Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35286f85be522ab120b67ef86a9b2fea852320beeec84ecb8e980c2c25acc3dc
+oid sha256:62497b1ca504d1310b68dc519967d6d4ad55c91a32a6a46ecc9cbcd64c350822
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9186371be341491f8cddef66b45c7672dd44b1d906084bbec228e7ac80cb3411
+oid sha256:23b00c78a7f8a88749de0d5cd06138a4abff4275686adc65bdef23aae03d99bc
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15433f7b2e9dde73085fab120a65bed01df370c9b02a1594a472d70068457ea5
+oid sha256:21d4bab4bfb0f167510612de6f6d86a8fa795aa04f97ef3820248dfdf7828895
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53a7daa52c58fe1fb49f677ab523d6f9e6c00f2599813aaa026fc90badc494a1
+oid sha256:e4ef2096322b2582d886494838c6b92cbab2b79b497264212b2709668919a955
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70429062c9260565eaadd7c683e4ca4b0df3e30951bd8422b10d4ac7e4ffd7b8
+oid sha256:511bea8ca7667c104169e77857c9fe88b52ea9a7bbb974853581e0287769431e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecdce592e98f25cf4a04063424668eaa8d77ff8c0a42490c9215deb661680414
+oid sha256:e89ef2598d83a81782a3378fd777be478981830df2a2e31cca5d378206dcf907
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3477b2d9f0cb08adf52a30b7e6192998cc41f2cc3eb4ead00d452c0bcd1756e
+oid sha256:00a4a4e203ef8c30b2c83f2af09081d69ba50b6306ba427554aeaca400d12948
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8721866607666016,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-1400",
-  "epoch": 1.8741633199464525,
+  "best_metric": 0.8718409538269043,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-1500",
+  "epoch": 2.0080321285140563,
   "eval_steps": 100,
-  "global_step": 1400,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,6 +217,21 @@
       "eval_samples_per_second": 892.551,
       "eval_steps_per_second": 3.607,
       "step": 1400
+    },
+    {
+      "epoch": 2.0080321285140563,
+      "grad_norm": 0.19012120366096497,
+      "learning_rate": 0.0007991967871485943,
+      "loss": 0.885,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0080321285140563,
+      "eval_loss": 0.8718409538269043,
+      "eval_runtime": 6.3647,
+      "eval_samples_per_second": 894.312,
+      "eval_steps_per_second": 3.614,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
@@ -245,7 +260,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.0837179072512e+16,
+  "total_flos": 5.446840614912e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null