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:ddb42b9dd236c6cc859a84f90dcbe2f9b78fe2c30a51845c28f99379f9620338
+oid sha256:78e089490ff8cf7166ddbd08b4211f4563778e960b26bf6f911b293f3be96655
 size 104902272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df6fcbbe140db10b7a2acae28ab139f9625d783ac2685d6a1f7f5c89f1c91505
+oid sha256:e910a182b424c638fc382211d461942bd9eda97eb045e0d2ba0626894986c050
 size 53622996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8880f5e7e9c5f006034293f841b64800e7ef66ac3fa358c859a5a03ca7f51060
+oid sha256:dbeefd08ec2aa8197f94fe04076d868dd754153352801b80ac54cccd6a4f00ed
 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": 0.22075055187637968,
+  "epoch": 0.29433406916850624,
   "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": 14.023,
       "eval_steps_per_second": 7.036,
       "step": 150
+    },
+    {
+      "epoch": 0.235467255334805,
+      "grad_norm": 2.044692277908325,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 3.262,
+      "step": 160
+    },
+    {
+      "epoch": 0.2501839587932303,
+      "grad_norm": 1.9837390184402466,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 3.3449,
+      "step": 170
+    },
+    {
+      "epoch": 0.26490066225165565,
+      "grad_norm": 2.7401065826416016,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 3.4668,
+      "step": 180
+    },
+    {
+      "epoch": 0.27961736571008095,
+      "grad_norm": 2.0782437324523926,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 3.5672,
+      "step": 190
+    },
+    {
+      "epoch": 0.29433406916850624,
+      "grad_norm": 2.970066547393799,
+      "learning_rate": 0.0,
+      "loss": 3.5145,
+      "step": 200
+    },
+    {
+      "epoch": 0.29433406916850624,
+      "eval_loss": 0.8831089735031128,
+      "eval_runtime": 20.4639,
+      "eval_samples_per_second": 14.025,
+      "eval_steps_per_second": 7.037,
+      "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": 8.86294349611008e+16,
+  "total_flos": 1.1851245683736576e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null