Training in progress, step 900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a850f231bb777137d7033935d2bc54b8a6cd1d1fd3245021ac5efda5109266c
+oid sha256:9126573abdea57442c91871f495c557fbdd0d91b4a04859b8278fd29a71b8773
 size 35668592

metrics.json

@@ -15,3 +15,4 @@
 {"Step":750,"eval_loss":0.7549133897,"eval_runtime":56.529,"eval_samples_per_second":1.769,"eval_steps_per_second":0.23,"epoch":1.4506769826}
 {"Step":800,"eval_loss":0.7541146278,"eval_runtime":60.5765,"eval_samples_per_second":1.651,"eval_steps_per_second":0.215,"epoch":1.5473887814}
 {"Step":850,"eval_loss":0.7533394098,"eval_runtime":56.7119,"eval_samples_per_second":1.763,"eval_steps_per_second":0.229,"epoch":1.6441005803}
+{"Step":900,"eval_loss":0.7530195117,"eval_runtime":56.5303,"eval_samples_per_second":1.769,"eval_steps_per_second":0.23,"epoch":1.7408123791}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.644100580270793,
+  "epoch": 1.7408123791102514,
   "eval_steps": 50,
-  "global_step": 850,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,21 @@
       "eval_samples_per_second": 1.651,
       "eval_steps_per_second": 0.215,
       "step": 800
+    },
+    {
+      "epoch": 1.644100580270793,
+      "grad_norm": 0.041316960006952286,
+      "learning_rate": 0.00025125448028673835,
+      "loss": 0.742,
+      "step": 850
+    },
+    {
+      "epoch": 1.644100580270793,
+      "eval_loss": 0.753339409828186,
+      "eval_runtime": 56.7119,
+      "eval_samples_per_second": 1.763,
+      "eval_steps_per_second": 0.229,
+      "step": 850
     }
   ],
   "logging_steps": 50,
@@ -266,7 +281,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.037249876599296e+17,
+  "total_flos": 1.1029014455129088e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null