Training in progress, step 230, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cd7abe507a25f89fc943570866a0cd9542ea07ff0be5ba353e6e69f5e6f5245
+oid sha256:19681a6e019210b62365a143ca2bcfa14deb2eab8b48fe74d719a59650dc30c3
 size 838922248

last-checkpoint/global_step230/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d28c5f8f855fde5ea21cb6dbd2b880c4c07ecd0be38b703a4637f430d626bdf2
+size 2516610352

last-checkpoint/global_step230/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a1704c15637410adf1cda479608dc83fea792160d962cf06930b4824e46e6ab
+size 2516610480

last-checkpoint/global_step230/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96c9644ef3422f44f2452f5bcc4f35c0be47c6fb0dee2047e315b37db86d1cac
+size 839203308

last-checkpoint/latest

@@ -1 +1 @@
-global_step220
+global_step230

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0212678bdfd12f5e771de1237e044853f4945c4146cb9c89a9c4c95248a16b29
+oid sha256:9e89bc3e773ea70d76254d676255c70de160bb22db7216884ff941ca88de2b40
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33029e789fcd42453ea34680d14dbbf43ac473446a15c334ff26604d9c090e51
+oid sha256:679fbf91facbe9c53d33446c7075a3f372a0f1f00954d01b70779336d2e38552
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da1ea98faceffa379118e67dff018abe556db2e0944820c6da999968eab4b3ce
+oid sha256:086918aaf41a43fc720d3c947494466fce1fbac837c34e535ac4192608dc7bcf
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 210,
   "best_metric": 0.15481556951999664,
   "best_model_checkpoint": "miner_id_24/checkpoint-210",
-  "epoch": 0.19855595667870035,
+  "epoch": 0.2075812274368231,
   "eval_steps": 10,
-  "global_step": 220,
+  "global_step": 230,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1732,6 +1732,84 @@
       "eval_samples_per_second": 6.63,
       "eval_steps_per_second": 0.838,
       "step": 220
+    },
+    {
+      "epoch": 0.19945848375451264,
+      "grad_norm": 2.7720537185668945,
+      "learning_rate": 2.702120432801935e-05,
+      "loss": 0.2478,
+      "step": 221
+    },
+    {
+      "epoch": 0.2003610108303249,
+      "grad_norm": 2.182992935180664,
+      "learning_rate": 2.699238210421629e-05,
+      "loss": 0.1792,
+      "step": 222
+    },
+    {
+      "epoch": 0.20126353790613719,
+      "grad_norm": 2.793783664703369,
+      "learning_rate": 2.696343664013227e-05,
+      "loss": 0.3028,
+      "step": 223
+    },
+    {
+      "epoch": 0.20216606498194944,
+      "grad_norm": 1.7117496728897095,
+      "learning_rate": 2.6934368233226717e-05,
+      "loss": 0.1177,
+      "step": 224
+    },
+    {
+      "epoch": 0.20306859205776173,
+      "grad_norm": 1.5346475839614868,
+      "learning_rate": 2.6905177182222488e-05,
+      "loss": 0.1537,
+      "step": 225
+    },
+    {
+      "epoch": 0.20397111913357402,
+      "grad_norm": 2.023026466369629,
+      "learning_rate": 2.6875863787102798e-05,
+      "loss": 0.223,
+      "step": 226
+    },
+    {
+      "epoch": 0.20487364620938628,
+      "grad_norm": 0.8650408387184143,
+      "learning_rate": 2.6846428349108137e-05,
+      "loss": 0.0614,
+      "step": 227
+    },
+    {
+      "epoch": 0.20577617328519857,
+      "grad_norm": 1.9878193140029907,
+      "learning_rate": 2.681687117073317e-05,
+      "loss": 0.1216,
+      "step": 228
+    },
+    {
+      "epoch": 0.20667870036101083,
+      "grad_norm": 1.7673425674438477,
+      "learning_rate": 2.6787192555723637e-05,
+      "loss": 0.1016,
+      "step": 229
+    },
+    {
+      "epoch": 0.2075812274368231,
+      "grad_norm": 1.2054425477981567,
+      "learning_rate": 2.6757392809073227e-05,
+      "loss": 0.0684,
+      "step": 230
+    },
+    {
+      "epoch": 0.2075812274368231,
+      "eval_loss": 0.1877218633890152,
+      "eval_runtime": 69.9572,
+      "eval_samples_per_second": 6.676,
+      "eval_steps_per_second": 0.843,
+      "step": 230
     }
   ],
   "logging_steps": 1,
@@ -1746,7 +1824,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -1760,7 +1838,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.855163048781414e+17,
+  "total_flos": 7.16676136918057e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null