Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a74fc0286a7cb36b3eadd1adadbc194da3ed3ee0a5cb63f02985f361b361feb
+oid sha256:9a97713d08cce0de8b3517917b5a0b9632d4ebb3f59fd2ea32c04a88c7239b28
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34e4abcae202ea50add3376fd2482b47db14096c2f0055e8f25277f396dbb625
+oid sha256:6f2b7c8896c627223ddf87f733fb7c339bbfd4279de82eb5e19eb42e1540c371
 size 111142

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8f9bfbb25b5742af971410f7969204872224492d0748212c97b7e3aec33a144
+oid sha256:8b6a6a011f28f85007de1213aaf2d9d99df9d84c0278f3612751bd8de1562285
 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": 0.015737704918032787,
+  "epoch": 0.02360655737704918,
   "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": 26.064,
       "eval_steps_per_second": 13.113,
       "step": 6
+    },
+    {
+      "epoch": 0.018360655737704918,
+      "grad_norm": 0.03210461512207985,
+      "learning_rate": 0.00014,
+      "loss": 11.7568,
+      "step": 7
+    },
+    {
+      "epoch": 0.02098360655737705,
+      "grad_norm": 0.042795587331056595,
+      "learning_rate": 0.00016,
+      "loss": 11.7597,
+      "step": 8
+    },
+    {
+      "epoch": 0.02360655737704918,
+      "grad_norm": 0.03623143583536148,
+      "learning_rate": 0.00018,
+      "loss": 11.7611,
+      "step": 9
+    },
+    {
+      "epoch": 0.02360655737704918,
+      "eval_loss": 11.759139060974121,
+      "eval_runtime": 6.1857,
+      "eval_samples_per_second": 26.028,
+      "eval_steps_per_second": 13.095,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2444400525312.0,
+  "total_flos": 3666600787968.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null