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:e4b910ffc3edf094e16ea5b3afc5d721d2f33c11503cba85e8b1ec7453de07e9
+oid sha256:a3feb46c97d7d92c3b3e5ee18d7535b99d1eaa76e55d7e1db50b631f9e7f0758
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e9052b190146314964605d67c789952c35edd8a1ba3c36a27738ff646bece26
+oid sha256:b16d45d1a0af4a7cb93e7962406421a692d6fa6a1c621d2f3c2422c5be21cf08
 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": 0.0008861244834490692,
+  "epoch": 0.0017722489668981383,
   "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": 6.835,
       "eval_steps_per_second": 3.418,
       "step": 13
+    },
+    {
+      "epoch": 0.0009542879052528437,
+      "grad_norm": 10.216886520385742,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.108,
+      "step": 14
+    },
+    {
+      "epoch": 0.0010224513270566183,
+      "grad_norm": 9.747845649719238,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.9771,
+      "step": 15
+    },
+    {
+      "epoch": 0.0010906147488603927,
+      "grad_norm": 5.7691216468811035,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 0.9156,
+      "step": 16
+    },
+    {
+      "epoch": 0.0011587781706641673,
+      "grad_norm": 5.967700958251953,
+      "learning_rate": 9.263200821770461e-05,
+      "loss": 0.803,
+      "step": 17
+    },
+    {
+      "epoch": 0.001226941592467942,
+      "grad_norm": 5.386447906494141,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.0213,
+      "step": 18
+    },
+    {
+      "epoch": 0.0012951050142717164,
+      "grad_norm": 5.265084743499756,
+      "learning_rate": 8.802029828000156e-05,
+      "loss": 1.1579,
+      "step": 19
+    },
+    {
+      "epoch": 0.001363268436075491,
+      "grad_norm": 3.2680466175079346,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.7542,
+      "step": 20
+    },
+    {
+      "epoch": 0.0014314318578792656,
+      "grad_norm": 5.0342020988464355,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 1.1486,
+      "step": 21
+    },
+    {
+      "epoch": 0.00149959527968304,
+      "grad_norm": 3.5533130168914795,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.7507,
+      "step": 22
+    },
+    {
+      "epoch": 0.0015677587014868146,
+      "grad_norm": 3.747938871383667,
+      "learning_rate": 7.612492823579745e-05,
+      "loss": 0.7606,
+      "step": 23
+    },
+    {
+      "epoch": 0.0016359221232905893,
+      "grad_norm": 3.583609104156494,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 0.5768,
+      "step": 24
+    },
+    {
+      "epoch": 0.0017040855450943637,
+      "grad_norm": 3.155369281768799,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.6934,
+      "step": 25
+    },
+    {
+      "epoch": 0.0017722489668981383,
+      "grad_norm": 3.687058448791504,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.7966,
+      "step": 26
+    },
+    {
+      "epoch": 0.0017722489668981383,
+      "eval_loss": 0.6649627685546875,
+      "eval_runtime": 3621.1469,
+      "eval_samples_per_second": 6.824,
+      "eval_steps_per_second": 3.412,
+      "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