Training in progress, step 3000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7df6efaf3479df75dd3f240aa0deaecfa553e8dd4922633b6fd9e3d93510d4c0
+oid sha256:1d121c234703115065cb1c42acce976d8219608537e091e947a9f60228423283
 size 2682482800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:402a389b6557c2fb0a540c46b58022ae6c3462bad9c7f07206dff1d510985d12
+oid sha256:35a4bcbad19596bd9ff25b0cb5180d5c0ef1d8aad778355bdd1a050fe063bb5c
 size 5365108834

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49aeb81dec758bb845227eb0ece2bc88efabbe9639e92f4b77310c772ef30111
+oid sha256:d1a206d3f461a04e1705d768bf9ee9f4e1d43872d3c805720a5fcfdcd1c2fde2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:584dc0282c266e7acbd2b133cd5329f45751980f00c2875f476a8bdc1ebbeb4e
+oid sha256:d55af9f05e45e54d704719d9962a1a4b666003c2031e29596f0a28ff61626fa0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:933292b2d94ca70b4493534389dbddf5888e0d81ecc65103071a3ee2cc561863
+oid sha256:5e731228e65cdad293c5d9de7ec953cc46b834ed0add902c06c23f7dc47cf45f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64dba4ebc106a15b3d3dc6ad915f8de1d3566136ab0566e7f79333b0f1ff1c71
+oid sha256:bd8992a9c2839cbf3be0b9721e659e911e005b61f52ff7504b2e6cc3d343df40
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8da03d8897acf9728edfb4d452369c8865b03641c697f2b4969095966c59c18
+oid sha256:a5d7a7fadead41de5e72358e9a555c72cb33ae5f368d62819e428093a71b7139
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.19180236684120683,
+  "epoch": 0.2301628402094482,
   "eval_steps": 500,
-  "global_step": 2500,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -357,6 +357,76 @@
       "learning_rate": 8.081939542734386e-05,
       "loss": 61.6991,
       "step": 2500
+    },
+    {
+      "epoch": 0.19563841417803096,
+      "grad_norm": 35.88410186767578,
+      "learning_rate": 8.043578333589075e-05,
+      "loss": 61.6338,
+      "step": 2550
+    },
+    {
+      "epoch": 0.1994744615148551,
+      "grad_norm": 35.40159225463867,
+      "learning_rate": 8.005217124443763e-05,
+      "loss": 61.4948,
+      "step": 2600
+    },
+    {
+      "epoch": 0.20331050885167923,
+      "grad_norm": 26.17939567565918,
+      "learning_rate": 7.96685591529845e-05,
+      "loss": 61.1859,
+      "step": 2650
+    },
+    {
+      "epoch": 0.20714655618850336,
+      "grad_norm": 40.978424072265625,
+      "learning_rate": 7.928494706153138e-05,
+      "loss": 61.0628,
+      "step": 2700
+    },
+    {
+      "epoch": 0.2109826035253275,
+      "grad_norm": 48.16961669921875,
+      "learning_rate": 7.890133497007825e-05,
+      "loss": 61.0898,
+      "step": 2750
+    },
+    {
+      "epoch": 0.21481865086215163,
+      "grad_norm": 38.556034088134766,
+      "learning_rate": 7.851772287862513e-05,
+      "loss": 60.5673,
+      "step": 2800
+    },
+    {
+      "epoch": 0.2186546981989758,
+      "grad_norm": 47.85882568359375,
+      "learning_rate": 7.8134110787172e-05,
+      "loss": 60.3441,
+      "step": 2850
+    },
+    {
+      "epoch": 0.22249074553579992,
+      "grad_norm": 37.2432975769043,
+      "learning_rate": 7.775049869571888e-05,
+      "loss": 60.3992,
+      "step": 2900
+    },
+    {
+      "epoch": 0.22632679287262406,
+      "grad_norm": 22.40682029724121,
+      "learning_rate": 7.736688660426577e-05,
+      "loss": 60.2252,
+      "step": 2950
+    },
+    {
+      "epoch": 0.2301628402094482,
+      "grad_norm": 63.746803283691406,
+      "learning_rate": 7.698327451281265e-05,
+      "loss": 60.2993,
+      "step": 3000
     }
   ],
   "logging_steps": 50,
@@ -376,7 +446,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.285389072253321e+18,
+  "total_flos": 5.14177314984244e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null