Training in progress, step 35, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96a12281eff4b7ceaa9f5a0ab209147f2789e19452548285fb7f102b6e5f6742
+oid sha256:cca6cbed7377fff19fabaff2054ca15e604e8b9d395ade1e589629497c93eedc
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89d01bee0c233c1ea4ffcd696462ebbfe933f17444b255e527c5a9a213367563
+oid sha256:ad36d118e75a5ab9f6234c280429f6e2fb25a36f18a20b770888afe30599d45f
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cbd51d7850190ce4ca9c72f35700265d6b316a61a36d717db982e8ff3e7521f
+oid sha256:7fe88e7cab455920be97304b3d7e1b205cac3723b106861e810dca2c7ae37858
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e564be273a0ead09d6669d61932fdc102782bc49c45280282032b22cdbb9b0b9
+oid sha256:99d6019f63922aa49a1fcc328c3559cf53a0110fe021fa5fd65bb7b5ecf66240
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:772904dd2ba778765092aecf0459cde9e92fef74c7cce02dd302b8a9fb782c03
+oid sha256:c6093d880eb54dd4bd99152b10d9fac74830f7e828ff0bb3dc59d75c5cb76f50
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3586bae705399a0b8c3b90dc641d99100afb7c195eee02d27687454011cc4da
+oid sha256:4c49ea40f582be90a4cd08897e351d3003124f7438133a317b4c4d7efd808d5c
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42c052e81d046347be3074b07671b8743acfee2fa86afcaf4cf737a53f8e085c
+oid sha256:400690333b498d3c3ea4cd1446f834c1cb37202647b1e68e58a488ea7599ce2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.26085758209228516,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.150537634408602,
+  "epoch": 3.010752688172043,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 35,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,76 @@
       "eval_samples_per_second": 22.298,
       "eval_steps_per_second": 2.823,
       "step": 25
+    },
+    {
+      "epoch": 2.236559139784946,
+      "grad_norm": 0.350571870803833,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 0.2556,
+      "step": 26
+    },
+    {
+      "epoch": 2.3225806451612905,
+      "grad_norm": 0.33824387192726135,
+      "learning_rate": 1.3813298094746491e-05,
+      "loss": 0.2453,
+      "step": 27
+    },
+    {
+      "epoch": 2.4086021505376345,
+      "grad_norm": 0.33050841093063354,
+      "learning_rate": 1.0697345262860636e-05,
+      "loss": 0.2701,
+      "step": 28
+    },
+    {
+      "epoch": 2.4946236559139785,
+      "grad_norm": 0.4018042981624603,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 0.2571,
+      "step": 29
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 0.3769586384296417,
+      "learning_rate": 5.558227567253832e-06,
+      "loss": 0.265,
+      "step": 30
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.3363115191459656,
+      "learning_rate": 3.581603349196372e-06,
+      "loss": 0.2491,
+      "step": 31
+    },
+    {
+      "epoch": 2.752688172043011,
+      "grad_norm": 0.3187609612941742,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 0.2414,
+      "step": 32
+    },
+    {
+      "epoch": 2.838709677419355,
+      "grad_norm": 0.29826077818870544,
+      "learning_rate": 9.035651368646648e-07,
+      "loss": 0.2394,
+      "step": 33
+    },
+    {
+      "epoch": 2.924731182795699,
+      "grad_norm": 0.4264858663082123,
+      "learning_rate": 2.2640387134577058e-07,
+      "loss": 0.2775,
+      "step": 34
+    },
+    {
+      "epoch": 3.010752688172043,
+      "grad_norm": 0.34414350986480713,
+      "learning_rate": 0.0,
+      "loss": 0.3759,
+      "step": 35
     }
   ],
   "logging_steps": 1,
@@ -221,12 +291,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.28244602173653e+17,
+  "total_flos": 4.595424428283658e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null