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:dc5dc84a51e205fd90e2621942ba5f3b890e38bff1df9e3062c7ace07308f5ba
+oid sha256:32c673550a3cb95c97c6d2dc651037aa997b67e7981e6bdbce51f88918676cef
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:475070eb12288fff51c139c75e77ad9c002859f88bf45e7a73cb2d2ef8e1e2b0
+oid sha256:aaf348916c1d3c9e339e5fe18457f16b2f78b40b1bdee1307b24d17347da4847
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
+oid sha256:4542ee77b862586921f712605c9da4a157f7c6fb74687d0b6cef8d69e7a87363
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.019015925837889233,
+  "epoch": 0.02852388875683385,
   "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": 209.647,
       "eval_steps_per_second": 105.06,
       "step": 20
+    },
+    {
+      "epoch": 0.019966722129783693,
+      "grad_norm": 0.04312145337462425,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 11.7611,
+      "step": 21
+    },
+    {
+      "epoch": 0.022819111005467078,
+      "grad_norm": 0.04996311292052269,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 11.7617,
+      "step": 24
+    },
+    {
+      "epoch": 0.02376990729736154,
+      "eval_loss": 11.761777877807617,
+      "eval_runtime": 2.0759,
+      "eval_samples_per_second": 213.399,
+      "eval_steps_per_second": 106.94,
+      "step": 25
+    },
+    {
+      "epoch": 0.025671499881150462,
+      "grad_norm": 0.041388753801584244,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 11.7614,
+      "step": 27
+    },
+    {
+      "epoch": 0.02852388875683385,
+      "grad_norm": 0.043048761785030365,
+      "learning_rate": 0.0,
+      "loss": 11.7594,
+      "step": 30
+    },
+    {
+      "epoch": 0.02852388875683385,
+      "eval_loss": 11.761744499206543,
+      "eval_runtime": 2.0399,
+      "eval_samples_per_second": 217.168,
+      "eval_steps_per_second": 108.829,
+      "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": 2037000437760.0,
+  "total_flos": 3055500656640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null