Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7cb3e037bdce69674d876090e02534850f44fdc8760524a13123cc446ee8775
+oid sha256:08847e4297a4f3580c24179e7fad59a879503daea5ad4e402c5ec291963f4d43
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98b7aabe82568b7119f483097ec00f50abdc4295d673c0a79af791281e7e06a0
+oid sha256:f22524d1ba9c27d3fbae4a488da1a28690e9bd087957706151576f3bc746fa27
 size 37134420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d63f7a496bcd2565d401f276d2feed4b5c2a5d1160a87b647230fc7a7b03806
+oid sha256:6e3d6ff809682f42a3de0e4608089e32d07b128d6b5ad5946f834559794b5091
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
+oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16869728209934395,
+  "epoch": 0.20243673851921273,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,35 @@
       "eval_samples_per_second": 34.689,
       "eval_steps_per_second": 4.394,
       "step": 45
+    },
+    {
+      "epoch": 0.17994376757263356,
+      "grad_norm": 0.22030919790267944,
+      "learning_rate": 3.104804738999169e-05,
+      "loss": 2.0074,
+      "step": 48
+    },
+    {
+      "epoch": 0.19119025304592316,
+      "grad_norm": 0.20402924716472626,
+      "learning_rate": 2.8479327524001636e-05,
+      "loss": 1.9598,
+      "step": 51
+    },
+    {
+      "epoch": 0.20243673851921273,
+      "grad_norm": 0.21052472293376923,
+      "learning_rate": 2.587248741756253e-05,
+      "loss": 1.9229,
+      "step": 54
+    },
+    {
+      "epoch": 0.20243673851921273,
+      "eval_loss": 1.9371302127838135,
+      "eval_runtime": 12.9738,
+      "eval_samples_per_second": 34.685,
+      "eval_steps_per_second": 4.393,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4730824339423232e+16,
+  "total_flos": 1.761294214496256e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null