Training in progress, step 2350

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bc3ce7ffec46ebc27c5cd985eb6e14e8348d3cfa838a7a007617e8dc6429e08
+oid sha256:415b303df99ddef4a29d58e398b0d9ffbf940590ae1978745d7a747f2e77c8e2
 size 35668592

metrics.json

@@ -44,3 +44,4 @@
 {"Step":2200,"eval_loss":1.7969157696,"eval_runtime":29.4741,"eval_samples_per_second":3.393,"eval_steps_per_second":0.441,"epoch":1.7282010998}
 {"Step":2250,"eval_loss":1.7962598801,"eval_runtime":29.3661,"eval_samples_per_second":3.405,"eval_steps_per_second":0.443,"epoch":1.7674783975}
 {"Step":2300,"eval_loss":1.7972977161,"eval_runtime":29.4909,"eval_samples_per_second":3.391,"eval_steps_per_second":0.441,"epoch":1.8067556952}
+{"Step":2350,"eval_loss":1.7902172804,"eval_runtime":29.5667,"eval_samples_per_second":3.382,"eval_steps_per_second":0.44,"epoch":1.8460329929}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.8067556952081696,
+  "epoch": 1.8460329929300863,
   "eval_steps": 50,
-  "global_step": 2300,
+  "global_step": 2350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -682,6 +682,21 @@
       "eval_samples_per_second": 3.405,
       "eval_steps_per_second": 0.443,
       "step": 2250
+    },
+    {
+      "epoch": 1.8067556952081696,
+      "grad_norm": 0.19466279447078705,
+      "learning_rate": 0.00022097759674134421,
+      "loss": 1.8242,
+      "step": 2300
+    },
+    {
+      "epoch": 1.8067556952081696,
+      "eval_loss": 1.797297716140747,
+      "eval_runtime": 29.4909,
+      "eval_samples_per_second": 3.391,
+      "eval_steps_per_second": 0.441,
+      "step": 2300
     }
   ],
   "logging_steps": 50,
@@ -701,7 +716,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.833899389048832e+16,
+  "total_flos": 2.896283962226688e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null