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:fdcf4286bf7155d87f68366b7b66c2a0b30a87f5308541318bf2d72003f913c9
+oid sha256:619ed3347bb0940bc714b31681d1eca82bf31e5919b408f034972213a70416cc
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2601ba1c458b09c41ad2f2fb937bec8965891b6558fb0dababb798678fe7364a
+oid sha256:d22f98b7d61c9d798e0db5058f0e680a099171a721882351b816e79058229eba
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fea276383daa6be11cb41bcf079e20917a66b8a1df06264809ff50445c989c9
+oid sha256:70bb08e79cd87e26411515d4cfe540a1dfafd998745c321dfb4680b9ed334a58
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd5d42bb0afda20ec4c83d38c6af1131541c335ecab229c74e7f418894f3c13b
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.45112781954887216,
+  "epoch": 0.6015037593984962,
   "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": 406.439,
       "eval_steps_per_second": 203.219,
       "step": 150
+    },
+    {
+      "epoch": 0.48120300751879697,
+      "grad_norm": 0.10246419161558151,
+      "learning_rate": 2.1085949060360654e-05,
+      "loss": 10.3492,
+      "step": 160
+    },
+    {
+      "epoch": 0.5112781954887218,
+      "grad_norm": 0.09414087980985641,
+      "learning_rate": 1.2052624879351104e-05,
+      "loss": 10.3486,
+      "step": 170
+    },
+    {
+      "epoch": 0.5413533834586466,
+      "grad_norm": 0.10483800619840622,
+      "learning_rate": 5.418275829936537e-06,
+      "loss": 10.3502,
+      "step": 180
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.10983836650848389,
+      "learning_rate": 1.3638696597277679e-06,
+      "loss": 10.3475,
+      "step": 190
+    },
+    {
+      "epoch": 0.6015037593984962,
+      "grad_norm": 0.12176923453807831,
+      "learning_rate": 0.0,
+      "loss": 10.35,
+      "step": 200
+    },
+    {
+      "epoch": 0.6015037593984962,
+      "eval_loss": 10.350138664245605,
+      "eval_runtime": 0.3546,
+      "eval_samples_per_second": 394.795,
+      "eval_steps_per_second": 197.398,
+      "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": 1939636224000.0,
+  "total_flos": 2586181632000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null