Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5705e7af05b27ed5ad80eeb0dae22c64e16bff581aaf95045a9a3c2b27d7f21
+oid sha256:f8a5c6f637a1a02dcc7ffaf9221661cd85b1333abef16fc488c6b215871a6822
 size 734275920

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e9ff05a88f38ae15dcd4e979b30ea6e420ba8aa2182c4adeee6f99722b56a5e
+oid sha256:52c3777540c9cd45951a7ac81a4e2bd9cf7e915ec27607f40e65e0ff5e617376
 size 1468687243

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac82640fafcec4ed8ce64644dd9dc382f3c142b4db92d38741fbda9a0d9aa763
+oid sha256:bab46455b81fe89286c0ac46f8274ae8d3f1816023d3983b6a1b462f39004a0d
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78b31fd960caa060732c4a15ecd9d246ac0b9616bb6fb26ea726c7f67997fc86
+oid sha256:47566dba2923569afde0e0a5ff4f2c437f9949274f917cc17b4936577ce63ab0
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af82b03ee66a3766dd3122ac1bd62daf83a9a7fc283f1df0579a5c40ddfef85e
+oid sha256:3324888af4fe870d448514f0b37d040d89d6aebdf2c735d51b734b3cbec36311
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c03e28169c2c00e7fe490c6e4aa7935441cb75b55aeeb2e3bed7d76862fc0206
+oid sha256:39b762073c3a91474269912b3ac897e24094100f62acadd0675372ec65e569e0
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce0140d9aef0aa9f9eff1f556146a51b440b5ca7bd8c9b6043e06890735ba840
+oid sha256:a4f51ed2846fc1924bdb38919225f48ce1c91d4b4e7f33ffeffcc034c81c3137
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5362ad2368a4ee2c667be0d3d1a656244a24515027b86ba737e31a78d06f0d5
+oid sha256:b3591e1beb54a633e255be3082ac8130dcb0fb2f006bfea6cd68b941d0fc906f
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:983aeb93e8b1ee3cd8c0ae6e23e1979775495cab73d44b292da46ee36a3343a5
+oid sha256:d023a9bb27873f11f312f75e42b2c4fe8003df9343f38bb24a6ae408e1b22e14
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d75816da70d512d83fb7557d7a5c717448c64bfd6d870f6115bed5b80d2a1e9f
+oid sha256:04aea28178ef35e5c4d53227bf7103f8d69d1ab082c35d47cd15905005ed5538
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97205df308aacb47c267cc39a5798ea630f3942b814c426e195523287df99abf
+oid sha256:49159d7a99a47c2c1201791bfa611289fd4e18fce3afc4b5f5914a4bf7836d08
 size 1465

last-checkpoint/trainer_state.json

@@ -11,158 +11,158 @@
   "log_history": [
     {
       "epoch": 0.002,
-      "grad_norm": 5.65625,
-      "learning_rate": 6.6e-05,
-      "loss": 73.6,
+      "grad_norm": 4.729869365692139,
+      "learning_rate": 0.00033,
+      "loss": 64.03521484375,
       "step": 100
     },
     {
       "epoch": 0.004,
-      "grad_norm": 3.375,
-      "learning_rate": 9.999976160274871e-05,
-      "loss": 57.8,
+      "grad_norm": 7.427474021911621,
+      "learning_rate": 0.0004999988080137436,
+      "loss": 50.4660400390625,
       "step": 200
     },
     {
       "epoch": 0.006,
-      "grad_norm": 4.71875,
-      "learning_rate": 9.999779565902032e-05,
-      "loss": 53.08,
+      "grad_norm": 499.43450927734375,
+      "learning_rate": 0.0004999889782951015,
+      "loss": 55.620224609375,
       "step": 300
     },
     {
       "epoch": 0.008,
-      "grad_norm": 5.0,
-      "learning_rate": 9.999384399149714e-05,
-      "loss": 51.56,
+      "grad_norm": 5.543099880218506,
+      "learning_rate": 0.0004999692199574857,
+      "loss": 55.512568359375,
       "step": 400
     },
     {
       "epoch": 0.01,
-      "grad_norm": 4.5,
-      "learning_rate": 9.998790675712448e-05,
-      "loss": 50.32,
+      "grad_norm": 3.913767099380493,
+      "learning_rate": 0.0004999395337856224,
+      "loss": 54.5164111328125,
       "step": 500
     },
     {
       "epoch": 0.012,
-      "grad_norm": 5.5,
-      "learning_rate": 9.99799841917069e-05,
-      "loss": 48.76,
+      "grad_norm": 3.7103848457336426,
+      "learning_rate": 0.0004998999209585345,
+      "loss": 48.3706103515625,
       "step": 600
     },
     {
       "epoch": 0.014,
-      "grad_norm": 6.65625,
-      "learning_rate": 9.997007660989881e-05,
-      "loss": 47.36,
+      "grad_norm": 27.09828758239746,
+      "learning_rate": 0.0004998503830494941,
+      "loss": 48.7948681640625,
       "step": 700
     },
     {
       "epoch": 0.016,
-      "grad_norm": 10.8125,
-      "learning_rate": 9.995818440519196e-05,
-      "loss": 47.32,
+      "grad_norm": 357.75579833984375,
+      "learning_rate": 0.0004997909220259598,
+      "loss": 47.264482421875,
       "step": 800
     },
     {
       "epoch": 0.018,
-      "grad_norm": 11.9375,
-      "learning_rate": 9.994430804989984e-05,
-      "loss": 46.28,
+      "grad_norm": 21.32952117919922,
+      "learning_rate": 0.0004997215402494993,
+      "loss": 46.945810546875,
       "step": 900
     },
     {
       "epoch": 0.02,
-      "grad_norm": 17.625,
-      "learning_rate": 9.992844809513897e-05,
-      "loss": 46.84,
+      "grad_norm": 1339.14501953125,
+      "learning_rate": 0.0004996422404756948,
+      "loss": 50.6924609375,
       "step": 1000
     },
     {
       "epoch": 0.02,
-      "eval_loss": 46.71875,
-      "eval_runtime": 9.8626,
-      "eval_samples_per_second": 0.406,
-      "eval_steps_per_second": 0.101,
+      "eval_loss": 62.66343307495117,
+      "eval_runtime": 11.6524,
+      "eval_samples_per_second": 1.716,
+      "eval_steps_per_second": 0.086,
       "step": 1000
     },
     {
       "epoch": 0.022,
-      "grad_norm": 406.0,
-      "learning_rate": 9.991060517080687e-05,
-      "loss": 47.04,
+      "grad_norm": 29.14947509765625,
+      "learning_rate": 0.0004995530258540343,
+      "loss": 49.645908203125,
       "step": 1100
     },
     {
       "epoch": 0.024,
-      "grad_norm": 278.0,
-      "learning_rate": 9.989077998555717e-05,
-      "loss": 47.24,
+      "grad_norm": 199.71112060546875,
+      "learning_rate": 0.0004994538999277859,
+      "loss": 46.0685693359375,
       "step": 1200
     },
     {
       "epoch": 0.026,
-      "grad_norm": 300.0,
-      "learning_rate": 9.986897332677145e-05,
-      "loss": 47.44,
+      "grad_norm": 26.30093002319336,
+      "learning_rate": 0.0004993448666338572,
+      "loss": 45.418486328125,
       "step": 1300
     },
     {
       "epoch": 0.028,
-      "grad_norm": 132.0,
-      "learning_rate": 9.984518606052792e-05,
-      "loss": 46.84,
+      "grad_norm": 72.15017700195312,
+      "learning_rate": 0.0004992259303026396,
+      "loss": 46.6232666015625,
       "step": 1400
     },
     {
       "epoch": 0.03,
-      "grad_norm": 336.0,
-      "learning_rate": 9.9819419131567e-05,
-      "loss": 47.36,
+      "grad_norm": 16.536649703979492,
+      "learning_rate": 0.0004990970956578351,
+      "loss": 52.807451171875,
       "step": 1500
     },
     {
       "epoch": 0.032,
-      "grad_norm": 161.0,
-      "learning_rate": 9.979167356325394e-05,
-      "loss": 48.16,
+      "grad_norm": 75235.25,
+      "learning_rate": 0.0004989583678162697,
+      "loss": 58.359990234375,
       "step": 1600
     },
     {
       "epoch": 0.034,
-      "grad_norm": 400.0,
-      "learning_rate": 9.976195045753797e-05,
-      "loss": 48.08,
+      "grad_norm": 7981.73974609375,
+      "learning_rate": 0.0004988097522876898,
+      "loss": 58.0731103515625,
       "step": 1700
     },
     {
       "epoch": 0.036,
-      "grad_norm": 372.0,
-      "learning_rate": 9.973025099490876e-05,
-      "loss": 48.12,
+      "grad_norm": 10026.5595703125,
+      "learning_rate": 0.0004986512549745438,
+      "loss": 59.05083984375,
       "step": 1800
     },
     {
       "epoch": 0.038,
-      "grad_norm": 209.0,
-      "learning_rate": 9.969657643434932e-05,
-      "loss": 48.92,
+      "grad_norm": 534.1368408203125,
+      "learning_rate": 0.0004984828821717466,
+      "loss": 54.8443310546875,
       "step": 1900
     },
     {
       "epoch": 0.04,
-      "grad_norm": 1192.0,
-      "learning_rate": 9.966092811328614e-05,
-      "loss": 47.6,
+      "grad_norm": 423.7434997558594,
+      "learning_rate": 0.0004983046405664306,
+      "loss": 54.6559326171875,
       "step": 2000
     },
     {
       "epoch": 0.04,
-      "eval_loss": 47.21875,
-      "eval_runtime": 0.2475,
-      "eval_samples_per_second": 16.161,
-      "eval_steps_per_second": 4.04,
+      "eval_loss": 55.864173889160156,
+      "eval_runtime": 1.8383,
+      "eval_samples_per_second": 10.88,
+      "eval_steps_per_second": 0.544,
       "step": 2000
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:018db098c009b077a596bcd57ca4359ea322e874799c144a100d3d03ea3ce145
+oid sha256:744f7f42a0433e89c0af056b3090bcf31492ca1b3769a40409cf21aea20f0c1f
 size 5201