Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b82d700c79a62668f142c896d9d3aba0d517086975680b84a5397ba3207a2765
+oid sha256:1f395867bd1951a22243a862ef6aa32ffcfd693937f549b6ed90a80377416358
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d914b2bb904da7ee9727282e6618e1afcf3f7ebdd433b4f6db70715a6b21eb18
+oid sha256:077533fa4868541d75c56f96cd38795d4c933c27e66b383d37da2e59dc0819d2
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54cdfa6b1013c49fd23e9efce055ce2c1e5c06692714ab261dc5b6f5af5ec63b
+oid sha256:2e503237893a0f22e96f4b13c303b8c86e4e3120bc4b4c8149a972e355144067
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de129e14f7f6774719d46c01d0b8e337151f15f042d9f9e392f41b9467b1dbe7
+oid sha256:4943d7967984a915923b302429483ed1d2abb00e536614a585f4518b6ad55921
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c4530efea70c3d333e5d53408519414e60590859a793a8c22ccf058f1e72ef3
+oid sha256:76fc857bbc7194422d78f0d2e93c06a3808ad523f824c01c5ad732b935fcdeb0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5eb2e8a04d21826264e2557e2eb80b9defae874ff06988e6da91f1f1db66f01
+oid sha256:3778fb658a5a585908f1a47102fc328fc177ce0f5c0c7238d2772f575441dcd7
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2696326255476913,
+  "epoch": 0.5392652510953826,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 22.31,
       "eval_steps_per_second": 5.801,
       "step": 25
+    },
+    {
+      "epoch": 0.2804179305695989,
+      "grad_norm": 2.680741548538208,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 4.7656,
+      "step": 26
+    },
+    {
+      "epoch": 0.29120323559150657,
+      "grad_norm": 1.608992099761963,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 4.0335,
+      "step": 27
+    },
+    {
+      "epoch": 0.30198854061341424,
+      "grad_norm": 1.2295485734939575,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 3.6691,
+      "step": 28
+    },
+    {
+      "epoch": 0.3127738456353219,
+      "grad_norm": 0.9207251071929932,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 3.3744,
+      "step": 29
+    },
+    {
+      "epoch": 0.3235591506572295,
+      "grad_norm": 1.0553677082061768,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.0976,
+      "step": 30
+    },
+    {
+      "epoch": 0.3343444556791372,
+      "grad_norm": 1.3266836404800415,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.8384,
+      "step": 31
+    },
+    {
+      "epoch": 0.34512976070104484,
+      "grad_norm": 1.3463107347488403,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.6958,
+      "step": 32
+    },
+    {
+      "epoch": 0.35591506572295245,
+      "grad_norm": 1.297961711883545,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.6287,
+      "step": 33
+    },
+    {
+      "epoch": 0.3667003707448601,
+      "grad_norm": 1.0394666194915771,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.5336,
+      "step": 34
+    },
+    {
+      "epoch": 0.3774856757667678,
+      "grad_norm": 0.8954881429672241,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.5946,
+      "step": 35
+    },
+    {
+      "epoch": 0.38827098078867545,
+      "grad_norm": 0.7060102224349976,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.4813,
+      "step": 36
+    },
+    {
+      "epoch": 0.39905628581058306,
+      "grad_norm": 0.40887507796287537,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 2.3328,
+      "step": 37
+    },
+    {
+      "epoch": 0.4098415908324907,
+      "grad_norm": 2.2469213008880615,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 4.5164,
+      "step": 38
+    },
+    {
+      "epoch": 0.4206268958543984,
+      "grad_norm": 2.1526901721954346,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 3.9944,
+      "step": 39
+    },
+    {
+      "epoch": 0.43141220087630605,
+      "grad_norm": 1.8147079944610596,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 3.5679,
+      "step": 40
+    },
+    {
+      "epoch": 0.44219750589821366,
+      "grad_norm": 1.4103679656982422,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 3.2538,
+      "step": 41
+    },
+    {
+      "epoch": 0.4529828109201213,
+      "grad_norm": 1.1426249742507935,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.9928,
+      "step": 42
+    },
+    {
+      "epoch": 0.463768115942029,
+      "grad_norm": 0.9264675974845886,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.8695,
+      "step": 43
+    },
+    {
+      "epoch": 0.47455342096393666,
+      "grad_norm": 0.6036688089370728,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.7405,
+      "step": 44
+    },
+    {
+      "epoch": 0.48533872598584427,
+      "grad_norm": 0.3461301028728485,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.5788,
+      "step": 45
+    },
+    {
+      "epoch": 0.49612403100775193,
+      "grad_norm": 0.3648104667663574,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.5385,
+      "step": 46
+    },
+    {
+      "epoch": 0.5069093360296596,
+      "grad_norm": 0.40517136454582214,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.495,
+      "step": 47
+    },
+    {
+      "epoch": 0.5176946410515673,
+      "grad_norm": 0.41946572065353394,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.5453,
+      "step": 48
+    },
+    {
+      "epoch": 0.5284799460734749,
+      "grad_norm": 0.4738365709781647,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.3179,
+      "step": 49
+    },
+    {
+      "epoch": 0.5392652510953826,
+      "grad_norm": 0.3218916356563568,
+      "learning_rate": 1e-05,
+      "loss": 2.4055,
+      "step": 50
+    },
+    {
+      "epoch": 0.5392652510953826,
+      "eval_loss": 2.980289936065674,
+      "eval_runtime": 2.2402,
+      "eval_samples_per_second": 22.32,
+      "eval_steps_per_second": 5.803,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,12 +395,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.81197642825728e+16,
+  "total_flos": 1.5594001969184768e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null