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:b8e8f5308db76f1b44635257123a7c2421175e10d0fee1c109bb92d531417f9c
+oid sha256:cfe986621d54a5031f322e296df966a92ec855b06c200f72c9ffa1595e6b6c33
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94442eda4a97593d72b768d0640966f111f57947c91995f26955d951837f4b14
+oid sha256:9bdca06c03bb2a58fc5b3033b348c7511777d0708e5eb5052da5ec903e067743
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85ff64795f7e510dacb51bb74fec234486393c05038fc8707d7ba3d767a5f849
+oid sha256:66430a755ef6716c47abdc6e759c29a892143e92df9000e90dd7bbba0d1e7d22
 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": 0.06748397255651782,
+  "epoch": 0.0899786300753571,
   "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": 13.89,
       "eval_steps_per_second": 6.945,
       "step": 150
+    },
+    {
+      "epoch": 0.07198290406028568,
+      "grad_norm": 1.271436333656311,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 4.4779,
+      "step": 160
+    },
+    {
+      "epoch": 0.07648183556405354,
+      "grad_norm": 2.2995824813842773,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 5.2814,
+      "step": 170
+    },
+    {
+      "epoch": 0.0809807670678214,
+      "grad_norm": 1.5166254043579102,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 4.0981,
+      "step": 180
+    },
+    {
+      "epoch": 0.08547969857158924,
+      "grad_norm": 1.4079911708831787,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 5.1431,
+      "step": 190
+    },
+    {
+      "epoch": 0.0899786300753571,
+      "grad_norm": 1.253096342086792,
+      "learning_rate": 0.0,
+      "loss": 4.4208,
+      "step": 200
+    },
+    {
+      "epoch": 0.0899786300753571,
+      "eval_loss": 1.170989751815796,
+      "eval_runtime": 67.3419,
+      "eval_samples_per_second": 13.899,
+      "eval_steps_per_second": 6.95,
+      "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": 7.432664295407616e+16,
+  "total_flos": 9.89438803968e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null