Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ed26db1cf798cdc1529be9bf308d0cc9012544f31bbeefb5862c581e68057a4
+oid sha256:c55870e9c93bf8ea795f8078ca7aa38aadaa639fd367254a38a4f4122d145515
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f51a83c7fa54fe12c07cc7a6017aec1c250bdbd7dd769a042d15ddb16763f621
+oid sha256:791f7305c315eb465082ca0e7d31ee2c6fc7b06904bf680d65219bade415844a
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c25690fee540c8a083995f9d671371c1b023b3c333abe69506927a0de708bf9f
+oid sha256:13136cabcb90a4fc95f848a79095fa497aaad9b4ba3857e5fc59e2a7d32f6835
 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": 0.013844515441959531,
+  "epoch": 0.027689030883919063,
   "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": 11.244,
       "eval_steps_per_second": 5.622,
       "step": 10
+    },
+    {
+      "epoch": 0.01597444089456869,
+      "grad_norm": 0.9349473714828491,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.4579,
+      "step": 15
+    },
+    {
+      "epoch": 0.021299254526091587,
+      "grad_norm": 1.4881868362426758,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.4518,
+      "step": 20
+    },
+    {
+      "epoch": 0.021299254526091587,
+      "eval_loss": 1.4283188581466675,
+      "eval_runtime": 35.2186,
+      "eval_samples_per_second": 11.244,
+      "eval_steps_per_second": 5.622,
+      "step": 20
+    },
+    {
+      "epoch": 0.026624068157614485,
+      "grad_norm": 0.8776378631591797,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.4113,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3329215646662656.0,
+  "total_flos": 6704670399528960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null