Training in progress, step 120, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e55c29b985fa1cc18b56f46733fd17a718d9f1690457d49a95bf9bec674c4578
+oid sha256:1a615b73ef13d55b893bfe6b4f001d26c5b34460f5be6922e5b227dc2c371b9b
 size 493963120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7103f530aba0fb0ef51b64ec9539a60845b28b1c16ad8188b2f93e1ffd1309c
+oid sha256:c2912a776a3ba3d591ebe9d16148710ec3dbfe56c52df9cc26ad15a95c574fec
 size 501746490

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9906b173df03663b222bd12a0e83af5aaa020a12d4ad3b4f49197437057c696b
+oid sha256:c8717e6db6dad3bdb0d92afa70b8fbe0c4677a2360eab813a627812a62061fd4
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7bf7c9d7fc97693b96ee7a514a4d88728c8624bc298bf36b68fd64703b6ce38
+oid sha256:b6c7dfa9863eadd74540b95922e8cee67d3b691b168a951cb8b3349087d7a629
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cba90fd12df41e2a3afe0aa9bdbcb01ea64e70a37cf6d3f1b6f819528d9eedb2
+oid sha256:e7596c043bb61ec6ab94f537047f856762fd577107f970ea392238fff0ea6ef1
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f677ceac78336a23596ad2dfff49115dd4f2798e6c718f3d9a417036aecc78d
+oid sha256:712dd66678ab2f0cf679625d414555daee92b448e39ad2db26b98722c1b424fc
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b66cb249efdcbeae07a93ab18308b0dad6ab1938b8cda1783930dd7ca16e400
+oid sha256:6bb08d77b3a8f33a22badf4599bdece3856ac2be5b489c3048c3951f5a13e4fd
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a32fc5b45250ceb9579d6cdb22a9de146f720394a5fb1a94da8455a621d02420
+oid sha256:d84262c7d232955fd6ce9f416c4b38411017050149a8346d4ddba5d641d0b78f
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdaa72ece53788894cbf7d690659103118093c50cbe7ebcc4ad29ce77864063c
+oid sha256:144141c670561050eb2f8450fb88edb4facad52016564e94dfc875ba7b564975
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e1077a981f60bb0c73ac0edeec6a361fda9845f8d5236c4bc77fda2663cf80d
+oid sha256:dbe39dd1e728e6b0298971fe77b09b4d43dbe6b288ac55d64a2318e60f21229e
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fce9536ff5f950cceb3fa69a1e2f266b5d6de86d1ea82239294fb327d0664db
+oid sha256:416b2ea21de930aef02b3dd806b882963de9b98a0a8d9ff11b933cd6bf4116bc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09467455621301775,
+  "epoch": 0.14201183431952663,
   "eval_steps": 20,
-  "global_step": 80,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,98 +11,142 @@
     {
       "epoch": 0.001183431952662722,
       "eval_loss": 10.566378593444824,
-      "eval_runtime": 2.0211,
-      "eval_samples_per_second": 743.163,
-      "eval_steps_per_second": 46.51,
+      "eval_runtime": 1.9917,
+      "eval_samples_per_second": 754.145,
+      "eval_steps_per_second": 47.197,
       "step": 1
     },
     {
       "epoch": 0.011834319526627219,
-      "grad_norm": 6.454888820648193,
+      "grad_norm": 6.460504531860352,
       "learning_rate": 1.6000000000000003e-05,
-      "loss": 10.5688,
+      "loss": 10.5689,
       "step": 10
     },
     {
       "epoch": 0.023668639053254437,
-      "grad_norm": 4.221368789672852,
+      "grad_norm": 4.217194557189941,
       "learning_rate": 3.2000000000000005e-05,
       "loss": 10.5293,
       "step": 20
     },
     {
       "epoch": 0.023668639053254437,
-      "eval_loss": 10.471421241760254,
-      "eval_runtime": 2.0335,
-      "eval_samples_per_second": 738.623,
-      "eval_steps_per_second": 46.225,
+      "eval_loss": 10.470946311950684,
+      "eval_runtime": 1.962,
+      "eval_samples_per_second": 765.537,
+      "eval_steps_per_second": 47.91,
       "step": 20
     },
     {
       "epoch": 0.03550295857988166,
-      "grad_norm": 7.107753753662109,
+      "grad_norm": 7.088407039642334,
       "learning_rate": 4.8e-05,
-      "loss": 10.3814,
+      "loss": 10.3793,
       "step": 30
     },
     {
       "epoch": 0.047337278106508875,
-      "grad_norm": 4.7665696144104,
+      "grad_norm": 4.761963844299316,
       "learning_rate": 6.400000000000001e-05,
-      "loss": 9.9244,
+      "loss": 9.924,
       "step": 40
     },
     {
       "epoch": 0.047337278106508875,
-      "eval_loss": 9.445327758789062,
-      "eval_runtime": 2.0204,
-      "eval_samples_per_second": 743.435,
-      "eval_steps_per_second": 46.527,
+      "eval_loss": 9.448060035705566,
+      "eval_runtime": 2.0352,
+      "eval_samples_per_second": 738.016,
+      "eval_steps_per_second": 46.187,
       "step": 40
     },
     {
       "epoch": 0.05917159763313609,
-      "grad_norm": 5.4297027587890625,
+      "grad_norm": 5.449029922485352,
       "learning_rate": 8e-05,
-      "loss": 8.9648,
+      "loss": 8.9682,
       "step": 50
     },
     {
       "epoch": 0.07100591715976332,
-      "grad_norm": 2.0724003314971924,
+      "grad_norm": 2.087066173553467,
       "learning_rate": 9.6e-05,
-      "loss": 8.2558,
+      "loss": 8.2576,
       "step": 60
     },
     {
       "epoch": 0.07100591715976332,
-      "eval_loss": 7.835418224334717,
-      "eval_runtime": 6.0797,
-      "eval_samples_per_second": 247.052,
-      "eval_steps_per_second": 15.461,
+      "eval_loss": 7.836277961730957,
+      "eval_runtime": 2.012,
+      "eval_samples_per_second": 746.529,
+      "eval_steps_per_second": 46.72,
       "step": 60
     },
     {
       "epoch": 0.08284023668639054,
-      "grad_norm": 1.815529227256775,
+      "grad_norm": 1.812099575996399,
       "learning_rate": 0.00011200000000000001,
-      "loss": 7.658,
+      "loss": 7.6596,
       "step": 70
     },
     {
       "epoch": 0.09467455621301775,
-      "grad_norm": 2.478553295135498,
+      "grad_norm": 2.425971269607544,
       "learning_rate": 0.00012800000000000002,
-      "loss": 7.4762,
+      "loss": 7.4757,
       "step": 80
     },
     {
       "epoch": 0.09467455621301775,
-      "eval_loss": 7.448663711547852,
-      "eval_runtime": 2.0159,
-      "eval_samples_per_second": 745.071,
-      "eval_steps_per_second": 46.629,
+      "eval_loss": 7.445075988769531,
+      "eval_runtime": 2.0477,
+      "eval_samples_per_second": 733.507,
+      "eval_steps_per_second": 45.905,
       "step": 80
+    },
+    {
+      "epoch": 0.10650887573964497,
+      "grad_norm": 1.7427077293395996,
+      "learning_rate": 0.000144,
+      "loss": 7.4227,
+      "step": 90
+    },
+    {
+      "epoch": 0.11834319526627218,
+      "grad_norm": 5.246922492980957,
+      "learning_rate": 0.00016,
+      "loss": 7.2513,
+      "step": 100
+    },
+    {
+      "epoch": 0.11834319526627218,
+      "eval_loss": 7.342855930328369,
+      "eval_runtime": 1.997,
+      "eval_samples_per_second": 752.143,
+      "eval_steps_per_second": 47.072,
+      "step": 100
+    },
+    {
+      "epoch": 0.1301775147928994,
+      "grad_norm": 2.3408617973327637,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 7.3941,
+      "step": 110
+    },
+    {
+      "epoch": 0.14201183431952663,
+      "grad_norm": 2.138099431991577,
+      "learning_rate": 0.000192,
+      "loss": 7.1604,
+      "step": 120
+    },
+    {
+      "epoch": 0.14201183431952663,
+      "eval_loss": 7.194538593292236,
+      "eval_runtime": 1.9979,
+      "eval_samples_per_second": 751.783,
+      "eval_steps_per_second": 47.049,
+      "step": 120
     }
   ],
   "logging_steps": 10,
@@ -122,7 +166,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3374230997565440.0,
+  "total_flos": 5058714486702080.0,
   "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:bed78fd5996b9487484b47ba579fb5de2f0cc969aa32dc5681ad0a64670cef49
+oid sha256:01e4bd870199f946b0dde37c8d3c5b2ff41c0ebf5f378b5c9bc1cee4d33e12ad
 size 6712