Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07e62ac60d9843fe1f10a62bfdeab4d7b3b595d3803d1b2c746ad5f9b0a77ec8
+oid sha256:6f528bf75a27985bbbf60dc6ad0eb9f77afcbb0c014509efef36801c2d231232
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc3b912d5cdd4e89fe9a82bfd072cb9c15c71075f6f1ad5fd633ecf1d242aa87
+oid sha256:005da64c9edec12e4163632aff8352e7000771a8597feb519ab224700a09582e
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55f5b8fc91a819fc39bd479452495c8f8f43e1c210ee91583af5c241cfc6079a
+oid sha256:ab25f1bb566d6940a6c530bc3bcd4512bcc2278b20c9a86ed24b271b2778f563
 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": 0.08025682182985554,
+  "epoch": 0.10700909577314072,
   "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": 21.161,
       "eval_steps_per_second": 10.594,
       "step": 150
+    },
+    {
+      "epoch": 0.08560727661851257,
+      "grad_norm": 0.665091335773468,
+      "learning_rate": 0.0002,
+      "loss": 0.9073,
+      "step": 160
+    },
+    {
+      "epoch": 0.0909577314071696,
+      "grad_norm": 0.5974867343902588,
+      "learning_rate": 0.0002,
+      "loss": 0.8846,
+      "step": 170
+    },
+    {
+      "epoch": 0.09630818619582665,
+      "grad_norm": 0.5943084359169006,
+      "learning_rate": 0.0002,
+      "loss": 0.8716,
+      "step": 180
+    },
+    {
+      "epoch": 0.10165864098448368,
+      "grad_norm": 0.595061182975769,
+      "learning_rate": 0.0002,
+      "loss": 0.8635,
+      "step": 190
+    },
+    {
+      "epoch": 0.10700909577314072,
+      "grad_norm": 0.575626790523529,
+      "learning_rate": 0.0002,
+      "loss": 0.8597,
+      "step": 200
+    },
+    {
+      "epoch": 0.10700909577314072,
+      "eval_loss": 0.8620458245277405,
+      "eval_runtime": 37.2066,
+      "eval_samples_per_second": 21.152,
+      "eval_steps_per_second": 10.59,
+      "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": 4.7493062590464e+16,
+  "total_flos": 6.3324083453952e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null