Training in progress, step 24000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8780b961dcbf09881cce6a4ec4f3ce77d0ac1ee0f91af800fa2edc12b4f6187
+oid sha256:34a5bf7d80afb43e227b324a1b6cda7e106c37feb23b0824b268c18e7b3a3d1a
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef9bac5420d614e9bac93f0dd5fea2e0183354a0f7d5a23ad1f55f6681e9e683
+oid sha256:dd314d98a4869313e973a437be445c914aa71bb8b03a7af5f6f9a32ad34d63bf
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:243e2ec3e6c9bc99b16b0183c86988f987cd95808c30f0890be20ce20d1d5d66
+oid sha256:727aa5fd6a222ba79327243b6bf0f36bc88c1b723f0949eac077fe52d4306974
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06c57df543e7b3168b7bf3184803db11f7fb923e889cb830127c49143334357b
+oid sha256:751ad724592c1d67b441302a9338d9d899df51042c6edaf69d5d08369bc3c9df
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.5666666666666667,
+  "epoch": 1.6,
   "eval_steps": 500,
-  "global_step": 23500,
+  "global_step": 24000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1660,6 +1660,41 @@
       "learning_rate": 9.558666666666667e-06,
       "loss": 0.0621,
       "step": 23500
+    },
+    {
+      "epoch": 1.5733333333333333,
+      "grad_norm": 0.2637277841567993,
+      "learning_rate": 9.514666666666667e-06,
+      "loss": 0.0505,
+      "step": 23600
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.17785485088825226,
+      "learning_rate": 9.470222222222222e-06,
+      "loss": 0.0587,
+      "step": 23700
+    },
+    {
+      "epoch": 1.5866666666666667,
+      "grad_norm": 0.11615557968616486,
+      "learning_rate": 9.425777777777778e-06,
+      "loss": 0.0545,
+      "step": 23800
+    },
+    {
+      "epoch": 1.5933333333333333,
+      "grad_norm": 0.2337283492088318,
+      "learning_rate": 9.381333333333335e-06,
+      "loss": 0.0574,
+      "step": 23900
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.21848595142364502,
+      "learning_rate": 9.33688888888889e-06,
+      "loss": 0.0581,
+      "step": 24000
     }
   ],
   "logging_steps": 100,
@@ -1679,7 +1714,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.724204171264e+16,
+  "total_flos": 5.845995749376e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null