Training in progress, step 2300, checkpoint

last-checkpoint/model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c8c6ff74448961f63c682755ee44b066c13961022d73c35618f424b0b3b04f2
+oid sha256:4480cf94e90fbcff6ded4ea0e033092e231273c07472d355d57709c17971b8c0
 size 4976698672

last-checkpoint/model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19ad29e2afc3f664caef80f5f659fd2e3564bb5cc89ac52c1e921a1fa793063f
+oid sha256:5cab56d644789b3d0d8a275c1d8bb39ee8a44ddb72a82700ae804ea2df595a0c
 size 4999802720

last-checkpoint/model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de778ad033fb57d0c77011ce2efc5adbb4d2d05637cac1cc29a51ee29f3a143a
+oid sha256:e2576b8c41b55fcd088c51000da64fb5acf75a9919b8c7663a460d9d3353867f
 size 4915916176

last-checkpoint/model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70e0ab1944abe87b05cd898915e49be1d42ad8b7bcf4d4fd71d39ce17c168f52
+oid sha256:d9c70312c9c125fe0ca49b749fdf3d0f1672e3e046c39375a7f1e758e7ec2176
 size 1168138808

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14109e8a50e6b2db2412f32737fe9c023d674ef95a0a8795aecdbf2daa7b9b3f
+oid sha256:524e6c358512b5845edfe3223d57c6d965a4abb689d2e5543ab49bf57b265729
 size 16311821444

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3134a0ee77592caf611ce2f68e680b25ae8deac50b353e39ae4a57c957fb3acf
+oid sha256:79370aa8e64e10f5426d7aadbbf1bb1c37647728868a165ccce129881ecf31d5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.015873015873016,
+  "epoch": 6.068783068783069,
   "eval_steps": 40,
-  "global_step": 2280,
+  "global_step": 2300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2067,6 +2067,20 @@
       "eval_samples_per_second": 51.543,
       "eval_steps_per_second": 6.459,
       "step": 2280
+    },
+    {
+      "epoch": 6.042328042328043,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 1.0336163855129144e-08,
+      "loss": 0.0056,
+      "step": 2290
+    },
+    {
+      "epoch": 6.068783068783069,
+      "grad_norm": 0.10400390625,
+      "learning_rate": 0.0,
+      "loss": 0.0075,
+      "step": 2300
     }
   ],
   "logging_steps": 10,
@@ -2081,12 +2095,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.6821022433036206e+18,
+  "total_flos": 1.6968575261396173e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null