Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ac01be4e4efadb46ae0a5aee8b3d4bd8d42c622a224365887fe78ebf53b5ab5
+oid sha256:542dc45f5e6c6415f8fbe22602f98ce51b71420116fa4c2b17ce85eeef4338f5
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb274ef53fb2cd8d846c51a7ef4341bac838a69fab940cb45f7574bf00490432
+oid sha256:666b389f52b9c9a6f58c84df241a42fa9eaeeb2ec11cf3e0c9cbfacefb5ac030
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28cb1b5e093b2599d8fa1806646d1f09bc9ce7ac92f9796c6863470342508537
+oid sha256:1842e55417742168b8bd9b1516cf24155d20a6818e0bf2f1d963bcf713e15763
 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": 0.0013766962044485644,
+  "epoch": 0.0018355949392647524,
   "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": 63.612,
       "eval_steps_per_second": 31.807,
       "step": 150
+    },
+    {
+      "epoch": 0.0014684759514118019,
+      "grad_norm": 4.073799133300781,
+      "learning_rate": 0.0002,
+      "loss": 2.6564,
+      "step": 160
+    },
+    {
+      "epoch": 0.0015602556983750396,
+      "grad_norm": 4.067333221435547,
+      "learning_rate": 0.0002,
+      "loss": 2.609,
+      "step": 170
+    },
+    {
+      "epoch": 0.0016520354453382772,
+      "grad_norm": 5.727188587188721,
+      "learning_rate": 0.0002,
+      "loss": 2.7113,
+      "step": 180
+    },
+    {
+      "epoch": 0.001743815192301515,
+      "grad_norm": 4.845877647399902,
+      "learning_rate": 0.0002,
+      "loss": 2.8146,
+      "step": 190
+    },
+    {
+      "epoch": 0.0018355949392647524,
+      "grad_norm": 4.398877143859863,
+      "learning_rate": 0.0002,
+      "loss": 2.8552,
+      "step": 200
+    },
+    {
+      "epoch": 0.0018355949392647524,
+      "eval_loss": 2.7687087059020996,
+      "eval_runtime": 719.1671,
+      "eval_samples_per_second": 63.792,
+      "eval_steps_per_second": 31.897,
+      "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": 7342166900736000.0,
+  "total_flos": 9789555867648000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null