Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:803debd806dc1599453d26189aa93a91d55ccde27ce073e5a76f77124d1416e1
+oid sha256:77cf949a0f97184343b7d38f784b04fdb71aaee58aa4de38e1e5079b54b4ba58
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cfaccd4f937bced7521f5235ea6790eb0f5b209dbca9e77047814b9953eb4e6
+oid sha256:0048ca8ae538b9b924a62e63ceffd10e5b7e2ad8f482ef7babfb9890a931dd73
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b5d8e9b9db0784c3f5644d0a76f28ad18847aa47c892ea065246aec4366811b
+oid sha256:8ab606683dee59e251ef2cbfcb1aebf2f02037a37af81cb49a67b06660659a4f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db7cce94191358964e35b668c9bdb6e486f8a8bf168079d634ab7bccc775845b
+oid sha256:b911007def71d4e0760e095fb38b9695588c94c6dfc0cb1ee70d933b50c5ece7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4311259388923645,
-  "best_model_checkpoint": "mikhail-panzo/fil_b64_le5_s8000/checkpoint-1500",
-  "epoch": 65.21739130434783,
+  "best_metric": 0.4230838716030121,
+  "best_model_checkpoint": "mikhail-panzo/fil_b64_le5_s8000/checkpoint-2000",
+  "epoch": 86.95652173913044,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -241,6 +241,84 @@
       "eval_samples_per_second": 24.653,
       "eval_steps_per_second": 3.101,
       "step": 1500
+    },
+    {
+      "epoch": 67.3913043478261,
+      "grad_norm": 1.2938276529312134,
+      "learning_rate": 7.74e-06,
+      "loss": 0.4684,
+      "step": 1550
+    },
+    {
+      "epoch": 69.56521739130434,
+      "grad_norm": 1.8100048303604126,
+      "learning_rate": 7.990000000000001e-06,
+      "loss": 0.4797,
+      "step": 1600
+    },
+    {
+      "epoch": 71.73913043478261,
+      "grad_norm": 1.8357532024383545,
+      "learning_rate": 8.24e-06,
+      "loss": 0.4813,
+      "step": 1650
+    },
+    {
+      "epoch": 73.91304347826087,
+      "grad_norm": 1.4251928329467773,
+      "learning_rate": 8.49e-06,
+      "loss": 0.4622,
+      "step": 1700
+    },
+    {
+      "epoch": 76.08695652173913,
+      "grad_norm": 1.1764353513717651,
+      "learning_rate": 8.740000000000001e-06,
+      "loss": 0.4642,
+      "step": 1750
+    },
+    {
+      "epoch": 78.26086956521739,
+      "grad_norm": 1.6363924741744995,
+      "learning_rate": 8.99e-06,
+      "loss": 0.4669,
+      "step": 1800
+    },
+    {
+      "epoch": 80.43478260869566,
+      "grad_norm": 1.485127568244934,
+      "learning_rate": 9.240000000000001e-06,
+      "loss": 0.4595,
+      "step": 1850
+    },
+    {
+      "epoch": 82.6086956521739,
+      "grad_norm": 1.2844778299331665,
+      "learning_rate": 9.49e-06,
+      "loss": 0.463,
+      "step": 1900
+    },
+    {
+      "epoch": 84.78260869565217,
+      "grad_norm": 1.0181550979614258,
+      "learning_rate": 9.74e-06,
+      "loss": 0.4529,
+      "step": 1950
+    },
+    {
+      "epoch": 86.95652173913044,
+      "grad_norm": 1.3658286333084106,
+      "learning_rate": 9.990000000000001e-06,
+      "loss": 0.454,
+      "step": 2000
+    },
+    {
+      "epoch": 86.95652173913044,
+      "eval_loss": 0.4230838716030121,
+      "eval_runtime": 6.4713,
+      "eval_samples_per_second": 24.57,
+      "eval_steps_per_second": 3.091,
+      "step": 2000
     }
   ],
   "logging_steps": 50,
@@ -260,7 +338,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.226780270809741e+16,
+  "total_flos": 2.9689323880306464e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null