Training in progress, step 25000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d9340baea21904af277f14b100fc25e1d3e6f36458993b320d7dbfed9bf7cb7
+oid sha256:80bca253a0f5ca66dc3e39e1ce546bd0defe3bc6421b10a84896e73a3a79706b
 size 135998360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:007a6671f04ca066121aae3ebb6373bb5a806fe72dba55b7843d0774f29bb8c9
+oid sha256:d566c40915b75ee469c3c4f6352e6e59976f6c1e3d2aab8aecbb14c369ba3494
 size 268169559

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f022f893d7b58cc5ca502c3d8274d0eda388a77a6cc92ed7d64838869a3ac7e
+oid sha256:d16354864875b00aae19f2df9f099d4e5255f760791cc560d17cb09adeb84c8a
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5a34eb909dc0357010bb4840789630addfcb5e8da555dfa8f68a1c2f150d0cb
+oid sha256:5a963a7b936f55de824412516d865da5a9f6f0018131e283851ae1cda8ff2849
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.027928264811635017,
-  "best_model_checkpoint": "mgh6/TCS_Pairing/checkpoint-24000",
-  "epoch": 2.8643036161833155,
+  "best_metric": 0.027055351063609123,
+  "best_model_checkpoint": "mgh6/TCS_Pairing/checkpoint-25000",
+  "epoch": 2.9836496001909536,
   "eval_steps": 1000,
-  "global_step": 24000,
+  "global_step": 25000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -343,6 +343,20 @@
       "eval_samples_per_second": 179.117,
       "eval_steps_per_second": 22.395,
       "step": 24000
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 5.450133269682142e-07,
+      "loss": 0.0115,
+      "step": 25000
+    },
+    {
+      "epoch": 2.98,
+      "eval_loss": 0.027055351063609123,
+      "eval_runtime": 142.8238,
+      "eval_samples_per_second": 177.856,
+      "eval_steps_per_second": 22.237,
+      "step": 25000
     }
   ],
   "logging_steps": 1000,
@@ -350,7 +364,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 1000,
-  "total_flos": 6.002202698915189e+16,
+  "total_flos": 6.252295780604789e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null