Training in progress, step 22000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9498cb3e3306e8357a032524622b5d26748d8db258d513acaef4c7e389559f2c
+oid sha256:4cf00b77a940691d2a87a25214434a0d48f9864c65fc3b0b19e53bccdbef0226
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4fcf3c27385ce93621769bdc2dbf10817c3a0a9703e9571bb7778f1cc3f2198
+oid sha256:2faa9161687d4c30fe8c5c851dcaf7629e9d07b563b4b1ca8c6d9fe9490b63c8
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6135b553c57e576683ea34e2125a95123075dc2da6ac1f60418ada8ca13529ab
+oid sha256:92097f0b98245def4fd493d6f93f0c40c3a4e7e4f11939d1bbd3057b8f076619
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3693f6d21626ad0956a90ced9d517a1b2895382ded929533dfbb38ad2b207f63
+oid sha256:1a00533389a4678d5ecaa8f25d54446914041611d7541f6bf05750bdc13a462b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4333333333333333,
+  "epoch": 1.4666666666666668,
   "eval_steps": 500,
-  "global_step": 21500,
+  "global_step": 22000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1520,6 +1520,41 @@
       "learning_rate": 1.0447555555555557e-05,
       "loss": 0.0576,
       "step": 21500
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.1996719092130661,
+      "learning_rate": 1.0403111111111113e-05,
+      "loss": 0.0569,
+      "step": 21600
+    },
+    {
+      "epoch": 1.4466666666666668,
+      "grad_norm": 0.2424512505531311,
+      "learning_rate": 1.0358666666666668e-05,
+      "loss": 0.0592,
+      "step": 21700
+    },
+    {
+      "epoch": 1.4533333333333334,
+      "grad_norm": 0.139984592795372,
+      "learning_rate": 1.0314222222222223e-05,
+      "loss": 0.0541,
+      "step": 21800
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.21083594858646393,
+      "learning_rate": 1.0269777777777778e-05,
+      "loss": 0.0509,
+      "step": 21900
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 0.2649674713611603,
+      "learning_rate": 1.0225333333333334e-05,
+      "loss": 0.0624,
+      "step": 22000
     }
   ],
   "logging_steps": 100,
@@ -1539,7 +1574,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.237037858816e+16,
+  "total_flos": 5.358829436928e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null