Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fffe989d2ee97d3d62cc7091b870276d764db85c56a2a741a7b91ad41e5e6b72
+oid sha256:0488ffe2817b80ca4606a42889a735911c4effb49520ec0a230c66e9b727c4ea
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95b7874d29fe785653c7c3aacea25164cb32403cde9cf5f8e12a60a07f9155a4
+oid sha256:cbf817b27e890b9ab6bc9ea279859d4decd38a42b821989b4e1f510978bb734b
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc695d50fa9c7a7b39e7508c0827b13b4400b02508b8aa483545d12dba8b4308
+oid sha256:42700a3931f169d1a7cb24ca5c5bfdf8c30401d4efdc7d55be9e5bed753e25b1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cbe95d5ecd33771846042e20aabf210775f4e6a78ced16f0764898d40abeba5
+oid sha256:cedaf8893734b19717a3bbbc716629d55965a18bdde504cf46d9182fcb60eb14
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012225686166636102,
+  "epoch": 0.014670823399963322,
   "eval_steps": 34,
-  "global_step": 25,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -190,6 +190,41 @@
       "learning_rate": 0.0001666666666666667,
       "loss": 1.471,
       "step": 25
+    },
+    {
+      "epoch": 0.012714713613301546,
+      "grad_norm": 1.876035451889038,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 1.4368,
+      "step": 26
+    },
+    {
+      "epoch": 0.013203741059966991,
+      "grad_norm": 1.6051979064941406,
+      "learning_rate": 0.00018,
+      "loss": 1.3951,
+      "step": 27
+    },
+    {
+      "epoch": 0.013692768506632435,
+      "grad_norm": 1.7268619537353516,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 1.1915,
+      "step": 28
+    },
+    {
+      "epoch": 0.014181795953297879,
+      "grad_norm": 1.888218879699707,
+      "learning_rate": 0.00019333333333333333,
+      "loss": 1.1358,
+      "step": 29
+    },
+    {
+      "epoch": 0.014670823399963322,
+      "grad_norm": 1.7404896020889282,
+      "learning_rate": 0.0002,
+      "loss": 1.2051,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -209,7 +244,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.109738548887552e+17,
+  "total_flos": 1.3316862586650624e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null