Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23122852a1d78dd9885084376826247048f43487873c4011b7823752dd5a854d
+oid sha256:4c1fd888ab13596690bbcb0671733303b4b7a1e80fd132f003c903634945d921
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12c8d009b378acd577937c15837674ae473f53799417966d5e2cf429368df8c8
+oid sha256:f2cfd2ce066812636a3eaef4cb69f3b0d5a92bb55d624a7a00dedba533bc1d1e
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2a3d0f18704952f5e489fd373140093b1ec2232d5123df9941b8b0ec34244b4
+oid sha256:61ee61db9f3f3739b049a6acd43b22783c35f4d0fec5ec7ee0be88bcf53e1565
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.022589052997393572,
+  "epoch": 0.045178105994787145,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 14.734,
       "eval_steps_per_second": 7.397,
       "step": 10
+    },
+    {
+      "epoch": 0.026064291920069503,
+      "grad_norm": 0.746576189994812,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.8945,
+      "step": 15
+    },
+    {
+      "epoch": 0.03475238922675934,
+      "grad_norm": 0.7681987881660461,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.7169,
+      "step": 20
+    },
+    {
+      "epoch": 0.03475238922675934,
+      "eval_loss": 1.6828279495239258,
+      "eval_runtime": 16.6,
+      "eval_samples_per_second": 14.639,
+      "eval_steps_per_second": 7.349,
+      "step": 20
+    },
+    {
+      "epoch": 0.043440486533449174,
+      "grad_norm": 0.7900924682617188,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.7015,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2677712250470400.0,
+  "total_flos": 5025859916267520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null