Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:465aa0e6592abf061075a7325916b9ecefc8319eb63546b50a4895c4b2c73b0a
+oid sha256:2e2bdd38eeae5f704658234d912c17e86e1fcbf4b191aa872dbae8ec17d5e631
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eebdc7fe1c9b1749572e1c818b0db8fe3799ed040845c660077ee46b8f256e0
+oid sha256:d042bba9ce5cc89ce68b0f231577f0bac13e283b205457243b4a9470e0976a2d
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e029eb4948e78d3baec5a28b1d457b35bd248ab09130b2c52006c8708c222df
+oid sha256:1e67f81cfb6fcca783b0ed7d3b9da537b3cb909b5b27b2db86db92809d1fcdba
 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": 0.026698613725825774,
+  "epoch": 0.03422899195618689,
   "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": 0.5539,
       "step": 35
+    },
+    {
+      "epoch": 0.02738319356494951,
+      "grad_norm": 0.49816638231277466,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5579,
+      "step": 40
+    },
+    {
+      "epoch": 0.02738319356494951,
+      "eval_loss": 0.6132375597953796,
+      "eval_runtime": 50.8294,
+      "eval_samples_per_second": 12.099,
+      "eval_steps_per_second": 6.059,
+      "step": 40
+    },
+    {
+      "epoch": 0.030806092760568202,
+      "grad_norm": 0.6280885934829712,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5663,
+      "step": 45
+    },
+    {
+      "epoch": 0.03422899195618689,
+      "grad_norm": 0.6226765513420105,
+      "learning_rate": 0.0,
+      "loss": 0.4916,
+      "step": 50
+    },
+    {
+      "epoch": 0.03422899195618689,
+      "eval_loss": 0.6118356585502625,
+      "eval_runtime": 50.4851,
+      "eval_samples_per_second": 12.182,
+      "eval_steps_per_second": 6.101,
+      "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": 9247821240729600.0,
+  "total_flos": 1.1929689400541184e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null