Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c607fc655902c46412843d9ca049a404c044881352606c7075ea0846fb136b0a
+oid sha256:68dd8f2d2d56102eb9141982551236a8c09b678e7910191025e46b80eb452885
 size 1579352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:233e9fe9e92d5aa5c74aaf7c245e354cb9acf867996a79bcfb2f66b15f472aba
+oid sha256:d2a032a30748bcec7315f149f89aa6b2963b7f25bbbe8b081f289baab112d776
 size 857338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36ef582aee20a74150e9453503b6181f999d478c653e0f80448b88e81817295d
+oid sha256:561c96a9de2039e2fc252d4f61038d8c0e79bafac8eb8ddb35ced95407e0d204
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006783788484953905,
+  "epoch": 0.008697164724299879,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 123.5801,
       "step": 35
+    },
+    {
+      "epoch": 0.006957731779439902,
+      "grad_norm": 1099.8424072265625,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 118.5984,
+      "step": 40
+    },
+    {
+      "epoch": 0.006957731779439902,
+      "eval_loss": 31.008041381835938,
+      "eval_runtime": 15.4761,
+      "eval_samples_per_second": 156.434,
+      "eval_steps_per_second": 78.25,
+      "step": 40
+    },
+    {
+      "epoch": 0.00782744825186989,
+      "grad_norm": 1610.44189453125,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 116.2029,
+      "step": 45
+    },
+    {
+      "epoch": 0.008697164724299879,
+      "grad_norm": 1207.9334716796875,
+      "learning_rate": 0.0,
+      "loss": 115.5269,
+      "step": 50
+    },
+    {
+      "epoch": 0.008697164724299879,
+      "eval_loss": 31.008386611938477,
+      "eval_runtime": 15.4359,
+      "eval_samples_per_second": 156.843,
+      "eval_steps_per_second": 78.454,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 43192405721088.0,
+  "total_flos": 55374879129600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null