Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b88e92787bc903679da5ad344cc01f40faf61ca71659133a1c6231d287247bc
+oid sha256:42d6eb5f85750d758527cd7eceb0a4e10276690a41193fb970c4b98284f7b0c2
 size 5327496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b659381a7046e9b1b9766991994c31a656244e89b7dd93bd33b8d7a29d03021
+oid sha256:e0dc10cfd8519e51874b09f0665d7bc0c5e452b883d258c4fa72c6159e8491f7
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:973fc011780b0afe41e09d8a05bd28fe24f518f7ba19d3578d6880cef8185006
+oid sha256:50a2c607209d9e8f29def4e81b8b88d033719105d940e691ce1a762bec8c9c84
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.826231002807617,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.015926737009755127,
+  "best_metric": 2.813061475753784,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.02389010551463269,
   "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": 29.822,
       "eval_steps_per_second": 7.47,
       "step": 20
+    },
+    {
+      "epoch": 0.016723073860242882,
+      "grad_norm": 0.5223943591117859,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 11.3615,
+      "step": 21
+    },
+    {
+      "epoch": 0.019112084411706153,
+      "grad_norm": 0.4995236098766327,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 11.3577,
+      "step": 24
+    },
+    {
+      "epoch": 0.019908421262193908,
+      "eval_loss": 2.8152737617492676,
+      "eval_runtime": 35.0917,
+      "eval_samples_per_second": 30.15,
+      "eval_steps_per_second": 7.552,
+      "step": 25
+    },
+    {
+      "epoch": 0.02150109496316942,
+      "grad_norm": 0.5261664390563965,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 11.4294,
+      "step": 27
+    },
+    {
+      "epoch": 0.02389010551463269,
+      "grad_norm": 0.5537786483764648,
+      "learning_rate": 0.0,
+      "loss": 11.2336,
+      "step": 30
+    },
+    {
+      "epoch": 0.02389010551463269,
+      "eval_loss": 2.813061475753784,
+      "eval_runtime": 35.3003,
+      "eval_samples_per_second": 29.971,
+      "eval_steps_per_second": 7.507,
+      "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": 297118036131840.0,
+  "total_flos": 382008903598080.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null