Training in progress, step 1050

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f87517e81deb2327e3774df0844e2fc915422e75255827a9ad0df08c51e59c9
+oid sha256:29fabdd7a48613dbbbd18d98542a8c73ac5f6d3931a7ddb3c9edadb5be9aa7af
 size 35668592

metrics.json

@@ -18,3 +18,4 @@
 {"Step":900,"eval_loss":1.9176784754,"eval_runtime":29.544,"eval_samples_per_second":3.385,"eval_steps_per_second":0.44,"epoch":0.706991359}
 {"Step":950,"eval_loss":1.9149932861,"eval_runtime":29.4076,"eval_samples_per_second":3.4,"eval_steps_per_second":0.442,"epoch":0.7462686567}
 {"Step":1000,"eval_loss":1.9071648121,"eval_runtime":29.4527,"eval_samples_per_second":3.395,"eval_steps_per_second":0.441,"epoch":0.7855459544}
+{"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}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7855459544383346,
+  "epoch": 0.8248232521602514,
   "eval_steps": 50,
-  "global_step": 1000,
+  "global_step": 1050,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -292,6 +292,21 @@
       "eval_samples_per_second": 3.4,
       "eval_steps_per_second": 0.442,
       "step": 950
+    },
+    {
+      "epoch": 0.7855459544383346,
+      "grad_norm": 0.15130634605884552,
+      "learning_rate": 0.00041009601396566775,
+      "loss": 1.9104,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7855459544383346,
+      "eval_loss": 1.9071648120880127,
+      "eval_runtime": 29.4527,
+      "eval_samples_per_second": 3.395,
+      "eval_steps_per_second": 0.441,
+      "step": 1000
     }
   ],
   "logging_steps": 50,
@@ -311,7 +326,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.188566721650688e+16,
+  "total_flos": 1.253172278771712e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null