Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3923c6c2d238cd3361024c80cac4a57bea4c1dd24732d212c7c0481b868aeeb4
+oid sha256:8bf3b554a722161d949f66405978a8112bd762c52b942d8b436544e3dad153d9
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca49e2c253d38e24ae4972e1bc709e59f2e1296805f1052620ce8f42596247ac
+oid sha256:9659418d3605e5b40babd95284fbf5ec8686f8df71e70dc60388ce063f42d584
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e841c8d708d2d450b0eab7be6e2c4e08cbedd4e297878439ca4360fd0b733323
+oid sha256:5f121b3f8e6b3ed310c94a49893eb97a3ee7cfc910bf43c67bb9322868d758fd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b52924c88c1c80163d374a6650253dd74b8b46052a3da6fc5e4076e57b5effa
+oid sha256:5d605401690d7669ff16aeaca6820cbd8d0d605afe748c51045ce90888810a22
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00479077775282581,
+  "epoch": 0.005988472191032263,
   "eval_steps": 4,
-  "global_step": 16,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -159,6 +159,42 @@
       "eval_samples_per_second": 8.417,
       "eval_steps_per_second": 8.417,
       "step": 16
+    },
+    {
+      "epoch": 0.005090201362377423,
+      "grad_norm": 26.169757843017578,
+      "learning_rate": 0.00018526401643540922,
+      "loss": 4.8565,
+      "step": 17
+    },
+    {
+      "epoch": 0.005389624971929036,
+      "grad_norm": 27.142152786254883,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 4.9723,
+      "step": 18
+    },
+    {
+      "epoch": 0.00568904858148065,
+      "grad_norm": 18.188777923583984,
+      "learning_rate": 0.0001760405965600031,
+      "loss": 2.6307,
+      "step": 19
+    },
+    {
+      "epoch": 0.005988472191032263,
+      "grad_norm": 21.539011001586914,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 3.5522,
+      "step": 20
+    },
+    {
+      "epoch": 0.005988472191032263,
+      "eval_loss": 4.069602012634277,
+      "eval_runtime": 83.15,
+      "eval_samples_per_second": 8.467,
+      "eval_steps_per_second": 8.467,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -178,7 +214,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5935098268483584.0,
+  "total_flos": 7418872835604480.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null