Training in progress, step 40000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f89e86203fc6f340f2bb2ff8e994975dfeb321d8847629162cb09b057f7a04af
+oid sha256:5b86dc095c2649030c80dbb3b306b6dc458cfc29054732a394c23118a3921570
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb05543b93a1625973f09dd8a4f47b7ff974fc94669448d693bf400cf4b1820e
+oid sha256:cbe16dcb2945b2b310dff07ecbc105e5d8932c93cc840533642e145b021fcd46
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86347a47866fbcda684d924341c7041bee88821d888a3574e3156decc1c5d213
+oid sha256:996bcc2fc9a86c5f72875fc2c94242013d036dcc7c497de3b8bae67dc7683e4b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9ca915c8cfa9f185cabf22307b900bc37acbb465a96ff7179034cb96d5b0895
+oid sha256:3bc8f3c97f58f2fb9ce92ef34272eb4a5ca6976677613743a4e1abd3e5adada4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.6333333333333333,
+  "epoch": 2.6666666666666665,
   "eval_steps": 500,
-  "global_step": 39500,
+  "global_step": 40000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2788,6 +2788,41 @@
       "learning_rate": 2.4506666666666667e-06,
       "loss": 0.053,
       "step": 39500
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.10127383470535278,
+      "learning_rate": 2.4062222222222223e-06,
+      "loss": 0.0494,
+      "step": 39600
+    },
+    {
+      "epoch": 2.6466666666666665,
+      "grad_norm": 0.1442176252603531,
+      "learning_rate": 2.3622222222222224e-06,
+      "loss": 0.0489,
+      "step": 39700
+    },
+    {
+      "epoch": 2.6533333333333333,
+      "grad_norm": 0.2334638386964798,
+      "learning_rate": 2.317777777777778e-06,
+      "loss": 0.0493,
+      "step": 39800
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 0.2831490635871887,
+      "learning_rate": 2.2733333333333333e-06,
+      "loss": 0.0515,
+      "step": 39900
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.35798129439353943,
+      "learning_rate": 2.228888888888889e-06,
+      "loss": 0.0502,
+      "step": 40000
     }
   ],
   "logging_steps": 100,
@@ -2807,7 +2842,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.621534670848e+16,
+  "total_flos": 9.74332624896e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null