Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21f1cb12ec6dd2d4aa8d26fe10259535f69d064ac22b2d8e516c172b54477e73
+oid sha256:3205c2df9b5e8deefa7d97877695b23ae46023441a608c8e7f1a53043310783b
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:457e51e4f200eb4aa3921a5a160def2ae1569e11b5f85b55ff33066bd68a0d5c
+oid sha256:7cbe7ffddcf84f6ea38928d7db3aa94267c99ef2965a9d35658be2e8246a0358
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39acb5a2530dc832149c5d18e7a15da6846a800c716036ccf187a7e397862da3
+oid sha256:22d0e0f373f425efa292dac5abf951f67103d9d788fea236fa7b5ab0e5d83fa6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1f9e237c4e244cd6a21b3069d52ab1ce3e784c965dcb77abb8266616185916c
+oid sha256:e9573e9d18ad7803441c819253e1705231d5811c0e4f29747c0574440f588f00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.318232044198895,
+  "epoch": 0.4243093922651934,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 5.919,
       "eval_steps_per_second": 2.96,
       "step": 27
+    },
+    {
+      "epoch": 0.35359116022099446,
+      "grad_norm": 22.00638198852539,
+      "learning_rate": 0.0001442909649383465,
+      "loss": 65.7473,
+      "step": 30
+    },
+    {
+      "epoch": 0.3889502762430939,
+      "grad_norm": 26.196809768676758,
+      "learning_rate": 0.0001404372005304598,
+      "loss": 64.8032,
+      "step": 33
+    },
+    {
+      "epoch": 0.4243093922651934,
+      "grad_norm": 30.012163162231445,
+      "learning_rate": 0.00013567627457812106,
+      "loss": 62.5845,
+      "step": 36
+    },
+    {
+      "epoch": 0.4243093922651934,
+      "eval_loss": 1.9335837364196777,
+      "eval_runtime": 48.3129,
+      "eval_samples_per_second": 5.92,
+      "eval_steps_per_second": 2.96,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.419972205168558e+17,
+  "total_flos": 1.8932962735580774e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null