Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d0d0c03c0a620e93cfed795a3e332866d538b99c997dd4d5087833b58dddc45
+oid sha256:69fd489d4499bd2247d94a7d3d857cd3d7ae9496471a6199bcc7582ef18ffaaf
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ea719924057030a0fddf7d19d4791498a42890580e5f1761223042c323c4739
+oid sha256:89d6f5c15f636678ed73ae6facf89b8ae6543315c86c8eb67b05c628708a776b
 size 3633466

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": 0.014871731317387532,
+  "epoch": 0.019828975089850043,
   "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": 235.68,
       "eval_steps_per_second": 117.909,
       "step": 15
+    },
+    {
+      "epoch": 0.015863180071880034,
+      "grad_norm": 0.5831274390220642,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 3.0963,
+      "step": 16
+    },
+    {
+      "epoch": 0.016854628826372536,
+      "grad_norm": 0.5969480276107788,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.9478,
+      "step": 17
+    },
+    {
+      "epoch": 0.01784607758086504,
+      "grad_norm": 0.5915560722351074,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 3.0661,
+      "step": 18
+    },
+    {
+      "epoch": 0.01883752633535754,
+      "grad_norm": 0.525524914264679,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.9725,
+      "step": 19
+    },
+    {
+      "epoch": 0.019828975089850043,
+      "grad_norm": 0.6235185861587524,
+      "learning_rate": 0.0,
+      "loss": 3.102,
+      "step": 20
+    },
+    {
+      "epoch": 0.019828975089850043,
+      "eval_loss": 3.069692850112915,
+      "eval_runtime": 7.281,
+      "eval_samples_per_second": 233.347,
+      "eval_steps_per_second": 116.742,
+      "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": 219472963043328.0,
+  "total_flos": 292344845303808.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null