Training in progress, step 34, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20476cd7c594a37b87e2e5f066938d80b47aa5fe31ec4c688576410f064e4600
+oid sha256:3a7edddc1af76be37f02e3e538e92012e04bdbe252253ac446610a57566dc8f5
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c7866ca77b2dd2c3cecf0a7c8915e217fe8c318e13cec824512e1b991230be6
+oid sha256:afd631a925f42608d56247ae67b3f0ef6ca8b77b463668920f747762dca00752
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ba1c31d151d1b9bd34b79b863f17b9cd94fd1935e125ecf02e890fa08d06d9a
+oid sha256:c415ab21661709deb54d3f5b1af59ad0ef3f71a6592bce15af188ce87af38de2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e70538ae8d0e462178176fbf6fa0f463390010edd21a43cb478729b26f490af
+oid sha256:5fc585dc9fd222c4cbd66e7bc9788f3fb115a2fd8960ceb98cd48dadae2e4e6d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64376fe408be1bca07c5cc5f7754bdbbb6f62ddfe83e14d2a20bfb156884983a
+oid sha256:980a12c04d8c8602e71f6d5b227e8a075dd6823b3cce79a1951691aa3ee8ee04
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9efe98928de10d1ff2431faf4c63ac7b49860544415532c5c6120ad606c07f3f
+oid sha256:28bf423b3d035c0f41731474a4874edb06ff4eb8889d8f11f5ef3a8e39c35181
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c220d2fbe9a2870f9ac93749b3d4b3852ce94b5983d948fa8de3d35e453f98ce
+oid sha256:7312f49c1e1b01f68cdaee175129535fda49cd22ed1f251a2745d2c8c42996be
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.3648199141025543,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.2598870056497176,
+  "epoch": 3.073446327683616,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 34,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,69 @@
       "eval_samples_per_second": 57.021,
       "eval_steps_per_second": 14.826,
       "step": 25
+    },
+    {
+      "epoch": 2.3502824858757063,
+      "grad_norm": 1.5733007192611694,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.3583,
+      "step": 26
+    },
+    {
+      "epoch": 2.440677966101695,
+      "grad_norm": 0.6812260150909424,
+      "learning_rate": 2.0214529598676836e-05,
+      "loss": 0.362,
+      "step": 27
+    },
+    {
+      "epoch": 2.5310734463276834,
+      "grad_norm": 1.1533381938934326,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.3392,
+      "step": 28
+    },
+    {
+      "epoch": 2.621468926553672,
+      "grad_norm": 0.9058969020843506,
+      "learning_rate": 1.531354310432403e-05,
+      "loss": 0.3486,
+      "step": 29
+    },
+    {
+      "epoch": 2.711864406779661,
+      "grad_norm": 1.0298035144805908,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.3511,
+      "step": 30
+    },
+    {
+      "epoch": 2.8022598870056497,
+      "grad_norm": 0.258158802986145,
+      "learning_rate": 1.1937684892050604e-05,
+      "loss": 0.339,
+      "step": 31
+    },
+    {
+      "epoch": 2.8926553672316384,
+      "grad_norm": 0.6644238829612732,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.3545,
+      "step": 32
+    },
+    {
+      "epoch": 2.983050847457627,
+      "grad_norm": 1.3119802474975586,
+      "learning_rate": 1.0216687299751144e-05,
+      "loss": 0.3612,
+      "step": 33
+    },
+    {
+      "epoch": 3.073446327683616,
+      "grad_norm": 1.9420535564422607,
+      "learning_rate": 1e-05,
+      "loss": 0.6584,
+      "step": 34
     }
   ],
   "logging_steps": 1,
@@ -221,12 +284,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.94731890081792e+16,
+  "total_flos": 1.0808353705112371e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null