Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a66a4cda6017883824f770b4695b30087a070dba8017f3f7248c326f7396853
+oid sha256:178d451c0c99330543e2cd4f25889e92a00805c3c58468909c06b3e75dae9c37
 size 598799664

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:542873921921ed915734abe43832a65e76be0b31b65bcaab7e5f2e2ed2d335d5
+oid sha256:1b1c438d48ba296099d095e6e4cae05652393a203da7d724b0cb8f20ee0dbb91
 size 167987322

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebdf4a26cda3cae3baab82ad304b90f23b79c0e45c25d45196bc7b9b403beb0e
+oid sha256:cee48272d2c45123f302d3a2a2de668135690acbc0f4d7c95a58cf1868581c88
 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": 1.1831579208374023,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0006941431670281996,
+  "best_metric": 1.1736942529678345,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0010412147505422993,
   "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": 16.129,
       "eval_steps_per_second": 8.064,
       "step": 20
+    },
+    {
+      "epoch": 0.0007288503253796095,
+      "grad_norm": 1.8782596588134766,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 4.4198,
+      "step": 21
+    },
+    {
+      "epoch": 0.0008329718004338395,
+      "grad_norm": 2.016456365585327,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 4.5838,
+      "step": 24
+    },
+    {
+      "epoch": 0.0008676789587852494,
+      "eval_loss": 1.1758105754852295,
+      "eval_runtime": 752.151,
+      "eval_samples_per_second": 16.13,
+      "eval_steps_per_second": 8.065,
+      "step": 25
+    },
+    {
+      "epoch": 0.0009370932754880694,
+      "grad_norm": 2.0421838760375977,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 4.7747,
+      "step": 27
+    },
+    {
+      "epoch": 0.0010412147505422993,
+      "grad_norm": 3.63925838470459,
+      "learning_rate": 0.0,
+      "loss": 5.1371,
+      "step": 30
+    },
+    {
+      "epoch": 0.0010412147505422993,
+      "eval_loss": 1.1736942529678345,
+      "eval_runtime": 752.2778,
+      "eval_samples_per_second": 16.127,
+      "eval_steps_per_second": 8.064,
+      "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": 4064263085752320.0,
+  "total_flos": 6063618313420800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null