Training in progress, step 2500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e5df61f042594bdcf440df5c2750da3a3adebab8a36e1d3b1903402c4fc3091
+oid sha256:2ea9dc04b1d9910f1a84e8124e410e0f21c46481305045ae2609225cac7adbcd
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ff826d4f45c57b5599542715ce59b0e1300878f883547db063dfb3f453c1877
+oid sha256:0766f573b0e38d5a96d5fcb59c888adac46f3c73ade3435cd35f3bc72b95414a
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7889ea0c99419f757623bd536c886c76ec1b2bc48f8905f0fbdab85178a3efa4
+oid sha256:f80da795dbb27c3d8f1091b4c3160f1bae711b20ee8838c992f0071cc9f91f10
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0c3706980993013e323b4cb71cb92383ee3053aec5ea4cdc2e4fe52fced544d
+oid sha256:787cdc2717a9f69d2534a49e908f0c04a317c018ada55bdb87d14c0859039210
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8312551953449709,
+  "epoch": 1.0390689941812137,
   "eval_steps": 500,
-  "global_step": 2000,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,6 +35,21 @@
       "learning_rate": 1.4463840399002496e-05,
       "loss": 0.3804,
       "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.30536511540412903,
+      "eval_runtime": 26.8313,
+      "eval_samples_per_second": 18.411,
+      "eval_steps_per_second": 4.621,
+      "step": 2406
+    },
+    {
+      "epoch": 1.0390689941812137,
+      "grad_norm": 0.5247063636779785,
+      "learning_rate": 1.3078415073427544e-05,
+      "loss": 0.3753,
+      "step": 2500
     }
   ],
   "logging_steps": 500,
@@ -54,7 +69,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4871663124480000.0,
+  "total_flos": 6088969947709440.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null