Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eec6ae3c232115c0c2fe4bcf646b1c03138328548b645022df7b55df2d6ff03b
+oid sha256:bcc177d71a1506005267437007f2de8d24b91691c13a50b732ea2bcf9fe2581f
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c8dc5c30771f73079678db63765b219aafca9ea4b8e33ef2987d0d846fa62d3
+oid sha256:acb87da978e2dad13433319692c27084c166b313f922269425e1c29be9ff602b
 size 1386414411

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7864fb6e928e45d4215a1ae96eab6e34cbc82f54e4a38e3cf2e1449f98239105
+oid sha256:7578bdc324f9e75df38586eb586132281169978ccdfb68af7c97dfe72a3c31b4
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb8ff3d7c5e846455471242a9719dd9767ec3729631e3efca61eaecbd0ad4ee7
+oid sha256:6ffeaed815dfe24a3d4d30e6928de6e80034c94a6e68899611f9c7a0a75684d5
 size 14917

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:561e0049aa6e5e793844e867537a9c947ef9ba1ad03fe6ba44d328d1dffc9702
+oid sha256:ead4bfc2097774b0bab8635cdb6eefc7edb67d58c75bf9f6514bf7d08d200842
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.26666666666666666,
+  "epoch": 0.4,
   "eval_steps": 1000,
-  "global_step": 4000,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -324,6 +324,164 @@
       "eval_samples_per_second": 7.638,
       "eval_steps_per_second": 0.382,
       "step": 4000
+    },
+    {
+      "epoch": 0.2733333333333333,
+      "grad_norm": 1.0034714937210083,
+      "learning_rate": 0.00034791880006519195,
+      "loss": 9.250709838867188,
+      "step": 4100
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.2436392307281494,
+      "learning_rate": 0.00034491543277181,
+      "loss": 9.246346435546876,
+      "step": 4200
+    },
+    {
+      "epoch": 0.2866666666666667,
+      "grad_norm": 1.180080771446228,
+      "learning_rate": 0.00034184163395788343,
+      "loss": 9.188368530273438,
+      "step": 4300
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 1.0143563747406006,
+      "learning_rate": 0.00033869889754521314,
+      "loss": 9.10044677734375,
+      "step": 4400
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.2389507293701172,
+      "learning_rate": 0.0003354887509605197,
+      "loss": 9.080850830078125,
+      "step": 4500
+    },
+    {
+      "epoch": 0.30666666666666664,
+      "grad_norm": 0.997056782245636,
+      "learning_rate": 0.0003322127543930859,
+      "loss": 9.041187744140625,
+      "step": 4600
+    },
+    {
+      "epoch": 0.31333333333333335,
+      "grad_norm": 1.006325364112854,
+      "learning_rate": 0.00032887250003647676,
+      "loss": 9.152498779296875,
+      "step": 4700
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.1522862911224365,
+      "learning_rate": 0.00032546961131470485,
+      "loss": 8.979527587890624,
+      "step": 4800
+    },
+    {
+      "epoch": 0.32666666666666666,
+      "grad_norm": 0.9992244839668274,
+      "learning_rate": 0.00032200574209321657,
+      "loss": 8.930678100585938,
+      "step": 4900
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 1.188022255897522,
+      "learning_rate": 0.0003184825758750839,
+      "loss": 8.919720458984376,
+      "step": 5000
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "eval_accuracy": 0.27488649706457924,
+      "eval_loss": 8.979753494262695,
+      "eval_runtime": 65.4227,
+      "eval_samples_per_second": 7.643,
+      "eval_steps_per_second": 0.382,
+      "step": 5000
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.9783419966697693,
+      "learning_rate": 0.00031490182498279115,
+      "loss": 8.924981079101563,
+      "step": 5100
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 1.0431445837020874,
+      "learning_rate": 0.0003112652297260157,
+      "loss": 8.822501220703124,
+      "step": 5200
+    },
+    {
+      "epoch": 0.35333333333333333,
+      "grad_norm": 0.9755280613899231,
+      "learning_rate": 0.00030757455755580553,
+      "loss": 8.865919189453125,
+      "step": 5300
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.1168733835220337,
+      "learning_rate": 0.0003038316022055665,
+      "loss": 8.899959716796875,
+      "step": 5400
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 0.9611853957176208,
+      "learning_rate": 0.00030003818281927526,
+      "loss": 8.851053466796875,
+      "step": 5500
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 1.040235996246338,
+      "learning_rate": 0.00029619614306734235,
+      "loss": 8.790068359375,
+      "step": 5600
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.0123136043548584,
+      "learning_rate": 0.00029230735025055524,
+      "loss": 8.8330029296875,
+      "step": 5700
+    },
+    {
+      "epoch": 0.38666666666666666,
+      "grad_norm": 1.0311475992202759,
+      "learning_rate": 0.00028837369439253617,
+      "loss": 8.824832153320312,
+      "step": 5800
+    },
+    {
+      "epoch": 0.3933333333333333,
+      "grad_norm": 0.997328519821167,
+      "learning_rate": 0.0002843970873211566,
+      "loss": 8.828201904296876,
+      "step": 5900
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.5238865613937378,
+      "learning_rate": 0.0002803794617393543,
+      "loss": 8.719149169921875,
+      "step": 6000
+    },
+    {
+      "epoch": 0.4,
+      "eval_accuracy": 0.28737377690802346,
+      "eval_loss": 8.731175422668457,
+      "eval_runtime": 65.6219,
+      "eval_samples_per_second": 7.619,
+      "eval_steps_per_second": 0.381,
+      "step": 6000
     }
   ],
   "logging_steps": 100,