Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47162bcc6ae49c731d2a219d05593ebd9fe395db8864d22efab807f7d79c18b5
+oid sha256:72dc34677e2b55ea9cb73a706b780d94ecf35bb9dbe45b8f89cc5a5f6298b13f
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb5595b40a0d9ae4cee30c273edf32c5153dcef605e7f89c871bf420c4e7b9f5
+oid sha256:c68a0099039b357ca655efd94253b4a9e85c68e894904b2b8f6d3dd31208f453
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b20dbda7e6f6d207a2ac79e39292a33f26a6858d0645f61c513d4e235a7b864
+oid sha256:aca265427dc35da1e721f577ae26d12d91969b15787ac51500354158e058df67
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5871251821517944,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0011073583965450417,
+  "best_metric": 0.5729724168777466,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0016610375948175628,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 15.59,
       "eval_steps_per_second": 7.796,
       "step": 20
+    },
+    {
+      "epoch": 0.0011627263163722938,
+      "grad_norm": 0.7146998643875122,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.5619,
+      "step": 21
+    },
+    {
+      "epoch": 0.00132883007585405,
+      "grad_norm": 0.46887776255607605,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.5796,
+      "step": 24
+    },
+    {
+      "epoch": 0.0013841979956813022,
+      "eval_loss": 0.5751184225082397,
+      "eval_runtime": 487.4735,
+      "eval_samples_per_second": 15.601,
+      "eval_steps_per_second": 7.801,
+      "step": 25
+    },
+    {
+      "epoch": 0.0014949338353358065,
+      "grad_norm": 0.4254571199417114,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.5382,
+      "step": 27
+    },
+    {
+      "epoch": 0.0016610375948175628,
+      "grad_norm": 0.43398526310920715,
+      "learning_rate": 0.0,
+      "loss": 0.5356,
+      "step": 30
+    },
+    {
+      "epoch": 0.0016610375948175628,
+      "eval_loss": 0.5729724168777466,
+      "eval_runtime": 487.6501,
+      "eval_samples_per_second": 15.595,
+      "eval_steps_per_second": 7.799,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2287053610942464.0,
+  "total_flos": 3392881730519040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null