Training in progress, step 87, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4f8d9985c2635879636cf00dea398d289e06f556a9bc127706823b67b69e4de
+oid sha256:7e2d5ccac9eb6537d0304c1d9a2664be207cec54a4ffa4f7a1d25f97df0299e7
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7381ad45bafd9493c2d7b5b0a9f2ce11aeb313a4937b52ef4165ee14e53fdb10
+oid sha256:4fc6ccd88e5c6b445ddb81486e1b8bb3250cd0ab8d1994a6c77c83f6e34745a6
 size 41119636

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d931b5a9a1c7c4ddb717a41ecc1a1bb4eb430909791d123997f51c75f91c490d
+oid sha256:a57a79985839c1144630cf23e24a752af1717970babccc404e738d94f6a44f55
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e7e0a55494e7d81c76fc8e458c22a814a6e9f15e7e51449ad1c3b49f9fb8407
+oid sha256:f78f02857b552b73e80fba53ae03b2fe594f4ff8718b2b7a00f9874950315d8f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e6a0f1af9be0d83b44f9e958b08ec44d55376c6b6631c7ae00138e67f7c10e5
+oid sha256:61d763d8dd1b3cf0dec042ca7fcbae7698d20d5c131f3d0f4d2e0fa72962640d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab4a0706f8a1ef41420cf44b38130e84f08877e0e32fed36597afc61a8413269
+oid sha256:553a6b90849b840223e58a50b84e206a3b835868d03a26f2274252e82e65b480
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cfdef11c14a1e0e885d8851a9b351a3cf07332cd6b6e094393ff246c0c83551
+oid sha256:3a7a33c3c310055cbe2d20c9c9ebccba7f04bc435d5cf767eccc98d4867335d2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5155555555555555,
+  "epoch": 0.7733333333333333,
   "eval_steps": 29,
-  "global_step": 58,
+  "global_step": 87,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -108,6 +108,56 @@
       "eval_samples_per_second": 38.347,
       "eval_steps_per_second": 4.844,
       "step": 58
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.18255767226219177,
+      "learning_rate": 5.228676949903973e-05,
+      "loss": 0.3758,
+      "step": 60
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 0.18403491377830505,
+      "learning_rate": 4.46724750030062e-05,
+      "loss": 0.3703,
+      "step": 65
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.17554476857185364,
+      "learning_rate": 3.7181846109031005e-05,
+      "loss": 0.3369,
+      "step": 70
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.15826810896396637,
+      "learning_rate": 2.9988759642186097e-05,
+      "loss": 0.3342,
+      "step": 75
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.16748899221420288,
+      "learning_rate": 2.3260185700046294e-05,
+      "loss": 0.3578,
+      "step": 80
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 0.17350205779075623,
+      "learning_rate": 1.7152311845883095e-05,
+      "loss": 0.3359,
+      "step": 85
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "eval_loss": 0.39618706703186035,
+      "eval_runtime": 4.9273,
+      "eval_samples_per_second": 38.56,
+      "eval_steps_per_second": 4.871,
+      "step": 87
     }
   ],
   "logging_steps": 5,
@@ -127,7 +177,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1888293086389862e+17,
+  "total_flos": 1.78283317752234e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null