Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f39a40b818f775ce1c192a14b9d318ff8a0f58d5eec020e207119ca329ef14d
+oid sha256:e54c0f2b7bc39100b25341d998d9fa350019a4823ce41eb6fc0cc529fe4c86b2
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dbf7f1d5d4c6ffd6658be14a7b09eb9d8e6e9372c3b44f9157e129c232b9484
+oid sha256:7fd565fedbd2a164adfdae703d25d69a349773efd47d6cc99069da5eb53606da
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae1e9ddc14f76e64f69bc8614da3eb72fbe37e07f13884bc604b91bc90280775
+oid sha256:344c2554134ae1c5130cac2aeb1170c5308b1488574a5fdb9090888f1fde9d91
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fec74e92563bbe4b510ec939dc1c78d591826119d26043cc49e0a868b67121a2
+oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0027134209977040286,
+  "epoch": 0.005426841995408057,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 61.529,
       "eval_steps_per_second": 30.795,
       "step": 13
+    },
+    {
+      "epoch": 0.004174493842621582,
+      "grad_norm": 1.7829546928405762,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 2.9497,
+      "step": 20
+    },
+    {
+      "epoch": 0.005426841995408057,
+      "eval_loss": 2.953101396560669,
+      "eval_runtime": 16.483,
+      "eval_samples_per_second": 61.215,
+      "eval_steps_per_second": 30.638,
+      "step": 26
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 60830519132160.0,
+  "total_flos": 130672967024640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null