Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65bf2f3e6818d7e332a12477e6d9374aacbc71b5913924eeffa326467d0e3572
+oid sha256:b85ac63b7673601dd6ad48edc7481fff09f372bc86650459c07ef019feb464c3
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72a74d0ec5f90cc0be6cf47a1130b48aeade2fd1afac346ae979a86546689d3c
+oid sha256:91301770dfa94b6480d11e80770f9a98d6c37472f77daa565e0422474ab5d3f6
 size 6614970

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": 0.0043031574417729005,
+  "epoch": 0.005737543255697201,
   "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": 135.105,
       "eval_steps_per_second": 67.564,
       "step": 15
+    },
+    {
+      "epoch": 0.004590034604557761,
+      "grad_norm": 9.434167861938477,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 59.1094,
+      "step": 16
+    },
+    {
+      "epoch": 0.004876911767342621,
+      "grad_norm": 8.841327667236328,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 58.3125,
+      "step": 17
+    },
+    {
+      "epoch": 0.005163788930127481,
+      "grad_norm": 8.895508766174316,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 59.25,
+      "step": 18
+    },
+    {
+      "epoch": 0.005450666092912341,
+      "grad_norm": 8.961664199829102,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 59.3125,
+      "step": 19
+    },
+    {
+      "epoch": 0.005737543255697201,
+      "grad_norm": 9.52428150177002,
+      "learning_rate": 0.0,
+      "loss": 59.6406,
+      "step": 20
+    },
+    {
+      "epoch": 0.005737543255697201,
+      "eval_loss": 3.680753469467163,
+      "eval_runtime": 50.2242,
+      "eval_samples_per_second": 116.896,
+      "eval_steps_per_second": 58.458,
+      "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": 452294659276800.0,
+  "total_flos": 602433965260800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null