Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a69e69df1c215c9fbd45805f864ee3ac4c779dc496d6f4a5065ef792e21302a
+oid sha256:1835c4eface419c90acbf7ce6083472fe6cfa84a00c8e93405eb55eb383c46d9
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa69e17bdeb510add6d20eb825063a8f124666a15f04da1625db2aa0e4664d82
+oid sha256:2a78d945c74756277c2d17e95e03f175ffcb8ed3e86f4c080c466230d2982552
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e31e0fdb3869a241061ca27b64da9fbd0a58f71586f852b6544558cc627e89db
+oid sha256:54d202e015217cec7b2f893b2c1397811e414d5ff08c7a02993da8b5e53e8bf0
 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": 1.1583677530288696,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.01690259877456159,
+  "best_metric": 1.1394572257995605,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.025353898161842383,
   "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": 6.617,
       "eval_steps_per_second": 3.315,
       "step": 20
+    },
+    {
+      "epoch": 0.017747728713289668,
+      "grad_norm": 1.0871113538742065,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.2662,
+      "step": 21
+    },
+    {
+      "epoch": 0.020283118529473905,
+      "grad_norm": 1.0731533765792847,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.2018,
+      "step": 24
+    },
+    {
+      "epoch": 0.021128248468201986,
+      "eval_loss": 1.1418037414550781,
+      "eval_runtime": 75.2574,
+      "eval_samples_per_second": 6.631,
+      "eval_steps_per_second": 3.322,
+      "step": 25
+    },
+    {
+      "epoch": 0.022818508345658146,
+      "grad_norm": 2.0396690368652344,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.4101,
+      "step": 27
+    },
+    {
+      "epoch": 0.025353898161842383,
+      "grad_norm": 1.3838458061218262,
+      "learning_rate": 0.0,
+      "loss": 1.2446,
+      "step": 30
+    },
+    {
+      "epoch": 0.025353898161842383,
+      "eval_loss": 1.1394572257995605,
+      "eval_runtime": 74.6998,
+      "eval_samples_per_second": 6.68,
+      "eval_steps_per_second": 3.347,
+      "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": 7668943615426560.0,
+  "total_flos": 1.150341542313984e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null