Training in progress, step 1600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62497b1ca504d1310b68dc519967d6d4ad55c91a32a6a46ecc9cbcd64c350822
+oid sha256:5a548e85abc2ff3d129d10fed437dbdead9272cb44a66886e9e3ff230ed6e2d7
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23b00c78a7f8a88749de0d5cd06138a4abff4275686adc65bdef23aae03d99bc
+oid sha256:2941bb931f849e81894f9fc2dac0f376bacd497144ebd1a1e5f60fee1892d7bf
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21d4bab4bfb0f167510612de6f6d86a8fa795aa04f97ef3820248dfdf7828895
+oid sha256:db97249fb2abce3310b9eff58ce2e1650afeaabc2a34f23519369128cb8bf65c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4ef2096322b2582d886494838c6b92cbab2b79b497264212b2709668919a955
+oid sha256:41a51497602956bd9b9282bb348f82132dc02721f9d74081c5a4aadcaf218b9c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:511bea8ca7667c104169e77857c9fe88b52ea9a7bbb974853581e0287769431e
+oid sha256:e1b76dc6c723cbb4062a49610014821f5a119c1ef21bb357c8bd77b2feb3f887
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e89ef2598d83a81782a3378fd777be478981830df2a2e31cca5d378206dcf907
+oid sha256:b864370896443027245508af4848f87950729c2cd9ac0f4a6ca8c789d252276a
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00a4a4e203ef8c30b2c83f2af09081d69ba50b6306ba427554aeaca400d12948
+oid sha256:c5aeeb3fdfc3b5c117df4adc83127f79aac59e6de065d632826c06a43c29056b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8718409538269043,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-1500",
-  "epoch": 2.0080321285140563,
+  "best_metric": 0.8591811060905457,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-1600",
+  "epoch": 2.14190093708166,
   "eval_steps": 100,
-  "global_step": 1500,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -232,6 +232,21 @@
       "eval_samples_per_second": 894.312,
       "eval_steps_per_second": 3.614,
       "step": 1500
+    },
+    {
+      "epoch": 2.14190093708166,
+      "grad_norm": 0.21610258519649506,
+      "learning_rate": 0.0007858099062918341,
+      "loss": 0.8716,
+      "step": 1600
+    },
+    {
+      "epoch": 2.14190093708166,
+      "eval_loss": 0.8591811060905457,
+      "eval_runtime": 6.3979,
+      "eval_samples_per_second": 889.671,
+      "eval_steps_per_second": 3.595,
+      "step": 1600
     }
   ],
   "logging_steps": 100,
@@ -260,7 +275,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.446840614912e+16,
+  "total_flos": 5.8099633225728e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null