Training in progress, step 23000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83d01386cb3582868485a9b1916de93caeac2c7e2ab0073e55c5cd3485363073
+oid sha256:ea01acb0b995946588af91942d4bfb439c330626af87c4b964a235a7c0611731
 size 135998360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f235701e57b888ac98c1d92fa53167b1d117322cf85bc7642e8f689cefc95f7
+oid sha256:417d1e612ebbc3c5c1f636d4a1bd8eeb240857c2e5414772c5b974df71cdc010
 size 268169559

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7448a6e079433f284d9c2bb8f9371197efaad670758f5fd07c2e6939d0f36a6f
+oid sha256:fb100cd2672f6f911dab0cfaa93cd0ea63787054323e121622cc0ad1321fc050
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:337e9f830354319c5e26e3c0a8eced787189e3b59dea3a97ec90f3c4d683f4bc
+oid sha256:f2365f5fbb067300527e856b1aced93d4eadc012e3cb9878f348e580aff0bfea
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.028801346197724342,
-  "best_model_checkpoint": "mgh6/TCS_Pairing/checkpoint-22000",
-  "epoch": 2.6256116481680394,
+  "best_metric": 0.027987737208604813,
+  "best_model_checkpoint": "mgh6/TCS_Pairing/checkpoint-23000",
+  "epoch": 2.7449576321756775,
   "eval_steps": 1000,
-  "global_step": 22000,
+  "global_step": 23000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -315,6 +315,20 @@
       "eval_samples_per_second": 178.863,
       "eval_steps_per_second": 22.363,
       "step": 22000
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 8.501412260810758e-06,
+      "loss": 0.0116,
+      "step": 23000
+    },
+    {
+      "epoch": 2.74,
+      "eval_loss": 0.027987737208604813,
+      "eval_runtime": 141.3339,
+      "eval_samples_per_second": 179.73,
+      "eval_steps_per_second": 22.472,
+      "step": 23000
     }
   ],
   "logging_steps": 1000,
@@ -322,7 +336,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 1000,
-  "total_flos": 5.502016535535989e+16,
+  "total_flos": 5.752109617225589e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null