Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66eb884803e7c4c4e8a9cde168ade3c62cb13178550a3738b115a9928e79afce
+oid sha256:f83afac017a56c5dff80e4ce3601f3b2096c940cbbb447cb1dd764452c57b8aa
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cf9dc533d20f4ca7a96e944e92a6e28010ba04df65556355e36581114c773f2
+oid sha256:e91d070186b59530ca750f9db7d630fb313ef9136c1c9f5468e11a0b0be4547d
 size 111142

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80cccb7a7c0cf957086fe40150be43377dbd4fb9e40f589f5ac68c8deef5d825
+oid sha256:02b01d0e486dff2cb85accbdc44d4df7dcae2859f47fe7b514d80ec6d14b00a8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e57dfee72cef42b1eb19a9f964e8b349f870bbdd7049e20836aa0156a048302b
+oid sha256:da9184a96ec4d1e06ae289f0051378762191f4ba60f23b6d59e9aba10761c2ed
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f7dbcd24299732ea62bee1605adde4c30a470c02eacf7f2edd194cb9f094c2f
+oid sha256:491c54d7af28cf6eaa7a5ccd9b218155b2b3b0de07fd7b2323686cf341c901fa
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4851c2e8b4f8c53c21926c518bc2ef1a939f1e5b2536fc42571ee2deac92424a
+oid sha256:dbe024f27ffc6e5316283ccc9cfc939e46edfe07ea42e65b4dc94b8ae9077ad3
 size 15024

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": 0.021937842778793418,
+  "epoch": 0.03290676416819013,
   "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": 472.593,
       "eval_steps_per_second": 59.459,
       "step": 6
+    },
+    {
+      "epoch": 0.025594149908592323,
+      "grad_norm": 0.09561645984649658,
+      "learning_rate": 0.00014,
+      "loss": 10.3701,
+      "step": 7
+    },
+    {
+      "epoch": 0.029250457038391225,
+      "grad_norm": 0.08754566311836243,
+      "learning_rate": 0.00016,
+      "loss": 10.3637,
+      "step": 8
+    },
+    {
+      "epoch": 0.03290676416819013,
+      "grad_norm": 0.08271048218011856,
+      "learning_rate": 0.00018,
+      "loss": 10.3623,
+      "step": 9
+    },
+    {
+      "epoch": 0.03290676416819013,
+      "eval_loss": 10.36262035369873,
+      "eval_runtime": 1.0009,
+      "eval_samples_per_second": 460.563,
+      "eval_steps_per_second": 57.945,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2510517436416.0,
+  "total_flos": 3765776154624.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null