Training in progress, step 34, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb3239615ba8696562965b0680d912e14cbaeee3b82030ee2246e1f4f01c374f
+oid sha256:6cba6fac2bc95ff24364f564fc59c17cf3c6dc0e94c84279f0c46f12885426bb
 size 34793120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7b8d8601a8a11554d6750b274a41c26c7939d5f28565b34583f5597d47ec088
+oid sha256:28bccce51cabb77efeb176e3ac5242a92606e30552237a19ad530d046d1902c8
 size 18132116

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a1e960047bcda347adbb9dfc01ab9e44a91c6703626e6ee144882c27c0688b6
+oid sha256:0a6714fca8ec6b267e6537a7b9479bb2dd4d3ba46cfb03a3eaaef094137d2167
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61d8ec93266e4bc8a64331da6b277e98dfae3d3d4bab70d66d65fad27bc26c8c
+oid sha256:0af27ed5b5e5c3013f1da7a97e494138e751399ceff1f8e7486b6e269bc7092f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09379310344827586,
+  "epoch": 0.18758620689655173,
   "eval_steps": 17,
-  "global_step": 17,
+  "global_step": 34,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,56 @@
       "eval_samples_per_second": 68.701,
       "eval_steps_per_second": 8.785,
       "step": 17
+    },
+    {
+      "epoch": 0.0993103448275862,
+      "grad_norm": 1.1075429916381836,
+      "learning_rate": 9.956320346634876e-05,
+      "loss": 3.3909,
+      "step": 18
+    },
+    {
+      "epoch": 0.11586206896551725,
+      "grad_norm": 1.0358085632324219,
+      "learning_rate": 9.917525374361912e-05,
+      "loss": 3.0781,
+      "step": 21
+    },
+    {
+      "epoch": 0.13241379310344828,
+      "grad_norm": 0.6941744685173035,
+      "learning_rate": 9.86663298624003e-05,
+      "loss": 3.1513,
+      "step": 24
+    },
+    {
+      "epoch": 0.1489655172413793,
+      "grad_norm": 0.7888012528419495,
+      "learning_rate": 9.803768380684242e-05,
+      "loss": 2.815,
+      "step": 27
+    },
+    {
+      "epoch": 0.16551724137931034,
+      "grad_norm": 0.6974669694900513,
+      "learning_rate": 9.729086208503174e-05,
+      "loss": 2.7661,
+      "step": 30
+    },
+    {
+      "epoch": 0.1820689655172414,
+      "grad_norm": 0.7885407209396362,
+      "learning_rate": 9.642770192448536e-05,
+      "loss": 2.8794,
+      "step": 33
+    },
+    {
+      "epoch": 0.18758620689655173,
+      "eval_loss": 2.820341110229492,
+      "eval_runtime": 4.4584,
+      "eval_samples_per_second": 68.411,
+      "eval_steps_per_second": 8.748,
+      "step": 34
     }
   ],
   "logging_steps": 3,
@@ -77,7 +127,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1080639797329920.0,
+  "total_flos": 2161279594659840.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null