Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9ea622c8a3ae4b59a8a654fb9b816a6441441a0ec016517cea76ba07c389661
+oid sha256:569475ef979edab3c418976d9c91404412b404952406423eb2e9ccff805dc5cb
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d49636346021d81f2d7cc722ec13261c206beec25caa17e53c798c19ba71615
+oid sha256:ce08756aa8570024caa604b64eed8a0ee274be2e8e1985fbb30c916f38666ade
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b963127b22ddeab5c967c77cf61654178062a733d4a71d3b34be157aad97ad
+oid sha256:37a754b69282774388bd86935d90c82a6607dc2b521ab62662f3cd5555009319
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
+oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.037954665260938325,
+  "epoch": 0.04428044280442804,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 7.109,
       "eval_steps_per_second": 0.89,
       "step": 54
+    },
+    {
+      "epoch": 0.040063257775434895,
+      "grad_norm": 0.22594496607780457,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 0.7247,
+      "step": 57
+    },
+    {
+      "epoch": 0.04217185028993147,
+      "grad_norm": 0.17635485529899597,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.6246,
+      "step": 60
+    },
+    {
+      "epoch": 0.04428044280442804,
+      "grad_norm": 0.1977640837430954,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 0.7231,
+      "step": 63
+    },
+    {
+      "epoch": 0.04428044280442804,
+      "eval_loss": 0.7249730825424194,
+      "eval_runtime": 337.0353,
+      "eval_samples_per_second": 7.112,
+      "eval_steps_per_second": 0.89,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4279632924704768e+17,
+  "total_flos": 1.6659571745488896e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null