Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e977ce0493c6a6a95b8a00029318c7e955a5052e6584067bdb42631ce40ad1b5
+oid sha256:951f33cbcd4fa21b228d71b126f1bfa11a696790a84e2d32696c3ea64ae60320
 size 604317736

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89dc1498c78d927bfbd9c8e882c13d3e2e5fc0b8d55d0225dc06ed21736cc26b
+oid sha256:aaea8d00e0a1a6c79c5a18d4ecfa3fe886c5e5a269da2336e5432e79798b21c9
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d04ce38a4b1ebe155394d1cb2e43ba46dcd389805a0df7f2671ac2a395b23d6c
+oid sha256:376a84af6354b555ba2fbd8c3fc92d9086d0a9dcf2c9793e8d456dbd561d4eb5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006002539535957521,
+  "epoch": 0.012005079071915042,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 17.043,
       "eval_steps_per_second": 8.522,
       "step": 10
+    },
+    {
+      "epoch": 0.006926007156874062,
+      "grad_norm": 18.49090576171875,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 3.5476,
+      "step": 15
+    },
+    {
+      "epoch": 0.009234676209165417,
+      "grad_norm": 8.904321670532227,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.0529,
+      "step": 20
+    },
+    {
+      "epoch": 0.009234676209165417,
+      "eval_loss": 1.4587453603744507,
+      "eval_runtime": 54.09,
+      "eval_samples_per_second": 16.861,
+      "eval_steps_per_second": 8.43,
+      "step": 20
+    },
+    {
+      "epoch": 0.01154334526145677,
+      "grad_norm": 5.717966556549072,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.6869,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2117354385309696.0,
+  "total_flos": 4234708770619392.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null