Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da6bd126faa846a2025c8ccba85dba684cf40394b31b68f4a7195d963e83b3c6
+oid sha256:0f5d14ccdc0cf38826140a8d628bcd3d97b01f43ad2ea1da3d7ee16ff3f94c1e
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6ec71cb2c3a8f711ffb81cc80b59af6536c03dd5f2e3d4b7fada75ef2a8d858
+oid sha256:f56079b9f33616aec5116b7c3bb131a5553b1e6fbb75f1b68917a6d414535393
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:739fe21477d2aa5ee8ca475032c6b06ecc8cb3431ba981576644fe32bc04c31d
+oid sha256:4d1b6f11521cc4c0071d85dab3d691b1284d51267ed8434d323710cb5687862f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8712da1b2787df41952a507984ec77e0f72c59fac7ee6cf21606445686249de
+oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06349206349206349,
+  "epoch": 0.09523809523809523,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 17.997,
       "eval_steps_per_second": 9.051,
       "step": 26
+    },
+    {
+      "epoch": 0.06593406593406594,
+      "grad_norm": 4.8426642417907715,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 3.401,
+      "step": 27
+    },
+    {
+      "epoch": 0.06837606837606838,
+      "grad_norm": 5.795990467071533,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 2.9777,
+      "step": 28
+    },
+    {
+      "epoch": 0.07081807081807082,
+      "grad_norm": 4.810328006744385,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 3.521,
+      "step": 29
+    },
+    {
+      "epoch": 0.07326007326007326,
+      "grad_norm": 4.852537155151367,
+      "learning_rate": 0.0001,
+      "loss": 4.1673,
+      "step": 30
+    },
+    {
+      "epoch": 0.0757020757020757,
+      "grad_norm": 4.484468936920166,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 3.6741,
+      "step": 31
+    },
+    {
+      "epoch": 0.07814407814407814,
+      "grad_norm": 4.853067398071289,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 4.0416,
+      "step": 32
+    },
+    {
+      "epoch": 0.08058608058608059,
+      "grad_norm": 4.60617733001709,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 3.7521,
+      "step": 33
+    },
+    {
+      "epoch": 0.08302808302808302,
+      "grad_norm": 4.862529754638672,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 4.4834,
+      "step": 34
+    },
+    {
+      "epoch": 0.08547008547008547,
+      "grad_norm": 7.072017669677734,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 3.3401,
+      "step": 35
+    },
+    {
+      "epoch": 0.08791208791208792,
+      "grad_norm": 4.830531597137451,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 4.1713,
+      "step": 36
+    },
+    {
+      "epoch": 0.09035409035409035,
+      "grad_norm": 5.034257411956787,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 3.7257,
+      "step": 37
+    },
+    {
+      "epoch": 0.0927960927960928,
+      "grad_norm": 4.702934265136719,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 4.1393,
+      "step": 38
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 5.5372490882873535,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 3.0928,
+      "step": 39
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "eval_loss": 0.9581138491630554,
+      "eval_runtime": 9.6122,
+      "eval_samples_per_second": 17.998,
+      "eval_steps_per_second": 9.051,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8850992586031104.0,
+  "total_flos": 1.3188855289085952e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null