Training in progress, epoch 4, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ac4f10040e66e431df938b7856d13f664df0b46d6101710def3a334fcb9ba6
+oid sha256:b49e9d5c8dd881f520e5a83128f40de519e68051af511937686445660ec5001b
 size 2610104820

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75140785cd75a1282efaf5e3f8124ffe807377629f03660cc850719c0ef15a2b
+oid sha256:ef26bd0d9cddd87b41bd441bf83979bef25265f8afb106bf9f07ea1c78276a60
 size 5210004271

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d01c0856a6fb316f12ae7b5a00934bd3a02b2c39928e0f3f92795aaa541bbc2
+oid sha256:b7cf274d687459d8fbef424ee490939d2e6b5b3ea4569321a0d69cd2a401ebb4
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9885f6cee74ee5ecf8b98902b21218a1e0a6e8b4b6018e56d76ad82d9af7fb58
+oid sha256:847be9d40b77e3bc7d7f6246e96a0e0054d918fd2ef8f822e1dd9b59a4a52a77
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3419935703277588,
-  "best_model_checkpoint": "mgh6/HTH_prob/checkpoint-976",
-  "epoch": 3.9960454139558617,
+  "best_metric": 1.3339548110961914,
+  "best_model_checkpoint": "mgh6/HTH_prob/checkpoint-1220",
+  "epoch": 4.996045413955862,
   "eval_steps": 500,
-  "global_step": 976,
+  "global_step": 1220,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -67,6 +67,21 @@
       "eval_samples_per_second": 32.751,
       "eval_steps_per_second": 16.376,
       "step": 976
+    },
+    {
+      "epoch": 4.996045413955862,
+      "grad_norm": 0.16875308752059937,
+      "learning_rate": 0.0009166666666666666,
+      "loss": 1.3448,
+      "step": 1220
+    },
+    {
+      "epoch": 4.996045413955862,
+      "eval_loss": 1.3339548110961914,
+      "eval_runtime": 25.1789,
+      "eval_samples_per_second": 32.805,
+      "eval_steps_per_second": 16.403,
+      "step": 1220
     }
   ],
   "logging_steps": 500,