Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1df449a58440ab4984101f289e7c81de1534eff35f0452f95a8bf75765e00b1e
+oid sha256:58e26400501cfdc336f854139f0b434621712c18baf846fb8425f29f14fa0eaf
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6142aacc69a7153008fc81ddc6a402c5c5cb19949042b5ebd3f92b20f3eccc65
+oid sha256:86a0acc9f5b3d266682e9fe1a0607e367fb81a9832b5cea7f12c9760cb803ba0
 size 56088084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
+oid sha256:9ea24ba22f005ab5531315a7c25fe17ce3b0d82d32e4d057cd4a8d9beeaa0eb4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.027649769585253458,
+  "epoch": 0.03686635944700461,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 22.554,
       "eval_steps_per_second": 11.277,
       "step": 15
+    },
+    {
+      "epoch": 0.029493087557603687,
+      "grad_norm": 0.7435203790664673,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.2576,
+      "step": 16
+    },
+    {
+      "epoch": 0.03133640552995392,
+      "grad_norm": 0.8554832339286804,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.3472,
+      "step": 17
+    },
+    {
+      "epoch": 0.03317972350230415,
+      "grad_norm": 0.859761118888855,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.3136,
+      "step": 18
+    },
+    {
+      "epoch": 0.035023041474654376,
+      "grad_norm": 0.6912463307380676,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.4231,
+      "step": 19
+    },
+    {
+      "epoch": 0.03686635944700461,
+      "grad_norm": 0.7137346863746643,
+      "learning_rate": 0.0,
+      "loss": 1.2482,
+      "step": 20
+    },
+    {
+      "epoch": 0.03686635944700461,
+      "eval_loss": 1.3629361391067505,
+      "eval_runtime": 40.5333,
+      "eval_samples_per_second": 22.549,
+      "eval_steps_per_second": 11.275,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.879842609954816e+16,
+  "total_flos": 2.497656051990528e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null