Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6200f3351419b2a4547eca661f5841296cde5f4569610dbfa211652b2a53987f
+oid sha256:a465af8d048a7f031e16d6270216ca95942101bc69690b769ef7b6e52b69e30a
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:845d72071b47bbed6c4db119ad1309b76050bd81a2736b635ad13ac11f5298fb
+oid sha256:c2fd7a3d1e41234aca57bacb5a2a1fb24a1405b183989ab703699954f57c5e6f
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2b52d82f73e570b1698336d070d85ea4c32ca359687f3058f1f92bb220326cb
+oid sha256:3d12b7db194a200f2097696f9a8fe9cdee71176d5f1c0acf060124b4ab20294d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53c29fa3f5d39e373c71b4c0a778590fc5fcdd4d7e21f2a64fb25f5ebf63cca1
+oid sha256:e1d32deee4e1dfc49eda1ce5d9828c1b08d693293cc00d6985a2e425f87cd3dd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8312551953449709,
+  "epoch": 1.2468827930174564,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,6 +21,21 @@
       "learning_rate": 1.4458298697700195e-05,
       "loss": 0.392,
       "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.31241247057914734,
+      "eval_runtime": 34.4517,
+      "eval_samples_per_second": 14.339,
+      "eval_steps_per_second": 1.8,
+      "step": 1203
+    },
+    {
+      "epoch": 1.2468827930174564,
+      "grad_norm": 29103.794921875,
+      "learning_rate": 1.1687448046550292e-05,
+      "loss": 0.3735,
+      "step": 1500
     }
   ],
   "logging_steps": 500,
@@ -40,7 +55,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4871663124480000.0,
+  "total_flos": 7306885728829440.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c6902ddb0f6942cea8435dc8faed1ce85b2ddfb716f52e329197e58e67bcbec
+oid sha256:2a0eee04499ccdf8d802fc08cc9a27a978fedc8125cdd17ba42f942e0fa36ff2
 size 5368