Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31d875cbd3d547e30f36b53abec9bf2720fefe02575e4b3eb714b0c8231a8104
+oid sha256:fa66dd96e10954e809a75aa9f44d4a8600b8e16528b4daf9603f39f4083e98a1
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb32435b311af51579bf9720c7e24680ed2702a37aed31cd4868ec397af5e978
+oid sha256:3173e41f7ce7c670c9d420c8ec6ec18bee80629eacc6e7eccb04a16877ec6070
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83414027c749edb66c16bec9b9387bd04590d2fbfe14a6eadfab76c8d346fb63
+oid sha256:ed434486b1d7b07803a120cbd1730b7689f7e68edbfec59359972d36c476cb03
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd5d42bb0afda20ec4c83d38c6af1131541c335ecab229c74e7f418894f3c13b
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00210561039890789,
+  "epoch": 0.0028074805318771866,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 34.061,
       "eval_steps_per_second": 17.031,
       "step": 150
+    },
+    {
+      "epoch": 0.002245984425501749,
+      "grad_norm": 0.8109742999076843,
+      "learning_rate": 2.1085949060360654e-05,
+      "loss": 1.0183,
+      "step": 160
+    },
+    {
+      "epoch": 0.0023863584520956087,
+      "grad_norm": 0.8836643099784851,
+      "learning_rate": 1.2052624879351104e-05,
+      "loss": 1.0171,
+      "step": 170
+    },
+    {
+      "epoch": 0.002526732478689468,
+      "grad_norm": 0.7057194113731384,
+      "learning_rate": 5.418275829936537e-06,
+      "loss": 0.9965,
+      "step": 180
+    },
+    {
+      "epoch": 0.0026671065052833276,
+      "grad_norm": 0.8731354475021362,
+      "learning_rate": 1.3638696597277679e-06,
+      "loss": 0.9927,
+      "step": 190
+    },
+    {
+      "epoch": 0.0028074805318771866,
+      "grad_norm": 0.8659088015556335,
+      "learning_rate": 0.0,
+      "loss": 0.9894,
+      "step": 200
+    },
+    {
+      "epoch": 0.0028074805318771866,
+      "eval_loss": 1.0074397325515747,
+      "eval_runtime": 880.2792,
+      "eval_samples_per_second": 34.074,
+      "eval_steps_per_second": 17.038,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.4717343850496e+16,
+  "total_flos": 3.2956458467328e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null