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:bee0f8a2b901490c86eef040f84de4ae7fb631697217e62d2bdd7372db403bb5
+oid sha256:e3d61446acdf406a2922f9f6dfb4b0a7e9f8d7308ccdcc647227cc0493f4efb6
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7de9e10d042c98a1ba2d679f3a262f6fa5821a17d684072b5fb4191f334cbe60
+oid sha256:bfc0a8fee32ae7f36758fd549783f01aa0ebaff3bd96a5c02beed6f3b07197d2
 size 49846260

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0634cfd3a595bdc9deaef4fa576cb8d5ef5b9c967ab34b22dc88c56b5fe30283
+oid sha256:4c9dd9d45556c33d7fbcb3e1a8ae0abe5b8e3a89d45df19cff538a2d8cbfabaf
 size 15920

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f871dcddb3a16517740514744491a9fbb42a57ff950fa5584abe57e7f9bec7a
+oid sha256:ab37aeb81638c7e1405129f777222eece8c9c3665872cf51936297325a5f0509
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0a54cd94578a84a985c5e49180616033169de995db4e81779ab471b641aae11
+oid sha256:de9b6cb873c354fc081abf478a94ecdbc31ea2ef25609e40af8cb59268ff524a
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8ee91319a9a983a75121cb19712b95b91e7b2b1f75e8835fc9e7d00fe28cbc2
+oid sha256:7d3d2a62ce57d01362552e872ba039b45a34d3c5be63de5246e99568a96be015
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:127f0207df027db84a408f13e3d9013cb7bab300a40c0f44e66959df53905984
+oid sha256:87b4bc45d3a2e880c9b182a869939cad806368ac4814a7fdac66687aa51a1aba
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1ef139c25fc2e488bff40dd5eeea268125cefd1f9f75ff908cdfea5cf13d729
+oid sha256:166cac575840e174f53a465fe012199c43ac43f19628c44c9120e620cc1a68d0
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36f262e0350c5145a3741ec496e88c275b236cc6b18ad5b962dc0f0cc997870c
+oid sha256:e5d314580653496906204b80c025e86607c218e0330cdff7f4bd48f8b69dd775
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e689191ffaaead2363233c20f7c2f8ba604a3aaa2ea1af4f9a817f6e3496763
+oid sha256:98e5b246de8f9fe11bd458afcb4f3982399918e03e5b8340aa16b7142ab3a407
 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": 0.1095890410958904,
+  "epoch": 0.1643835616438356,
   "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": 49.9,
       "eval_steps_per_second": 6.439,
       "step": 6
+    },
+    {
+      "epoch": 0.1278538812785388,
+      "grad_norm": 0.40307268500328064,
+      "learning_rate": 0.00014,
+      "loss": 0.9424,
+      "step": 7
+    },
+    {
+      "epoch": 0.1461187214611872,
+      "grad_norm": 0.39569929242134094,
+      "learning_rate": 0.00016,
+      "loss": 0.8835,
+      "step": 8
+    },
+    {
+      "epoch": 0.1643835616438356,
+      "grad_norm": 0.4634018540382385,
+      "learning_rate": 0.00018,
+      "loss": 0.8178,
+      "step": 9
+    },
+    {
+      "epoch": 0.1643835616438356,
+      "eval_loss": 0.8397897481918335,
+      "eval_runtime": 1.867,
+      "eval_samples_per_second": 49.812,
+      "eval_steps_per_second": 6.427,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3415246060322816e+16,
+  "total_flos": 2.0122869090484224e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null