Training in progress, step 20000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0fa309b3fed136967feb592bfa4c7d4ecb17617ab07cc6695c3cc855fb2e4b8
+oid sha256:d48b0a44dbe63da6c9020bb5bb394c5ff71c9ddcfdd7b0da7a1eb0579aff377c
 size 135998360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08aee113126a9d4246b99e1dd455dc4d904b7cc05c638a809b8fa697c0cb7097
+oid sha256:a3eed3814c4228d3a78cce1ac2ca3519ee19f47266255a5e08c1f0b3fd29b8be
 size 268169559

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f8ef1e2ae8dbf26dac35c5e3a9c5666c45388e54825fca38608098cfac04806
+oid sha256:34694258354d18f315f069c900377f9e4b8cd501dbb2a2fc08388222938aa9bf
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd90c849bfa83dbf6e2a35622878977aba534edc2987732f6dd3f35b865a1231
+oid sha256:65a41063ac1e34e89f9f393fe5e0b87724ffce211c51ac4312fe4d7e5bca144b
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.03128109499812126,
   "best_model_checkpoint": "mgh6/TCS_Pairing/checkpoint-19000",
-  "epoch": 2.2675736961451247,
+  "epoch": 2.386919680152763,
   "eval_steps": 1000,
-  "global_step": 19000,
+  "global_step": 20000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,20 @@
       "eval_samples_per_second": 178.764,
       "eval_steps_per_second": 22.351,
       "step": 19000
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 2.043601066157457e-05,
+      "loss": 0.0123,
+      "step": 20000
+    },
+    {
+      "epoch": 2.39,
+      "eval_loss": 0.03134540468454361,
+      "eval_runtime": 142.1226,
+      "eval_samples_per_second": 178.733,
+      "eval_steps_per_second": 22.347,
+      "step": 20000
     }
   ],
   "logging_steps": 1000,
@@ -280,7 +294,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 1000,
-  "total_flos": 4.751737290467189e+16,
+  "total_flos": 5.001830372156789e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null