Training in progress, step 650

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91876958a48a18a8691ed246756e14c40177e66fc5b6fdc6cf29c5889cd29822
+oid sha256:10d831e3f94755bf97b32e4180c84decc01e3b1623ac5cd23312a52e7183d82f
 size 35668592

metrics.json

@@ -10,3 +10,4 @@
 {"Step":500,"eval_loss":0.7601596117,"eval_runtime":56.9725,"eval_samples_per_second":1.755,"eval_steps_per_second":0.228,"epoch":0.9671179884}
 {"Step":550,"eval_loss":0.7588610053,"eval_runtime":60.6429,"eval_samples_per_second":1.649,"eval_steps_per_second":0.214,"epoch":1.0638297872}
 {"Step":600,"eval_loss":0.7574188113,"eval_runtime":56.7788,"eval_samples_per_second":1.761,"eval_steps_per_second":0.229,"epoch":1.1605415861}
+{"Step":650,"eval_loss":0.7570986748,"eval_runtime":56.5753,"eval_samples_per_second":1.768,"eval_steps_per_second":0.23,"epoch":1.2572533849}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.1605415860735009,
+  "epoch": 1.2572533849129595,
   "eval_steps": 50,
-  "global_step": 600,
+  "global_step": 650,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -172,6 +172,21 @@
       "eval_samples_per_second": 1.649,
       "eval_steps_per_second": 0.214,
       "step": 550
+    },
+    {
+      "epoch": 1.1605415860735009,
+      "grad_norm": 0.0375722236931324,
+      "learning_rate": 0.0003408602150537635,
+      "loss": 0.7422,
+      "step": 600
+    },
+    {
+      "epoch": 1.1605415860735009,
+      "eval_loss": 0.7574188113212585,
+      "eval_runtime": 56.7788,
+      "eval_samples_per_second": 1.761,
+      "eval_steps_per_second": 0.229,
+      "step": 600
     }
   ],
   "logging_steps": 50,
@@ -191,7 +206,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.15126604616192e+16,
+  "total_flos": 7.792449781625856e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null