Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aeae40df2a41d01426f95a28e9affecc07bfed517f95ce6bc7e9f7080eea4b7
+oid sha256:a7ccfea7493079d4335aaa57d4ded75f730d46fd3dcdb73a48b322472c6c6220
 size 161714

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42d030f98f0b106c134f5da049847e30789e35f83c6dad72848639e64412c8f9
+oid sha256:dbcb299686bb604f5db327dce91d5b66b41072b0497e8307b8bea23dbd90232a
 size 64750

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:872c1161ac0d8b2e9f04a948a3b27a13cec6f9ed82cefc1f06cd5658419b5833
+oid sha256:27e993de387eaf1c76836fe66cd1e5dad0a9ea203c11a45d9654a843d94d4d08
 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": 0.00022011606889632958,
+  "epoch": 0.00044023213779265916,
   "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": 61.794,
       "eval_steps_per_second": 30.897,
       "step": 10
+    },
+    {
+      "epoch": 0.0002539800794957649,
+      "grad_norm": 0.28503113985061646,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 6.9318,
+      "step": 15
+    },
+    {
+      "epoch": 0.0003386401059943532,
+      "grad_norm": 0.24860993027687073,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 6.9316,
+      "step": 20
+    },
+    {
+      "epoch": 0.0003386401059943532,
+      "eval_loss": 6.928938388824463,
+      "eval_runtime": 310.0666,
+      "eval_samples_per_second": 80.202,
+      "eval_steps_per_second": 40.101,
+      "step": 20
+    },
+    {
+      "epoch": 0.00042330013249294147,
+      "grad_norm": 0.2915782928466797,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 6.9273,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 22082033664.0,
+  "total_flos": 44164067328.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null