Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d6bb51fcf9079aaa165a541b157bc6a004764f22eaaec08e14699d271a0e27d
+oid sha256:d4f7d9e1d5df4e77286d18d3265fdc3b7d77d4ed16405247a114ce67fbe8d6ea
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee09656ad9fc7b7117291207e1ba5b0a0718dd19ed58eecdd9bc3feb1a848e0a
+oid sha256:6c14105e75a8d6767fa2b5ffa0b73437f51459bad87576fad705a3cb7b6a6053
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9f6b6891926822ed477171c9fab6080cf64ba0a4f2417be5775f0ab7bb630c0
+oid sha256:4c5e6b6e9252cbf5ff0046d8ad736d29ab685bea39411cdeee1ff014d01d9e55
 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": 0.004555186079351342,
+  "epoch": 0.006073581439135122,
   "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": 10.616,
       "eval_steps_per_second": 5.309,
       "step": 150
+    },
+    {
+      "epoch": 0.0048588651513080975,
+      "grad_norm": 0.6850274801254272,
+      "learning_rate": 0.0002,
+      "loss": 0.5936,
+      "step": 160
+    },
+    {
+      "epoch": 0.0051625442232648535,
+      "grad_norm": 0.7021895051002502,
+      "learning_rate": 0.0002,
+      "loss": 0.6144,
+      "step": 170
+    },
+    {
+      "epoch": 0.005466223295221609,
+      "grad_norm": 0.575738251209259,
+      "learning_rate": 0.0002,
+      "loss": 0.6461,
+      "step": 180
+    },
+    {
+      "epoch": 0.005769902367178366,
+      "grad_norm": 0.6139180064201355,
+      "learning_rate": 0.0002,
+      "loss": 0.5935,
+      "step": 190
+    },
+    {
+      "epoch": 0.006073581439135122,
+      "grad_norm": 0.534476101398468,
+      "learning_rate": 0.0002,
+      "loss": 0.6254,
+      "step": 200
+    },
+    {
+      "epoch": 0.006073581439135122,
+      "eval_loss": 0.6035110354423523,
+      "eval_runtime": 1305.0507,
+      "eval_samples_per_second": 10.624,
+      "eval_steps_per_second": 5.312,
+      "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": 6.15718085197824e+16,
+  "total_flos": 8.20957446930432e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null