Training in progress, step 120, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4e3ef39237376eea0610039942644047b455d4d22b8c4a09798da77ce164f7d
+oid sha256:1024b6f55ee5c34ec9f8f76a2fa6a5b777d86e51d383d39af071b2c0182b7fab
 size 8227136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96f5b0710e3071b34c45b0203dbe7c308548c652473fc24a00576741de41a01e
+oid sha256:a04e77e83da80a91aa5e73a77d6102ee36778c17ba045c8482f28c6647d08975
 size 8419438

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,
@@ -11,9 +11,9 @@
     {
       "epoch": 0.001183431952662722,
       "eval_loss": 11.76406478881836,
-      "eval_runtime": 3.5088,
-      "eval_samples_per_second": 428.069,
-      "eval_steps_per_second": 26.79,
+      "eval_runtime": 3.4692,
+      "eval_samples_per_second": 432.957,
+      "eval_steps_per_second": 27.096,
       "step": 1
     },
     {
@@ -33,9 +33,9 @@
     {
       "epoch": 0.023668639053254437,
       "eval_loss": 11.763768196105957,
-      "eval_runtime": 3.4457,
-      "eval_samples_per_second": 435.899,
-      "eval_steps_per_second": 27.28,
+      "eval_runtime": 3.458,
+      "eval_samples_per_second": 434.354,
+      "eval_steps_per_second": 27.183,
       "step": 20
     },
     {
@@ -55,9 +55,9 @@
     {
       "epoch": 0.047337278106508875,
       "eval_loss": 11.76196575164795,
-      "eval_runtime": 3.4655,
-      "eval_samples_per_second": 433.411,
-      "eval_steps_per_second": 27.124,
+      "eval_runtime": 3.4907,
+      "eval_samples_per_second": 430.288,
+      "eval_steps_per_second": 26.929,
       "step": 40
     },
     {
@@ -77,9 +77,9 @@
     {
       "epoch": 0.07100591715976332,
       "eval_loss": 11.75584888458252,
-      "eval_runtime": 3.423,
-      "eval_samples_per_second": 438.792,
-      "eval_steps_per_second": 27.461,
+      "eval_runtime": 3.5046,
+      "eval_samples_per_second": 428.581,
+      "eval_steps_per_second": 26.822,
       "step": 60
     },
     {
@@ -99,10 +99,54 @@
     {
       "epoch": 0.09467455621301775,
       "eval_loss": 11.732006072998047,
-      "eval_runtime": 3.5178,
-      "eval_samples_per_second": 426.968,
-      "eval_steps_per_second": 26.721,
+      "eval_runtime": 3.435,
+      "eval_samples_per_second": 437.26,
+      "eval_steps_per_second": 27.365,
       "step": 80
+    },
+    {
+      "epoch": 0.10650887573964497,
+      "grad_norm": 0.5,
+      "learning_rate": 0.000144,
+      "loss": 11.7175,
+      "step": 90
+    },
+    {
+      "epoch": 0.11834319526627218,
+      "grad_norm": 0.9140625,
+      "learning_rate": 0.00016,
+      "loss": 11.6553,
+      "step": 100
+    },
+    {
+      "epoch": 0.11834319526627218,
+      "eval_loss": 11.619158744812012,
+      "eval_runtime": 3.4761,
+      "eval_samples_per_second": 432.097,
+      "eval_steps_per_second": 27.042,
+      "step": 100
+    },
+    {
+      "epoch": 0.1301775147928994,
+      "grad_norm": 0.453125,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 11.5808,
+      "step": 110
+    },
+    {
+      "epoch": 0.14201183431952663,
+      "grad_norm": 0.36328125,
+      "learning_rate": 0.000192,
+      "loss": 11.4893,
+      "step": 120
+    },
+    {
+      "epoch": 0.14201183431952663,
+      "eval_loss": 11.44636344909668,
+      "eval_runtime": 3.5054,
+      "eval_samples_per_second": 428.478,
+      "eval_steps_per_second": 26.816,
+      "step": 120
     }
   ],
   "logging_steps": 10,
@@ -122,7 +166,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 32457422274560.0,
+  "total_flos": 48660815544320.0,
   "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 sha256:0fd36bb67789118be3840a4bf1eff67232f65f9c7663f5cf9ffc3866191dc251
+oid sha256:da5eaeeb367bdae382027a540f1ec8826c3d86c4b3a677fe0d03ba38e9ce29fa
 size 6904