Training in progress, step 39500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8cd71b89eb4cf5b54368e95fa13ee6cc3864c3091e759091438dd601d6f1af7
+oid sha256:f89e86203fc6f340f2bb2ff8e994975dfeb321d8847629162cb09b057f7a04af
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc0dd7a1f2c9ad84ebf73220aa56cda18faf115b1e79f8dbee1b26db6cddaa7d
+oid sha256:eb05543b93a1625973f09dd8a4f47b7ff974fc94669448d693bf400cf4b1820e
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:823ea6f73dcec531968a187071c6ecff33e9bb6c6d030f15a43dbc4f25e7c39e
+oid sha256:86347a47866fbcda684d924341c7041bee88821d888a3574e3156decc1c5d213
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90e54113eca63b2259f253dad8dc263308f86084513f881434f4da417da62d75
+oid sha256:a9ca915c8cfa9f185cabf22307b900bc37acbb465a96ff7179034cb96d5b0895
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.6,
+  "epoch": 2.6333333333333333,
   "eval_steps": 500,
-  "global_step": 39000,
+  "global_step": 39500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2753,6 +2753,41 @@
       "learning_rate": 2.6728888888888893e-06,
       "loss": 0.0516,
       "step": 39000
+    },
+    {
+      "epoch": 2.6066666666666665,
+      "grad_norm": 0.11047784239053726,
+      "learning_rate": 2.6284444444444445e-06,
+      "loss": 0.0494,
+      "step": 39100
+    },
+    {
+      "epoch": 2.6133333333333333,
+      "grad_norm": 0.27986884117126465,
+      "learning_rate": 2.5840000000000006e-06,
+      "loss": 0.0523,
+      "step": 39200
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 0.17573469877243042,
+      "learning_rate": 2.539555555555556e-06,
+      "loss": 0.0549,
+      "step": 39300
+    },
+    {
+      "epoch": 2.626666666666667,
+      "grad_norm": 0.26180362701416016,
+      "learning_rate": 2.495111111111111e-06,
+      "loss": 0.0543,
+      "step": 39400
+    },
+    {
+      "epoch": 2.6333333333333333,
+      "grad_norm": 0.22933009266853333,
+      "learning_rate": 2.4506666666666667e-06,
+      "loss": 0.053,
+      "step": 39500
     }
   ],
   "logging_steps": 100,
@@ -2772,7 +2807,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.499743092736e+16,
+  "total_flos": 9.621534670848e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null