Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3db1f765b2c03a0fa1533ee49bba6ccd2805a8fe8fd0db097871584a885a3dc5
+oid sha256:d8f9c2b1a01b0e974ba3c43c297d141bce0e0f3a8af1e5fdbac6ea9a6525b5b0
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07fe565650efccf784843f888e5b62e941ebbc132edec9966c82a0b2f15b71fb
+oid sha256:a9c68e2a3510886f093f8f0a370bae190de84181fb26b4422eac073e8572064c
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
+oid sha256:9ea24ba22f005ab5531315a7c25fe17ce3b0d82d32e4d057cd4a8d9beeaa0eb4
 size 14244

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": 0.0016853340823707033,
+  "epoch": 0.0022471121098276044,
   "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": 25.246,
       "eval_steps_per_second": 12.623,
       "step": 15
+    },
+    {
+      "epoch": 0.0017976896878620836,
+      "grad_norm": 9.519815444946289,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 8.389,
+      "step": 16
+    },
+    {
+      "epoch": 0.0019100452933534637,
+      "grad_norm": 9.816612243652344,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 8.4567,
+      "step": 17
+    },
+    {
+      "epoch": 0.0020224008988448438,
+      "grad_norm": 7.924627780914307,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 7.5395,
+      "step": 18
+    },
+    {
+      "epoch": 0.002134756504336224,
+      "grad_norm": 9.166494369506836,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 8.6007,
+      "step": 19
+    },
+    {
+      "epoch": 0.0022471121098276044,
+      "grad_norm": 9.202842712402344,
+      "learning_rate": 0.0,
+      "loss": 7.9256,
+      "step": 20
+    },
+    {
+      "epoch": 0.0022471121098276044,
+      "eval_loss": 0.4830845594406128,
+      "eval_runtime": 604.6011,
+      "eval_samples_per_second": 24.793,
+      "eval_steps_per_second": 12.397,
+      "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": 1.923557299637453e+16,
+  "total_flos": 2.5720458653466624e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null