Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:746646e7a6a6925ca7ebb29d53fcf0b1c0893b8f20d6362eeb750ff6f122341b
+oid sha256:8602602d27b89a8d5aa06cbaaa7afce4df95670e302824b14d2d995dc4681680
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c85ac0ba301141ca1014d25de18920f7b9670970e107f1a01d438569192cbc6f
+oid sha256:dba108f0cdce82ad3e2cd068b6f849f104457a9e357302d101aa78149d8dd441
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ea4c86c7e8a86ff4c17a1f954f7b8c92b5100baf63d25f32ca35b20d0a8cdf7
+oid sha256:04232fce99c4802dc579b85d4a7938b6bd47a3fd2dae4192a67625460029c733
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16178af669793c21eac8710459f1cc10bcf09af1984c5f2d80e76b26b329c8ba
+oid sha256:67680b8b35ea230d53acee387012f8809825a2c511bd41340f42320f849e349d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0024451372333272204,
+  "epoch": 0.004890274466654441,
   "eval_steps": 34,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -50,6 +50,41 @@
       "learning_rate": 3.3333333333333335e-05,
       "loss": 8.8885,
       "step": 5
+    },
+    {
+      "epoch": 0.0029341646799926646,
+      "grad_norm": 8.087092190490132e+18,
+      "learning_rate": 4e-05,
+      "loss": 9.0537,
+      "step": 6
+    },
+    {
+      "epoch": 0.0034231921266581087,
+      "grad_norm": Infinity,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 8.6808,
+      "step": 7
+    },
+    {
+      "epoch": 0.0039122195733235525,
+      "grad_norm": Infinity,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 8.8092,
+      "step": 8
+    },
+    {
+      "epoch": 0.004401247019988997,
+      "grad_norm": Infinity,
+      "learning_rate": 6e-05,
+      "loss": 9.7075,
+      "step": 9
+    },
+    {
+      "epoch": 0.004890274466654441,
+      "grad_norm": Infinity,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 9.2624,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -69,7 +104,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.102239837978624e+16,
+  "total_flos": 2.204479675957248e+16,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null