Training in progress, step 19500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:935e2f81b626e71b298466c51f498096f378414ac276b4d4ea19f4650105a4cf
+oid sha256:48d50eeabfb6258b47f80c4287b04eae339f2bcdd2adc92422732cfea4385d47
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b16c83dc7260ee2348e5de945bd725aa12ab974c28241b500cd256e88062c5e
+oid sha256:925f490db36c228becd31509d72df687d2fa95aa8acf7ad4097ac7ecd0f54d30
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46737d1e5768cf0de571a9bd47793403b2513f0c1ee54de55bfe17b1b1fdc49a
+oid sha256:43b0884f157293c23ccd8333c122a369315e2deb59504578aa420ad7f9561fc9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db8de303a11187ec0581f91507bd8428f995b03d53d2e944a4543899602e0467
+oid sha256:e20da249583a46b691b28ceb0e3fd46db03f73ee684cd77a32c44cbf4d68cb68
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2666666666666666,
+  "epoch": 1.3,
   "eval_steps": 500,
-  "global_step": 19000,
+  "global_step": 19500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1345,6 +1345,41 @@
       "learning_rate": 1.1558222222222223e-05,
       "loss": 0.0581,
       "step": 19000
+    },
+    {
+      "epoch": 1.2733333333333334,
+      "grad_norm": 0.13157618045806885,
+      "learning_rate": 1.1513777777777779e-05,
+      "loss": 0.0544,
+      "step": 19100
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.3684869110584259,
+      "learning_rate": 1.1469333333333334e-05,
+      "loss": 0.0633,
+      "step": 19200
+    },
+    {
+      "epoch": 1.2866666666666666,
+      "grad_norm": 0.12658458948135376,
+      "learning_rate": 1.1424888888888889e-05,
+      "loss": 0.0561,
+      "step": 19300
+    },
+    {
+      "epoch": 1.2933333333333334,
+      "grad_norm": 0.24430914223194122,
+      "learning_rate": 1.1380444444444444e-05,
+      "loss": 0.0532,
+      "step": 19400
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.29242023825645447,
+      "learning_rate": 1.1336e-05,
+      "loss": 0.0578,
+      "step": 19500
     }
   ],
   "logging_steps": 100,
@@ -1364,7 +1399,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.628079968256e+16,
+  "total_flos": 4.749871546368e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null