Training in progress, step 14500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e948c8d9a7ad56ccbd6700926716442cecc28d16ec12db2c3ed5e7e3f659db9b
+oid sha256:44b5263c1decc645c9e701779bd3d240d1bd128257b6edb8ead3471aa6e882ff
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af58a191c850477c58ee5c9fd6d80b4f79d202f3c260b244c0bb72f25e9c46bf
+oid sha256:4662d2a8a819e0d85a2d8fe1130697f20508f25fc829adbfc7041f6ee0ff9440
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aba8071d282c3cb60c40a4d3269fc6a11f1d4d5aa00c59a4ed8e5ce671a0abf0
+oid sha256:bcf69dbca5717fd7e2d59b8c55b37845db01c5e5f067d9b29c7651b0c07744c5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aecb0190c300aa10c453b1ef86e11d1993afb13996c225cb9c0fcb417f89ff36
+oid sha256:9ac2ccaa6ddf120173c07745369f72632efad440b0563e86a0141350749aa0ae
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9333333333333333,
+  "epoch": 0.9666666666666667,
   "eval_steps": 500,
-  "global_step": 14000,
+  "global_step": 14500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -987,6 +987,41 @@
       "learning_rate": 1.3779555555555557e-05,
       "loss": 0.0666,
       "step": 14000
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.12045079469680786,
+      "learning_rate": 1.3735111111111112e-05,
+      "loss": 0.0712,
+      "step": 14100
+    },
+    {
+      "epoch": 0.9466666666666667,
+      "grad_norm": 0.1625666618347168,
+      "learning_rate": 1.3690666666666667e-05,
+      "loss": 0.0633,
+      "step": 14200
+    },
+    {
+      "epoch": 0.9533333333333334,
+      "grad_norm": 0.17143802344799042,
+      "learning_rate": 1.3646222222222223e-05,
+      "loss": 0.0627,
+      "step": 14300
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.19708478450775146,
+      "learning_rate": 1.3601777777777778e-05,
+      "loss": 0.067,
+      "step": 14400
+    },
+    {
+      "epoch": 0.9666666666666667,
+      "grad_norm": 0.1801692545413971,
+      "learning_rate": 1.3557333333333333e-05,
+      "loss": 0.0643,
+      "step": 14500
     }
   ],
   "logging_steps": 100,
@@ -1006,7 +1041,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.410164187136e+16,
+  "total_flos": 3.531955765248e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null