Training in progress, step 660, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:753b312283d73a72ca99b1d1d1ffee6620efa88ab793579d9e15f4ca0ae1af73
+oid sha256:82f67cbe9e89ea2da575b60c5410847310ec4df02b9c6d92a6859e332eacbb1a
 size 1976163472

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:106ff0ce09a38420db18c8b793f298b4cebda4c3454b295a84c99e6c8c842121
+oid sha256:d2c52059a0ace4821d5364e966b4df8b16f3e773b35b9b1efdd18136d59f9441
 size 1816765835

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b40356dc87f933072688e24d199ff6f594a63bfd128de071b6824c1e3453a79
+oid sha256:ca202fc25cecd2e3dfae2a87978621e5f552f2c88fe716b567b699919d821583
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8858a295d00c72f24ae28810bb37a9a4de6f9a3e105940ebdbeac616da712648
+oid sha256:47597edb455ef686d71b9e2fdfad1e99b404dc1a854723bde359a0fdeff5c2f3
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.020602289960880177,
+  "epoch": 0.021583351387588757,
   "eval_steps": 500,
-  "global_step": 630,
+  "global_step": 660,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -449,6 +449,27 @@
       "learning_rate": 9.794310006540224e-06,
       "loss": 1.0060985565185547,
       "step": 630
+    },
+    {
+      "epoch": 0.020929310436449702,
+      "grad_norm": 2.1337103843688965,
+      "learning_rate": 9.791039895356443e-06,
+      "loss": 1.0044135093688964,
+      "step": 640
+    },
+    {
+      "epoch": 0.021256330912019228,
+      "grad_norm": 2.3290762901306152,
+      "learning_rate": 9.787769784172662e-06,
+      "loss": 1.0389455795288085,
+      "step": 650
+    },
+    {
+      "epoch": 0.021583351387588757,
+      "grad_norm": 2.148353338241577,
+      "learning_rate": 9.784499672988883e-06,
+      "loss": 1.041367530822754,
+      "step": 660
     }
   ],
   "logging_steps": 10,
@@ -468,7 +489,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.031704549462016e+16,
+  "total_flos": 2.129457117633331e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null