Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04bfe7cbf5fdf6c12c66bdfbd4ca6c6514b29ad860026dd80db4336fd3cc0273
+oid sha256:9fc36e2b5fdcea80e9b50359388e3deff5056cdaed37c649741e1854d518859d
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5029b63f2a422e2350412128b96e8f21cf7b67990b5f5c93be04728f27f1487
+oid sha256:a8b4b2f54d9bdb50b83e4f46b389adb10ff31e5e90cc8a87bfe0a549a96b38b4
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e28f3b74a45f2c0dd30153fccda1a09054d4dff99c523026499904ccc7b004ad
+oid sha256:8cd2c2db909b5610cb81844a3a4192ff748d7b027e55d410a7738eeb5f21f438
 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": 0.0006005735477380899,
+  "epoch": 0.0009008603216071348,
   "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": 8.511,
       "eval_steps_per_second": 4.256,
       "step": 20
+    },
+    {
+      "epoch": 0.0006306022251249943,
+      "grad_norm": 0.30331218242645264,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.6797,
+      "step": 21
+    },
+    {
+      "epoch": 0.0007206882572857079,
+      "grad_norm": 0.2817479074001312,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.6745,
+      "step": 24
+    },
+    {
+      "epoch": 0.0007507169346726123,
+      "eval_loss": 0.6795505881309509,
+      "eval_runtime": 1647.8113,
+      "eval_samples_per_second": 8.509,
+      "eval_steps_per_second": 4.255,
+      "step": 25
+    },
+    {
+      "epoch": 0.0008107742894464214,
+      "grad_norm": 0.25237756967544556,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.7254,
+      "step": 27
+    },
+    {
+      "epoch": 0.0009008603216071348,
+      "grad_norm": 0.2647419273853302,
+      "learning_rate": 0.0,
+      "loss": 0.6637,
+      "step": 30
+    },
+    {
+      "epoch": 0.0009008603216071348,
+      "eval_loss": 0.6759388446807861,
+      "eval_runtime": 1647.7113,
+      "eval_samples_per_second": 8.51,
+      "eval_steps_per_second": 4.255,
+      "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": 1.68216426971136e+16,
+  "total_flos": 2.47563798183936e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null