Training in progress, step 2900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5a441d7626d2dcc89857225abb72e5e945117611169865fb3c04a312eeb0019
+oid sha256:9ac1e1d1c32b00d6d777fa3c34d41acfc1b48d7d6be55be71fe48d5fd32f9a52
 size 35668592

metrics.json

@@ -55,3 +55,4 @@
 {"Step":2750,"eval_loss":1.7644474506,"eval_runtime":29.5003,"eval_samples_per_second":3.39,"eval_steps_per_second":0.441,"epoch":2.1602513747}
 {"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}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.2388059701492535,
+  "epoch": 2.27808326787117,
   "eval_steps": 50,
-  "global_step": 2850,
+  "global_step": 2900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -847,6 +847,21 @@
       "eval_samples_per_second": 3.403,
       "eval_steps_per_second": 0.442,
       "step": 2800
+    },
+    {
+      "epoch": 2.2388059701492535,
+      "grad_norm": 0.2436445653438568,
+      "learning_rate": 0.00014096595868489962,
+      "loss": 1.7616,
+      "step": 2850
+    },
+    {
+      "epoch": 2.2388059701492535,
+      "eval_loss": 1.7602554559707642,
+      "eval_runtime": 29.4586,
+      "eval_samples_per_second": 3.395,
+      "eval_steps_per_second": 0.441,
+      "step": 2850
     }
   ],
   "logging_steps": 50,
@@ -866,7 +881,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.518249022117888e+16,
+  "total_flos": 3.581672442624e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null