Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eb7c8a017a3ef49b6118f506d46ec32adbb0c776386a53f68c7604902eb9055
+oid sha256:b1998222069d39e2f1a3f61817ad7bd9c3165c96a8ad66bb7cc054b768e56c0a
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad0175cc34e6393516d09422e07a05b00d51239f94f657da8f76bbcfc25ceb74
+oid sha256:93b3a6e43cf2e54821b5e00f89f0604c5819f0b05153acce0d8261af85539df2
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fdbb6c5c2f8a3babb3fc37d54b607fc9354b33540d06a0b7b5bf287462ca599
+oid sha256:38409eba6413bce3b94b991e47f4c82368cb4192db5df85e36439951931f100f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
+oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01282051282051282,
+  "epoch": 0.017094017094017096,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,21 @@
       "eval_samples_per_second": 6.537,
       "eval_steps_per_second": 0.819,
       "step": 15
+    },
+    {
+      "epoch": 0.015384615384615385,
+      "grad_norm": 1.7674269676208496,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.9702,
+      "step": 18
+    },
+    {
+      "epoch": 0.017094017094017096,
+      "eval_loss": 0.6842172741889954,
+      "eval_runtime": 301.3897,
+      "eval_samples_per_second": 6.54,
+      "eval_steps_per_second": 0.82,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.86407084326912e+16,
+  "total_flos": 5.15209445769216e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null