Training in progress, step 140, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1f94ce60ad18907bfe378be4ba63c3cb07211d25772e7578153e59c360d0334
+oid sha256:8fdc91dddc9a166a95b38156dbe0a1400b141fa6a01a22b79fcbf7762105f13a
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af22c1f6025a1e35c54cfaffb9aa264061cac162f2b52caade7115ff260d713e
+oid sha256:298c35aeb88b8e142a8b2e9ae3b30b40502512f283bdbad9131877cf177376cb
 size 46057082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad4c4d2d769c6f52183fdfe62140ef02b36aa1e936b1d8050f51672d3d58fb1e
+oid sha256:43a84554481cf5ef7909ff3c93940e7b945a013d30bf7c3f575e7278bcae704e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3511d75105f53c278279e3dade6f856082c8693b0424c0bf567bdcf23028dd2b
+oid sha256:c049ad9892b8ae242eb26f06a6af3edec6b865f6613ddc97103e21f4231f6420
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.5968632698059082,
   "best_model_checkpoint": "miner_id_24/checkpoint-130",
-  "epoch": 0.03671020120014119,
+  "epoch": 0.039534062830921285,
   "eval_steps": 10,
-  "global_step": 130,
+  "global_step": 140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1029,6 +1029,84 @@
       "eval_samples_per_second": 5.599,
       "eval_steps_per_second": 5.599,
       "step": 130
+    },
+    {
+      "epoch": 0.036992587363219205,
+      "grad_norm": 0.9281368851661682,
+      "learning_rate": 0.0001713874307839863,
+      "loss": 1.8154,
+      "step": 131
+    },
+    {
+      "epoch": 0.03727497352629721,
+      "grad_norm": 2.6511611938476562,
+      "learning_rate": 0.0001709369921005258,
+      "loss": 1.4,
+      "step": 132
+    },
+    {
+      "epoch": 0.03755735968937522,
+      "grad_norm": 1.9646121263504028,
+      "learning_rate": 0.00017048363747516117,
+      "loss": 1.4126,
+      "step": 133
+    },
+    {
+      "epoch": 0.03783974585245323,
+      "grad_norm": 1.7208032608032227,
+      "learning_rate": 0.00017002738554352552,
+      "loss": 0.5568,
+      "step": 134
+    },
+    {
+      "epoch": 0.03812213201553124,
+      "grad_norm": 2.9022722244262695,
+      "learning_rate": 0.00016956825506034867,
+      "loss": 1.6914,
+      "step": 135
+    },
+    {
+      "epoch": 0.03840451817860925,
+      "grad_norm": 1.368131160736084,
+      "learning_rate": 0.00016910626489868649,
+      "loss": 1.5647,
+      "step": 136
+    },
+    {
+      "epoch": 0.038686904341687256,
+      "grad_norm": 1.5058932304382324,
+      "learning_rate": 0.00016864143404914504,
+      "loss": 2.4011,
+      "step": 137
+    },
+    {
+      "epoch": 0.03896929050476527,
+      "grad_norm": 2.3039586544036865,
+      "learning_rate": 0.00016817378161909996,
+      "loss": 0.9973,
+      "step": 138
+    },
+    {
+      "epoch": 0.03925167666784327,
+      "grad_norm": 1.9210929870605469,
+      "learning_rate": 0.00016770332683191096,
+      "loss": 1.7679,
+      "step": 139
+    },
+    {
+      "epoch": 0.039534062830921285,
+      "grad_norm": 1.3414863348007202,
+      "learning_rate": 0.0001672300890261317,
+      "loss": 1.4788,
+      "step": 140
+    },
+    {
+      "epoch": 0.039534062830921285,
+      "eval_loss": 1.6231486797332764,
+      "eval_runtime": 133.2243,
+      "eval_samples_per_second": 5.6,
+      "eval_steps_per_second": 5.6,
+      "step": 140
     }
   ],
   "logging_steps": 1,
@@ -1043,7 +1121,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -1057,7 +1135,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.272444660744192e+16,
+  "total_flos": 1.370325019262976e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null