Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f71ba216f075d892733de38cfea6a9f3d366c9d227043e562b05d0bd2c5cd4ba
+oid sha256:f7b96e79d3cfd6ab29e34e5c2d32f782014fc2618c8ceb530405224e78b832ac
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a1ef920d4b3dcf4279a301e863c4d0983babc7710262449bbd1b92253c12bbf
+oid sha256:151e22c4835d1c1b38142522b6beb995bf5f0e0b5abba6f946f5413979fb18a9
 size 37965300

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:617810b977cc1e6ca73dc6bfc0370d79fcbc698e6f8bdb1947885c4502d9ece2
+oid sha256:d28f71a183f0a67a9d174bb4cd7b33b832d8562e06b5e3665e5e431d6d9ea01f
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfd15564f58ad647bdb087a89b4193296dea60904822986703543037d8ee1837
+oid sha256:5e82224a25ddffa02df88f19ea586ab1c036794b31b4a630cfd08b6acc0a6cdb
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01007028217769852,
+  "epoch": 0.013427042903598028,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 24.565,
       "eval_steps_per_second": 6.142,
       "step": 15
+    },
+    {
+      "epoch": 0.010741634322878422,
+      "grad_norm": 0.23266065120697021,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0488,
+      "step": 16
+    },
+    {
+      "epoch": 0.011412986468058323,
+      "grad_norm": 0.2226492166519165,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0493,
+      "step": 17
+    },
+    {
+      "epoch": 0.012084338613238226,
+      "grad_norm": 0.23076535761356354,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0403,
+      "step": 18
+    },
+    {
+      "epoch": 0.012755690758418127,
+      "grad_norm": 0.21546129882335663,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0362,
+      "step": 19
+    },
+    {
+      "epoch": 0.013427042903598028,
+      "grad_norm": 0.23565559089183807,
+      "learning_rate": 0.0,
+      "loss": 0.0457,
+      "step": 20
+    },
+    {
+      "epoch": 0.013427042903598028,
+      "eval_loss": 0.05111876502633095,
+      "eval_runtime": 408.1451,
+      "eval_samples_per_second": 24.587,
+      "eval_steps_per_second": 6.147,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.270090416750592e+16,
+  "total_flos": 8.360120555667456e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null