Training in progress, step 2000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6524a89004f895ebb40c163fb000120939b69136f746115239717cf901755d3e
+oid sha256:482d033c346824d7aae735e0a30cb3e8c41e0c5f81d53f22ebe44258c3425d26
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d455c6c55f12ede83a7170a5f2cf7f7d3b794ba66628ebfc430a5dcafdf7926
+oid sha256:2d011aeead383547fdef45678632afedc62a2962158c32e8cb4ce8e90d692ad0
 size 1540661735

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aab1a00b4d9b32049303ef4af942ff14a8e5e82dd0b87eb74624773875cbfec6
+oid sha256:6b1991cc99e86c95e5ef139f6421894a5757fd1b892dab95840668814509c4cb
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c8e5122a2511d9698fdb40ad4c5e9dba86073caa4528bb29f64b0c2db36211e
+oid sha256:28158218281a80eaa5c1e06ab030551152161ff67e14ea3969da4953f1446edf
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53292cfa81423e3fba0ca0eaeede4a19951968275bcc1cc60812a11cce946cc0
+oid sha256:a8532a948bb3a20cc440fe262d4aed275beeed50de257f08279070a99339d577
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01fd44eef4683e280cb94994fe3453eb9c8fba26a61d8293ecd10ee8d79014a0
+oid sha256:65cb6f2cd04253d39e6e8a66ab2ad12b1df978d3afeb82f6ffaa53f610295f4e
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:767578033895723160df2c072f5a3b9649854a2a5038024ad00d035a11ada228
+oid sha256:133b88ea6938699834d9214a043b01ec9753babf93f7342c4d965c731f9ca3fa
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73a2c821a372ebcef6a65ed2212135f44619cf13f3a82318285c44a3c0e93134
+oid sha256:2569b59cbd12a55fc23ea1de67cfa40d8ce399abd6061b317cf5cd83d9f589ad
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31bc6ada37be16d9b94ba875e83129ab0a1becdb21d7e0dd9569e43988e69d1a
+oid sha256:5ca0a826dbc599964473aabc25a5eff43d974a031a177512095eff6c593a4a29
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c264b2b347d872eccfee31d56f07535129be708a2786a1f9335f4447665abd9
+oid sha256:799cf010f91f5055e7bac3df01758db699f980ad15cd9440967d7e87ae060f04
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08b58c9897520381532a491e6de506782301d0c07a05fa690317ee93b73255c6
+oid sha256:32e12c26fc7187e12c6806b82566389f8bad1946f6607f89dddf407ce49f8742
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5,
+  "epoch": 0.6666666666666666,
   "eval_steps": 250,
-  "global_step": 1500,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": false,
   "is_world_process_zero": true,
@@ -272,6 +272,94 @@
       "eval_samples_per_second": 16.938,
       "eval_steps_per_second": 0.542,
       "step": 1500
+    },
+    {
+      "epoch": 0.5166666666666667,
+      "grad_norm": 389.8416748046875,
+      "learning_rate": 0.00020573124401513043,
+      "loss": 1758.96953125,
+      "step": 1550
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 650.4288330078125,
+      "learning_rate": 0.00019470951376409043,
+      "loss": 1757.52515625,
+      "step": 1600
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 847.1361694335938,
+      "learning_rate": 0.0001837038505458685,
+      "loss": 1753.61921875,
+      "step": 1650
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 488.51898193359375,
+      "learning_rate": 0.00017274767819793914,
+      "loss": 1753.27640625,
+      "step": 1700
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 306.435791015625,
+      "learning_rate": 0.00016187427025563068,
+      "loss": 1751.60140625,
+      "step": 1750
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "eval_accuracy": 0.17743304007820138,
+      "eval_loss": 57.92564392089844,
+      "eval_runtime": 7.3883,
+      "eval_samples_per_second": 16.919,
+      "eval_steps_per_second": 0.541,
+      "step": 1750
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 362.682373046875,
+      "learning_rate": 0.0001511166489014914,
+      "loss": 1750.76390625,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6166666666666667,
+      "grad_norm": 428.01727294921875,
+      "learning_rate": 0.00014050748467800728,
+      "loss": 1748.945625,
+      "step": 1850
+    },
+    {
+      "epoch": 0.6333333333333333,
+      "grad_norm": 572.7185668945312,
+      "learning_rate": 0.0001300789972682373,
+      "loss": 1747.49421875,
+      "step": 1900
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 404.1789855957031,
+      "learning_rate": 0.00011986285764569589,
+      "loss": 1747.0315625,
+      "step": 1950
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 516.892578125,
+      "learning_rate": 0.00010989009189064648,
+      "loss": 1745.6384375,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_accuracy": 0.17842521994134897,
+      "eval_loss": 57.703956604003906,
+      "eval_runtime": 8.2449,
+      "eval_samples_per_second": 15.161,
+      "eval_steps_per_second": 0.485,
+      "step": 2000
     }
   ],
   "logging_steps": 50,