Training in progress, step 1550

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:961dd85beef37ccacf0af3624f506e0ee221f191245c5a6eeaa8fb47e2e609e9
+oid sha256:f4de2bd4cdd01b9d956c11a46ee8bca7c8f0935552162434a0d8986c319a6ee2
 size 35668592

metrics.json

@@ -28,3 +28,4 @@
 {"Step":1400,"eval_loss":1.8661786318,"eval_runtime":29.4511,"eval_samples_per_second":3.395,"eval_steps_per_second":0.441,"epoch":1.0997643362}
 {"Step":1450,"eval_loss":1.8573988676,"eval_runtime":29.4384,"eval_samples_per_second":3.397,"eval_steps_per_second":0.442,"epoch":1.1390416339}
 {"Step":1500,"eval_loss":1.8574242592,"eval_runtime":29.4845,"eval_samples_per_second":3.392,"eval_steps_per_second":0.441,"epoch":1.1783189317}
+{"Step":1550,"eval_loss":1.8602547646,"eval_runtime":29.5084,"eval_samples_per_second":3.389,"eval_steps_per_second":0.441,"epoch":1.2175962294}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.178318931657502,
+  "epoch": 1.2175962293794187,
   "eval_steps": 50,
-  "global_step": 1500,
+  "global_step": 1550,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -442,6 +442,21 @@
       "eval_samples_per_second": 3.397,
       "eval_steps_per_second": 0.442,
       "step": 1450
+    },
+    {
+      "epoch": 1.178318931657502,
+      "grad_norm": 0.16769160330295563,
+      "learning_rate": 0.0003373581611870818,
+      "loss": 1.8923,
+      "step": 1500
+    },
+    {
+      "epoch": 1.178318931657502,
+      "eval_loss": 1.857424259185791,
+      "eval_runtime": 29.4845,
+      "eval_samples_per_second": 3.392,
+      "eval_steps_per_second": 0.441,
+      "step": 1500
     }
   ],
   "logging_steps": 50,
@@ -461,7 +476,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.825518945368064e+16,
+  "total_flos": 1.8863810698752e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null