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:dfc3bbef39f72920cc0ce4ee04cc303b32dd9b3319747a71ffae39fa4520afd3
+oid sha256:66eb884803e7c4c4e8a9cde168ade3c62cb13178550a3738b115a9928e79afce
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51265d2d64690d2fc6fd7b1eab712dde8e98b4e7abf7b1ff06ca6386382cade7
+oid sha256:8cf9dc533d20f4ca7a96e944e92a6e28010ba04df65556355e36581114c773f2
 size 111142

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb8e94ed7d2e5345474bc4e6ef357149b03775ea97dbbd35213421e1ad780c7b
+oid sha256:80cccb7a7c0cf957086fe40150be43377dbd4fb9e40f589f5ac68c8deef5d825
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ec3b2672901b1703f10a1efcda338ac81906ecc6ac1ad04f258af0d5c221cec
+oid sha256:e57dfee72cef42b1eb19a9f964e8b349f870bbdd7049e20836aa0156a048302b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c93a2f7bad7007dde3c0b86763497774dfa862182e21a4b3325cb597be70adbe
+oid sha256:8f7dbcd24299732ea62bee1605adde4c30a470c02eacf7f2edd194cb9f094c2f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64a9b766484bd538fc4a2e80d2dbd0f217606f04c0ab90e19f3fce6deb5fed69
+oid sha256:4851c2e8b4f8c53c21926c518bc2ef1a939f1e5b2536fc42571ee2deac92424a
 size 15024

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": 0.010968921389396709,
+  "epoch": 0.021937842778793418,
   "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": 481.543,
       "eval_steps_per_second": 60.585,
       "step": 3
+    },
+    {
+      "epoch": 0.014625228519195612,
+      "grad_norm": 0.06676133722066879,
+      "learning_rate": 8e-05,
+      "loss": 10.3638,
+      "step": 4
+    },
+    {
+      "epoch": 0.018281535648994516,
+      "grad_norm": 0.08866722881793976,
+      "learning_rate": 0.0001,
+      "loss": 10.3619,
+      "step": 5
+    },
+    {
+      "epoch": 0.021937842778793418,
+      "grad_norm": 0.08508071303367615,
+      "learning_rate": 0.00012,
+      "loss": 10.361,
+      "step": 6
+    },
+    {
+      "epoch": 0.021937842778793418,
+      "eval_loss": 10.36319351196289,
+      "eval_runtime": 0.9755,
+      "eval_samples_per_second": 472.593,
+      "eval_steps_per_second": 59.459,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1255258718208.0,
+  "total_flos": 2510517436416.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null