Training in progress, step 160, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1024b6f55ee5c34ec9f8f76a2fa6a5b777d86e51d383d39af071b2c0182b7fab
+oid sha256:567d9184e3928b4b69aa416b671aa81fcc29e93bf1011c74f506789b3f8674c0
 size 8227136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a04e77e83da80a91aa5e73a77d6102ee36778c17ba045c8482f28c6647d08975
+oid sha256:284c08ad0ac0ad17af937d6d7bd023ba1ab0e544888e98ab515244010e69e929
 size 8419438

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8717e6db6dad3bdb0d92afa70b8fbe0c4677a2360eab813a627812a62061fd4
+oid sha256:ca96cd8cea5e89c26f322ab0bc4569dd89f58599184456a2a043cfe41d0a9016
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6c7dfa9863eadd74540b95922e8cee67d3b691b168a951cb8b3349087d7a629
+oid sha256:3e1c8b411336f8c21c042cf34f54cd83fe460e6146fa041149703c71f00d1e7b
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7596c043bb61ec6ab94f537047f856762fd577107f970ea392238fff0ea6ef1
+oid sha256:9c588e7a6251848ca72003d225e2e8cf344e2b4645d7ce1e51f191dc1db88063
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:712dd66678ab2f0cf679625d414555daee92b448e39ad2db26b98722c1b424fc
+oid sha256:f5b050aa4a26eb700ebc404ec1ff62750644e1e3fa94786597f4b7eda4b17bfa
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bb08d77b3a8f33a22badf4599bdece3856ac2be5b489c3048c3951f5a13e4fd
+oid sha256:e397ffcf130e7acafde3d20cb6e16fdb641f8e06485f1c15d8ff4eb284addba3
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d84262c7d232955fd6ce9f416c4b38411017050149a8346d4ddba5d641d0b78f
+oid sha256:63e0a7403419853c906dc2a28ee5a75408f4aa4439daaf673dc94372a55a22d4
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:144141c670561050eb2f8450fb88edb4facad52016564e94dfc875ba7b564975
+oid sha256:e8f9663d63b5d724c82dcf4a32718ed3fc7be625d342141f353e8daafed1a8ab
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbe39dd1e728e6b0298971fe77b09b4d43dbe6b288ac55d64a2318e60f21229e
+oid sha256:e34e10848d2dbdc394eecb9997530b5e1ea02407c4d3d521c60cc28f7a872d18
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:416b2ea21de930aef02b3dd806b882963de9b98a0a8d9ff11b933cd6bf4116bc
+oid sha256:8f0c7ff54b85ffef1dcbffa5d8d256d7b7e02cf6f2a611b338e53d605c1ee098
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14201183431952663,
+  "epoch": 0.1893491124260355,
   "eval_steps": 20,
-  "global_step": 120,
+  "global_step": 160,
   "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": 3.4692,
-      "eval_samples_per_second": 432.957,
-      "eval_steps_per_second": 27.096,
+      "eval_runtime": 3.448,
+      "eval_samples_per_second": 435.611,
+      "eval_steps_per_second": 27.262,
       "step": 1
     },
     {
@@ -33,9 +33,9 @@
     {
       "epoch": 0.023668639053254437,
       "eval_loss": 11.763768196105957,
-      "eval_runtime": 3.458,
-      "eval_samples_per_second": 434.354,
-      "eval_steps_per_second": 27.183,
+      "eval_runtime": 3.4066,
+      "eval_samples_per_second": 440.914,
+      "eval_steps_per_second": 27.594,
       "step": 20
     },
     {
@@ -55,9 +55,9 @@
     {
       "epoch": 0.047337278106508875,
       "eval_loss": 11.76196575164795,
-      "eval_runtime": 3.4907,
-      "eval_samples_per_second": 430.288,
-      "eval_steps_per_second": 26.929,
+      "eval_runtime": 3.4379,
+      "eval_samples_per_second": 436.894,
+      "eval_steps_per_second": 27.342,
       "step": 40
     },
     {
@@ -77,9 +77,9 @@
     {
       "epoch": 0.07100591715976332,
       "eval_loss": 11.75584888458252,
-      "eval_runtime": 3.5046,
-      "eval_samples_per_second": 428.581,
-      "eval_steps_per_second": 26.822,
+      "eval_runtime": 3.6091,
+      "eval_samples_per_second": 416.17,
+      "eval_steps_per_second": 26.045,
       "step": 60
     },
     {
@@ -99,9 +99,9 @@
     {
       "epoch": 0.09467455621301775,
       "eval_loss": 11.732006072998047,
-      "eval_runtime": 3.435,
-      "eval_samples_per_second": 437.26,
-      "eval_steps_per_second": 27.365,
+      "eval_runtime": 3.4157,
+      "eval_samples_per_second": 439.736,
+      "eval_steps_per_second": 27.52,
       "step": 80
     },
     {
@@ -121,9 +121,9 @@
     {
       "epoch": 0.11834319526627218,
       "eval_loss": 11.619158744812012,
-      "eval_runtime": 3.4761,
-      "eval_samples_per_second": 432.097,
-      "eval_steps_per_second": 27.042,
+      "eval_runtime": 3.4756,
+      "eval_samples_per_second": 432.159,
+      "eval_steps_per_second": 27.046,
       "step": 100
     },
     {
@@ -143,10 +143,54 @@
     {
       "epoch": 0.14201183431952663,
       "eval_loss": 11.44636344909668,
-      "eval_runtime": 3.5054,
-      "eval_samples_per_second": 428.478,
-      "eval_steps_per_second": 26.816,
+      "eval_runtime": 3.4158,
+      "eval_samples_per_second": 439.727,
+      "eval_steps_per_second": 27.52,
       "step": 120
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 0.51171875,
+      "learning_rate": 0.0001999978128380225,
+      "loss": 11.404,
+      "step": 130
+    },
+    {
+      "epoch": 0.16568047337278108,
+      "grad_norm": 0.41015625,
+      "learning_rate": 0.0001999803161162393,
+      "loss": 11.3215,
+      "step": 140
+    },
+    {
+      "epoch": 0.16568047337278108,
+      "eval_loss": 11.274709701538086,
+      "eval_runtime": 3.4634,
+      "eval_samples_per_second": 433.675,
+      "eval_steps_per_second": 27.141,
+      "step": 140
+    },
+    {
+      "epoch": 0.17751479289940827,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.00019994532573409262,
+      "loss": 11.2396,
+      "step": 150
+    },
+    {
+      "epoch": 0.1893491124260355,
+      "grad_norm": 0.4296875,
+      "learning_rate": 0.00019989284781388617,
+      "loss": 11.1631,
+      "step": 160
+    },
+    {
+      "epoch": 0.1893491124260355,
+      "eval_loss": 11.122227668762207,
+      "eval_runtime": 3.3962,
+      "eval_samples_per_second": 442.264,
+      "eval_steps_per_second": 27.678,
+      "step": 160
     }
   ],
   "logging_steps": 10,
@@ -166,7 +210,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 48660815544320.0,
+  "total_flos": 64864208814080.0,
   "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:da5eaeeb367bdae382027a540f1ec8826c3d86c4b3a677fe0d03ba38e9ce29fa
+oid sha256:466b98a6feb81b94710080ff6fc343968a149c28f9b50abf17adb261ed2cad15
 size 6904