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:d9eb7be1955e914f66672e4e0e1530fc0d1376707cdc90ad369d22b157027375
+oid sha256:c2380e3e61e092a89679dee80363b0adb64c1fc1367184fe86777c27f051f472
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9122c0feba9c981e46517b56406e25a879ce82feb8d9792fa9ef73a41ff1151b
+oid sha256:e2e9e4ab7e1ff6348b65d587eef953867a36c6f6ad772d71bc6b842a7871d63c
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdde3ec3ee1ba7531772170d89a5d7f54043d0790ffa76d22a3a219e00fe00f9
+oid sha256:3c103f85206916bbddbfdec4d0ebb18b19e3d0dd8d88c9b4c12898c57e206a7e
 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": 0.14464534075104313,
+  "epoch": 0.28929068150208626,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,6 +114,105 @@
       "eval_samples_per_second": 6.943,
       "eval_steps_per_second": 3.472,
       "step": 13
+    },
+    {
+      "epoch": 0.15577190542420027,
+      "grad_norm": 0.507627010345459,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.6689,
+      "step": 14
+    },
+    {
+      "epoch": 0.16689847009735745,
+      "grad_norm": 0.3133050203323364,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.6608,
+      "step": 15
+    },
+    {
+      "epoch": 0.1780250347705146,
+      "grad_norm": 0.6398417949676514,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 0.7098,
+      "step": 16
+    },
+    {
+      "epoch": 0.18915159944367177,
+      "grad_norm": 0.38771340250968933,
+      "learning_rate": 9.263200821770461e-05,
+      "loss": 0.6498,
+      "step": 17
+    },
+    {
+      "epoch": 0.20027816411682892,
+      "grad_norm": 0.3491506278514862,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.7382,
+      "step": 18
+    },
+    {
+      "epoch": 0.2114047287899861,
+      "grad_norm": 0.4874832034111023,
+      "learning_rate": 8.802029828000156e-05,
+      "loss": 0.6976,
+      "step": 19
+    },
+    {
+      "epoch": 0.22253129346314326,
+      "grad_norm": 0.4010584354400635,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.7317,
+      "step": 20
+    },
+    {
+      "epoch": 0.2336578581363004,
+      "grad_norm": 0.4318137466907501,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 0.6688,
+      "step": 21
+    },
+    {
+      "epoch": 0.24478442280945759,
+      "grad_norm": 0.26157474517822266,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.6209,
+      "step": 22
+    },
+    {
+      "epoch": 0.25591098748261476,
+      "grad_norm": 0.3200092613697052,
+      "learning_rate": 7.612492823579745e-05,
+      "loss": 0.7758,
+      "step": 23
+    },
+    {
+      "epoch": 0.2670375521557719,
+      "grad_norm": 0.2472483515739441,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 0.7097,
+      "step": 24
+    },
+    {
+      "epoch": 0.27816411682892905,
+      "grad_norm": 0.44432780146598816,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.6646,
+      "step": 25
+    },
+    {
+      "epoch": 0.28929068150208626,
+      "grad_norm": 0.3959880769252777,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.7104,
+      "step": 26
+    },
+    {
+      "epoch": 0.28929068150208626,
+      "eval_loss": 0.7206902503967285,
+      "eval_runtime": 21.7904,
+      "eval_samples_per_second": 6.976,
+      "eval_steps_per_second": 3.488,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.71562774902866e+16,
+  "total_flos": 1.543125549805732e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null