Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5550db9e478ea87d4f88c4bdfacd8405ca847486d071575d0c550026d6da5970
+oid sha256:16f48d99ad318bd1b3ef41de65ec66fbc8c1e22f6a6bb57d690f32101cd5e8bc
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd6badf75573821d165f64f807bb4d18764c15bbdfe80440621a7a36eba59143
+oid sha256:073b9d91a384d0f2b7d8611bae0f5e84fe725e6e2d8fa5dfef6705ba1144a2c1
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eabc4c6534ef93123c1386a68bfedd2b9d4f40032f88ace4c9615f83893ae17
+oid sha256:a2b24b89fc33cbe8d8d45fd00fafb48d0af14cae75f04e9d92782a501466b631
 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": 0.0005479163373900216,
+  "epoch": 0.0010958326747800432,
   "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": 6.409,
       "eval_steps_per_second": 3.204,
       "step": 10
+    },
+    {
+      "epoch": 0.000632211158526948,
+      "grad_norm": 5.0703887939453125,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 3.0742,
+      "step": 15
+    },
+    {
+      "epoch": 0.000842948211369264,
+      "grad_norm": 3.5031182765960693,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.9059,
+      "step": 20
+    },
+    {
+      "epoch": 0.000842948211369264,
+      "eval_loss": 0.7205164432525635,
+      "eval_runtime": 1556.9817,
+      "eval_samples_per_second": 6.416,
+      "eval_steps_per_second": 3.208,
+      "step": 20
+    },
+    {
+      "epoch": 0.00105368526421158,
+      "grad_norm": 4.231757640838623,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.7684,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4162595523133440.0,
+  "total_flos": 8193740661325824.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null