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:a1515be038ebae6ba896b812c9fb36588ac212e2496b7dce8d8e1a573d7ef495
+oid sha256:2d4dc8b6f6e757ac613167db4744fac48dd90885c49c9bb25274bf11bd81e106
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:192de313d3b0ee1f0c04969f8292c090846a5bcd657c72fb165f89f9314d4d44
+oid sha256:21c7725042eb28191bdf4d5b0b4df65b3adc7113ea94a280510cf5b43dd63c91
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e60e5956c0a7b74d35d0ed67c9b4ca8ab443a3d0e395506619944f38db12ce3
+oid sha256:b4d536c921c4a338d70900c25a6f2576863b612bf59335d17a7780873e753d26
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02452783909737552,
+  "epoch": 0.032703785463167365,
   "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": 56.817,
       "eval_steps_per_second": 28.419,
       "step": 150
+    },
+    {
+      "epoch": 0.02616302837053389,
+      "grad_norm": 1.6720688343048096,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 1.8257,
+      "step": 160
+    },
+    {
+      "epoch": 0.027798217643692256,
+      "grad_norm": 1.2190316915512085,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 1.4768,
+      "step": 170
+    },
+    {
+      "epoch": 0.029433406916850625,
+      "grad_norm": 1.2517452239990234,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 1.6874,
+      "step": 180
+    },
+    {
+      "epoch": 0.031068596190008995,
+      "grad_norm": 1.924039602279663,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 1.5098,
+      "step": 190
+    },
+    {
+      "epoch": 0.032703785463167365,
+      "grad_norm": 1.1937552690505981,
+      "learning_rate": 0.0,
+      "loss": 1.5143,
+      "step": 200
+    },
+    {
+      "epoch": 0.032703785463167365,
+      "eval_loss": 1.723392367362976,
+      "eval_runtime": 44.894,
+      "eval_samples_per_second": 57.357,
+      "eval_steps_per_second": 28.69,
+      "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": 1335572457062400.0,
+  "total_flos": 1782989230178304.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null