Training in progress, step 38, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37ca400809743ad724a75fc8120002994bcf55aef780e7af3640ddffc6c97e1d
+oid sha256:497dc676785beb383b9f099a8482c0ea57fafc006e87697f03398ee5adb1d9b6
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf2a803568d3bb68ae57d518d41dc00149ff29f8d9a9a0d69ff4184a1aab5e36
+oid sha256:148e508385876ad32f729637bc131f0025c9ac42b632e02c524f878128fca734
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0e42294df9512e7c116315845180216fb1f60f3a010f69bc8c5a96d867b57e3
+oid sha256:7cefb3260275ef519fb425c009264085b55a609450a7c0476c6b3630815c1078
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64e8ee9dc572fdb5aef8856fc796aedb2efb2cbfbbfb16dd3007c6ea897303b0
+oid sha256:43ee65b27c38323e6fbeafe58efe3985bf738ad898bc864e4816441c0f6944da
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b46f7761637563f6f03daf4e3a79a281de1c751de838f6f501a93331ba1daa3b
+oid sha256:cd6676eab2ea43be1b4693eb63a22f9d7ceec875c26c02746e0e89eec92b4f08
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7aa2dbd4b137e725078aaf0924baea6c75b45623f5ccd35909e5abada926709
+oid sha256:d73893d6058fc50c49db34b958b7c1b22473d08ad1662b91264232a47abab965
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36089259610accd3515d84595c73a617e4c6ffdd43b0303eafcd586eb191ea60
+oid sha256:d68c5e6597fbe8c8cd503bbe96844944996bb2c8646d83e3c51d984760006005
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.767305374145508,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.040201005025126,
+  "epoch": 3.100502512562814,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 38,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,97 @@
       "eval_samples_per_second": 582.265,
       "eval_steps_per_second": 76.249,
       "step": 25
+    },
+    {
+      "epoch": 2.120603015075377,
+      "grad_norm": 0.18161916732788086,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.5824,
+      "step": 26
+    },
+    {
+      "epoch": 2.201005025125628,
+      "grad_norm": 0.2802564203739166,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 10.6324,
+      "step": 27
+    },
+    {
+      "epoch": 2.2814070351758793,
+      "grad_norm": 0.2961265742778778,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 11.3607,
+      "step": 28
+    },
+    {
+      "epoch": 2.3618090452261304,
+      "grad_norm": 0.1732824742794037,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.4676,
+      "step": 29
+    },
+    {
+      "epoch": 2.442211055276382,
+      "grad_norm": 0.26101455092430115,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.9159,
+      "step": 30
+    },
+    {
+      "epoch": 2.522613065326633,
+      "grad_norm": 0.23604969680309296,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 11.4271,
+      "step": 31
+    },
+    {
+      "epoch": 2.6030150753768844,
+      "grad_norm": 0.1926390826702118,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.4621,
+      "step": 32
+    },
+    {
+      "epoch": 2.6834170854271355,
+      "grad_norm": 0.3302035629749298,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 10.6902,
+      "step": 33
+    },
+    {
+      "epoch": 2.7638190954773867,
+      "grad_norm": 0.2632927894592285,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 11.2976,
+      "step": 34
+    },
+    {
+      "epoch": 2.8442211055276383,
+      "grad_norm": 0.1927858144044876,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.4873,
+      "step": 35
+    },
+    {
+      "epoch": 2.9246231155778895,
+      "grad_norm": 0.2852284014225006,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 11.0213,
+      "step": 36
+    },
+    {
+      "epoch": 3.020100502512563,
+      "grad_norm": 0.315874844789505,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 19.506,
+      "step": 37
+    },
+    {
+      "epoch": 3.100502512562814,
+      "grad_norm": 0.14532816410064697,
+      "learning_rate": 0.0,
+      "loss": 10.3719,
+      "step": 38
     }
   ],
   "logging_steps": 1,
@@ -221,12 +312,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 81943068672000.0,
+  "total_flos": 124553464381440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null