Training in progress, step 2950

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ac1e1d1c32b00d6d777fa3c34d41acfc1b48d7d6be55be71fe48d5fd32f9a52
+oid sha256:1dc34e0ca512a9073d7c881b0ee31f4a67e9e0834497973fc4780046779a305f
 size 35668592

metrics.json

@@ -56,3 +56,4 @@
 {"Step":2800,"eval_loss":1.76300776,"eval_runtime":29.3837,"eval_samples_per_second":3.403,"eval_steps_per_second":0.442,"epoch":2.1995286724}
 {"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}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.27808326787117,
+  "epoch": 2.3173605655930873,
   "eval_steps": 50,
-  "global_step": 2900,
+  "global_step": 2950,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -862,6 +862,21 @@
       "eval_samples_per_second": 3.395,
       "eval_steps_per_second": 0.441,
       "step": 2850
+    },
+    {
+      "epoch": 2.27808326787117,
+      "grad_norm": 0.24777990579605103,
+      "learning_rate": 0.00013369217340704104,
+      "loss": 1.7751,
+      "step": 2900
+    },
+    {
+      "epoch": 2.27808326787117,
+      "eval_loss": 1.7579619884490967,
+      "eval_runtime": 29.3692,
+      "eval_samples_per_second": 3.405,
+      "eval_steps_per_second": 0.443,
+      "step": 2900
     }
   ],
   "logging_steps": 50,
@@ -881,7 +896,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.581672442624e+16,
+  "total_flos": 3.64471972875264e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null