Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ef91f6640aa90249f9a82d289c307962dfc34f11fadf995f2fb5c9e0aabb328
+oid sha256:cb290f5f69f18ec782dd1de465416d973f2bf014926774f3ea0154cd6d10fd9c
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d86506c27468d4349a5c231d6ca0092484055fc94570422d839521471528e901
+oid sha256:ffd9709da484a21c2cc342f0067e4b2164bf6e422a86a35db37921b4b872ca29
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:294f9bf5597da0f13cd44b3c75479a3ad918315555d26ced62b654e5e28ba51d
+oid sha256:29fe70797b9c357f8e85a02878731e0f9a1b2811e511154a1ceeee22cf23db0c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001661371046456088,
+  "epoch": 0.0024920565696841318,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 32.391,
       "eval_steps_per_second": 16.199,
       "step": 20
+    },
+    {
+      "epoch": 0.0017444395987788923,
+      "grad_norm": 4.389698505401611,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 10.626,
+      "step": 21
+    },
+    {
+      "epoch": 0.0019936452557473053,
+      "grad_norm": 632.2576904296875,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 10.0273,
+      "step": 24
+    },
+    {
+      "epoch": 0.00207671380807011,
+      "eval_loss": 2.7169175148010254,
+      "eval_runtime": 156.3692,
+      "eval_samples_per_second": 32.417,
+      "eval_steps_per_second": 16.212,
+      "step": 25
+    },
+    {
+      "epoch": 0.0022428509127157188,
+      "grad_norm": 26.93422508239746,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 10.0801,
+      "step": 27
+    },
+    {
+      "epoch": 0.0024920565696841318,
+      "grad_norm": 20.8879451751709,
+      "learning_rate": 0.0,
+      "loss": 10.7652,
+      "step": 30
+    },
+    {
+      "epoch": 0.0024920565696841318,
+      "eval_loss": 2.7087886333465576,
+      "eval_runtime": 156.5552,
+      "eval_samples_per_second": 32.378,
+      "eval_steps_per_second": 16.192,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 348876636684288.0,
+  "total_flos": 523314955026432.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null