Training in progress, step 210, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ce726842d250f20c86c371d9e87a8ce9846060e663f40a17aa5220f549de934
+oid sha256:6e8b163ef36cc7e57a8ee15a6ebe44a66dd7b467f2cc54f8de9f11808fbf4a74
 size 125048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89d5bd83a26023b846c84f45639c04652bc00657132d2cf830dd829784d28815
+oid sha256:9e11899b82d3568219c123451efb8f9c3baa4ecaaf187d3d8094ff509232f7bf
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ebd8401c143f16f72b022f70333a3cfcf5c180eb2884806e8d3b16f8611859c
+oid sha256:578c17b2105d3c6bea4883770e5007551a3f2302d9968187a7d2ba2aece88a9c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53ada7ec389029bea855f553cfcb8ba6729038e26afcd278435a9c0b241e2783
+oid sha256:99f3078781d07b22b8aceece06e9b1a7abc294ae09750b1339d4cf73fa58b867
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.022467613220215,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.009039343743644212,
+  "best_metric": 11.02186393737793,
+  "best_model_checkpoint": "miner_id_24/checkpoint-210",
+  "epoch": 0.009491310930826422,
   "eval_steps": 5,
-  "global_step": 200,
+  "global_step": 210,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1735,6 +1735,92 @@
       "eval_samples_per_second": 52.886,
       "eval_steps_per_second": 26.446,
       "step": 200
+    },
+    {
+      "epoch": 0.009084540462362432,
+      "grad_norm": 0.6612194776535034,
+      "learning_rate": 0.00013393410881565876,
+      "loss": 44.1568,
+      "step": 201
+    },
+    {
+      "epoch": 0.009129737181080653,
+      "grad_norm": 0.5365848541259766,
+      "learning_rate": 0.00013333031729088419,
+      "loss": 44.0318,
+      "step": 202
+    },
+    {
+      "epoch": 0.009174933899798874,
+      "grad_norm": 0.43999558687210083,
+      "learning_rate": 0.0001327251556873117,
+      "loss": 44.0544,
+      "step": 203
+    },
+    {
+      "epoch": 0.009220130618517095,
+      "grad_norm": 0.5535528659820557,
+      "learning_rate": 0.00013211864888076457,
+      "loss": 44.0657,
+      "step": 204
+    },
+    {
+      "epoch": 0.009265327337235316,
+      "grad_norm": 0.5289484262466431,
+      "learning_rate": 0.0001315108218023621,
+      "loss": 44.0946,
+      "step": 205
+    },
+    {
+      "epoch": 0.009265327337235316,
+      "eval_loss": 11.022246360778809,
+      "eval_runtime": 175.5631,
+      "eval_samples_per_second": 53.069,
+      "eval_steps_per_second": 26.537,
+      "step": 205
+    },
+    {
+      "epoch": 0.009310524055953538,
+      "grad_norm": 0.515040934085846,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 44.1026,
+      "step": 206
+    },
+    {
+      "epoch": 0.009355720774671759,
+      "grad_norm": 0.43807700276374817,
+      "learning_rate": 0.00013029130682479722,
+      "loss": 44.0529,
+      "step": 207
+    },
+    {
+      "epoch": 0.00940091749338998,
+      "grad_norm": 0.40383437275886536,
+      "learning_rate": 0.00012967966905511906,
+      "loss": 44.0854,
+      "step": 208
+    },
+    {
+      "epoch": 0.009446114212108201,
+      "grad_norm": 0.42450079321861267,
+      "learning_rate": 0.00012906681127049338,
+      "loss": 44.0488,
+      "step": 209
+    },
+    {
+      "epoch": 0.009491310930826422,
+      "grad_norm": 0.5043962597846985,
+      "learning_rate": 0.00012845275866310324,
+      "loss": 44.047,
+      "step": 210
+    },
+    {
+      "epoch": 0.009491310930826422,
+      "eval_loss": 11.02186393737793,
+      "eval_runtime": 176.4502,
+      "eval_samples_per_second": 52.802,
+      "eval_steps_per_second": 26.404,
+      "step": 210
     }
   ],
   "logging_steps": 1,
@@ -1763,7 +1849,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2101346304000.0,
+  "total_flos": 2206413619200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null