Training in progress, step 160, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a3951e3588da4d12a28e9c1f4f7ff09ae0987de1e9e0842aebec5e0c9cb9404
+oid sha256:d8a051a97436cbb9ced7d9e533e00b6fc981dc733924f80205517ea188706c54
 size 28130688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d082f72679ad57bd0eee09f2ab2986fb84ba7847fa90ef843c2705e8b1e91719
+oid sha256:ba9ca81d0e648b9f245b287b59cac8a934e081397b8c14fb05b16f75f4007821
 size 28684730

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,
@@ -11,142 +11,186 @@
     {
       "epoch": 0.001183431952662722,
       "eval_loss": 6.91423225402832,
-      "eval_runtime": 2.3595,
-      "eval_samples_per_second": 636.584,
-      "eval_steps_per_second": 39.839,
+      "eval_runtime": 2.3165,
+      "eval_samples_per_second": 648.398,
+      "eval_steps_per_second": 40.579,
       "step": 1
     },
     {
       "epoch": 0.011834319526627219,
-      "grad_norm": 4016.0,
+      "grad_norm": 8640.0,
       "learning_rate": 1.6000000000000003e-05,
-      "loss": 6.6987,
+      "loss": 6.7118,
       "step": 10
     },
     {
       "epoch": 0.023668639053254437,
-      "grad_norm": 2384.0,
+      "grad_norm": 2368.0,
       "learning_rate": 3.2000000000000005e-05,
-      "loss": 6.731,
+      "loss": 6.7944,
       "step": 20
     },
     {
       "epoch": 0.023668639053254437,
-      "eval_loss": 6.770394802093506,
-      "eval_runtime": 2.3718,
-      "eval_samples_per_second": 633.275,
-      "eval_steps_per_second": 39.632,
+      "eval_loss": 6.8260087966918945,
+      "eval_runtime": 2.3051,
+      "eval_samples_per_second": 651.607,
+      "eval_steps_per_second": 40.78,
       "step": 20
     },
     {
       "epoch": 0.03550295857988166,
-      "grad_norm": 6144.0,
+      "grad_norm": 8096.0,
       "learning_rate": 4.8e-05,
-      "loss": 6.7332,
+      "loss": 6.762,
       "step": 30
     },
     {
       "epoch": 0.047337278106508875,
-      "grad_norm": 3520.0,
+      "grad_norm": 4160.0,
       "learning_rate": 6.400000000000001e-05,
-      "loss": 6.501,
+      "loss": 6.5961,
       "step": 40
     },
     {
       "epoch": 0.047337278106508875,
-      "eval_loss": 6.59076452255249,
-      "eval_runtime": 2.3851,
-      "eval_samples_per_second": 629.744,
-      "eval_steps_per_second": 39.411,
+      "eval_loss": 6.617987632751465,
+      "eval_runtime": 2.3313,
+      "eval_samples_per_second": 644.27,
+      "eval_steps_per_second": 40.321,
       "step": 40
     },
     {
       "epoch": 0.05917159763313609,
-      "grad_norm": 9280.0,
+      "grad_norm": 17920.0,
       "learning_rate": 8e-05,
-      "loss": 6.5837,
+      "loss": 6.4182,
       "step": 50
     },
     {
       "epoch": 0.07100591715976332,
-      "grad_norm": 4768.0,
+      "grad_norm": 13632.0,
       "learning_rate": 9.6e-05,
-      "loss": 7.248,
+      "loss": 6.5851,
       "step": 60
     },
     {
       "epoch": 0.07100591715976332,
-      "eval_loss": 7.2996826171875,
-      "eval_runtime": 2.4128,
-      "eval_samples_per_second": 622.511,
-      "eval_steps_per_second": 38.959,
+      "eval_loss": 6.849647045135498,
+      "eval_runtime": 2.5266,
+      "eval_samples_per_second": 594.476,
+      "eval_steps_per_second": 37.204,
       "step": 60
     },
     {
       "epoch": 0.08284023668639054,
-      "grad_norm": 4288.0,
+      "grad_norm": 11136.0,
       "learning_rate": 0.00011200000000000001,
-      "loss": 7.4279,
+      "loss": 7.1215,
       "step": 70
     },
     {
       "epoch": 0.09467455621301775,
-      "grad_norm": 4320.0,
+      "grad_norm": 13568.0,
       "learning_rate": 0.00012800000000000002,
-      "loss": 7.0818,
+      "loss": 6.9277,
       "step": 80
     },
     {
       "epoch": 0.09467455621301775,
-      "eval_loss": 7.198533535003662,
-      "eval_runtime": 2.3911,
-      "eval_samples_per_second": 628.164,
-      "eval_steps_per_second": 39.313,
+      "eval_loss": 7.1117143630981445,
+      "eval_runtime": 2.3547,
+      "eval_samples_per_second": 637.865,
+      "eval_steps_per_second": 39.92,
       "step": 80
     },
     {
       "epoch": 0.10650887573964497,
-      "grad_norm": 3488.0,
+      "grad_norm": 7520.0,
       "learning_rate": 0.000144,
-      "loss": 7.0218,
+      "loss": 6.9477,
       "step": 90
     },
     {
       "epoch": 0.11834319526627218,
-      "grad_norm": 5056.0,
+      "grad_norm": 5344.0,
       "learning_rate": 0.00016,
-      "loss": 7.4375,
+      "loss": 7.4897,
       "step": 100
     },
     {
       "epoch": 0.11834319526627218,
-      "eval_loss": 7.641583442687988,
-      "eval_runtime": 2.4227,
-      "eval_samples_per_second": 619.959,
-      "eval_steps_per_second": 38.799,
+      "eval_loss": 7.819643497467041,
+      "eval_runtime": 2.3681,
+      "eval_samples_per_second": 634.257,
+      "eval_steps_per_second": 39.694,
       "step": 100
     },
     {
       "epoch": 0.1301775147928994,
-      "grad_norm": 1712.0,
+      "grad_norm": 1944.0,
       "learning_rate": 0.00017600000000000002,
-      "loss": 7.8192,
+      "loss": 8.0353,
       "step": 110
     },
     {
       "epoch": 0.14201183431952663,
-      "grad_norm": 324.0,
+      "grad_norm": 386.0,
       "learning_rate": 0.000192,
-      "loss": 8.5739,
+      "loss": 8.3949,
       "step": 120
     },
     {
       "epoch": 0.14201183431952663,
-      "eval_loss": 9.108259201049805,
-      "eval_runtime": 2.4234,
-      "eval_samples_per_second": 619.802,
-      "eval_steps_per_second": 38.789,
+      "eval_loss": 8.92322063446045,
+      "eval_runtime": 2.2886,
+      "eval_samples_per_second": 656.309,
+      "eval_steps_per_second": 41.074,
       "step": 120
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 2752.0,
+      "learning_rate": 0.0001999978128380225,
+      "loss": 8.8096,
+      "step": 130
+    },
+    {
+      "epoch": 0.16568047337278108,
+      "grad_norm": 2208.0,
+      "learning_rate": 0.0001999803161162393,
+      "loss": 9.3893,
+      "step": 140
+    },
+    {
+      "epoch": 0.16568047337278108,
+      "eval_loss": 10.95390510559082,
+      "eval_runtime": 2.3845,
+      "eval_samples_per_second": 629.893,
+      "eval_steps_per_second": 39.421,
+      "step": 140
+    },
+    {
+      "epoch": 0.17751479289940827,
+      "grad_norm": 1104.0,
+      "learning_rate": 0.00019994532573409262,
+      "loss": 10.2318,
+      "step": 150
+    },
+    {
+      "epoch": 0.1893491124260355,
+      "grad_norm": 664.0,
+      "learning_rate": 0.00019989284781388617,
+      "loss": 8.9254,
+      "step": 160
+    },
+    {
+      "epoch": 0.1893491124260355,
+      "eval_loss": 9.343338966369629,
+      "eval_runtime": 2.3475,
+      "eval_samples_per_second": 639.824,
+      "eval_steps_per_second": 40.042,
+      "step": 160
     }
   ],
   "logging_steps": 10,
@@ -166,7 +210,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 180282263076864.0,
+  "total_flos": 240251415035904.0,
   "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:a6c7e7c5f21dbcaedc62ce8e58ac8c381dfbca0f0f8847ff8493ecb68e799bc5
+oid sha256:c733d91ae8e6c85156e620fe003f3edb50e80afe2abe62c2d021547d726d6f81
 size 6712