Training in progress, step 35, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f54285af820322f413bedf90a197fab9546824b126b677e531d7a3e34609c30c
+oid sha256:5bde0c002a7b60c273b49837e4b851b5ed52b90428c55fb5930c878504512491
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28c7adf268e87dd0a41446aaa874ecc5ab743fb9a94da50a96ececdd5a3bee8f
+oid sha256:3488476f49083977e86d89a5ee9a6936f17d633cb87e683274b5f9fba011b84a
 size 85723284

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fc23edab8ba1108a86a5e66e050703f0e0017d14e4377e9cbd25e332b216c4b
+oid sha256:467264eb57c59c955e813f6c6054e4885698642ee168306af423fe1c31108531
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a43d18fc96a7898854e74a08413f3781a39c478df43b8b248b0577bb9030b97
+oid sha256:7aea477e0332bd49137a9e7099a31c4933b9652e14b7c883036946eaf8f98dec
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2bb4b588419b60e1f59dda48eeb3b428275266887083bc814e29c779f54f5c8
+oid sha256:400690333b498d3c3ea4cd1446f834c1cb37202647b1e68e58a488ea7599ce2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7783783783783784,
+  "epoch": 1.009009009009009,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 35,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -228,6 +228,62 @@
       "eval_samples_per_second": 10.197,
       "eval_steps_per_second": 2.571,
       "step": 27
+    },
+    {
+      "epoch": 0.8072072072072072,
+      "grad_norm": 3.502157688140869,
+      "learning_rate": 1.0697345262860636e-05,
+      "loss": 24.1016,
+      "step": 28
+    },
+    {
+      "epoch": 0.836036036036036,
+      "grad_norm": 3.466275930404663,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 23.6451,
+      "step": 29
+    },
+    {
+      "epoch": 0.8648648648648649,
+      "grad_norm": 3.245530128479004,
+      "learning_rate": 5.558227567253832e-06,
+      "loss": 23.9141,
+      "step": 30
+    },
+    {
+      "epoch": 0.8936936936936937,
+      "grad_norm": 3.150803804397583,
+      "learning_rate": 3.581603349196372e-06,
+      "loss": 23.176,
+      "step": 31
+    },
+    {
+      "epoch": 0.9225225225225225,
+      "grad_norm": 3.4905145168304443,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 23.8849,
+      "step": 32
+    },
+    {
+      "epoch": 0.9513513513513514,
+      "grad_norm": 3.366611957550049,
+      "learning_rate": 9.035651368646648e-07,
+      "loss": 23.4103,
+      "step": 33
+    },
+    {
+      "epoch": 0.9801801801801802,
+      "grad_norm": 3.181520700454712,
+      "learning_rate": 2.2640387134577058e-07,
+      "loss": 22.1288,
+      "step": 34
+    },
+    {
+      "epoch": 1.009009009009009,
+      "grad_norm": 3.0065629482269287,
+      "learning_rate": 0.0,
+      "loss": 22.3399,
+      "step": 35
     }
   ],
   "logging_steps": 1,
@@ -242,12 +298,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.075038868606812e+17,
+  "total_flos": 7.875050385231053e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null