Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70092ff5d48e5c4c81638e2df08e0401c4a59a160a5c5fb37edc1e6d577bcd05
+oid sha256:92eed607f6094bfec0ddef605e2d6e0ad0d5574093862aa2509824d0e1e4524b
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:026d04cb270b1eebab3c8335504b56c51589e51f6f0e6178d272f8227dd48041
+oid sha256:f88d38b1b968b1ea6fded2190ee1d8c40d35b143fe211c7d4f54aa475351505d
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c05e73ce412217540a94cc6ab79e79b85d356b77d6c6ce36ab7ac868a37c23e5
+oid sha256:a016336d93edcd191b83a8946638bf367d98ef3251ef0c4e1323fa1a1c147701
 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": 0.01650982334489021,
+  "epoch": 0.022013097793186946,
   "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": 15.89,
       "eval_steps_per_second": 7.945,
       "step": 150
+    },
+    {
+      "epoch": 0.017610478234549556,
+      "grad_norm": 0.5414583086967468,
+      "learning_rate": 0.0002,
+      "loss": 0.9461,
+      "step": 160
+    },
+    {
+      "epoch": 0.018711133124208905,
+      "grad_norm": 0.47824686765670776,
+      "learning_rate": 0.0002,
+      "loss": 1.0095,
+      "step": 170
+    },
+    {
+      "epoch": 0.01981178801386825,
+      "grad_norm": 0.47877955436706543,
+      "learning_rate": 0.0002,
+      "loss": 0.9779,
+      "step": 180
+    },
+    {
+      "epoch": 0.0209124429035276,
+      "grad_norm": 0.3664035499095917,
+      "learning_rate": 0.0002,
+      "loss": 1.0182,
+      "step": 190
+    },
+    {
+      "epoch": 0.022013097793186946,
+      "grad_norm": 0.4645732045173645,
+      "learning_rate": 0.0002,
+      "loss": 0.9779,
+      "step": 200
+    },
+    {
+      "epoch": 0.022013097793186946,
+      "eval_loss": 0.9666519165039062,
+      "eval_runtime": 240.7663,
+      "eval_samples_per_second": 15.891,
+      "eval_steps_per_second": 7.945,
+      "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": 6.680690804391936e+16,
+  "total_flos": 8.78621657923584e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null