Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:101c627e7d23876499abf6e4681eb73f4e5a23f6fb55acd4a290c1d65459aa1d
+oid sha256:b3729254bf455003dd8ead988a0e73894eb1c052f40c6cca5499f58432c4a0e1
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f272835f550dc2c03f2bc589ad8b72bed230fdf37d1e497c0fc3b65660fd7d21
+oid sha256:433f82a3f33bc230ebf33e7b3ecf12f4ef0790bcab065417a63ed23c15dd8edb
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b52214f9bd9fd90e146416d19db727ff822d3ff4dfe457467cf1dd46cfde3948
+oid sha256:5da98638b5afea10e0de2f4fc87452ede8bc4b95ee5e48c3293a3388722f1e2e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07346189164370982,
+  "epoch": 0.11019283746556474,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 4.3512,
       "step": 18
+    },
+    {
+      "epoch": 0.07713498622589532,
+      "grad_norm": 2.991180419921875,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 3.8412,
+      "step": 21
+    },
+    {
+      "epoch": 0.0881542699724518,
+      "grad_norm": 3.2314670085906982,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 3.2882,
+      "step": 24
+    },
+    {
+      "epoch": 0.0881542699724518,
+      "eval_loss": 0.7786951065063477,
+      "eval_runtime": 10.5393,
+      "eval_samples_per_second": 10.912,
+      "eval_steps_per_second": 5.503,
+      "step": 24
+    },
+    {
+      "epoch": 0.09917355371900827,
+      "grad_norm": 5.712580680847168,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 3.264,
+      "step": 27
+    },
+    {
+      "epoch": 0.11019283746556474,
+      "grad_norm": 3.50492787361145,
+      "learning_rate": 0.0,
+      "loss": 2.9104,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.2695579394048e+16,
+  "total_flos": 1.9043369091072e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null