Training in progress, step 700, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9b2eabc12da250440d3bcee455252db7820de35e0dde6a74683ffcbe6210128
+oid sha256:a64a16ac8bcfc48d63b4e0abe555c3637d19c4893dcc9c2e65725d89e533c2fa
 size 4995335576

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db2c10affbd55265833d3104f1ad1d88af75493c70c996f85d014ca22d4daf65
+oid sha256:f348204adafef46dc7e0fd50ecb0e932998188d7d13d918d4c9afc30c676751d
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8244fb95d6d2fbe32035ed66a387c58853a4f00c22b863f65882db812cac78b7
+oid sha256:3b60a9cf0fdbfc5bba7d1a478c8a45ab406f366a113a90ee6b35a4bd5e057c9b
 size 13706103974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c07c9483d2aaa0e0aa4859fa05bacc55a60e0f30ff9c95a3b76854e880483a96
+oid sha256:6cfe3540f24c66f9bc38a546448a9e5d9989705fafc8d4b37aa5dafd0c7460f2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94df8b4b2d639d3f58ff36db997bdfab0ce18552982960aa949cca45016f5382
+oid sha256:d00596a2a77c6d3c29d66ae8e723565a357207bb2e5d1c235f7357b00a4b32b7
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1,
   "best_metric": 1.4945952892303467,
   "best_model_checkpoint": null,
-  "epoch": 0.04059962523422861,
+  "epoch": 0.04372267332916927,
   "eval_steps": 50,
-  "global_step": 650,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -575,6 +575,49 @@
       "eval_samples_per_second": 15.741,
       "eval_steps_per_second": 15.741,
       "step": 650
+    },
+    {
+      "epoch": 0.04122423485321674,
+      "grad_norm": 2672.0,
+      "learning_rate": 0.013263210930352737,
+      "loss": 7.9423,
+      "step": 660
+    },
+    {
+      "epoch": 0.04184884447220487,
+      "grad_norm": 47185920.0,
+      "learning_rate": 0.01256876734349413,
+      "loss": 8.6554,
+      "step": 670
+    },
+    {
+      "epoch": 0.042473454091193005,
+      "grad_norm": 31.125,
+      "learning_rate": 0.011886840954170141,
+      "loss": 8.6544,
+      "step": 680
+    },
+    {
+      "epoch": 0.043098063710181135,
+      "grad_norm": 916.0,
+      "learning_rate": 0.011218118404450424,
+      "loss": 8.0047,
+      "step": 690
+    },
+    {
+      "epoch": 0.04372267332916927,
+      "grad_norm": 44.25,
+      "learning_rate": 0.010563273041257332,
+      "loss": 8.3487,
+      "step": 700
+    },
+    {
+      "epoch": 0.04372267332916927,
+      "eval_loss": 8.62705135345459,
+      "eval_runtime": 56.6085,
+      "eval_samples_per_second": 14.892,
+      "eval_steps_per_second": 14.892,
+      "step": 700
     }
   ],
   "logging_steps": 10,
@@ -589,7 +632,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 13
+        "early_stopping_patience_counter": 14
       }
     },
     "TrainerControl": {
@@ -603,7 +646,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.655004065792e+16,
+  "total_flos": 2.859235147776e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null