Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:075dab25755f35a388f38d5ec254131cd38b4dbe9faa3f08c45fd634de714013
+oid sha256:35dfcdb2eb191f1beddcea46e2ac9926a6c6e3ea6ac2eda4f6063febe7090e40
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a16241656ee6d887dafa8f05435f9233e8af1574f90f009525fc21aaead3ac02
+oid sha256:9cd576b2e5df85c2efee5156f3dcc874240875ec97cb286155ca205814be54b2
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a235bd5b22847df5efc576b2d53304138bedaafdab52b3f19ffc508dcd8204f7
+oid sha256:0a7ec423b1e2a3fc2ca790ddc4370fec88c8249a3964daf8a870d6f32dd37903
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0873218b672c06f65bcbdbef35d38ce732851774107c53582718a1316dbb1e40
+oid sha256:cd7cf500208b0b7f84d388a948be38cab3fa49ec9e5ed4521e775b2c1f3ef453
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.49298894405365,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.03678499172337686,
+  "best_metric": 1.4784965515136719,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.05517748758506529,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 17.526,
       "eval_steps_per_second": 4.393,
       "step": 100
+    },
+    {
+      "epoch": 0.04046349089571455,
+      "grad_norm": 0.8449574708938599,
+      "learning_rate": 0.00019231131849308138,
+      "loss": 1.5649,
+      "step": 110
+    },
+    {
+      "epoch": 0.044141990068052236,
+      "grad_norm": 0.9605708718299866,
+      "learning_rate": 0.00018923623308232218,
+      "loss": 1.4462,
+      "step": 120
+    },
+    {
+      "epoch": 0.047820489240389924,
+      "grad_norm": 0.93846595287323,
+      "learning_rate": 0.00018572883366372081,
+      "loss": 1.4542,
+      "step": 130
+    },
+    {
+      "epoch": 0.051498988412727605,
+      "grad_norm": 0.9066504240036011,
+      "learning_rate": 0.00018180620793468224,
+      "loss": 1.3955,
+      "step": 140
+    },
+    {
+      "epoch": 0.05517748758506529,
+      "grad_norm": 1.112593412399292,
+      "learning_rate": 0.00017748746653345728,
+      "loss": 1.3078,
+      "step": 150
+    },
+    {
+      "epoch": 0.05517748758506529,
+      "eval_loss": 1.4784965515136719,
+      "eval_runtime": 65.2041,
+      "eval_samples_per_second": 17.56,
+      "eval_steps_per_second": 4.402,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7773608566784e+16,
+  "total_flos": 2.6660412850176e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null