Training in progress, step 3000

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dc34e0ca512a9073d7c881b0ee31f4a67e9e0834497973fc4780046779a305f
+oid sha256:eb3275278fc02dff024f8bbbbe169f36646d84b0bee6929d8281968acd072334
 size 35668592

metrics.json

@@ -57,3 +57,4 @@
 {"Step":2850,"eval_loss":1.760255456,"eval_runtime":29.4586,"eval_samples_per_second":3.395,"eval_steps_per_second":0.441,"epoch":2.2388059701}
 {"Step":2900,"eval_loss":1.7579619884,"eval_runtime":29.3692,"eval_samples_per_second":3.405,"eval_steps_per_second":0.443,"epoch":2.2780832679}
 {"Step":2950,"eval_loss":1.7549589872,"eval_runtime":29.4284,"eval_samples_per_second":3.398,"eval_steps_per_second":0.442,"epoch":2.3173605656}
+{"Step":3000,"eval_loss":1.7528626919,"eval_runtime":29.4272,"eval_samples_per_second":3.398,"eval_steps_per_second":0.442,"epoch":2.3566378633}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.3173605655930873,
+  "epoch": 2.356637863315004,
   "eval_steps": 50,
-  "global_step": 2950,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -877,6 +877,21 @@
       "eval_samples_per_second": 3.405,
       "eval_steps_per_second": 0.443,
       "step": 2900
+    },
+    {
+      "epoch": 2.3173605655930873,
+      "grad_norm": 0.21132971346378326,
+      "learning_rate": 0.00012641838812918243,
+      "loss": 1.7811,
+      "step": 2950
+    },
+    {
+      "epoch": 2.3173605655930873,
+      "eval_loss": 1.754958987236023,
+      "eval_runtime": 29.4284,
+      "eval_samples_per_second": 3.398,
+      "eval_steps_per_second": 0.442,
+      "step": 2950
     }
   ],
   "logging_steps": 50,
@@ -896,7 +911,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.64471972875264e+16,
+  "total_flos": 3.708716306405376e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null