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:a4585e308cbc7cce38012732fe7a52214d6c8b959fa73c398dd8f7b1b272bd2e
+oid sha256:f5ca66ac30a6c9dbf7b6dfaaf14500a9a9f761e71a0616373803085ed65decb9
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f8dc55c4a804dd67459da3562249a84ee12906c6b0b25dc2f9bd11fb28b4dac
+oid sha256:b209297609489530ab7d77c9e4f1cdaf98b82df68ad0f19e3a7da2714b701139
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:551c6190aa7460da0f5f87f766f1e262863111d15319ee98d5b09ac189feeb2f
+oid sha256:d6a9101315bed33e0f3a0fc84fd93cd1f88e425b915b76ec585cd3942cf27abe
 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": 0.0079155672823219,
+  "epoch": 0.010148163182463974,
   "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": 1.3817,
       "step": 35
+    },
+    {
+      "epoch": 0.008118530545971179,
+      "grad_norm": 2.0624611377716064,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2526,
+      "step": 40
+    },
+    {
+      "epoch": 0.008118530545971179,
+      "eval_loss": 1.2399094104766846,
+      "eval_runtime": 61.9297,
+      "eval_samples_per_second": 33.506,
+      "eval_steps_per_second": 16.761,
+      "step": 40
+    },
+    {
+      "epoch": 0.009133346864217576,
+      "grad_norm": 2.5647053718566895,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1881,
+      "step": 45
+    },
+    {
+      "epoch": 0.010148163182463974,
+      "grad_norm": 1.8386671543121338,
+      "learning_rate": 0.0,
+      "loss": 1.2177,
+      "step": 50
+    },
+    {
+      "epoch": 0.010148163182463974,
+      "eval_loss": 1.2173258066177368,
+      "eval_runtime": 61.5869,
+      "eval_samples_per_second": 33.692,
+      "eval_steps_per_second": 16.854,
+      "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": 997588715175936.0,
+  "total_flos": 1278959891251200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null