Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e5150098a9a2e31c64c8d59be0b297b92c01bdb6980152aeb3021a883670cc4
+oid sha256:28cbddda9d257521e9e2f218047907a33b25b97f19005c4a8110ca8dcff2ef64
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a36f39f0aa4d6095440bbb90a2542e32f77136061b7461d1e23338447b42c9e
+oid sha256:8b9dc77baa19cc2e6218d3eba71603ef8b7ed134c202c9910d9a2e5825223c00
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1175f7f6d603f3dec10e6fd81cb9384614254a9e3a1c52cc05ae61d811272d2
+oid sha256:2ad10b0445c4e5df218bf881d92cb452dbecc738c393fa525aa6d7f4fa3b47d1
 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": 0.043225270157938485,
+  "epoch": 0.05541701302299806,
   "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": 0.8016,
       "step": 35
+    },
+    {
+      "epoch": 0.04433361041839845,
+      "grad_norm": 6.490550518035889,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5576,
+      "step": 40
+    },
+    {
+      "epoch": 0.04433361041839845,
+      "eval_loss": 0.5033486485481262,
+      "eval_runtime": 40.4082,
+      "eval_samples_per_second": 9.404,
+      "eval_steps_per_second": 4.702,
+      "step": 40
+    },
+    {
+      "epoch": 0.04987531172069826,
+      "grad_norm": 7.61575174331665,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8051,
+      "step": 45
+    },
+    {
+      "epoch": 0.05541701302299806,
+      "grad_norm": 9.808037757873535,
+      "learning_rate": 0.0,
+      "loss": 0.6257,
+      "step": 50
+    },
+    {
+      "epoch": 0.05541701302299806,
+      "eval_loss": 0.4961331784725189,
+      "eval_runtime": 40.2997,
+      "eval_samples_per_second": 9.429,
+      "eval_steps_per_second": 4.715,
+      "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": 1.2345841356374016e+16,
+  "total_flos": 1.5628817896833024e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null