Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1f6883302685faa1deceef1f53ee90ec530996e23b2747215dd7ea65daa6db8
+oid sha256:336fa09b07144084bf0b85cc9992216745b93e4fff84d6ff92594ae5648125ce
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df5e09110609d03078c74a94bbf3e31e9b79e49ff5c54f32598b4e1979794932
+oid sha256:c2f46bb2321fe42ff8423ef5392039f5c6eecc1bae74ba0e7e2ce0f9f41bc014
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22d0e0f373f425efa292dac5abf951f67103d9d788fea236fa7b5ab0e5d83fa6
+oid sha256:c6ad7439565a5462d968f8d3364199f027aa6f68d9890049e5a20a8e24781131
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1fbe8f3807fcf2c9b342444bf912c2b4a5837aba74951c80e3f443bde6ab488
+oid sha256:e917c3eea1680bab35c1f582cbc388a7464296952762325512c323f5f76cc5cb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003463755348224675,
+  "epoch": 0.004329694185280844,
   "eval_steps": 9,
-  "global_step": 36,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,35 @@
       "eval_samples_per_second": 3.485,
       "eval_steps_per_second": 1.743,
       "step": 36
+    },
+    {
+      "epoch": 0.003752401627243398,
+      "grad_norm": 32.828285217285156,
+      "learning_rate": 0.00017343225094356855,
+      "loss": 11.2033,
+      "step": 39
+    },
+    {
+      "epoch": 0.004041047906262121,
+      "grad_norm": 46.57306671142578,
+      "learning_rate": 0.00016494480483301836,
+      "loss": 10.001,
+      "step": 42
+    },
+    {
+      "epoch": 0.004329694185280844,
+      "grad_norm": 33.11753845214844,
+      "learning_rate": 0.00015555702330196023,
+      "loss": 8.5669,
+      "step": 45
+    },
+    {
+      "epoch": 0.004329694185280844,
+      "eval_loss": 0.25203973054885864,
+      "eval_runtime": 11473.7667,
+      "eval_samples_per_second": 3.051,
+      "eval_steps_per_second": 1.526,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8932962735580774e+17,
+  "total_flos": 2.3666203419475968e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null