Training in progress, step 5500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ae5c81c1c60500c4a5e1dd6dc813ec1e98722c56c518f3879627e98375fc97c
+oid sha256:37eb7a5e4bceab7d32011b5d17f5f7c727abd642937f2f5113f334b54b67ecce
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02ec7dd85fee160cc36f0c35de11d3c1f3f62be09dc2acdbea1436d93df16a1f
+oid sha256:c9719ee3b3f8442d6fc5e8f63a83f241cd994c81df3f6f1e293214b163473444
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e395ce6518143962b06454b53148180fd527e3c70ad1a04b860142fa90882881
+oid sha256:eca803041d1c71084d00ad4722811ed67342df4d01c4b5a158f3fbc70c751c86
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:133e76e86cd14a96bc531992fc191ed101dcf5373cd51d0b24c7b1c479a2d7b7
+oid sha256:0c79865c40bc524fb8d08f87fe96773f5e5e19275573e12c21b3c870bc7e6d8a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3333333333333333,
+  "epoch": 0.36666666666666664,
   "eval_steps": 500,
-  "global_step": 5000,
+  "global_step": 5500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -357,6 +357,41 @@
       "learning_rate": 1.777866666666667e-05,
       "loss": 0.0669,
       "step": 5000
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.16804884374141693,
+      "learning_rate": 1.7734222222222225e-05,
+      "loss": 0.0664,
+      "step": 5100
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 0.17912818491458893,
+      "learning_rate": 1.768977777777778e-05,
+      "loss": 0.0695,
+      "step": 5200
+    },
+    {
+      "epoch": 0.35333333333333333,
+      "grad_norm": 0.18144488334655762,
+      "learning_rate": 1.764577777777778e-05,
+      "loss": 0.0721,
+      "step": 5300
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.22347889840602875,
+      "learning_rate": 1.7601333333333334e-05,
+      "loss": 0.0723,
+      "step": 5400
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 0.16477668285369873,
+      "learning_rate": 1.755688888888889e-05,
+      "loss": 0.0708,
+      "step": 5500
     }
   ],
   "logging_steps": 100,
@@ -376,7 +411,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.21791578112e+16,
+  "total_flos": 1.339707359232e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null