Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1d14bcce38aede51387cf640be849365192e77b53302ae61a760936a8b3513a
+oid sha256:0344f19f774f9e28a4795f567a37e757097b9d67d4a6aad3078b0d0387a2054a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e84f91fc46d9b8d4c7c61d241568651136786a38a7e0557b99d4a5c1f6d432d1
+oid sha256:041aadda93a1c8a3431c9c5f9d8a82d42ae0450530c2bd56162f04b5286a5b6c
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a14c9deb8ff4708c2ea491fb60635316be958194c4fe145c894226a400011fc
+oid sha256:9c52dce652ebf6469a9b4eede37f30417b88ed28bf51b9b5600ecc74aac7895d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014783927217589083,
+  "epoch": 0.018953752843062926,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 2.731,
       "step": 35
+    },
+    {
+      "epoch": 0.015163002274450341,
+      "grad_norm": 0.625622034072876,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.6668,
+      "step": 40
+    },
+    {
+      "epoch": 0.015163002274450341,
+      "eval_loss": 2.714552402496338,
+      "eval_runtime": 84.8308,
+      "eval_samples_per_second": 13.097,
+      "eval_steps_per_second": 6.554,
+      "step": 40
+    },
+    {
+      "epoch": 0.017058377558756634,
+      "grad_norm": 0.7131534218788147,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.6289,
+      "step": 45
+    },
+    {
+      "epoch": 0.018953752843062926,
+      "grad_norm": 0.8475868701934814,
+      "learning_rate": 0.0,
+      "loss": 2.7705,
+      "step": 50
+    },
+    {
+      "epoch": 0.018953752843062926,
+      "eval_loss": 2.7110021114349365,
+      "eval_runtime": 84.9824,
+      "eval_samples_per_second": 13.073,
+      "eval_steps_per_second": 6.543,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7999365373231104.0,
+  "total_flos": 1.04037988958208e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null