Training in progress, step 2500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4976591835d5aca83e7b5f41a00cb52acee5cb572e72a643fb9be051e9f83d1
+oid sha256:4c72b0c08a0fc04f2c153825fcc0362e59c4afb8c1846b6e60697a4f256f4a98
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61279ee4a931a5ad88cec6cf2852e6f43ed00d1fcc1a243cbc084b1c64b079ad
+oid sha256:0b7169cbbeba028ae9ab8039f7f1d231654e7b974aa4e1a587716973f591ee85
 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 sha256:7840dd1a31d2cba594152573000c19a8714961f30a02991b54083675256ff19f
+oid sha256:4d8d89f1ee6ff0e3b8b2a4fe1683c6e81327aff0190ec7348dca55e5b3647902
 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": 1.6678304239401496e-05,
       "loss": 0.4326,
       "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.33564111590385437,
+      "eval_runtime": 26.4357,
+      "eval_samples_per_second": 18.687,
+      "eval_steps_per_second": 4.691,
+      "step": 2406
+    },
+    {
+      "epoch": 1.0390689941812137,
+      "grad_norm": 0.7427258491516113,
+      "learning_rate": 1.5847049044056525e-05,
+      "loss": 0.4225,
+      "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