Training in progress, step 950

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9126573abdea57442c91871f495c557fbdd0d91b4a04859b8278fd29a71b8773
+oid sha256:60e2b0ee150b869cb62251e4a973b3d51f039b25dd1ea70a2a7a0f7c1286d492
 size 35668592

metrics.json

@@ -16,3 +16,4 @@
 {"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}
+{"Step":950,"eval_loss":0.7525290847,"eval_runtime":56.698,"eval_samples_per_second":1.764,"eval_steps_per_second":0.229,"epoch":1.8375241779}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.7408123791102514,
+  "epoch": 1.8375241779497098,
   "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": 1.763,
       "eval_steps_per_second": 0.229,
       "step": 850
+    },
+    {
+      "epoch": 1.7408123791102514,
+      "grad_norm": 0.04064641892910004,
+      "learning_rate": 0.00023333333333333333,
+      "loss": 0.7385,
+      "step": 900
+    },
+    {
+      "epoch": 1.7408123791102514,
+      "eval_loss": 0.7530195116996765,
+      "eval_runtime": 56.5303,
+      "eval_samples_per_second": 1.769,
+      "eval_steps_per_second": 0.23,
+      "step": 900
     }
   ],
   "logging_steps": 50,
@@ -281,7 +296,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1029014455129088e+17,
+  "total_flos": 1.1679404527260672e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null