Training in progress, step 430, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:893f5c8856fdc4a2b011a0f925f5f0a5a12489125014c73cd5998f9fc3897b44
+oid sha256:5dd61dbd46e4ee82fd33617e4a8411741cee905cc1e9401a102028fdb32c7ead
 size 147770888

last-checkpoint/global_step430/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:cafbbf4182b398aff7c66d586f1a5026e634425180bfde77a5a8f8acd8d31ba2
+size 443178960

last-checkpoint/global_step430/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bbf517ea4f7493903098ba52e54448f3715eae4e12ed7b79db25b739aa7cabd
+size 443179088

last-checkpoint/global_step430/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e818c7480088688c038a9bc96cd5ab4624f19a8f2b3804db6a40c872605c6fe
+size 614765880

last-checkpoint/latest

@@ -1 +1 @@
-global_step420
+global_step430

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85b27159412abe6a30485dc519cf403ee3db832c65abe733fbf34a73d6540791
+oid sha256:46a15aba38ae961b6e93b01cbaf204b4dfb1ff8281028ffbbf38cabbe605e87c
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ec1ea968138e2f514b82726a0056326f5069984d539a687bec45fbf72e0ccb1
+oid sha256:68cc2617943b1f6b82b3ab7caec02d1bb0162a82f58d1a50aea62b2e77f20038
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b76ff39d4805387c82a6745b83f0904cec0ca7e9eaedb729cc4bc23d42182fa
+oid sha256:98e7fcb688e077c6922e71258186f68ed91012a168b39ea778c3c18a2a291a0d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 410,
-  "best_metric": 1.0409541130065918,
-  "best_model_checkpoint": "miner_id_24/checkpoint-410",
-  "epoch": 0.3226425965047052,
+  "best_global_step": 430,
+  "best_metric": 1.0377129316329956,
+  "best_model_checkpoint": "miner_id_24/checkpoint-430",
+  "epoch": 0.33032456308815056,
   "eval_steps": 10,
-  "global_step": 420,
+  "global_step": 430,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3292,6 +3292,84 @@
       "eval_samples_per_second": 18.42,
       "eval_steps_per_second": 2.31,
       "step": 420
+    },
+    {
+      "epoch": 0.3234107931630497,
+      "grad_norm": 0.3012835383415222,
+      "learning_rate": 1.2845275866310325e-05,
+      "loss": 0.9846,
+      "step": 421
+    },
+    {
+      "epoch": 0.32417898982139426,
+      "grad_norm": 0.3492763042449951,
+      "learning_rate": 1.2814529218688688e-05,
+      "loss": 0.9851,
+      "step": 422
+    },
+    {
+      "epoch": 0.3249471864797388,
+      "grad_norm": 0.45387721061706543,
+      "learning_rate": 1.2783753647424635e-05,
+      "loss": 0.9763,
+      "step": 423
+    },
+    {
+      "epoch": 0.32571538313808335,
+      "grad_norm": 0.4614562392234802,
+      "learning_rate": 1.2752949468784776e-05,
+      "loss": 0.7974,
+      "step": 424
+    },
+    {
+      "epoch": 0.3264835797964279,
+      "grad_norm": 0.6264432072639465,
+      "learning_rate": 1.2722116999329712e-05,
+      "loss": 1.0572,
+      "step": 425
+    },
+    {
+      "epoch": 0.32725177645477244,
+      "grad_norm": 0.09508559107780457,
+      "learning_rate": 1.2691256555910769e-05,
+      "loss": 0.5381,
+      "step": 426
+    },
+    {
+      "epoch": 0.328019973113117,
+      "grad_norm": 0.16152898967266083,
+      "learning_rate": 1.2660368455666752e-05,
+      "loss": 1.0737,
+      "step": 427
+    },
+    {
+      "epoch": 0.32878816977146147,
+      "grad_norm": 0.1710013449192047,
+      "learning_rate": 1.2629453016020681e-05,
+      "loss": 1.2014,
+      "step": 428
+    },
+    {
+      "epoch": 0.329556366429806,
+      "grad_norm": 0.16182465851306915,
+      "learning_rate": 1.259851055467653e-05,
+      "loss": 1.1196,
+      "step": 429
+    },
+    {
+      "epoch": 0.33032456308815056,
+      "grad_norm": 0.1539359837770462,
+      "learning_rate": 1.2567541389615965e-05,
+      "loss": 1.0812,
+      "step": 430
+    },
+    {
+      "epoch": 0.33032456308815056,
+      "eval_loss": 1.0377129316329956,
+      "eval_runtime": 119.0772,
+      "eval_samples_per_second": 18.417,
+      "eval_steps_per_second": 2.309,
+      "step": 430
     }
   ],
   "logging_steps": 1,
@@ -3306,7 +3384,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -3320,7 +3398,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.572031475515392e+17,
+  "total_flos": 4.680889367789568e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null