Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94400bfdb540e84961f8f55eeb6ba6a3d5e74bc78e85d9834dd52457f6bb9738
+oid sha256:f5d69ff79962036c1f298ca3e46fd58477bbdaec621d07b028f632147232994e
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73be4c0d6c416751c8f0bcdb396cd4b0d9ec27d19fbdbe5de04effca7b68a910
+oid sha256:d6772774ec4d9e3f7005579a0c65bf6a23e602efc36e93983a568dae5526c488
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75457ff9047a61e3f41ba81a128623afe5b1ae5c7463bc37a9196ea84fd005fc
+oid sha256:f0b3186018a30c5ffc18c3acbe2fb9c6db6cc6718a81ff4342bee08442c4ca2c
 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": 0.003199488081906895,
+  "epoch": 0.004265984109209193,
   "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": 15.896,
       "eval_steps_per_second": 7.948,
       "step": 150
+    },
+    {
+      "epoch": 0.0034127872873673548,
+      "grad_norm": 1.258757472038269,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 1.0815,
+      "step": 160
+    },
+    {
+      "epoch": 0.0036260864928278143,
+      "grad_norm": 1.325924038887024,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 1.0969,
+      "step": 170
+    },
+    {
+      "epoch": 0.003839385698288274,
+      "grad_norm": 1.1691293716430664,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 1.0415,
+      "step": 180
+    },
+    {
+      "epoch": 0.004052684903748734,
+      "grad_norm": 1.2433751821517944,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 1.1115,
+      "step": 190
+    },
+    {
+      "epoch": 0.004265984109209193,
+      "grad_norm": 1.129075050354004,
+      "learning_rate": 0.0,
+      "loss": 1.1193,
+      "step": 200
+    },
+    {
+      "epoch": 0.004265984109209193,
+      "eval_loss": 0.28365498781204224,
+      "eval_runtime": 1241.6171,
+      "eval_samples_per_second": 15.899,
+      "eval_steps_per_second": 7.949,
+      "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": 5.5408925343744e+16,
+  "total_flos": 7.3218937061376e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null