Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c35b9ac6d0d8971f3757c009211f5509139451e2c9a3488f654f1ae247545e1
+oid sha256:11324dc04b5fbc1cb781458f3ddd1f644ea82ec96581686822c9c45e2e86783e
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e353f7ba27daa25438aedd003dfa890a5d30cbff7742ec67855885b758d810e4
+oid sha256:52f9db78f4ca8c6efc08cfdd447bfe05f94537b36ecdd7acca60af11907fd2b1
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:824529825332a2c7d7729b711c474655fc634345060d3fcc137b224627e0839c
+oid sha256:5943428fff408660db31cb576105f7dc96299a6798b303d63a12cf87a0f4e1b2
 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": 1.2183318138122559,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0009215740484747949,
+  "best_metric": 1.2058666944503784,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0013823610727121925,
   "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": 4.852,
       "eval_steps_per_second": 2.426,
       "step": 20
+    },
+    {
+      "epoch": 0.0009676527508985347,
+      "grad_norm": 0.8395941853523254,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 4.7077,
+      "step": 21
+    },
+    {
+      "epoch": 0.001105888858169754,
+      "grad_norm": 0.8471205234527588,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 4.414,
+      "step": 24
+    },
+    {
+      "epoch": 0.0011519675605934938,
+      "eval_loss": 1.2079477310180664,
+      "eval_runtime": 1882.5808,
+      "eval_samples_per_second": 4.854,
+      "eval_steps_per_second": 2.427,
+      "step": 25
+    },
+    {
+      "epoch": 0.0012441249654409731,
+      "grad_norm": 0.9873213768005371,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 4.72,
+      "step": 27
+    },
+    {
+      "epoch": 0.0013823610727121925,
+      "grad_norm": 0.850914716720581,
+      "learning_rate": 0.0,
+      "loss": 5.203,
+      "step": 30
+    },
+    {
+      "epoch": 0.0013823610727121925,
+      "eval_loss": 1.2058666944503784,
+      "eval_runtime": 1888.528,
+      "eval_samples_per_second": 4.839,
+      "eval_steps_per_second": 2.419,
+      "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": 1.412392166621184e+16,
+  "total_flos": 2.094783887572992e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null