248,
+      "eval_loss": 2.161860942840576,
+      "eval_runtime": 22.0604,
+      "eval_samples_per_second": 22.438,
+      "eval_steps_per_second": 11.242,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.135384500941619e+16,
+  "total_flos": 2.8471793345888256e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null