Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36e6c9cfa4f0fffe48b569f693bf970e8f7707e0b15b20eb7413938334be7f8d
+oid sha256:6884d7aff19fb40665e0f075ec10784d2cbe2bc2b6793f74747e10cf06b36ae7
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a93c0ea2d24e0dbbb9d57820d02cfa65f3c3ae0c642d704b22340ed3c75ddd3
+oid sha256:1683f6a35441e40f7e842857d434f7ea56f554b679472e927c2df2fd393a60f5
 size 61926

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb84fccdb034986df07aed729d9a79295916a31144f77cecc2887a8cb2a66ae1
+oid sha256:5222ef92d88891b7866802aa36d7947acb8a459e0de913858a33fa5f1ed7e2f9
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a441b1772cc14d3839c3edaf3b2ef5dc6ec929a745367383c87a1eb114b20a7
+oid sha256:ff61da3f190db9f0cd95eac118c19d8931af626ac6cdcb3c28449124cb2df775
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7131f11887101a177e61549f670c2cbcd223abe396d29afa35352aaec068102f
+oid sha256:727f8e0235e7b519cc2e2530023082dcf7e1c75c2d034669d70b7c8226d03ba5
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2886482cd7daeb6a64084f756320fae8c88e5f90232720e09416de1fe53fda56
+oid sha256:bae6bc05bee45ec00fe0a891666a6d28ce15adb8600d281654ed026f02f79992
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74eb266835849465d4c45f347f11c52667179de64aeeb36cec3396161571b639
+oid sha256:8e39243e08531795e857ffe36d541ff93ef72277caf9bcdf9fb0056b34056a37
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa88b31f0a357ea96b8979eadd1064dc0461ffaa602fd29ae808212e12d1182c
+oid sha256:ae7edb9ae1d6d247ce5fcfd186b9a5c929b148b3a8adede9c37135a1985f18bf
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee3accaa898fc0e116963d9ee5e0ca87b423d29bb88611003bd2e8141d85dbe2
+oid sha256:43f6e9295785335c3718b4c386b046d4ee4b4a204f2c086d3a88aacc3e152339
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99ea7ecbafc361e3fbfda8f7a94c1d9be7f2d9597c61268dedf15723aaef60c6
+oid sha256:9f7443de9b1d1b6f5c63eaa4d687b4db8767c081bc08bda47125b08e17fb807c
 size 15984

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": 0.0036215482118605704,
+  "epoch": 0.005432322317790856,
   "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": 287.503,
       "eval_steps_per_second": 35.951,
       "step": 6
+    },
+    {
+      "epoch": 0.004225139580503999,
+      "grad_norm": 0.008809824474155903,
+      "learning_rate": 0.00014,
+      "loss": 11.9323,
+      "step": 7
+    },
+    {
+      "epoch": 0.004828730949147427,
+      "grad_norm": 0.00893594790250063,
+      "learning_rate": 0.00016,
+      "loss": 11.9324,
+      "step": 8
+    },
+    {
+      "epoch": 0.005432322317790856,
+      "grad_norm": 0.011988944374024868,
+      "learning_rate": 0.00018,
+      "loss": 11.9309,
+      "step": 9
+    },
+    {
+      "epoch": 0.005432322317790856,
+      "eval_loss": 11.931912422180176,
+      "eval_runtime": 9.7178,
+      "eval_samples_per_second": 287.206,
+      "eval_steps_per_second": 35.914,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 35974545408.0,
+  "total_flos": 53961818112.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null