Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13cb09fdec9deea4b06f65e52dd40468ab7f24422f43dd55390a60d1817df3b9
+oid sha256:d029e3c7fbf757782bd042f04c828071e646509ff1874afd0b68ef68de0c8716
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2844efac3b7c7de0361edf7a61e349209c6b1f564de8cb0451b380274a625f3
+oid sha256:7e0727bb7e7c6a685c5daaae1d6c23bff46a0c79c5699ee029690e8a9f493b90
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97a5f738eb482f4b2ac39449b97efb015e37d432596bae0b17d5be9d2820a4bf
+oid sha256:884181cdc565c65bf5ff64272d5d48915d11b997882ba7383a9b08f8a31a1ce5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea3a68034a6fca5f7c1565a9344e41aadbdff3752a8799ae94336c8c84c6d63d
+oid sha256:fa0fde01e60897f55f4ebaca5a490a1a483a2c53b2ae8e7543860a62c5b3298c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002584236159427492,
+  "epoch": 0.005168472318854984,
   "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": 28.601,
       "eval_steps_per_second": 14.307,
       "step": 13
+    },
+    {
+      "epoch": 0.0027830235563065303,
+      "grad_norm": 3.8479912281036377,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 13.0678,
+      "step": 14
+    },
+    {
+      "epoch": 0.002981810953185568,
+      "grad_norm": 4.167858600616455,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 13.3701,
+      "step": 15
+    },
+    {
+      "epoch": 0.003180598350064606,
+      "grad_norm": 3.2626233100891113,
+      "learning_rate": 4.72751631047092e-05,
+      "loss": 12.1547,
+      "step": 16
+    },
+    {
+      "epoch": 0.0033793857469436436,
+      "grad_norm": 3.215256690979004,
+      "learning_rate": 4.6316004108852305e-05,
+      "loss": 12.0763,
+      "step": 17
+    },
+    {
+      "epoch": 0.0035781731438226817,
+      "grad_norm": 5.636133670806885,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 14.4562,
+      "step": 18
+    },
+    {
+      "epoch": 0.0037769605407017197,
+      "grad_norm": 3.237064838409424,
+      "learning_rate": 4.401014914000078e-05,
+      "loss": 11.2384,
+      "step": 19
+    },
+    {
+      "epoch": 0.003975747937580758,
+      "grad_norm": 2.562439203262329,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 12.7868,
+      "step": 20
+    },
+    {
+      "epoch": 0.004174535334459795,
+      "grad_norm": 3.096048593521118,
+      "learning_rate": 4.123620120825459e-05,
+      "loss": 13.4175,
+      "step": 21
+    },
+    {
+      "epoch": 0.004373322731338833,
+      "grad_norm": 3.3756790161132812,
+      "learning_rate": 3.969463130731183e-05,
+      "loss": 11.9214,
+      "step": 22
+    },
+    {
+      "epoch": 0.004572110128217871,
+      "grad_norm": 3.1741342544555664,
+      "learning_rate": 3.8062464117898724e-05,
+      "loss": 11.5485,
+      "step": 23
+    },
+    {
+      "epoch": 0.004770897525096909,
+      "grad_norm": 3.0276670455932617,
+      "learning_rate": 3.634976249348867e-05,
+      "loss": 12.0198,
+      "step": 24
+    },
+    {
+      "epoch": 0.004969684921975946,
+      "grad_norm": 3.186634063720703,
+      "learning_rate": 3.456708580912725e-05,
+      "loss": 11.7737,
+      "step": 25
+    },
+    {
+      "epoch": 0.005168472318854984,
+      "grad_norm": 2.610215663909912,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 13.0966,
+      "step": 26
+    },
+    {
+      "epoch": 0.005168472318854984,
+      "eval_loss": 3.0876364707946777,
+      "eval_runtime": 74.3552,
+      "eval_samples_per_second": 28.498,
+      "eval_steps_per_second": 14.256,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2158071405084672.0,
+  "total_flos": 4275424481771520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null