Training in progress, step 80, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd1ab77025bc13ba8fd3a3ab33e66cd3d3895d274cfd19f5984b2f7fd28ebd37
+oid sha256:54d9635b7f594b29c34b9769bf5efec652a8931cb752214e49ff339c5ba89e21
 size 19745440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1732af4087baee42ae033819410e1e99af4ef26905cae47af0aa978accae2e71
+oid sha256:b7ec7187e6c03e10a7177434e622da4c4dd0fe596e67f4d00d169946e002df0f
 size 21069498

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0df10be429c2412198f2c4c684866a8c921cbd0d9ee4c865077476da07bda410
+oid sha256:9906b173df03663b222bd12a0e83af5aaa020a12d4ad3b4f49197437057c696b
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b14d8363b71c1e824421bf14a513f0f951f1c6c9b9494dcedc75b3fa1fecea91
+oid sha256:b7bf7c9d7fc97693b96ee7a514a4d88728c8624bc298bf36b68fd64703b6ce38
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0d27a8e9aed69fdd3b729f8cbf6300af5e0e26e9226d0e2307b0cf80aff9030
+oid sha256:cba90fd12df41e2a3afe0aa9bdbcb01ea64e70a37cf6d3f1b6f819528d9eedb2
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23de9e35ad029c7a59ff383920fe892474d8f295c2e2f82ec3e6f109f3f96960
+oid sha256:3f677ceac78336a23596ad2dfff49115dd4f2798e6c718f3d9a417036aecc78d
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50724f43561b5c511c4e37bb1b8ec7e620ff22332c4f39576452e56a9e02d18d
+oid sha256:1b66cb249efdcbeae07a93ab18308b0dad6ab1938b8cda1783930dd7ca16e400
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f8d108db37b78249e3b0beb22f6120e06fd369dd9fbaa19526994e040db5f9d
+oid sha256:a32fc5b45250ceb9579d6cdb22a9de146f720394a5fb1a94da8455a621d02420
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e62597393912992a3de2b36aa1663274b75b96f6525f5504e64377c5049c51e
+oid sha256:bdaa72ece53788894cbf7d690659103118093c50cbe7ebcc4ad29ce77864063c
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b1f0a5c61bcbceb46a2a335e00a59c951081a94126a8ae4cc9a9102e012eb65
+oid sha256:2e1077a981f60bb0c73ac0edeec6a361fda9845f8d5236c4bc77fda2663cf80d
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea54818dbc15bd81d4941b71d5e2806c555d1a733f768c00c5f1a670e0a08fb1
+oid sha256:6fce9536ff5f950cceb3fa69a1e2f266b5d6de86d1ea82239294fb327d0664db
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.047337278106508875,
+  "epoch": 0.09467455621301775,
   "eval_steps": 20,
-  "global_step": 40,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,9 +11,9 @@
     {
       "epoch": 0.001183431952662722,
       "eval_loss": 11.93152904510498,
-      "eval_runtime": 4.3808,
-      "eval_samples_per_second": 342.861,
-      "eval_steps_per_second": 21.457,
+      "eval_runtime": 4.308,
+      "eval_samples_per_second": 348.651,
+      "eval_steps_per_second": 21.82,
       "step": 1
     },
     {
@@ -33,9 +33,9 @@
     {
       "epoch": 0.023668639053254437,
       "eval_loss": 11.930181503295898,
-      "eval_runtime": 4.2798,
-      "eval_samples_per_second": 350.949,
-      "eval_steps_per_second": 21.963,
+      "eval_runtime": 4.2088,
+      "eval_samples_per_second": 356.87,
+      "eval_steps_per_second": 22.334,
       "step": 20
     },
     {
@@ -55,10 +55,54 @@
     {
       "epoch": 0.047337278106508875,
       "eval_loss": 11.922493934631348,
-      "eval_runtime": 4.3258,
-      "eval_samples_per_second": 347.218,
-      "eval_steps_per_second": 21.73,
+      "eval_runtime": 4.1897,
+      "eval_samples_per_second": 358.499,
+      "eval_steps_per_second": 22.436,
       "step": 40
+    },
+    {
+      "epoch": 0.05917159763313609,
+      "grad_norm": 0.8674926161766052,
+      "learning_rate": 8e-05,
+      "loss": 11.9178,
+      "step": 50
+    },
+    {
+      "epoch": 0.07100591715976332,
+      "grad_norm": 0.7298563718795776,
+      "learning_rate": 9.6e-05,
+      "loss": 11.9053,
+      "step": 60
+    },
+    {
+      "epoch": 0.07100591715976332,
+      "eval_loss": 11.886744499206543,
+      "eval_runtime": 4.2071,
+      "eval_samples_per_second": 357.015,
+      "eval_steps_per_second": 22.343,
+      "step": 60
+    },
+    {
+      "epoch": 0.08284023668639054,
+      "grad_norm": 0.8911345601081848,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 11.8688,
+      "step": 70
+    },
+    {
+      "epoch": 0.09467455621301775,
+      "grad_norm": 0.7649126052856445,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 11.7895,
+      "step": 80
+    },
+    {
+      "epoch": 0.09467455621301775,
+      "eval_loss": 11.73801040649414,
+      "eval_runtime": 4.214,
+      "eval_samples_per_second": 356.427,
+      "eval_steps_per_second": 22.306,
+      "step": 80
     }
   ],
   "logging_steps": 10,
@@ -78,7 +122,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 39525514477568.0,
+  "total_flos": 78927896772608.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b925c4aa24e9ed00a85109bf16795e4125cfa4c22e502965ecc2e11808027d4b
+oid sha256:6ac465c00ce11e18121baa7be0570d8e78b7ef53f3f78dd8fb2630a4bc3e7a21
 size 6840