Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:094ac975b91e65d4d8349d410cce3576eadcebccbab53e78c3f6c7bce09e7125
+oid sha256:9a3f93add0cb9c8f06bd9db04feb181f87addc603ce0d946aa448c8a0df2f2f2
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d1cb789dfa41099b074c61ae194baea3c36093f45e1e66562d7cd9a339c095d
+oid sha256:d793ec2b88cda653c4bad51a70108fc31bdeea9563f90990a3726d72fdf1390b
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:143e870d738587283e3eb314ed1cf43423d260c3deae7175ad2ce897670d0683
+oid sha256:387b923134d7486b9979d3ae7fb6b05f4a156a2eecef13919c0f504ab1e9dccc
 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": 0.0022641838052801927,
+  "epoch": 0.0029027997503592215,
   "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": 0.1444,
       "step": 35
+    },
+    {
+      "epoch": 0.002322239800287377,
+      "grad_norm": 1.540916919708252,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1318,
+      "step": 40
+    },
+    {
+      "epoch": 0.002322239800287377,
+      "eval_loss": 0.12594906985759735,
+      "eval_runtime": 713.5602,
+      "eval_samples_per_second": 10.165,
+      "eval_steps_per_second": 5.083,
+      "step": 40
+    },
+    {
+      "epoch": 0.0026125197753232993,
+      "grad_norm": 3.769254684448242,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1904,
+      "step": 45
+    },
+    {
+      "epoch": 0.0029027997503592215,
+      "grad_norm": 1.2325090169906616,
+      "learning_rate": 0.0,
+      "loss": 0.1386,
+      "step": 50
+    },
+    {
+      "epoch": 0.0029027997503592215,
+      "eval_loss": 0.12809544801712036,
+      "eval_runtime": 713.8918,
+      "eval_samples_per_second": 10.16,
+      "eval_steps_per_second": 5.081,
+      "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": 8184321798045696.0,
+  "total_flos": 1.0542516214431744e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null