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:c2286226470da6d60425fcfe468092ef768c8b9085963373fbde4074da799a63
+oid sha256:370ef08e615aa00169575f48a5a152d7e52d924260c18437e40ba26f10156f4b
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d11b4da0ba3a3f5ea5741ff5a23e38f5ac52788510f476693b7ee16153d7de87
+oid sha256:3622420c3f4907101d26e7758e56408fd6dc6ee80e655aa2207acc9d58e2d853
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:931c4cb6691233616bf5b1c6107fffe0dba00db02219ee36d8d78aa2418d5343
+oid sha256:be40b9eb2ca0e052d033b378fc6a66cb9b4d07db3404be7b6316676f9b9e44ef
 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": 0.06592682122843643,
+  "epoch": 0.08790242830458192,
   "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": 18.142,
       "eval_steps_per_second": 9.081,
       "step": 150
+    },
+    {
+      "epoch": 0.07032194264366554,
+      "grad_norm": 2.814330816268921,
+      "learning_rate": 0.0002,
+      "loss": 0.2583,
+      "step": 160
+    },
+    {
+      "epoch": 0.07471706405889462,
+      "grad_norm": 5.426441669464111,
+      "learning_rate": 0.0002,
+      "loss": 0.267,
+      "step": 170
+    },
+    {
+      "epoch": 0.07911218547412373,
+      "grad_norm": 10.835411071777344,
+      "learning_rate": 0.0002,
+      "loss": 0.2031,
+      "step": 180
+    },
+    {
+      "epoch": 0.08350730688935282,
+      "grad_norm": 6.394276142120361,
+      "learning_rate": 0.0002,
+      "loss": 0.3164,
+      "step": 190
+    },
+    {
+      "epoch": 0.08790242830458192,
+      "grad_norm": 3.249331474304199,
+      "learning_rate": 0.0002,
+      "loss": 0.2643,
+      "step": 200
+    },
+    {
+      "epoch": 0.08790242830458192,
+      "eval_loss": 0.07121116667985916,
+      "eval_runtime": 52.7891,
+      "eval_samples_per_second": 18.167,
+      "eval_steps_per_second": 9.093,
+      "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": 3.888638815371264e+16,
+  "total_flos": 5.216069447634125e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null