Training in progress, step 29500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0d7856ac14e3c9a690e3c9dee53a7a64870218a71216a1c30e598f861133e14
+oid sha256:66cae8324741bfb1c3cbb4cfed2559c012d8b417990bdb0c6e1b400f774dcc4e
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed3cf9b04c05bb73a17b1d26a6bf42f7dfd71e2f3a8b717e1cbc8e86af15e592
+oid sha256:c9055ac327c15e228dd6a4caa71093d65f0ca825571af69e5994cc7332daa9be
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13275cc6296652d5dbe96fab3538f55b506c905c768d5c0e2ff0cc00f18629a9
+oid sha256:8eba248c4c107e3630aeadfd11e69cd930737cf324d325de259160a726c9e173
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cce86ca086e9ceba19d07f438b59e29c1c4e8071fe80d69909be3a44b7f8d02
+oid sha256:b2b394b8045eb22d77503865620f9a9d287ea2ba93ffd3839a0365feff6f4d8b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9333333333333333,
+  "epoch": 1.9666666666666668,
   "eval_steps": 500,
-  "global_step": 29000,
+  "global_step": 29500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2045,6 +2045,41 @@
       "learning_rate": 7.115555555555557e-06,
       "loss": 0.0603,
       "step": 29000
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.18953697383403778,
+      "learning_rate": 7.071111111111112e-06,
+      "loss": 0.0554,
+      "step": 29100
+    },
+    {
+      "epoch": 1.9466666666666668,
+      "grad_norm": 0.14956802129745483,
+      "learning_rate": 7.0266666666666674e-06,
+      "loss": 0.0555,
+      "step": 29200
+    },
+    {
+      "epoch": 1.9533333333333334,
+      "grad_norm": 0.2314777970314026,
+      "learning_rate": 6.982222222222223e-06,
+      "loss": 0.0576,
+      "step": 29300
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.1524542272090912,
+      "learning_rate": 6.937777777777779e-06,
+      "loss": 0.0545,
+      "step": 29400
+    },
+    {
+      "epoch": 1.9666666666666668,
+      "grad_norm": 0.12564967572689056,
+      "learning_rate": 6.893333333333334e-06,
+      "loss": 0.0545,
+      "step": 29500
     }
   ],
   "logging_steps": 100,
@@ -2064,7 +2099,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.063911530496e+16,
+  "total_flos": 7.185703108608e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null