Training in progress, step 950

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ec1e0de18d9753d7daf261260fe976a3c8b53a9d8cd6b8c06bdf4ae649ee4be
+oid sha256:724d851fe98f8d7aaf10ccaba57ec68a6402e12cc9b430d2ed933d3281c14dea
 size 35668592

metrics.json

@@ -16,3 +16,4 @@
 {"Step":800,"eval_loss":1.9397352934,"eval_runtime":29.4107,"eval_samples_per_second":3.4,"eval_steps_per_second":0.442,"epoch":0.6284367636}
 {"Step":850,"eval_loss":1.9425079823,"eval_runtime":29.4898,"eval_samples_per_second":3.391,"eval_steps_per_second":0.441,"epoch":0.6677140613}
 {"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}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7069913589945012,
+  "epoch": 0.746268656716418,
   "eval_steps": 50,
-  "global_step": 900,
+  "global_step": 950,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -262,6 +262,21 @@
       "eval_samples_per_second": 3.391,
       "eval_steps_per_second": 0.441,
       "step": 850
+    },
+    {
+      "epoch": 0.7069913589945012,
+      "grad_norm": 0.16066303849220276,
+      "learning_rate": 0.00042464358452138495,
+      "loss": 1.9298,
+      "step": 900
+    },
+    {
+      "epoch": 0.7069913589945012,
+      "eval_loss": 1.9176784753799438,
+      "eval_runtime": 29.544,
+      "eval_samples_per_second": 3.385,
+      "eval_steps_per_second": 0.44,
+      "step": 900
     }
   ],
   "logging_steps": 50,
@@ -281,7 +296,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.064084153868288e+16,
+  "total_flos": 1.125734369452032e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null