Training in progress, step 3500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfaec2d0bd4afa23e06e77ddd63a3feb0a907863ea820a966a17a2a147b3b707
+oid sha256:7f87a1a364a4c3b074d33d923c337d1857c4daa5fb358a1762ecbe5edd921a65
 size 2682482800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4aeda745a7d780c168af088c2119cd2808e09d2b70ddf3b10fe991b8301f47a
+oid sha256:050bb814577fa11d9d1653fc91c52cba6e25bf23abddb567aab775e12c1b1db4
 size 5365108834

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1a206d3f461a04e1705d768bf9ee9f4e1d43872d3c805720a5fcfdcd1c2fde2
+oid sha256:2d018acbbeceb8f6ded094ffbf67a030bf83c1f54ca6f31bd5f038a52ac85034
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d55af9f05e45e54d704719d9962a1a4b666003c2031e29596f0a28ff61626fa0
+oid sha256:d8fbc117afd7b27eea894ff76f1b04973418f72f10dadd713f6dfa7c4713012d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e731228e65cdad293c5d9de7ec953cc46b834ed0add902c06c23f7dc47cf45f
+oid sha256:abd2a75ef074977893e3dd803f93d5726cebe2149302e0d0ae3ef1370abb200d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd8992a9c2839cbf3be0b9721e659e911e005b61f52ff7504b2e6cc3d343df40
+oid sha256:c7f1adac70acfa8a2122e4d3f5566d6d9f1d3efc180b57f0dbc4b7b17090217f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5d7a7fadead41de5e72358e9a555c72cb33ae5f368d62819e428093a71b7139
+oid sha256:5a199cc7b81fba53fabd1b994537c465f58151394382535a6c542ffe0cc02930
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2301628402094482,
+  "epoch": 0.26852331357768955,
   "eval_steps": 500,
-  "global_step": 3000,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -427,6 +427,76 @@
       "learning_rate": 7.698327451281265e-05,
       "loss": 62.4057,
       "step": 3000
+    },
+    {
+      "epoch": 0.23399888754627232,
+      "grad_norm": 30.12982940673828,
+      "learning_rate": 7.659966242135954e-05,
+      "loss": 62.3078,
+      "step": 3050
+    },
+    {
+      "epoch": 0.23783493488309645,
+      "grad_norm": 42.589744567871094,
+      "learning_rate": 7.621605032990641e-05,
+      "loss": 62.3119,
+      "step": 3100
+    },
+    {
+      "epoch": 0.2416709822199206,
+      "grad_norm": 27.961658477783203,
+      "learning_rate": 7.583243823845329e-05,
+      "loss": 62.0758,
+      "step": 3150
+    },
+    {
+      "epoch": 0.24550702955674472,
+      "grad_norm": 24.691585540771484,
+      "learning_rate": 7.544882614700016e-05,
+      "loss": 61.9141,
+      "step": 3200
+    },
+    {
+      "epoch": 0.24934307689356885,
+      "grad_norm": 28.78058433532715,
+      "learning_rate": 7.506521405554704e-05,
+      "loss": 61.6389,
+      "step": 3250
+    },
+    {
+      "epoch": 0.253179124230393,
+      "grad_norm": 24.537670135498047,
+      "learning_rate": 7.468160196409391e-05,
+      "loss": 61.7158,
+      "step": 3300
+    },
+    {
+      "epoch": 0.25701517156721715,
+      "grad_norm": 29.42478370666504,
+      "learning_rate": 7.429798987264079e-05,
+      "loss": 61.9078,
+      "step": 3350
+    },
+    {
+      "epoch": 0.2608512189040413,
+      "grad_norm": 25.205659866333008,
+      "learning_rate": 7.391437778118768e-05,
+      "loss": 61.7029,
+      "step": 3400
+    },
+    {
+      "epoch": 0.2646872662408654,
+      "grad_norm": 37.85655212402344,
+      "learning_rate": 7.353076568973455e-05,
+      "loss": 61.5407,
+      "step": 3450
+    },
+    {
+      "epoch": 0.26852331357768955,
+      "grad_norm": 23.54515838623047,
+      "learning_rate": 7.314715359828143e-05,
+      "loss": 61.2952,
+      "step": 3500
     }
   ],
   "logging_steps": 50,
@@ -446,7 +516,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.14177314984244e+18,
+  "total_flos": 5.99843679544279e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null