Training in progress, step 22000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae7656d802c40cc32e71f80a87339ed772f9327d1a02076254fc245072e9997d
+oid sha256:83d01386cb3582868485a9b1916de93caeac2c7e2ab0073e55c5cd3485363073
 size 135998360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d3a30ebc048fd61d63535a1c6fe9f067c75e9ccd3a341ba92de3439cc2a8d85
+oid sha256:1f235701e57b888ac98c1d92fa53167b1d117322cf85bc7642e8f689cefc95f7
 size 268169559

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cab7abce9c76cd4a5e9e32dd6177412a4c5d8017ce7b822ecd8a7881368976e4
+oid sha256:7448a6e079433f284d9c2bb8f9371197efaad670758f5fd07c2e6939d0f36a6f
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:781263dd3c87ac5a3d305141f91df0d8a3d44c07e8f063a67672d88efe279547
+oid sha256:337e9f830354319c5e26e3c0a8eced787189e3b59dea3a97ec90f3c4d683f4bc
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.030218619853258133,
-  "best_model_checkpoint": "mgh6/TCS_Pairing/checkpoint-21000",
-  "epoch": 2.506265664160401,
+  "best_metric": 0.028801346197724342,
+  "best_model_checkpoint": "mgh6/TCS_Pairing/checkpoint-22000",
+  "epoch": 2.6256116481680394,
   "eval_steps": 1000,
-  "global_step": 21000,
+  "global_step": 22000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -301,6 +301,20 @@
       "eval_samples_per_second": 179.091,
       "eval_steps_per_second": 22.392,
       "step": 21000
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 1.247961172773203e-05,
+      "loss": 0.012,
+      "step": 22000
+    },
+    {
+      "epoch": 2.63,
+      "eval_loss": 0.028801346197724342,
+      "eval_runtime": 142.0191,
+      "eval_samples_per_second": 178.863,
+      "eval_steps_per_second": 22.363,
+      "step": 22000
     }
   ],
   "logging_steps": 1000,
@@ -308,7 +322,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 1000,
-  "total_flos": 5.251923453846389e+16,
+  "total_flos": 5.502016535535989e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null