Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b32feb03bef74682dd00478366b7ab6f3fe36e62ad6f43eb0b6a45298c8c420
+oid sha256:86d8b734641afcfe9a7cd1d6da80ce228471ca86cb97a58be3140fb19c7c422b
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caf09d3b5479867cad574a9d4855fce3be35781906f4a4d330605331dc904195
+oid sha256:8af57cfd714c0b7ab3f23e52af9a802dba247a088b573f019e99a8faa44990fd
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:237cdd142ba1e146dbe902d7b81dd4a005d04aa5a22539b30a7f706ed6c82716
+oid sha256:a624c44263afb14378edac47214ec2c9da213c34fbe04289aef21a2b801784d7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0de9502ba6141c06b2056fb55ea065632b45dc42bb9ad6136e46e95f561ac79
+oid sha256:9517535082d3856241bb82290abcfc6ba4e812ae46ea90b0ce2e739b6902210d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.9484621778886115,
+  "epoch": 4.156275976724855,
   "eval_steps": 500,
-  "global_step": 9500,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -164,6 +164,21 @@
       "learning_rate": 4.212801330008313e-06,
       "loss": 0.3155,
       "step": 9500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.2871634364128113,
+      "eval_runtime": 26.8766,
+      "eval_samples_per_second": 18.38,
+      "eval_steps_per_second": 4.614,
+      "step": 9624
+    },
+    {
+      "epoch": 4.156275976724855,
+      "grad_norm": 1.265112280845642,
+      "learning_rate": 3.381546134663342e-06,
+      "loss": 0.3036,
+      "step": 10000
     }
   ],
   "logging_steps": 500,
@@ -183,7 +198,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.313857296760832e+16,
+  "total_flos": 2.435587979083776e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null