Training in progress, step 1200

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31bdb9899bcd39de8ac7c8798b488848ac89ad7e6d2485f73f56eab68c7e6e24
+oid sha256:a506900ef7b68c44ed7c9b2fc4220f560bce93148c6c6063f3c4d3e209b7ec81
 size 35668592

metrics.json

@@ -21,3 +21,4 @@
 {"Step":1050,"eval_loss":1.8993133307,"eval_runtime":29.5512,"eval_samples_per_second":3.384,"eval_steps_per_second":0.44,"epoch":0.8248232522}
 {"Step":1100,"eval_loss":1.9054021835,"eval_runtime":29.3876,"eval_samples_per_second":3.403,"eval_steps_per_second":0.442,"epoch":0.8641005499}
 {"Step":1150,"eval_loss":1.8948385715,"eval_runtime":29.428,"eval_samples_per_second":3.398,"eval_steps_per_second":0.442,"epoch":0.9033778476}
+{"Step":1200,"eval_loss":1.8822929859,"eval_runtime":29.4891,"eval_samples_per_second":3.391,"eval_steps_per_second":0.441,"epoch":0.9426551453}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9033778476040848,
+  "epoch": 0.9426551453260016,
   "eval_steps": 50,
-  "global_step": 1150,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -337,6 +337,21 @@
       "eval_samples_per_second": 3.403,
       "eval_steps_per_second": 0.442,
       "step": 1100
+    },
+    {
+      "epoch": 0.9033778476040848,
+      "grad_norm": 0.16718855500221252,
+      "learning_rate": 0.00038827465813209193,
+      "loss": 1.9557,
+      "step": 1150
+    },
+    {
+      "epoch": 0.9033778476040848,
+      "eval_loss": 1.894838571548462,
+      "eval_runtime": 29.428,
+      "eval_samples_per_second": 3.398,
+      "eval_steps_per_second": 0.442,
+      "step": 1150
     }
   ],
   "logging_steps": 50,
@@ -356,7 +371,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.378693693882368e+16,
+  "total_flos": 1.443890319310848e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null