Training in progress, step 187, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a75b8b4f060b70b4acbf15e2810188aa5e77f7b80896679941436511f37eca44
+oid sha256:f3706edcdecfde2245a9fbdae763676b8a5f18f9afe639cd7a959bedfc3cc861
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f67b104ef782f97707a79c624761edded35f0157553358c6b27c9b692cd99a3e
+oid sha256:5c6177daa5d0be97a10a56f5dc81361305f57cb6bf5970eedb65929e5e5e08c5
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03056d1c4ca5ebbca3689312a90ecc3659af7e67511e12c82f70b630038ea234
+oid sha256:f948cc070a855b0c2501c70b85e0997b7c5819d25d21c44b4c9314bc9b671b0a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fab1f30942a5e2bb9a9e5cc3477ef48cdcd39a7b78f8a45a46db0926bdbf2b4f
+oid sha256:43427779b8e6e83ef9780afcdea7472d2419de40e6f85cfedb90b60f89a2ff0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04363169714469041,
+  "epoch": 0.04799486685915945,
   "eval_steps": 17,
-  "global_step": 170,
+  "global_step": 187,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -487,6 +487,56 @@
       "eval_samples_per_second": 13.275,
       "eval_steps_per_second": 1.661,
       "step": 170
+    },
+    {
+      "epoch": 0.043888354186718,
+      "grad_norm": 0.38284480571746826,
+      "learning_rate": 5.6388590278194096e-06,
+      "loss": 2.3103,
+      "step": 171
+    },
+    {
+      "epoch": 0.04465832531280077,
+      "grad_norm": 0.3595847487449646,
+      "learning_rate": 4.549673247541875e-06,
+      "loss": 2.272,
+      "step": 174
+    },
+    {
+      "epoch": 0.04542829643888354,
+      "grad_norm": 0.3618505597114563,
+      "learning_rate": 3.5722980755146517e-06,
+      "loss": 2.2537,
+      "step": 177
+    },
+    {
+      "epoch": 0.04619826756496631,
+      "grad_norm": 0.3798527121543884,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 2.235,
+      "step": 180
+    },
+    {
+      "epoch": 0.04696823869104909,
+      "grad_norm": 0.4292336702346802,
+      "learning_rate": 1.962316193157593e-06,
+      "loss": 2.2815,
+      "step": 183
+    },
+    {
+      "epoch": 0.04773820981713186,
+      "grad_norm": 0.38992390036582947,
+      "learning_rate": 1.333670137599713e-06,
+      "loss": 2.3201,
+      "step": 186
+    },
+    {
+      "epoch": 0.04799486685915945,
+      "eval_loss": 2.283592462539673,
+      "eval_runtime": 494.1905,
+      "eval_samples_per_second": 13.28,
+      "eval_steps_per_second": 1.661,
+      "step": 187
     }
   ],
   "logging_steps": 3,
@@ -506,7 +556,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.528149496534139e+17,
+  "total_flos": 2.765472526195753e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null