Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8a206fd6fc82dc47865ca6972a848f653d5bb4c2cc530c6dc040a0487086171
+oid sha256:e9e8e9b466bc8d55224ee40bb0c8e1cbaa62dffad6cf01d452b3370f479c53d0
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1904d8aee5cd393e6742756d030dadbcc2a508b70f966870e41930044f0afabe
+oid sha256:f9d6909db8b8506fbadaafd9fe037db1b17541c1a307b9e5dab03223cccd54cd
 size 39398

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49d56c6fd229b79724ed3dcdb4b672517c1648204c72ac049f2492d414e60de1
+oid sha256:96d1713fc9fbda172b2834678b76866c7a2aa2e36d82155d4beea5f4ab98d349
 size 15920

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce7631bd4ab517ce695982f0c187210a288656770e5c42ef4faa0f4c7edd7a3b
+oid sha256:3a441b1772cc14d3839c3edaf3b2ef5dc6ec929a745367383c87a1eb114b20a7
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82b85acc8eedcc692a4ea50ce2ab6c5db7c647c8c83776e141cce4bb67023ceb
+oid sha256:7131f11887101a177e61549f670c2cbcd223abe396d29afa35352aaec068102f
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44e5a47f6caf446465a431fdda949366f3e32ce41cb8af2309a1630b254ebe18
+oid sha256:2886482cd7daeb6a64084f756320fae8c88e5f90232720e09416de1fe53fda56
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d17c75edd95d4e6d6a49098208613a584190e481ff384794811ac9f97688a1f4
+oid sha256:74eb266835849465d4c45f347f11c52667179de64aeeb36cec3396161571b639
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55f9a29d74bc179bd8107b8481e9c3e9e5582d1833bda5a5f55c2b0024f64b20
+oid sha256:fa88b31f0a357ea96b8979eadd1064dc0461ffaa602fd29ae808212e12d1182c
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d1c4d9a201fe2b5cd47cdb7e914822e96d14ce765e17bad5e47ded0b3392b99
+oid sha256:ee3accaa898fc0e116963d9ee5e0ca87b423d29bb88611003bd2e8141d85dbe2
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7969b1d053e2a68474c1dcbcff3192620975ee90d4433cd6a1c7abbad15fa205
+oid sha256:99ea7ecbafc361e3fbfda8f7a94c1d9be7f2d9597c61268dedf15723aaef60c6
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013452914798206279,
+  "epoch": 0.026905829596412557,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 1441.543,
       "eval_steps_per_second": 90.216,
       "step": 3
+    },
+    {
+      "epoch": 0.017937219730941704,
+      "grad_norm": 0.007786044850945473,
+      "learning_rate": 8e-05,
+      "loss": 11.9324,
+      "step": 4
+    },
+    {
+      "epoch": 0.02242152466367713,
+      "grad_norm": 0.009498490951955318,
+      "learning_rate": 0.0001,
+      "loss": 11.9317,
+      "step": 5
+    },
+    {
+      "epoch": 0.026905829596412557,
+      "grad_norm": 0.008360755629837513,
+      "learning_rate": 0.00012,
+      "loss": 11.9318,
+      "step": 6
+    },
+    {
+      "epoch": 0.026905829596412557,
+      "eval_loss": 11.931273460388184,
+      "eval_runtime": 0.5165,
+      "eval_samples_per_second": 1454.119,
+      "eval_steps_per_second": 91.003,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2894954496.0,
+  "total_flos": 5789908992.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null