Training in progress, step 21000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d48b0a44dbe63da6c9020bb5bb394c5ff71c9ddcfdd7b0da7a1eb0579aff377c
+oid sha256:ae7656d802c40cc32e71f80a87339ed772f9327d1a02076254fc245072e9997d
 size 135998360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3eed3814c4228d3a78cce1ac2ca3519ee19f47266255a5e08c1f0b3fd29b8be
+oid sha256:7d3a30ebc048fd61d63535a1c6fe9f067c75e9ccd3a341ba92de3439cc2a8d85
 size 268169559

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34694258354d18f315f069c900377f9e4b8cd501dbb2a2fc08388222938aa9bf
+oid sha256:cab7abce9c76cd4a5e9e32dd6177412a4c5d8017ce7b822ecd8a7881368976e4
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65a41063ac1e34e89f9f393fe5e0b87724ffce211c51ac4312fe4d7e5bca144b
+oid sha256:781263dd3c87ac5a3d305141f91df0d8a3d44c07e8f063a67672d88efe279547
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.03128109499812126,
-  "best_model_checkpoint": "mgh6/TCS_Pairing/checkpoint-19000",
-  "epoch": 2.386919680152763,
+  "best_metric": 0.030218619853258133,
+  "best_model_checkpoint": "mgh6/TCS_Pairing/checkpoint-21000",
+  "epoch": 2.506265664160401,
   "eval_steps": 1000,
-  "global_step": 20000,
+  "global_step": 21000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,6 +287,20 @@
       "eval_samples_per_second": 178.733,
       "eval_steps_per_second": 22.347,
       "step": 20000
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.64578111946533e-05,
+      "loss": 0.0123,
+      "step": 21000
+    },
+    {
+      "epoch": 2.51,
+      "eval_loss": 0.030218619853258133,
+      "eval_runtime": 141.8386,
+      "eval_samples_per_second": 179.091,
+      "eval_steps_per_second": 22.392,
+      "step": 21000
     }
   ],
   "logging_steps": 1000,
@@ -294,7 +308,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 1000,
-  "total_flos": 5.001830372156789e+16,
+  "total_flos": 5.251923453846389e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null