Training in progress, step 3100, checkpoint

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64d3ba99f0386e07f2feb4e2b3e05c69553c8f4ddeab5f324433fb42b11a9dfe
+oid sha256:71fd0fa3c83db34c04a261e6bd3242a5476745a9f7511efddbff7145d0dc8239
 size 50349441

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9abb7474dca374d074aba374d71ceac951c6873c599517b10e0b248d7ef88304
+oid sha256:e5660c8b38f29f9c62edfdc1f87d539132c89fbba7620bbffe5cb7cb482329b9
 size 100691721

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d235165de510ff0726cd98a164f0204996ff7e0ba0c0e785855b606d1a75815
+oid sha256:6e42983a0941a5ea3ab8dd356cda0bea564cad32d8e894b126d9bb07e48e1e57
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb57538b0fddb988f32d5e33311bcf25efee1aa4001ec3e33ef4a2dd884d77d3
+oid sha256:0f4766a50a63740d51a19c983a4de442d7f62ff1e951fc016c44cc6c58fb9db1
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3319122791290283,
-  "best_model_checkpoint": "./outputs/checkpoint-3000",
-  "epoch": 2.1861566484517305,
+  "best_metric": 1.320979356765747,
+  "best_model_checkpoint": "./outputs/checkpoint-3100",
+  "epoch": 2.259016393442623,
   "eval_steps": 100,
-  "global_step": 3000,
+  "global_step": 3100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -427,13 +427,27 @@
       "eval_samples_per_second": 47.003,
       "eval_steps_per_second": 5.881,
       "step": 3000
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 0.0002,
+      "loss": 1.2963,
+      "step": 3100
+    },
+    {
+      "epoch": 2.26,
+      "eval_loss": 1.320979356765747,
+      "eval_runtime": 133.3932,
+      "eval_samples_per_second": 47.034,
+      "eval_steps_per_second": 5.885,
+      "step": 3100
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.7882770130232115e+17,
+  "total_flos": 1.8479244039539098e+17,
   "trial_name": null,
   "trial_params": null
 }