Training in progress, step 24000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea01acb0b995946588af91942d4bfb439c330626af87c4b964a235a7c0611731
+oid sha256:4d9340baea21904af277f14b100fc25e1d3e6f36458993b320d7dbfed9bf7cb7
 size 135998360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:417d1e612ebbc3c5c1f636d4a1bd8eeb240857c2e5414772c5b974df71cdc010
+oid sha256:007a6671f04ca066121aae3ebb6373bb5a806fe72dba55b7843d0774f29bb8c9
 size 268169559

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb100cd2672f6f911dab0cfaa93cd0ea63787054323e121622cc0ad1321fc050
+oid sha256:6f022f893d7b58cc5ca502c3d8274d0eda388a77a6cc92ed7d64838869a3ac7e
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2365f5fbb067300527e856b1aced93d4eadc012e3cb9878f348e580aff0bfea
+oid sha256:c5a34eb909dc0357010bb4840789630addfcb5e8da555dfa8f68a1c2f150d0cb
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.027987737208604813,
-  "best_model_checkpoint": "mgh6/TCS_Pairing/checkpoint-23000",
-  "epoch": 2.7449576321756775,
+  "best_metric": 0.027928264811635017,
+  "best_model_checkpoint": "mgh6/TCS_Pairing/checkpoint-24000",
+  "epoch": 2.8643036161833155,
   "eval_steps": 1000,
-  "global_step": 23000,
+  "global_step": 24000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -329,6 +329,20 @@
       "eval_samples_per_second": 179.73,
       "eval_steps_per_second": 22.472,
       "step": 23000
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 4.523212793889486e-06,
+      "loss": 0.0107,
+      "step": 24000
+    },
+    {
+      "epoch": 2.86,
+      "eval_loss": 0.027928264811635017,
+      "eval_runtime": 141.818,
+      "eval_samples_per_second": 179.117,
+      "eval_steps_per_second": 22.395,
+      "step": 24000
     }
   ],
   "logging_steps": 1000,
@@ -336,7 +350,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 1000,
-  "total_flos": 5.752109617225589e+16,
+  "total_flos": 6.002202698915189e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null