Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86e54584c9fd0487ec7e4f14e496b28d5b067151048db5b0fee9d7e85a4a68c8
+oid sha256:96890b515b1013da54715ff9bf2f15c271d7d87ef6372e6e8e7b9227770411e1
 size 5327744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00878f593dca7653794211e8e4f6b8d4ce15f86a30e31646b3b30de59e656d9b
+oid sha256:98be2ea42534f69c5f601032b83c33bbdda7b679c760d98a3ff98858a8e81c87
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c58b0f87d75899bb7278d92ca01276981514ff3189f6f8b4388d4cdea082d8ad
+oid sha256:40079f2e1bd12b7260bddc0275896f1a40d137b73c8b1cc8ab30cd3e75972c79
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010526315789473684,
+  "epoch": 0.015789473684210527,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 99.637,
       "eval_steps_per_second": 49.818,
       "step": 6
+    },
+    {
+      "epoch": 0.012280701754385965,
+      "grad_norm": 5.6868414878845215,
+      "learning_rate": 0.00014,
+      "loss": 6.1701,
+      "step": 7
+    },
+    {
+      "epoch": 0.014035087719298246,
+      "grad_norm": 6.236565589904785,
+      "learning_rate": 0.00016,
+      "loss": 8.7456,
+      "step": 8
+    },
+    {
+      "epoch": 0.015789473684210527,
+      "grad_norm": 5.2089314460754395,
+      "learning_rate": 0.00018,
+      "loss": 6.338,
+      "step": 9
+    },
+    {
+      "epoch": 0.015789473684210527,
+      "eval_loss": 1.7883986234664917,
+      "eval_runtime": 2.3464,
+      "eval_samples_per_second": 102.283,
+      "eval_steps_per_second": 51.142,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 19637298266112.0,
+  "total_flos": 30252054085632.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null